‫گزارش مسابقات برگزار شده در‬

‫اولین کنفرانس بازشناسی الگو و تحلیل تصویر ایران‬

‫(‪)PRIA2013‬‬
 ‫محرمانه که توسط برگزارکنندگان مسابقه مطابق با شرایط استاندارد گردآوری شده‬ ‫تاثیرگذاری پژوهش و فناوری در تمدن کنونی دنیا و در آینده ی آن‪ ،‬بر کسی پوشیده‬
‫است انجام شده و رتبه بندی براساس معیارهای مطرح در هر مسابقه صورت پذیرفته‬ ‫نیست و هر چه در تاریخ بشری به زمان های اخیر نزدیک می شویم‪ ،‬این تاثیرگذاری‬
‫است‪ .‬بیشتر مجموعه داده های گردآوری شده برای اولین بار در این مسابقه مورد‬ ‫بیشتر می شود‪ .‬لذا ایده برگزاری مسابقات علمی– فناورانه به عنوان زیرمجموعه ای از‬
‫استفاده قرار گرفته است‪ .‬جدول ‪ 1‬خالصه ای از اطالعات مربوط به این مسابقات را‬ ‫فعالیتهای اولین کنفرانس بازشناسی الگو و تحلیل تصویر ایران (‪ )PRIA2013‬همراه‬
‫نشان می دهد‪ .‬جزئیات بیشتر این مسابقات و همچنین شرح سیستمهای شرکت داده‬ ‫با دیگر فعالیتهای کنفرانس برای افزایش مشارکت دانشجویان و محققین کشور در‬
‫شده‪ ،‬در گزارش مربوط به هر مسابقه به تفصیل آورده شده است‪.‬‬ ‫این رویداد علمی به پیشنهاد دکتر صدری دبیر کنفرانس در همان ابتدای شکل گیری‬
‫در این مسابقات در مجموع ‪ 15‬تیم شرکت نموده اند که دو تیم از کشورهای سنگاپور‬ ‫کنفرانس مطرح گردید و در ادامه با تشکیل کمیته مسابقات و پیگیری آن ادامه یافت‪.‬‬
‫و پاکستان و بقیه از دانشگاه های مختلف کشور می باشند‪ .‬جدول ‪ 2‬تیم های شرکت‬ ‫هدف از برگزاری مسابقات در این کنفرانس ایجاد اشتیاق و انگیزه برای پژوهش و تالش‬
‫کننده در هر مسابقه و رتبه بندی شرکت کنندگان در مسابقات مختلف را نشان می‬ ‫بیشتر در بین دانشجویان و محققین کشور‪ ،‬بکارگیری پژوهشهای انجام شده در قالب‬
‫دهد‪.‬‬ ‫سیستم های اجرایی و همچنین مقایسه و ارزیابی ایده های نوآورانه و جدید در زمینه‬
‫محورهای کنفرانس در بستری یکنواخت و عادالنه می باشد‪ .‬این مسابقات همچنین‬
‫می تواند به عنوان محکی برای انتخاب سیستم های برتر در زمینه های مختلف مورد‬
‫ﺟﺪول ‪ :1‬ﻣﺴﺎﺑﻘﺎت ﺑﺮﮔﺰار ﺷﺪه در ﭼﺎرﭼﻮب اوﻟﯿﻦ ﮐﻨﻔﺮاﻧﺲ ﺑﺎزﺷﻨﺎﺳﯽ اﻟﮕﻮ و ﺗﺤﻠﯿﻞ ﺗﺼﻮﯾﺮ اﯾﺮان‬ ‫استفاده قرار گیرد‪.‬‬
‫ﺗﻌﺪاد‬ ‫ﺗﻌﺪاد‬ ‫ﺳﺮﭘﺮﺳﺖ‬ ‫لیست زیر عناوین مسابقاتی است که در راستای اهداف علمی این کنفرانس برنامه ریزی‬
‫ﻋﻨﻮان ﻣﺴﺎﺑﻘﻪ‬
‫ﺗﯿﻤﻬﺎي ﺷﺮﮐﺖ ﮐﻨﻨﺪه ﻧﻬﺎﯾﯽ‬ ‫ﺗﯿﻢ ﻫﺎي ﺛﺒﺖ ﻧﺎم ﺷﺪه‬ ‫ﺗﯿﻢ ﺑﺮﮔﺰار ﮐﻨﻨﺪه‬ ‫شد که از این مسابقات‪ ،‬مسابقه بازشناسی کلمات دستنوشته مجزای فارسی به دلیل‬
‫‪4‬‬ ‫‪7‬‬ ‫ﻣﺮﯾﻢ ﺧﺮاﺷﺎدﯾﺰاده‬
‫ﺑﺎزﺷﻨﺎﺳﯽ ارﻗﺎم دﺳﺘﻨﻮﺷﺘﻪ‬
‫ﻣﺠﺰاي ﻓﺎرﺳﯽ )ﻋﺮﺑﯽ(‬
‫شرکت تنها یک تیم برگزار نگردید‪:‬‬
‫دودوﯾﯽ ﻧﻤﻮدن ﺗﺼﺎوﯾﺮ‬
‫‪3‬‬ ‫‪5‬‬ ‫ﺳﯿﺪ ﻣﺮﺗﻀﯽ آﯾﺖ اﻟﻠﻬﯽ‬
‫ﺧﻄﯽ ﻗﺪﯾﻤﯽ ﻓﺎرﺳﯽ‬ ‫بازشناسی ارقام دستنوشته مجزای فارسی (عربی)‬ ‫‪.1‬‬
‫‪3‬‬ ‫‪4‬‬ ‫ﯾﻮﻧﺲ اﮐﺒﺮي‬
‫ﺑﺮرﺳﯽ ﺻﺤﺖ اﻣﻀﺎي ﺑﺮون‬ ‫دودویی نمودن تصاویر خطی قدیمی‬ ‫‪.3‬‬
‫بررسی صحت امضای برون خط‬ ‫‪.4‬‬
‫ﺧﻂ ﻓﺎرﺳﯽ‬
‫ﺗﻔﮑﯿﮏ ﺧﻄﻮط در ﻣﺘﻮن‬
‫‪5‬‬ ‫‪5‬‬ ‫ﺣﺴﯿﻦ ﮐﺎردان ﻣﻘﺪم‬
‫دﺳﺖ ﻧﻮﯾﺲ‬ ‫تفکیک خطوط در متون دست نویس‬ ‫‪.5‬‬

‫ضوابط برگزاری مسابقات و همچنین شرکت در مسابقات با برگزاری جلسات مختلف با‬
‫حضور کمیته مسابقات و دبیر کنفرانس تدوین شده است‪ .‬این مسابقات به صورت غیر‬
‫حضوری و از طریق ثبت نام اولیه و سپس ارسال سیستم های نهایی به ایمیل مسابقات‬
‫برگزار شده است‪ .‬ارزیابی سیستم های ارسال شده با استفاده از نمونه های آزمایشی‬
‫در انتهــا ضمــن قدردانــی از حمایــت همــه جانبــه دبیــر کنفرانــس آفــای دکتــر صــدری‬ ‫ﺟﺪول ‪ :2‬ﺗﯿﻢ ﻫﺎي ﺷﺮﮐﺖ ﮐﻨﻨﺪه در ﻣﺴﺎﺑﻘﺎت ﻣﺨﺘﻠﻒ‬
‫و تمامــی همــکاران در کمیتــه هــای برگــزاری مســابقات مختلــف کــه تمامــی تــاش‬ ‫رﺗﺒﻪ‬ ‫ﻧﺎم داﻧﺸﮕﺎه‬ ‫ﻧﺎم ﺗﯿﻢ‬ ‫ﻋﻨﻮان ﻣﺴﺎﺑﻘﻪ‬

‫خــود را بــرای برگــزاری صحیــح و عادالنــه ایــن مســابقات نمــوده انــد‪ ،‬امیــدوارم کــه‬ ‫اول‬ ‫داﻧﺸﮕﺎه ﺷﺎﻫﺮود‬ ‫ﺷﺎﻫﺮود ‪OCR‬‬

‫برگــزاری مســابقات در دوره هــای بعــدی کنفرانــس نیــز ادامــه یابــد و تــداوم ایــن‬
‫دوم‬ ‫داﻧﺸﮕﺎه ﺑﯿﺮﺟﻨﺪ و ﻫﺮﻣﺰﮔﺎن‬ ‫ﭘﺮدازﺷﮕﺮان‬ ‫ﺑﺎزﺷﻨﺎﺳﯽ ارﻗﺎم‬
‫ﺳﻮم‬ ‫داﻧﺸﮕﺎه ﺻﻨﻌﺘﯽ اﻣﯿﺮﮐﺒﯿﺮ‬ ‫اﻣﯿﺮﮐﺒﯿﺮ‬ ‫دﺳﺘﻨﻮﺷﺘﻪ ﻣﺠﺰاي ﻓﺎرﺳﯽ‬
‫مســابقات باعــث افزایــش مشــارکت دانشــجویان و محققیــن مختلــف در داخــل و خارج‬ ‫ﭼﻬﺎرم‬ ‫داﻧﺸﮕﺎه ﺷﻬﯿﺪ ﺑﻬﺸﺘﯽ‬
‫ﮔﺮوه ﺑﺎزﺷﻨﺎﺳﯽ اﻟﮕﻮي‬ ‫)ﻋﺮﺑﯽ(‬
‫کشــور و در نتیجــه پیشــبرد علمــی کشــور عزیزمــان ایــران گــردد‪.‬‬ ‫‪National University of‬‬
‫داﻧﺸﮕﺎه ﺷﻬﯿﺪ ﺑﻬﺸﺘﯽ‬
‫اول‬ ‫‪Singapore‬‬
‫‪Singapore‬‬
‫دودوﯾﯽ ﻧﻤﻮدن ﺗﺼﺎوﯾﺮ‬
‫دوم‬ ‫داﻧﺸﮕﺎه ﺷﻬﯿﺪ ﭼﻤﺮان اﻫﻮاز‬ ‫ﺷﻬﯿﺪ ﭼﻤﺮان‬
‫مریم‬ ‫‪National University of‬‬
‫ﺧﻄﯽ ﻗﺪﯾﻤﯽ ﻓﺎرﺳﯽ‬
‫ﺳﻮم‬ ‫‪Pakistan‬‬
‫خراشادیزاده‬ ‫اول‬
‫‪Sciences and Technology‬‬
‫داﻧﺸﮕﺎه ﻓﺮدوﺳﯽ ﻣﺸﻬﺪ‬ ‫ﭘﺮدازش ﻫﻮﺷﻤﻨﺪ‬
‫دبیر کمیته مسابقات اولین کنفرانس بازشناسی الگو و تحلیل تصویر ایران‬ ‫دوم‬ ‫داﻧﺸﮕﺎه ﻫﺮﻣﺰﮔﺎن‬ ‫آرﯾﺎ‬ ‫ﺑﺮرﺳﯽ ﺻﺤﺖ اﻣﻀﺎي‬
‫داﻧﺸﮕﺎه آزاد اﺳﻼﻣﯽ‪ -‬واﺣﺪ ﻋﻠﻮم‬ ‫ﺑﺮون ﺧﻂ ﻓﺎرﺳﯽ‬
‫ﺳﻮم‬ ‫ﮐﺎوش‬
‫و ﺗﺤﻘﯿﻘﺎت ﺑﯿﺮﺟﻨﺪ‬
‫اول‬ ‫داﻧﺸﮕﺎه ﮔﻠﺴﺘﺎن‬ ‫داﻧﺸﮕﺎه ﮔﻠﺴﺘﺎن‬
‫دوم‬ ‫داﻧﺸﮕﺎه ﻫﺮﻣﺰﮔﺎن‬ ‫داﻧﺸﮕﺎه ﻫﺮﻣﺰﮔﺎن‬ ‫ﺗﻔﮑﯿﮏ ﺧﻄﻮط در ﻣﺘﻮن‬
‫ﺳﻮم‬ ‫داﻧﺸﮕﺎه ﺑﯿﺮﺟﻨﺪ‬ ‫اﻧﺪﯾﺸﻪ ﻧﻮ‬ ‫دﺳﺖ ﻧﻮﯾﺲ‬
‫ﭼﻬﺎرم‬ ‫داﻧﺸﮕﺎه ﺻﻨﻌﺘﯽ اﻣﯿﺮﮐﺒﯿﺮ‬ ‫اﻣﯿﺮﮐﺒﯿﺮ‬

‫در ایــن مســابقات در مجمــوع ‪ 25‬نفــر در قالــب تیــم هــای مختلــف بــه رقابــت‬
‫پرداختنــد کــه برخــی از ایــن شــرکت کننــدگان در بیــش از یــک مســابقه شــرکت‬
‫نمودنــد‪ .‬جــدول ‪ 3‬اطالعــات آمــاری ایــن شــرکت کننــدگان را نشــان مــی دهــد‪.‬‬
‫همــان طــور کــه در جــدول مشــاهده مــی شــود‪ ،‬بیشــترین آمــار شــرکت کننــدگان را‬
‫دانشــجویان مقطــع کارشناســی ارشــد تشــکیل مــی دهنــد‪.‬‬
‫ﺟﺪول‪ :3‬اﻃﻼﻋﺎت ﺷﺮﮐﺖ ﮐﻨﻨﺪﮔﺎن در ﻣﺴﺎﺑﻘﺎت‬
‫ﺗﻌﺪاد داﻧﺸﺠﻮﯾﺎن‬
‫ﺗﻌﺪاد داﻧﺸﺠﻮﯾﺎن‬ ‫ﺗﻌﺪاد داﻧﺸﺠﻮﯾﺎن‬ ‫ﺗﻌﺪاد اﻋﻀﺎي‬ ‫ﺗﻌﺪاد ﺷﺮﮐﺖ‬ ‫ﺗﻌﺪاد ﮐﻞ‬
‫ﻣﻘﻄﻊ ﮐﺎرﺷﻨﺎﺳﯽ‬
‫ﻣﻘﻄﻊ ﮐﺎرﺷﻨﺎﺳﯽ‬ ‫ﻣﻘﻄﻊ دﮐﺘﺮي‬ ‫ﻫﯿﺎت ﻋﻠﻤﯽ‬ ‫ﮐﻨﻨﺪﮔﺎن ﺧﺎرﺟﯽ‬ ‫ﺷﺮﮐﺖ ﮐﻨﻨﺪﮔﺎن‬
‫ارﺷﺪ‬
‫‪2‬‬ ‫‪12‬‬ ‫‪3‬‬ ‫‪3‬‬ ‫‪5‬‬ ‫‪25‬‬

‫`‬
 
  
 K-means  



 k k = 0, . . ., 9

       
  q k 

Bk 
()
 
   (SVD)    

()
 
          
   
k

 ()

Uk
k = 0, . . ., 9







  

             


  

      
 

           
            
  

            
   
            

 GrayLevl24 bit color 


      
 

   





         

     


PRIA 2013


          


           


ICDAR
          


 


    

           
            
            

 

  
         
 . 

 
            
        

  http://farsiocr.ir/farsi-digit-dataset



   

 
        


            

     




  

 
OCR: Optical Character Recognition
MLP: Multilayer Perseptron
KNN: K- Nearest Neighbor
 
          

  
OCR           
           



 
email: mkhorashadi@birjand.ac.irIT
     
        
email:ali_abbaszadeh@comp.iust.ac.ir
IT
 
email: jsadri@bijand.ac.ir 


[1] Sadri, J., Izadi, S., Solimanpour, F., Suen, C.Y., Bui, T.D.,
"State-of-the-art in Farsi script recognitions", Int. Symposium on
Signal Processing and its Applications, ISSPA, 2007.
[2] Kosravi, H., Kabir, E.,"Introducing a very large dataset of
Handwritten Farsi digits and a study on their varieties", Pattern
Recognition Letters, Vol. 28, pp. 1133-1141, 2007.
          



  

 

 
    
    

            
OCR  
k            
  
 

              
             


 
 
 KNN            
  
   k  
  
OCR               
         
              
  OCR           k                      
  
     k
                 
   k          
             OCR
K     
    MLP
 
  KNN   LBP      
s    K   
    k K k 
     

   kk  
OCR     
           Gray-scale
    


  LBP 



 OCR          

 
 
 OCR   


          
 MLP
 

                       
  
        
 
  MLP 

  

 



 
 
            
            
            
 

            

PRIA 2013







CPU: T7500 @ 2.20 GHZ 2.20 GHZIntel (R) core (TM) 2 Duo
RAM: 3.00 GB
  
(FLR)
    (ECR)      
(RR) (EWR)
   

 

           
            

 
    
 [] 
 
  [,]
  
            


           
 
    
            
 


          

   

 
 
 
 





 
  

 
      
              
        
        
            
   
           
           


• ICDAR2007 Handwriting Segmentation
Contest []
• ICDAR2009 Handwriting Segmentation
Contest []
• ICFHR 2010 Handwriting Segmentation
Contest []


     
            
  

  
           
            
             email:          
           
              
TIF     DPI       
   

  
  
 
         

     

            
           
 
  (Touching)       
 (slant)  (Overlapping) 



email: hkm.kardan@gmail.comIT
hhosseini@yazd.ac.ir
IT

email: akbari_younes@yahoo.com 

 
email: mjavad_jalili@yahoo.comIT


email:mkhorashadi@birjand.ac.irIT
IT
 
email: jsadri@birjand.ac.ir 



 
 
           


[1] Alaei, A., Pal, U., Nagabhushan, P.: A new scheme for
unconstrained handwritten text-line segmentation. Patten
Recognition 44(4), 917–928 (2011)
[2] M. Mohammadi, S.S. Mozaffari Chanijani,V.N. Manjunath
Aradhya, G.H. Kumar.: An Improved Handwritten Text Line
Segmentation Technique, pp. 289–296, 2011
[3] A. Zahour, B. Taconet, P. Mercy, S. Ramdane, Arabic hand-
written text-line extraction, in: Proceedings of the Sixth
International Conference on Document Analysis and
Recognition, 2001, pp. 281–285.
[4] A.Zahour, L. Likforman-Sulem, W. Boussalaa, B. Taconet,
Text-line segmenta- tion of historical Arabic documents, in:
Proceedings of Ninth International Conference on Document
Analysis and Recognition, 2007, pp. 138–142.
[5] M. Arivazhagan, H. Srinivasan, S.N. Srihari, A statistical
approach to hand- written line segmentation, in: Proceedings of
SPIE Document Recognition and Retrieval XIV, 2007, p.
6500T-1–11.
[6] V. Papavassiliou, T. Stafylakis, V. Katsouros, G. Carayannis,
Handwritten document image segmentation into text lines and
words, Pattern Recognition 43 (2010) 369–377.
[7] Y. Li, Y. Zheng, D. Doermann, S. Jaeger, Script-Independent
Text Line, Segmen- tation in freestyle handwritten documents,
IEEE Transaction on Pattern Analysis and Machine Intelligence
30 (8) (2008) 1313–1329.
[8] L. Likforman-Sulem, A. Zahour, B. Taconet, Text-line
segmentation of historical documents: a survey, International
Journal on Document Analysis and Recognition 9 (2) (2007)
123–138.
[9] L. Likforman-Sulem, A. Hanimyan, C. Faure, A Hough based
algorithm for extracting text-lines in handwritten documents, in:
Proceedings of the Third International Conference on Document
Analysis and Recognition, 1995, pp. 774–777.
[10] G. Louloudis, B. Gatos, I. Pratikakis, K. Halatsis, A. Block-
Based Hough, Trans- form mapping for text-line detection in
handwritten documents, in: Proceedings of 10th International
Workshop on Frontiers in Handwriting Recognition, 2006, pp.
515–520.
[11] G. Louloudis, B. Gatos, I. Pratikakis, C. Halatsis, Text-line
detection in hand- written documents, Pattern Recognition 41
(2008) 3758–3772.
[12] Z. Shi, V. Govindaraju, Line separation for complex document
images using fuzzy runlength, in: Proceedings of First

 
(RR)
             

 
FLR
 
  ECR
     

 
EWR
 

              
RR
              
 
 
           
  
             
 
          
       
           
    

                
            
  
FLR ECR EWR RR

     
      
        
      
                  
    
     
    

 
   
            

           
 
 
 
 
   
              
 
 
 
            
 
 
           
 
 

 
 

    
  
                      
          
             
         (FLR)       
  (EWR)(ECR) 
 Persian Heritage Image Binarization Competition
(PHIBC 2012)

Seyed Morteza Ayatollahi and Hossein Ziaei Nafchi

Synchromedia Laboratory for Multimedia Communication in Telepresence,
École de technologie supérieure, Montreal (QC), Canada H3C 1K3
Tel.: +1(514)396-8972
Fax: +1(514)396-8595
Email: sr.morteza@gmail.com, hossein zi@yahoo.com

Fig. 1. Sample original and ground truth images used in PHIBC 2012.
segmentation based on an average value computed through
multiple thresholds (based on 4 different Niblack inspired
thresholding formulas). In final step of post processing, again
conditional noise removal and constrained morphological
operations are performed to get the final binarised image.
3-1 Seyed Mehrdad Kankanan and Hossain Poyarad (Faculty
of engineering, Shahid Chamran University of Ahvaz, Ahvaz,
Iran).
Proposed method is mainly based on fuzzy measures
introduced in [11]. It finds a global threshold and apply it
for whole image. The main advantage of this method against
Otsu’s method, is its better classification of bleed-through in
the case of documents that include large amount of this type
of degradation. Afterward, an approach similar to Niblack and
some post-processing processes are applied to improve the
final binarization result.
III. E VALUATION MEASURES
For an objective comparison between submitted algorithms,
six evaluation measures used [10]. These are F-Measure [12],
pseudo F-Measure [13], peak signal-to-noise ratio (PSNR), dis-
tance reciprocal distortion metric (DRD) [14], misclassification
penalty metric (MPM) [15] and negative rate metric (NRM)
[2], [3].
Let’s bwout and GT denotes the binarized image and
ground truth image, respectively. PSNR for binary images can
be defined as:
N M
x=1 y=1 [GT (x, y) − bwout(x, y)]
M SE =
N ×M
1 Hereinafter,
we refer to each group with its assigned number.
Abstract—The first competition on the binarization of his-
torical Persian documents and manuscripts (PHIBC 2012) has
been organized in conjunction with the first Iranian conference
on pattern recognition and image analysis (PRIA 2013). The
main objective of PHIBC 2012 is to evaluate performance of
the binarization methodologies, when applied on the Persian
heritage images. This paper provides a report on the methodology
and performance of the three submitted algorithms based on
evaluation measures has been used.
Keywords—Document image processing, Historical document
1 binarization, Persian heritage manuscripts, Binarization contest
P SN R = 10 × log( ). (2)
M SE
I. I NTRODUCTION
F-Measure can be considered as an intelligent alternative
for PSNR because it takes into account the number of fore-
There are many old manuscripts and documents in the
ground and background pixels. Let’s T P , F P , F N and T N
libraries and museums of Iran. Many of them include histor-
denote the true positive, false positive, false negative and true
ically important data which needs automatic processing and
negative, respectively. Recall, precision and F-Measure can be
reading. However, less attention has been made to preserve
defined as:
these valuable types of documents. The PHIBC 2012 is a
primitive attempt toward evaluation of binarization methods,
TP
Recall = (3) when applied on the Persian manuscripts.
TP + FN
Persian heritage documents and manuscripts following their
similarity to Arabic documents [1] are in the form of handwrit-
TP
P recision = (4) ten document images. As usual, for handwritten documents,
TP + FP preservation of strokes and sub-strokes is of great interest.
Previously, five Latin datasets of historical manuscripts has
been publicly available for DIAR researchers [2]–[6]. PHIBC
2 × Recall × P recision
F − M easure = . (5) 2012 introduces the first dataset that developed for binarization
Recall + P recision of Persian heritage documents. The dataset used for PHIBC
2012 consisted of ten historical documents used with permis-
Also, pseudo F-Measure is computed like F-Measure ex- sion from ”Documents and old manuscripts treasury of Mirza
cept that recall value is taken from skeletonized ground truth: Mohammad Kazemaini (affiliated with Hazrate Emamzadeh
Jafar), Yazd, Iran”. The images in PHIBC 2012 suffered
from various types of degradation, including bleed-through,
2 × Recallskel × P recision
pseudo F − M easure = . (6) deterioration of cellulose structure, faded ink and alien ink,
Recallskel + P recision among others [7]. For each image in the dataset, a groud
truth is generated with a semi-automatic approach. At first,
Furthermore, NRM can be computed as:
document is processed with phase congruency features used
in [8], [9] to produce a rough binarized image. Then, the final
N R F N + N RF P ground truth is generated manually by human expert from the
N RM = . (7)
2 rough binary image produced in the first step. We will report
(1) where: the ground truth generation methodology in a dedicated report.
FN FP
N RF N = , N RF P = (8)
FN + FP FP + TN c
978-1-4673-6206-1/13/$31.00 2013 IEEE
Figure 1 shows sample images and corresponding ground truth
images used in the PHIBC 2012.
The dataset is available via competition website and tech-
nical committee 11 website (IAPR TC-11):
http://phibc2012.ir/
http://www.iapr-tc11.org/
Also, the source code of the evaluation measures used for
performance evaluation can be found at [10].
The rest of the paper is organized as follows. In section II,
a brief description of the submitted methods to PHIBC 2012
is provided. The evaluation measures used for comparison
between submitted algorithms are described in section III.
Section IV provides experimental results. Finally, section V
draws a conclusion.
II. D ESCRIPTION OF METHODOLOGIES
In the Persian heritage image binarization competition
(PHIBC 2012), three groups submitted three algorithms. The
description of each methodology is provided by these groups
and is as follows.
1- Su Bolan† , Tian Shangxuan† , Lu Shijian‡ and Tan
Chew Lim† († School of Computing, National University of
Singapore, and ‡ Department of Computer Vision and Image
Understanding Institute for Infocomm Research, Singapore).
There are four main steps in our proposed method. First,
local image contrast which is evaluated by local maximum
and minimum and local image gradient are combined using an
exponential function with an adaptive factor. Second, The local
image contrast is combined with the edge map to extract an
accurate text character edge image. Third, the document image
is binarized by a local threshold which is decided based on
the constructed edge map and estimated stroke width. At last,
some post-processing work is applied to produce better results.
2- Syed Ahsen Raza Ali Hamdani (National University
of Sciences and Technology (NUST), Islamabad, Pakistan).
The algorithm is based on three processing steps:
preprocessing, thresholding and postprocessing. In
preprocessing, conditional noise removal and edge based
processing is performed. Thresholding step involves a
computation of final threshold for background and text
 TABLE I. C HARACTERISTICS OF TEST IMAGES USED IN THE PHIBC 2012 DRD measures the distortion for all the S flipped pixels as higher rank. Table II provides detailed experimental results
Image name Size Degradation type(s)
follows: of the binarization algorithms participated in PHIBC 2012
and some state-of-the-art binarization methods. Between three
Persian01 1625×1269 faded ink, multi-degraded background, color background. S participated algorithms, the algorithm submitted by 1- Su
Persian02 845×691 bleed-through, alien ink, low resolution. DRDk
Persian03 1215×735 bleed-through, degraded background, small amount of text. DRD = k=1
. (9) Bolan† , Tian Shangxuan† , Lu Shijian‡ and Tan Chew Lim†
Persian04 1247×1829 faded ink, color background, degraded background. N U BN († School of Computing, National University of Singapore, and
Persian05 887×1149 faded ink, color background, visible fibers in the paper. ‡
Department of Computer Vision and Image Understanding
Persian06 697×1359 faded ink, lines, degraded background. where, DRDk is the distortion of the k − th flipped pixel
Persian07 637×1149 faded ink, lines, degraded background, multi-color background. Institute for Infocomm Research, Singapore) achieved the best
and it is calculated using a 5 × 5 normalized weight matrix
Persian08 1617×969 blur, faded ink, spots, degraded background. performance. Figure 2 shows binarization results of the winner
Persian09 1025×719 faded ink, ink smear, ink noise, alien ink, degraded background. WN m [14]. DRDk equals to the weighted sum of the pixels
Persian10 1649×1258 lines, blur, multi-color background, visible fibers in paper, bleed-through. of PHIBC 2012.
in the 5 × 5 block of the ground truth GT that differ from the
centered k − th flipped pixel at (x, y) in the binarization result
TABLE II. E VALUATION OF THE BINARIZATION METHODS PARTICIPATED IN THE PHIBC 2012 image B.
Method no. Rank / Score F-Measure pseudo F-Measure PSNR DRD MPM(×10−3 ) NRM(×10−2 )
1 1 / 51.3792 88.55 92.25 18.28 5.57 2.33 6.84 2 2
 
2 3 / 50.2433 86.79 86.29 17.64 6.08 2.74 5.59 DRDk = [GTk (i, j)−Bk (x, y)]×WN m (i, j) (10)
3 2 / 50.7329 87.30 89.50 17.95 5.87 3.79 5.42 i=−2 y=−2
Otsu [16] - 77.75 79.98 15.42 31.11 16.50 5.69
Grid based Sauvola [17] - 85.29 87.75 17.73 9.99 6.01 4.73 NUBN is the number of the non-uniform (not all black
ESBK [18] - 84.03 86.43 17.60 14.79 7.13 5.52 not all white pixels) 8 × 8 blocks in the GT image. MPM is
Su’s method [19] - 88.21 88.82 18.27 5.44 2.65 5.74 a measure of how well the resulting image representing the
PC [8] - 90.19 91.35 19.89 5.23 2.74 3.90 contour of ground truth image and defined as:
Howe [20] - 89.58 91.88 18.53 4.11 2.96 4.56

to PHIBC 2012. Based on the performance of the groups
participated in the competition and state-of-the-art binarization
methodologies, there is a lot of room for development of higher
performance binarization algorithms.
ACKNOWLEDGMENT
The organizers of PHIBC 2012 would like to thank ”Doc-
uments and old manuscripts treasury of Mirza Mohammad
Kazemaini (affiliated with Hazrate Emamzadeh Jafar), Yazd,
Iran” for providing us the images used in the PHIBC 2012.
R EFERENCES
[1] R. Farrahi Moghaddam, M. Cheriet, M. M. Adankan, K. Filonenko,
and R. Wiscovsky, “IBN SINA: A database for research on processing
and understanding of arabic manuscripts images,” in Document Analysis
Systems, 2010, pp. 11–18.
[2] B. Gatos, K. Ntirogiannis, and I. Pratikakis, “ICDAR 2009 document
image binarization contest (DIBCO 2009),” in International Conference
on Document Analysis and Recognition, 2009, pp. 1375–1382.
[3] I. Pratikakis, B. Gatos, and K. Ntirogiannis, “H-DIBCO 2010 hand-
written document image binarization competition,” International Con-
ference on Frontiers in Handwriting Recognition, pp. 727–732, 2010.
[4] ——, “ICDAR 2011 document image binarization contest (DIBCO
2011),” in International Conference on Document Analysis and Recog-
nition, 2011, pp. 1506–1510.
[5] ——, “ICFHR 2012 competition on handwritten document image
binarization competition,” in International Conference on Frontiers in
Handwriting Recognition, 2012, pp. 813–818.
[6] R. Rowley-Brook, F. Pitie, and A. Kokaram, “A ground truth bleed-
through document image database,” in International Conference on
Theory and Practice of Digital Libraries, 2012, pp. 185–196.
[7] “Special issue on recent advances in applications to visual cultural
heritage,” IEEE Signal Processing Magazine, vol. 12, no. 1, pp. 234–
778, 2008.
[8] H. Ziaei Nafchi, R. Farrahi Moghaddam, and M. Cheriet, “Historical
document binarization based on phase information of images,” in Lec-
ture Notes in Computer Science: Asian Conference on Computer Vision
(ACCV’12 Workshops). Springer Berlin / Heidelberg, 2013, vol. 7729,
pp. 1–12.
[9] H. Ziaei Nafchi and H. Rashidy Kanan, “A phase congruency based
document binarization,” in IAPR International Conference on Image
and Signal Processing, 2012, pp. 113–121.
[10] R. Farrahi Moghaddam and H. Ziaei Nafchi, “Objective evaluation of
binarization methods,” MATLAB Central File Exchange.
http://www.mathworks.com/matlabcentral/fileexchange/27652/, 2013.
[11] N. Vieira Lopes, P. A. Mogadouro do Couto, and H. Bustince, “Auto-
matic histogram threshold using fuzzy measures,” IEEE Transactions
on Image Processing, vol. 19, no. 1, pp. 199–204, 2010.
[12] M. Sokolova and G. Lapalme, “A systematic analysis of performance
measures for classification tasks,” Information Processing and Manage-
ment, vol. 45, pp. 427–437, 2009.
[13] K. Ntirogiannis, B. Gatos, and I. Pratikakis, “An objective evaluation
methodology for handwritten image document binarization techniques,”
in Document Analysis Systems, 2008, pp. 217–224.
[14] H. Lu, A. C. Kot, and Y. Q. Shi, “Distance-reciprocal distortion measure
for binary document images,” IEEE Signal Processing Letters, vol. 11,
no. 2, pp. 228–231, 2004.
[15] D. P. Young and J. M. Ferryman, “Pets metrics: On-line performance
evaluation service,” in Proceedings of the 14th International Conference
on Computer Communications and Networks, 2005, pp. 317–324.
[16] N. Otsu, “A threshold selection method from gray-level histograms,”
IEEE Trans. Systems, Man, and Cybernetics, vol. 9, no. 2, pp. 62–66,
1979.
[17] R. Farrahi Moghaddam and M. Cheriet, “A multi-scale framework for
adaptive binarization of degraded document images,” Pattern Recogni-
tion, vol. 43, no. 6, pp. 2186–2198, 2010.
[18] ——, “AdOtsu: An adaptive and parameterless generalization of otsu’s
method for document image binarization,” Pattern Recognition, vol. 45,
pp. 2419–2431, 2012.
[19] B. Su, S. Lu, and C. Tan, “Binarization of historical document im-
ages using the local maximum and minimum,” in Document Analysis
Systems, 2010, pp. 159–166.
[20] N. Howe, “A laplacian energy for document binarization,” in Interna-
tional Conference on Document Analysis and Recognition, 2011, pp.
6–10.
FN FP
1  i 
MPM = ( d + dj ) . (11)
2D i=1 F N j=1 F P
where, diF N and djF P denote the distance of the i−th false
positive and the j − th false negative pixel from the contour
of the text in the ground truth image. The factor D is the sum
of all the pixel-to-contour distances of the ground truth object.
A higher value for F-Measure, pseudo F-Measure and
PSNR measures, indicate to better classification, while a lower
value for DRD, MPM and NRM measures, shows better
performance.
IV. E XPERIMENTAL RESULTS
In this section, characteristics of test images used in
the PHIBC 2012 are described. Images in the PHIBD 2012
suffered from various types of degradation, include uneven
illumination changes, various types of bleed-through, etc. Ta-
ble I has summarized the degradation types of each document
image used in the PHIBC 2012.
For each image in the dataset, best value of each measure
between all of the methods is considered. A method with best
Fig. 2. Sample binarization results from the winner of PHIBC 2012.
value for a measure takes a score of 1, and other methods
takes a fraction of 1 by a comparison with the best value.
Since there are six evaluation measures and ten test images,
we can compute the score of a method as: V. C ONCLUSION
This paper provides a report on the first Persian heritage
10 6
Besti,j valuek,i,j image binarization competition (PHIBC 2012) which has been
3
(12)
Sk=1 = ( , ). organized in conjunction with the first Iranian conference on
valuek,i,j Besti,j
i=1 j=1 pattern recognition and image analysis (PRIA 2013). The main
objective of this competition is to evaluate the performance
where, k denotes the number of participators and value of the binarization methods, when applied on the historical
is the measure value obtained by a method. First fraction is Persian document images. The images used in PHIBC 2012
used for those measures in which a lower value indicates to include wide range of degradation types and their associated
better score, and the second one is used for measures with ground truth are publicly available. Six evaluation measures
inverse behavior. Finally, methods with higher scores take has been used for comparison between submitted algorithms
  


         
    

PRIA 2013
 

        
 


      

 

 



          
          
        


 []   

  [] 
[][]
[]
  
 


         
             
             
            
    

         
         
           
         
 
 

(FAR)

  (FRR)       
 
 (AER)
 

 
         
 
        
 
 
 

 
 
 
 
 

 

 
  
 


 

 


[,,,]
 


(SVC 2004) •
[]
         •
[](ICDAR 2009)
 •
[](BSEC 2009)
  •
(ICFHR 2010)     
[]
         •
[](ICDAR 2011)
  •
(ICFHR 2012)     
[]

 
         


 

          
        
(FRR)(FAR)

     
         off-line 
FRRFAR
 
FAR: False Acceptance Rate
FRR: False Rejection Rate
PDA: Personal Digital Assistance
AER: Average Error Rate
 
    
 [,]  

.

 (PDA)

          
email: akbari_younes@yahoo.com IT

 
email: mjavad_jalili@yahoo.comIT
  
 
email: km_farda2006@yahoo.com IT
  
 
email:mkhorashadi@birjand.ac.irIT
IT  
 
email:jsadri@birjand.ac.ir 


Workshop on Automated Forensic Handwriting Analysis
IWAFHA (2011) pp. 15.
[7] S. Ghandali and M. E. Moghaddam, “Off-line Persian signature
identification and verification cation based on image registration
and fusion,” J. Multimed., 4(3) (2009) 137-144.
[8] M. Radmehr, S. M. Anisheh, M. Nikpour and A. Yaseri,
“Designing an off-line method for signature recognition,”
World Appl. Sci. J. 13(3) (2011) 438-443.
[9] Atefeh Foroozandeh, Younes Akbari, Mohammad Javad Jalili,
Javad Sadri, “A Novel and Practical System for Verifying
Signatures on Persian Handwritten Bank Checks”, Accepted for
publication in the International Journal of Pattern Recognition
and Artificial Intelligence (IJPRAI),
Vol.26,No.6(2012)(27pages),doi:
10.1142/S0218001412560149.
[10] Atefeh Foroozandeh, Mohammad J. Jalili, Younes Akbari,
and Javad Sadri, “Persian Signature Verification Based on
Fractal Dimension Using Testing Hypothesis", Published in
the Proceedings of the 2012 International Conference on
Frontiers in Handwriting Recognition (ICFHR-2012, Italy) on
18-20 Sept. 2012, at Porto Giardino, Bari, Italy.
[11] D. yan Yeung, H. Chang, Y. Xiong, S. George, R. Kashi,
T. Matsumoto, and G. Rigoll, “SVC2004: First international
signature verification competition,” in In Int. Conf. on Bio-
metric Authentication (ICBA), Hong Kong. Springer, 2004,
pp. 16–22.
[12] N. Houmani, A. Mayoue, and et al., “BioSecure signature
evaluation campaign (BSEC’2009): Evaluating online
signaturealgorithms depending on the quality of signatures,”
Pattern Recognition, Aug. 2011.
[13] V. L. Blankers, C. E. van den Heuvel, K. Y. Franke, and L. G.
Vuurpijl, “ICDAR 2009 signature verification competition,”
inICDAR, 2009, pp. 1403–1407.
[14] M. Liwicki, C. E. van den Heuvel, B. Found, and M. I. Malik,
“Forensic signature verification competition 4NSigComp2010
- detection of simulated and disguised signatures,” in ICFHR,
November 16-18, India, 2010, pp. 715–720.
[15] M. Liwicki, M. I. Malik, C. E. van den Heuvel, X. Chen,C.
Berger, R. Stoel, M. Blumenstein, and B. Found, “Signature
verification competition for online and offline skilled
forgeries SigComp2011,” in ICDAR, 2011, pp. 1480–1484.
[16] M. Liwicki, M. I. Malik, L. Alewijnse, E. Heuvel and
B. found“ICFHR2012 Competition onAutomatic
Forensic Signature Verification (4NsigComp 2012),”
Published in the Proceedings of the 2012 International
Conference on Frontiers in Handwriting Recognition (ICFHR-
2012, Italy) on 18-20 Sept. 2012, at Porto Giardino, Bari,
Italy.



 FAR(%) FRR(%) AER(%)
   

  

   
 



 
          
     
      
         



[1] R. Plamondon and G. Lorette, “Automatic signature verification
and writer identification – the state of the art,” in Pattern
Recognition, vol. 22, 1989, pp. 107–131.
[2] F. Leclerc and R. Plamondon, “Automatic signature
verification: the state of the art 1989–1993,” in Progress in
Automatic Signature Verification, R. Plamondon, Ed. World
Scientific Publ. Co., 1994, pp. 13–19.
[3] V. Nguyen, M. Blumenstein and G. Leedham, “Global
features for the off-line signature verification problem, ” in
Proc. 10th Int. Conf. on Document Analysis and Recognition
ICDAR (2009) 1300-1304.
[4] R. Plamondon and S. N. Srihari, “On-line and off-line
handwriting recognition: a comprehensive survey,” IEEE
Trans.Pattern Analysis and Machine Intelligence, vol. 22, no. 1,
pp. 63–84, 2000.
[5] D. Impedovo and G. Pirlo, “Automatic signature verification:
The state of the art,” IEEE Transactions on Systems, Man,
and Cybernetics, Part C (Applications and Reviews), vol. 38,
no. 5, pp. 609–635, Sep. 2008.
[6] S. Pal, M. Blumenstein and U. Pal, “Non-English and non-Latin
signature verification systems: A survey,” in Proc 1st Int.






 
            

            

             
          



  
            

     
            
MLP
 


  





 
 
  (FRR)      (FAR)    
  

FAR=  

FRR=   

             
  
