THIAGARAJAR COLLEGE OF ENGINEERING, MADURAI–15

(A Govt. Aided Autonomous Institution, Affiliated to Anna University)

Department of Mechatronics

21ES590 - SYSTEM THINKING

A MACHINE LEARNING APPROACH FOR PREDICTING EDIBLE

FISH QUALITY

Submitted by

ABDULFARITH R A 917721F002
MOHAMED ASHWAQUE 917721F029
SARVESHWARAN S 917721F044

Guided by

Dr. S. JULIUS FUSIC

Assistant Professor
&
Mr. M. M. Devarajan
Assistant Professor
 THIAGARAJAR COLLEGE OF ENGINEERING, MADURAI-15
(A Govt. Aided Autonomous Institution, Affiliated to Anna University)

BONAFIDE CERTIFICATE
a) Certified that this Report Titled “A Machine Learning Approach for
Predicting Edible Fish Quality” is the bonafide work of ABDULFARITH R A
(917721F002), MOHAMED ASHWAQUE (917721F029), SARVESHWARAN
S (917721F044) who carried out the work under my supervision. Certified further that
to the best of my knowledge the work reported herein does not form part of any other
thesis or dissertation on the basis of which a degree or award was conferred on an
earlier occasion on this or any other candidate.

SIGNATURE

Dr. S. JULIUS FUSIC

ASSISTANT PROFESSOR
DEPARTMENT OF MECHATRONICS ENGINEERING
THIAGARAJAR COLLEGE OF ENGINEERING,
MADURAI - 625 015.

Mr .M. M. Devarajan
ASSISTANT PROFESSOR
DEPARTMENT OF MECHATRONICS ENGINEERING
THIAGARAJAR COLLEGE OF ENGINEERING,
MADURAI - 625 015.
 A MACHINE LEARNING APPROACH FOR
PREDICTING EDIBLE FISH QUALITY
ABDULFARITH R A MOHAMED ASHWAQUE
MECHATRONICS MECHATRONICS
THIAGARAJAR COLLEGE OF THIAGARAJAR COLLEGE OF SARVESHWARAN S
ENGINEERING ENGINEERING MECHATRONICS
MADURAI,INDIA MADURAI,INDIA THIAGARAJAR COLLEGE OF
abdulfarith@student.tce.edu hariprasadm@studet.tce.edu ENGINEERING
MADURAI,INDIA
sarveshwarans@student.tce.edu

Abstract— Fresh Fish food processing is the most
important factor in the food production industry. Fish
freshness is the main indicator for assessing the quality of fish
which is essential for commercial purposes. The local markets
showcase and sell two-week-older fishes that are collected from
the seas. To concern the health of fish consumers, one must
ensure the quality of the fish before consuming it. Therefore,
we have used a deep learning technique to increase the
accuracy in detecting the freshness of the fish. In this study,
two different types of fish (anchovy and horse mackerel) used
to determine fish freshness with convolutional neural networks,
one of the artificial intelligence techniques. it will make an
important contribution to the studies that will be conducted in
the freshness studies of fish using different storage days
I. INTRODUCTION
The consumption of fish is widely recognized for its
positive impact on health due to its rich nutritional content,
including high-quality protein, essential fatty acids, vitamin
D, and iodine.
Control and monitoring of fish freshness is very
important in the food industry. The taste, health, quality and
freshness of the fish are among the important factors. The
changes during the storage of fish can be categorized based
on apparent features including color, stiffness, odor,
secretions, scales, skin, flesh, abdomen, eyes, and gills.
In traditional methods they use sensory methods to
analyze but there are some shortcomings in sensory analysis
such as the high cost of the expert team, biased judgment
due to fatigue and subjectivity, and the inability to use
sensory analysis for continuous measurement. These quality
measures are mapped into an automated system that could
make the testing process faster with no errors.
The aim of this study is to evaluate the freshness of
anchovy (Engraulis encrasicolus) and horse mackerel
(Trachurus trachurus) by means of artificial intelligence
methods.
learning, has gained momentum in the detection and
prediction of fish quality attributes.
In that some are like an android application that
automatically identifies the fish freshness by using image
processing, the app categorizes the fish ranging from level 1
to level 5 based on its freshness by using the RGB color
values of the gills and eyes. Also, it helps to identify the
categories of fish and their freshness.
And others determines the correlation that exists
between the statistical wavelet coefficients and freshness in
the stored fish. Features Extraction plays a vital part in
detecting the quality of fish. The extracted features are
experimented with the conventional chemical laboratory-
based method. This image processing-based algorithm
serves as a robust diagnostic tool for food quality inspection
and control.
In other paper they describe about The standard of
the fish sample could also be decreased every other day until
it finally reaches the consumers. This paper suggests the
automated method for classifying tilapia fish freshness. The
proposed method is implemented using real-time dataset
images captured on several different days and aiming to find
the quality of fish taken at an appropriate time interval.
In other paper they explain about the design
methodology for An Intelligent Fish freshness system for
real-time classification of the freshness of fish using an
Artificial Neural Network (ANN). Automated Fish freshness
analysis and detection is the critical task in the fishery
industry. This research is a preliminary work to store and
analyze the sensory data using ANN. A specific network is
trained for the quality assessment of fish freshness. The
proposed system provides rapid response because a trained
neural network arranges data in real-time. It has been
successful in identifying the number of days after catching
the fish with an accuracy of up to 99%.
III. PROBLEM STATEMENT

II. LITERATURE REVIEW “A Machine Learning Approach for Predicting Edible

Fish Quality’
The assessment of fish quality is a critical concern
in the seafood industry to ensure consumer safety and
satisfaction. In recent years, the integration of machine
learning techniques, particularly machine vision and deep
 IV. METHODOLOGY

The images of the fish are collected. Then the fish images
are scaled to the standard size. After normalize the data from
0-255 into the range [0, 1]. Then partition the dataset into
the training set, test set, and validation set. During training,
the network learns the characteristics of images.
The validation datasets classifier model how well
it performs given the training dataset. During testing, unseen
images are given as input to the classifier to categorize the
images. The proposed system uses Deep Convolution Neural
Network (CNN) through which detailed features are Figure 1: data sets collected
extracted by superimposing the filter over an image during
convolution operation. Irrelevant and noisy features are
removed during the pooling operation. After the pooling
operation, the representative features are fed as an input to a
fully connected layer that uses the soft-max function to V. RESULT :
compute the maximum likelihood of a fish sample belongs
to a particular category. The proposed system is used for
finding the quality of fish whether it is the stale or fresh fish The results obtained from the training and testing for 3
models.
image.
From model 1:
Convolution Neural Network:
image size - 416
Convolution Neural Network CNN is a specialized type
of ANNs particularly used for image analysis. The computer batch size - 16
sees the image as a matrix of numbers where each
numberrepresents a single pixel. The relationship between epochs – 200
the pixels (values) must be preserved even after the image is
given as an input to the network. A convolution neural
network retains the spatial information between the pixels.
Different mathematical operations are piled on top of each
other layers to transform the input into the output.
Dataset Collection:
Dataset collection is a very important activity for the
research as it is much harder to generate. The snapshots of
the anchovy and horse mackerel are captured at a resolution
of 3000×4000×3 pixels by using High definition camera.
From an experimental perspective, fish sample images are Figure 2: Data obtained from Model 1
reduced to different sizes. The dataset consists of 1049
images of fresh sardine fish and 1078 images of stale sardine
fish. All images are stored at 16 bits per channel in RGB From model 2:
color space. The Images have huge differences in terms of
quality and brightness. Illumination is also part of these image size - 704
variations in the images. Images are also taken with different batch size - 32
conditions i.e. with lights of the room on and off, changing
the position of the camera at different angles, open windows, epoch – 200
and closed windows scenario. For a real-time application, it
is very essential to manage brightness variation, camera
snapshot artifacts, shadows, and specular reflections. The
datasets are constructed by considering all these real-world
challenges.

Figure 3:Data obtained from Model 2

From model 3:
image size - 224
batch size - 32
 epoch – 200
Figure 4: Data obtained from Model 3
VI. CONCLUSION
The Food Production industry plays a major part in the
economical growth of a country. Our country is the second-
largest producer of fishes. Particularly in the fishery industry,
it is a requirement to detect the quality of fish by finding its
freshness for commercial purposes. We find deep
convolution neural network provides remarkable results in
image processing. Hence our proposed system uses a deep
convolution neural network to detect the freshness of the
anchovy and horse mackerel samples and classify fish
samples as fresh fish and stale fish. From that the model 3
has high accuracy.
VII. REFERENCES
1. Issac A., Dutta M.K., Sarkar B. Computer Vision
Based Method for Quality and Freshness Check for
Fish from Segmented Gills. Computers and
Electronics in Agriculture. 2017; 139: 10–21.
10.1016/j.compag.2017.05.006 [CrossRef] [Google
Scholar]
2. Ni Made SatvikaIswari, Wella, Ronny, “Fish
Freshness Classification Method Based On Fish
Image using k-Nearest Neighbour", 4th
International Conference on New Media Studies,
2017.
3. AlefiaNoor,Evi J, AisyahD.A.T.Safitru, Mustari,
YuantTiandho, "Melastomamalabathricum Extracts
- based indicator for monitoring shrimp freshness
integrated with classification technology using
nearest neighbor algorithm".
4. Ekoprasetyo,R. Dimas adityo,Ranipurbaningtyas,"
Classification of segmented milkfish eyes using
cosine k-nearest neighbor”, International
Conference on Applied Information Technology
5. Ian C.Navotas, Charisse Nadine V. Santos ,Earl
John M.Balderrama, Francia Emmanuelle
B.Candido,Aloysius John E.Villacanas, Jessica
S.Velasco,"Fish identification and freshness
classification through image processing using
artificial neural network ",Asian Research
Publishing Network (ARPN)2016-2018