Professional Documents
Culture Documents
Edge Feature Extraction Based On Digital Image Processing
Edge Feature Extraction Based On Digital Image Processing
2320
Authorized licensed use limited to: Holy Trinity Educational Society. Downloaded on September 25, 2009 at 01:29 from IEEE Xplore. Restrictions apply.
∂f ∂f ∂f
= cos α + sin α (1)
∂α ∂x ∂y
2321
Authorized licensed use limited to: Holy Trinity Educational Society. Downloaded on September 25, 2009 at 01:29 from IEEE Xplore. Restrictions apply.
(2) Sobel and Prewitt operator
To reduce the influence of noise when detecting edge, the
Prewitt operator enlarges edge detection operator template
from two by two to three by three to compute difference
operator. Using the Prewitt operator can not only detect edge
points, but also restrain the noise. The Sobel operator counts
difference using weighted for 4 neighborhoods on the basis of
the Prewitt operator. The Sobel operator has the similar
function as the Prewitt operator, but the edge detected by the
Sobel operator is wider.
Suppose that the pixel number in the 3 × 3 sub-domain of
image is as follows:
Fig. 6 the original image
A0 A1 A2
A7 f (i , j ) A3
A6 A5 A4
Or G[ f (i, j )] = X + Y (8)
2322
Authorized licensed use limited to: Holy Trinity Educational Society. Downloaded on September 25, 2009 at 01:29 from IEEE Xplore. Restrictions apply.
pre-smooth the image with Gauss low-pass filter, and then find symmetrical around the origin. Firstly we corrupt A with B
the steep edge in the image making use of the Log operator. recorded as AΘB = {x | ( B) x ⊆ A} , where ( B) x is a translation
Finally we carry on Binarization with zero grey level to give B along the vector. The interior of region is available
birth to closed, connected outline and eliminate all internal with AΘB . And A − ( AΘB) is the borderline naturally. Then
spots. But double pixels boundary usually appears using the
Log operator to detect edge, and the operator is very sensitive β ( A) is obtained. The equation of edge extraction can be said
to noise. So the Log operator is often employed to judge that β ( A) = A − ( AΘB) .
edge pixels lie in either bright section or dark section of the Structuring element is larger, the edge gained will be
image. wider.
C. Canny operator E. Simulative results analysis
The Canny operator is a sort of new edge detection In order to know about the advantages and disadvantages
operator. It has good performance of detecting edge, which has of these edge detection operators, we detect edge using these
a wide application. The Canny operator edge detection is to different operators respectively. The simulation results are
search for the partial maximum value of image gradient. The shown in Fig. 9 and Fig. 10.
gradient is counted by the derivative of Gauss filter. The
Canny operator uses two thresholds to detect strong edge and
original image Binary image edge extraction
weak edge respectively. And only when strong edge is
connected with weak edge, weak edge will be contained in the
output value. The theory basis of canny operator is shown in
equations (12)-(15).
∂ ∂2
Maximal strengths: 0 = Gn P = [ g ∗ P] (15)
∂n⊥ ∂n⊥ 2
2323
Authorized licensed use limited to: Holy Trinity Educational Society. Downloaded on September 25, 2009 at 01:29 from IEEE Xplore. Restrictions apply.
using gradient algorithm to process image. One is the certain disadvantages always exist. For example, restraining
magnitude of gradient; the other is direction of gradient. noise and keeping detail can’t achieve optimal effect
According to edge pixels gradient’s similarity on these two simultaneously. Hence we will acquire satisfactory result if
aspects, the edge pixels can be connected. Specific speaking, choosing suitable edge detection operator according to specific
if the pixel( s, t ) is in the neighbor region of the pixel( x, y) situation in practice.
and their gradient magnitudes and gradient directions must
REFERENCES
satisfy two conditions (16) and (17) respectively, then the
[1] Lei Lizhen, Discussion of digital image edge detection method, Mapping
pixels in( s, t ) and the pixels in( x, y) can be connected. The aviso, 2006, 3:40-42.
closed boundary will be obtained if all edge pixels are judged [2] Lai Zhiguo, etc, “Image processing and analysis based on MATLAB” ,
and connected. Beijing: Defense Industry Publication, 2007,4.
[3] Chen Wufan, “Wavelet analysis and its application in image
∇f䯴 x䯸 y䯵 䯹∇f䯴 s䯸 t䯵 ≤ T (16) manipulation” ,Beijing: Science Publishing House, 2002.
[4] Kenneth RC, “Digital image processing[M]” , Beijing: Electronics
Industry Publication, 1998.
ϕ䯴 x䯸 y䯵 䯹ϕ䯴 x䯸 t䯵 ≤ A (17) [5] Wang Xiaodan etc, Image analysis and design based on
MATLAB-imagery processing [M], Xi’an: Publishing House of Xi’an
Where T is magnitude threshold, A is angle threshold. University of Electrical Science and Technology, 2000, 9.
[6] Ma Yan, and Zhang Zhihui, Several edge detection operators
V. CONCLUSION comparation, Industry and mining automation, 2004, (1): 54-56.
[7] Gao Cheng, and Lai Zhiguo etc, Image analysis and application based on
These edge detection operators can have better edge MATLAB, Beijing: Publishing House of National defence industry, 2007,
effect under the circumstances of obvious edge and low noise. 4: 133-175.
[8] Wang Zhengyao, Edge detection of digital image[Master paper], Xi’an:
But the actual collected image has lots of noises. So many Xi’an Jiaotong University, 2003.
noises may be considered as edge to be detected. In order to [9] Heung-Soo Kim and Jong-Hwan Kim. A two-step detection algorithm
solve the problem, wavelet transformation is used to denoise from the intersecting chords. Pattern Recognition Letters. 2001,
in the paper. Yet its effect will be better if those simulation 22:787-798.
[10] Canny J F. A computatioal approach tO edge detection[J]. IEEE Trans
images processed above are again processed through edge on PAMI, 1985, 8(6): 679-698.
thinning and tracking. Although there are various edge [11] Marr D. Theory of edge detection[J]. Proc Roy Soc, 1980, B(27):
detection methods in the domain of image edge detection, 187-217.
2324
Authorized licensed use limited to: Holy Trinity Educational Society. Downloaded on September 25, 2009 at 01:29 from IEEE Xplore. Restrictions apply.