TY  - JOUR
T1  - A Proposed Method of Face Recognition Based on Edge Detection and SVD
AU - Hadi Abbass, Husein AU - Radhi Mousa, Zainab 
JO  - Journal of Engineering and Applied Sciences
VL  - 14
IS  - 18
SP  - 6560
EP  - 6566
PY  - 2019
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2019.6560.6566
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2019.6560.6566
KW  - Image processing
KW  -edge detection
KW  -color and gray image
KW  -Laplace filter
KW  -Gaussian
KW  -Markov
AB  - In the last decades, there has been a stronger focus on security around the world. One of the
important issues in security is the need for correct authentication of persons. Traditional methods of
establishing a person’s identity include passwords, keys or identification cards but these surrogate
representations of identity can easily be lost shared, manipulated or stolen there by compromising the intended
security. In this study, we present a new approach for face recognition using Singular Values Decomposition
(SVD) to extract relevant face features and edge detection using Markov basis. The system consists of six steps
is edge detection for input images, image resize, image merge, segmentation of images, SVD to feature extraction
and classification by use Euclidian distance to select face image. Edge detection is one of the basic steps in
image processing, image pattern recognition, image analysis and computer vision techniques. It is solving many
complex problems, edge is determined on the basis of the boundary between two different areas of color
intensity in the image. In this study, the proposed method of detecting the edge was used to detect facial
expressions that has found by Abbas and Mousa, the results of using this suggested method to color image
or gray image is more accurate and clarity than traditional methods. All images in database will change it size
to improve the result and increment recognition ratio. All images implementation the segmentation for feature
extraction for each part in image, this segmentation increases the feature the extraction of image then applies
SVD algorithm on each part from segmentation image and tack features (U) and features (S). Finally, we use
Euclidean distance to classify the face images. The system has been evaluated on five databases the result of
a classification ratio in the overall system when the use of ORL database has been obtained on ratio 97.5%,
CMU database has been obtained on ratio 100%, MMI face database has been obtained on ratio 100%, face
94 database has been obtained on ratio 100% and HZFD (Husein and Zainab Face Database) has been obtained
on ratio 100%.
ER  -