Open AccessA New Texture Feature Based on GLCM and Its Application on Edge-detection
Author(s) -
Chen Liu,
Ao Xu,
Caibo Hu,
Fan Zhang,
Yan Fu,
Shenglong Cai
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/780/3/032042
Subject(s) - texture (cosmology) , enhanced data rates for gsm evolution , feature (linguistics) , artificial intelligence , computer science , computer vision , pattern recognition (psychology) , edge detection , computer graphics (images) , image processing , image (mathematics) , philosophy , linguistics
In visual interpretation and recognition, the distinction and discrimination of objects in an image depend not only on the complexity of the texture of the image, but also the intensity of the contrast of the image texture. In the commonly used texture features, entropy can better reflect the complexity of the texture, but it can not reflect the difference between the gray values. The contrast can reflect the contrast of the image texture, but since only the difference is taken into consideration, the difference in the size of the pixel value itself is not considered. In view of the above phenomenon, in order to make the texture features satisfy the higher recognition and recognition of image differentiation, this paper proposes a new texture feature based on the gray level co-occurrence matrix. The new texture feature not only reflects the sharpness of the texture, but also reflects the complexity of the texture and applies the texture feature to edge detection. The results show that the edge detection based on the new texture features proposed in this paper can effectively detect various edges and has a good inhibitory effect on noise. At the same time, the edge detection results can effectively distinguish the edges of different degrees of change.