Texture Image Segmentation by Detecting Texture Edges

この論文をさがす

抄録

This paper presents a new texture feature extraction method called Simple texel scale featare(STSF) based on the scale information of texels along a direction. And a new image segmentation method based on binary image processing is introduced.<br> The scale information of texels is extracted by comparing the gray value of two pixels. The position relation of these two pixels shows the scale feature of texels along a direction. Texel scale features can be extracted by using different position relation(distance and direction)<br> After obtaining texture feature images, we consider the texture image segmentation problem not a pattern classification problem but several texture edges integration problems, which are simple binary value line processing problems like Holes filling, Lines thinning and shorting. A new Cellular Neural Network(CNN) called Multi-step CNN(MSCNN) and Discrete MSCNN (DMSCNN) are proposed, some DMSCNNs are designed for these problems.

収録刊行物

参考文献 (9)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ