The aim of our research is to classify digital mammograms into two classes, abnormal microcalcification and normal. Texture is one of the major mammographic characteristics. The statistical textural of Gray Level Coocurrence Matrix (GLCM) used in characterizing images are contrast, energy and entropy. K-Nearest Neighbor (K-NN) and Fuzzy K-Nearest Neighbor (FK-NN) was proposed for classifying im...

Methods for extracting features and classifying textures in high resolution colour images are presented. The proposed features are directional texture features obtained from the convolution of the Walsh-Hadamard transform with different orientations of texture patches from high resolution images, as well as simple chromatic features that correspond to hue and saturation in the HLS colour space....

This paper presents a wavelet transform based tree structure model developed and evaluated for the classification of skin lesion images into melanoma and dysplastic nevus. The tree structure model utilizes a semantic representation of the spatial-frequency information contained in the skin lesion images including textural information. Results show that the presented method is effective in discr...

In this paper, we present an automatic method for character prototyping and font type characterization in machine-printed document images at a character level. To do so, we use a generic textural approach, which considers text as a texture, instead of working at a pixel level like most of the methods proposed so far. In this way, Gabor filtering seems to be an appropriate tool for texture chara...

This paper presents a multiscale method to detect neovascularization in the optic disc (NVD) using fundus images. Our method is applied to a manually selected region of interest (ROI) containing the optic disc. All the vessels in the ROI are segmented by adaptively combining contrast enhancement methods with a vessel segmentation technique. Textural features extracted using multiscale amplitude...

Contourlet domain Hidden Markov Models can provide a powerful approach for statis tical modeling and processing of contourlet coefficients of natural textural images. This multiscale model captures the statistical structure of smooth, texture and edge regions of an image. Contourlets have emerged as a new mathematical tool for image processing. They provide a compact and decorrelated image repr...

In this paper the performance of a simple scheme for the discrimination of different texture regions in colonoscopic images is investigated. The proposed scheme uses textural descriptors based on second order gray level statistics and employs a multilayer feedforward neural network to discriminate among normal and cancer regions. Preliminary results indicate that this scheme is capable of detec...

Texture analysis and classification are usual tasks in pattern recognition. Rock texture is a demanding classification task, because the texture is often non-homogenous. In this paper, we introduce a rock texture classification method, which is based on textural and spectral features of the rock. The spectral features are considered as some color parameters whereas the textural features are cal...

The multiresolution wavelet transform is an effective procedure in texture analysis. However, many images are still compressed by the methods based on the discrete cosine transform (DCT). Thus, decompression of the inverse DCT is required to yield the textural features based on the wavelet transform for the DCT-coded image. This investigation adopts the multiresolution reordered features in tex...