Texture description and segmentation through fractal geometry
Computer Vision, Graphics, and Image Processing
Texture Features for Browsing and Retrieval of Image Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Processing
Image Segmentation and Uncertainty
Image Segmentation and Uncertainty
| Hi-index | 0.00 |
The paper presents a classification and identification method for the zonal noise in the textural images. To identify zonal noise in the textural images, a reference database with the textural images is used. For the region recognition with zonal noise, a decision theoretic method is used. The features are of the statistic type and derive from the medium co-occurrence matrices: contrast, energy, entropy, homogeneity, and correlation. The algorithm is implemented in C++ programming language and allows the simultaneously display of both the investigated regions pairs, and the Euclidian distance between them. Our experimental results indicate that the five selected features for texture classification give good results to identify the zonal noise. The results also confirm that the distances between the similar regions are relatively small and the distances between regions from different textured images with zonal noise are relatively great.