Classification of Rock Images using Textural Analysis

The classification of natural images is an useful task in current computer vision, pattern recognition applications etc. Rock images are a typical example of natural images, therefore their analysis is of major importance in the rock industry and in bedrock investigations. Rock image classification is based on specific textural descriptors which are extracted from the images. Using these descriptors, images are divided into various types. In the case of natural images, the feature distributions are often non-homogeneous and the image classes are also overlapping in the feature space. This can be problematic, if all the descriptors are combined into a single feature vector in the classification of an image. A method is presented for combining different visual descriptors in rock image classification. In this paper, k-nearest neighbor classification will be carried out for pair of descriptor separately. After that, the final decision is made by combining the results of each classification. The total numbers of the neighbors representing each class are used as votes in the final classification. The classification method will be tested using three types of rock. DOI: 10.17762/ijritcc2321-8169.15039