Document Type: Original paper (Research paper)
University of Gonabad, Shohada Ave., Gonabad, IRAN
Department of geology, Faculty of science, University of Gonabad, Iran.
Detecting the size and shape of minerals is very important for collecting information on minerals and the texture of rocks for classification and naming. Therefore, it is necessary to study the size and shape of minerals. By combining image processing techniques and intelligent pattern recognition techniques, successful results can be gained in detecting minerals in sections as well as their size and shape, especially in thin-section images that have reduced the third dimensional effect. In this research, a method is proposed for segmentation of thin sections and finding train minerals in them. In this regard, user input is used to select some portion of the studied mineral. These data are used as seed points to learn the neural network. Support vector machine (SVM) are used as a strong classifier algorithm to find the mineral samples in the whole image. The combination of colour and mineral features is used to train the support vector machine, to find the minerals with high precision. As an example, the proposed algorithm is applied on two microscopic images of biotite diorite porphyry and Pyroxene andesite from the Khunik area of Birjand city, eastern Iran to identify the desired minerals in addition, were calculated their percentage of the whole image.