Abstarct: Formation Micro Imager (FMI) can directly reflect is an important factor to classify stratums and identify lithology for the oil and gas exploration. Conventionally, people analyze FMI images mainly with manual processing, which is, however, extremely inefficient and incurs a heavy workload for experts. In this thesis, we propose an automatic segmentation method using image processing and pattern recognition technologies. We investigate the characteristics of laxyers, fractures, vugs and pores in FMI images carefully. A key aspect in extracting quantitative information from FMI logs is to segment the FMI image to get image of laxyers, Fractures, vugs and pores. In this thesis, an automatic method baxsed on FCM clustering and Otsu thresholding method is introduced in order to extract quantitative information from FMI images. All pixels are clustered using FCM clustering algorithm at the first step. The second step uses KNN for other clustering. Then, uncovered columns of FMI image and image inequality are removed. Finally, the Otsu thresholding method is investigated for improving pixel-clustering step. Filed data processing examples show that sub image of laxyers, fractures, vugs and pores can be accurately separated from original FMI images.