An Anomaly Detection Method Based on Fuzzy Histogram Hyperbolization and Gray Level Co-occurrence Matrix

A method for an anomaly detection system was developed to automate process of recognizing an anomaly of roentgen image by utilizing fuzzy histogram hyperbolization image enhancement and gray level co-occurrence matrix(GLCM). The system consists of image acquisition, pre-processor, feature extractor, response selector and output. Fuzzy Histogram Hyperbolization is chosen to improve the quality of the roentgen image. The fuzzy histogram hyperbolization steps consist of fuzzyfication, modification of values of membership functions and defuzzyfication. The GLCM is computed from the resulting image and properties are measured from the GLCM. In order to reduce the size of the GLCM, the image intensity is reduced to the range of [0,63]. Experimental results indicate that the fuzzy histogram hyperbolization method can be used to improve the quality of the image. The proposed method is capable to detect the anomaly in the roentgen image.