Performance comparison of image segmentation techniques for Infrared images

Thermographic images are used for condition monitoring of electrical equipment. To identify thermal anomalies, segmentation is performed on infrared images. Segmentation of IR images needs special attention as compared to visual images because of over-centralized intensity distribution in Infrared images. This paper presents an effort to compare various segmentation techniques and to find out a technique which is more suitable for Infrared images. Comparison has been done in terms of Accuracy, Precision, Sensitivity and Specificity. Five most promising methods available in the literature are considered for analysis and comparison. Region growing method gives better result for Infrared images. All other techniques cause over-segmentation because of un-even distribution of intensity in thermographic images.