IRT image segmentation and enhancement using FCM-MALO approach

摘要： Infrared Thermography (IRT) is a method that has modernized the way for monitoring the thermal conditions, finding some potential faults or defects that could be available in electrical systems. In the proposed work, IRT electrical images are taken for diagnosing the faults by the image pre-processing and segmentation process. Initially, the IRT images are changed over into a grayscale image, trailed by image pre-processing is performed where histogram equalization is applied. With the intention of segmenting the faulty portion (high temperature zone) from the electrical equipment, Fuzzy C Means (FCM) strategy is introduced. For optimizing the centroid of FCM algorithm Modified Ant Lion Optimization (MALO) is proposed. From the segmented images, small size portions are removed by using Region Props function. This operation can remove the isolated pixels from the image and extract image components for better representation of images. The optimum results show that the proposed work accomplishes maximum segmentation accuracy compared to existing segmentation algorithms.