IMPROVING THE IMAGE QUALITY OF GRAYSCALE THERMAL IMAGES TAKING FROM PHOTOVOLTAIC PANEL WITH CONTRAST ENHANCEMENT METHOD

The condition of photovoltaic thermal image data is crucial to a great va- riety of developing research and implementations since thermal images are competent in exposing meaningful unseen features for detecting hotspots as the abnormality in a pho- tovoltaic module. However, the images may degrade from unsatisfactory image quality because several images may have too low contrast. In addition, the details are at variance with human visual perception due to limitations of the image acquisition device and di- versities of the surroundings of the photovoltaic. Therefore, an image enhancement stage is needed to solve these issues. This research presents the comparison methods for the image enhancement stage that promotes the details of photovoltaic thermal images by en- hancing contrast. These methods were completed using contrast-stretching and histogram equalization. The findings indicated that histogram equalization gave superior histogram and CDF properties than contrast-stretching. Additionally, it recognized hotspot cells well in quantitative analysis, with an average accuracy of 96.93% and an average F1 Score of 81.84% from 30 photovoltaic thermal images.