A Comparative Study on Performance Improvement for Camouflaged Object Detection

Due to high intrinsic similarities in the foreground and background of the image in Camouflaged objects it is hard for even humans to distinguish them from the background, let alone computers which perceive all visual media as numerical data. As a consequence of this approach, they require image processing algorithms to inspect the contents of images, especially ones that can differentiate the differences in foreground and background of such images. In this paper, two primary research contributions are presented. First, this research study attempts to find the most advantageous parameters to create a model to detect COD. Second, a comparative study has been presented on the performance of different sets of parameters to perform object detection. Experimental analysis provided in this paper can be used to serve as guidelines for future work in both object detection and relevant neural network-based learning systems.