Renyi Entropy Threshold Selection on Circular Histograms Based on GWO Algorithm
Jin Jin, Jiulun Fan · 2022 4th International Conference on Natural Language Processing (ICNLP) · 2022
The H component in the HSI color model has periodicity and the probability distribution of the H component is a circular histogram. Thresholding using circular histogram of H component is an effective way for color image segmentation. In this paper, the threshold selection criterion of Renyi entropy on circular histogram is given, and the parameters of Renyi entropy are obtained adaptively using Gray Wolf optimization algorithm. The images of Berkeley image library and remote sensing image NWPU Data Set are selected for testing, which shows that the method in this paper can effectively obtain the Renyi entropy parameters and get good segmentation results.