A two-dimensional entropy multi-threshold segmentation method of Yuan blue porcelain pattern based on firefly algorithm

To deal with issues such as background noise and partial information loss that arise during the process of dividing the Yuan blue porcelain pattern, a two-dimensional entropy multi-threshold method for segmenting blue-and-white porcelain patterns based on the firefly algorithm is proposed. Based on the characteristics of the patterns on the Yuan blue porcelain pattern, a median filtering matrix equation is designed to perform noise reduction on the Yuan blue porcelain pattern, and the background noise is weakened. By initializing the coefficients of fireflies, a two-dimensional entropy multi-threshold objective function is constructed, and the optimal threshold for the patterns is calculated to achieve the precise segmentation of the Yuan blue porcelain pattern. The results show that this method can effectively get rid of noise interference and missing patterns during the segmentation process. The segmentation index intersection over union of the Yuan blue porcelain patterns is 0.982, and the precision reaches 0.998. This effectively improves the accuracy rate of the segmentation of Yuan blue porcelain patterns and promotes the restoration and protection of Yuan blue porcelain cultural relics.