Bloch quantum artificial bee colony algorithm and its application in image threshold segmentation

Image segmentation is a key step in many computer vision applications. Threshold-based methods are widely used for image segmentation. The core problem of threshold segmentation is how to get a reasonable threshold. An improved algorithm of Bloch spherical coordinates for quantum artificial bee colony is proposed in this paper. The two-dimensional linear cross-entropy of the image is used as a fitness function. Meanwhile, the image threshold segmentation problem is researched with BQABC. Firstly, quantum computation is introduced and the quantum artificial bee colony algorithm is improved. Secondly, the improved quantum artificial bee colony algorithm is applied to image threshold segmentation. Finally, the OTSU algorithm, ME method, MEM, ABC algorithm and BQABC algorithm are applied to the threshold segmentation of standard images and network image. The response curve and performance index of five algorithms are compared and analyzed. The experimental results show that the BQABC algorithm can obtain the segmentation threshold and it has a good image segmentation effect accurately and quickly.