Segmentation of LSCM Images Based on Multi-channel Information Fusion
基于多通道信息融合的激光扫描共聚焦显微镜图像分割

A new and integrated approach is proposed to segment images in the fluorescent light channel of LSCM, which have rather low SNR and can not provide suffieiently high intensity gradient at the boundary. Rather than relying on information of the image in the fluorescent light channel alone, statistical information of corresponding image in the visible light channel is also utilized as priori knowledge. The approach is tested on LSCM images and experimental results are compared with results of C-V model.