摘要：Detecting the neural processes like axons and dendrites needs high quality SEM images. This paper proposes an approach using perceptual grouping via a graph cut and its combinations with Convolutional Neural Network (CNN) to achieve improved segmentation of SEM images. Experimental results demonstrate improved computational efficiency with linear running time.
关键词：Convolutional Neural Network; SEM image; perceptual grouping;constraints via a graph cut; segmentation using a graph cut; graph cut optimization;affinity graph; backpropagation; Maxflow/Mincut algorithm; Neuronal;segmentation.
