Plant Embryonic Cell Image Segmentation Using Pulse-Coupled Neural Networks
Traditional image segmentation algorithms in the literature exhibit weak performance on plant cells which have complex structure. On the other hand, pulse-coupled neural network (PCNN) based on Eckhorn s model of the cat visual cortex should be suitable to the segmentation of plant cell image. But the present theories are difficult to explain the relationship between the parameters of PCNN mathematical model and the effect of segmentation. Usually a good effect results from selecting the parameters experimentally many times. Meanwhile, in a proper selected parameter model, the number of iteration determines the segmented effect evaluated by visual judgment, which decreases the efficiency of image segmentation. To avoid these flaws, this paper proposes a new PCNN algorithm of automatically segmenting plant embryonic cell image based on maximum entropy principle. The algorithm realizes desirable effect. Also, in a proper set parameter model, it can automatically determine the number of iteration, avoid visual judgment, rapid the speed of segmentation and will be utilized subsequently by accurate quantitative analysis of micro- molecule of plant cell. So this algorithm is valuable for theoretic exploration and application of the PCNN. Index Terms-pulse-coupled neural network (PCNN), plant embryonic cell, image segmentation, entropy
Yi-De Ma Ro-Lan Dai Li Lian Wei Lin
The State Key Laboratory of Arid Agroecology, Lanzhou University, Lanzhou, Gansu,China 730000;School The State Key Laboratory of Arid Agroecology, Lanzhou University, Lanzhou, Gansu,China 730000 School of Information Science & Engineering, Lanzhou University, Lanzhou, Gansu, China 730000
国际会议
8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)
上海
英文
1424-1429
2001-11-14（万方平台首次上网日期，不代表论文的发表时间）