Image mathematical morphology and image restoration application in detecting underground bin level

• 来源期刊: 煤炭学报（英文版）
• 年，卷（期）: 2004,（2）
• 页码范围: 105-110
• 页数: 6页
• 语种: 英文

摘要

By using image recognition technology, the underground bin level can be detdcted. The bin image is noised by vibration, atomy, backgroun and so on. The image restoration and image mathematical morphology were used based on neural network.A modified Hopfield network was presented for image restoration. The greed algorithm with n-simultaneous updates and apartially asynchronous algorithm were combined, improving convergence and avoiding synchronization penalties. Mathematical morphology was widely applicated in digital image processing. The basic idea of mathematical morphology is to use construction element measure image morphology for solving understand problem. Presented advanced Cellular neural network that forms MMCNN equation to be suit for mathematical morphology filter. It gave the theory of MMCNN dynamic extent and stable state. It was evidenced that arrived mathematical morphology filter through steady of dynamic precess in definite condition. The results of implementation were applied in detecting undergroug bin level.