基于改进型脉冲耦合神经网络的图像二值分割

图象二值分割在图像分析和模式识别中是一项最基本也是最重要的预处理 ,它处理的好坏将直接影响后续的分析和处理效果。如何更有效、适应性更强地实现图像二值化 ,一直是困扰人们的一个难题。该文提出了一种新的图像二值分割方法———基于脉冲耦合神经网络的图像二值分割。它利用脉冲耦合神经网络的特性 ,实现图像的二值化。与传统图像二值化方法相比 ,它完全是一种与图像自适应的二值分割 ,易于软件和硬件的实现。对于含有丰富细节或低对比度的图像二值分割 ,该方法的优越性更为突出。实验结果表明了该方法的有效性。

Image Binary Segmentation Based on Improved PCNN Mode

Abstract Image binary segmentation is the most fundamental and important preprocessing in image analysis and pattern recognition, which directly affects analyses and results of post-processing. It is difficult problems that image binary segmentation is performed efficiently and adaptively. Because of poor quality of the image, some traditional automatically segmentations only based on histogram can not exactly or difficultly extract features of objects. In this paper, a new method of image binary segmentation based on improved Pulse-Coupled Neural Networks is presented. It is implemented by characteristics of Pulse-Coupled Neural Networks. Compared with other method, it is completely adaptive and precision in image binary segmentation. It is especially useful for low contrast image and segmentation of multiple objects. In our experiment, it is proved feasibly and efficiently.