改进遍历过程的PCNN在图像处理中的应用

Application of PCNN with the improved traversal process in image processing

图像通常包含多个颜色相同的连通区域,针对脉冲耦合神经网络无法对它们进行分离提取的问题,提出一种改进遍历过程的脉冲耦合神经网络模型。通过引入深度优先搜索遍历算法,将不连通的多个同色区域分层激活,从而实现分离。最后针对图像噪声对新模型的影响,对其作进一步改进。以每层激活区域的大小作为图像噪声杂点判定的依据,并引入均值滤波算法来消除。实验验证了改进后的模型对图像多个同色连通区域的分离效果及噪声杂点的去除能力。

Images usually have multiple connected regions of the same color. For the problem that Pulse Coupled Neural Networks （PCNN） cannot abstract these areas separately, a PCNN model with improved traversal process was proposed. By introduceing the depth-first search traversal algorithm, multi-unconnected regions were activated on different layers, so as to achieve a separation. Finally, the new model was improved again for the effect of image noise. The activated scope in each layer was used to detect noisy pixels, and then the mean-shift algorithm was introduced to eliminate the noisy pixels. The separation effect of multi-regions with the same color in the image and the ability to eliminate noise has been verified by experiment.