基于细胞神经网络的图像边缘检测研究

Research on Edge Detection in Digital Images Based on CNN

提出一种数字图像边缘检测算法,采用差分进化算法优化细胞神经网络,通过简单的训练图像对细胞神经网络的模板参数进行适应性调整,得到边缘检测算子,采用该算子提取图像的边缘。实验结果验证了算法的有效性,该算法能够获得较好的图像边缘。

An efficient algorithm for edge detection in digital images is introduced, that the cellular neural network （CNN） is optimized by differential evolution algorithm （DEA）. To obtain edge detection operator,the cloning template of the CNN is adaptively tuned by using simple training images. The edge in digital images is extracted by using the edge detection operator obtained. The experimental results indicate that the effectiveness of the proposed algorithm is verified and the algorithm can obtain better edge in digital images.