Abstract
Convolutional neural network is an important neural network model in deep learning and a common algorithm in computer vision problems. From the perspective of practical application scenarios, this paper studies whether padding in convolutional neural network convolution layer weakens the image edge information. In order to eliminate the background factor, this paper select MNIST dataset as the research object, move the 0-9 digital image to the specified image edge by clearing the white area pixels in the specified direction, and use OpenCV to realize bilinear interpolation to scale the image to ensure that the image dimension is 28×28. The convolution neural network is built to train the original dataset and the processed dataset, and the accuracy rates are 0.9892 and 0.1082 respectively. In the comparative experiment, padding cannot solve the problem of weakening the image edge weight well. In the actual digital recognition scene, it is necessary to consider whether the core recognition area in the input image is at the edge of the image.