Method for determining convolution neural network convolution kernel quantity based edge detection

Abstract

The invention provides a method for determining the convolution neural network convolution kernel quantity based edge detection. The method comprises steps that the convolution neural network layer quantity and convolution kernel sizes are set; after an image dimension is reduced to 30*30, and edge detection for a training image is carried out to acquire an edge image; edge block extraction and statistics analysis processing on the edge image is carried out according to the convolution kernel size of each convolution layer to acquire the convolution kernel quantity of each layer; lastly, an integral convolution neural network is constructed to train an RGB-D data set. The method is advantaged in that in a convolution neural network construction process, the convolution kernel quantity of each convolution layer can be automatically determined, efficiency of designing the convolution neural network is improved, adaptive capability of the convolution neural network is enhanced, and the designed convolution neural network is made to be able to adapt to different-size data sets.

Description

technical field [0001] The invention relates to the field of convolutional neural networks, in particular to a method for determining the number of convolutional neural network convolution kernels based on edge detection. Background technique [0002] Convolutional neural network is a multi-layer artificial neural network proposed in the late 1980s, especially a neural network that processes two-dimensional data. It fully extracts the information in the data space by combining the characteristics of local perception, weight sharing, and downsampling, and integrates the traditional feature extraction process into the entire neural network, omitting the complex feature extraction process, making it good at processing images related machine learning problems. Since AlexNet (an improved convolutional neural network structure) was proposed by Alex Krizhevsky et al. in 2012, convolutional neural networks have gradually become a research hotspot. [0003] In the field of images, ...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, and provide a method for determining the number of convolutional neural network convolution kernels based on edge detection. The purpose is to objectively determine the number of convolutional kernels so that the constructed convolutional neural network The network has good self-adaption ability, which avoids the problems of too large structure and too many weights of the constructed convolutional neural network, and improves the efficiency of the convolutional neural network.

Images