Richer feature for image classification with super and sub kernels based on deep convolutional neural network

Pengjie Tang, Hanli Wang

Abstract: Highlights•The concepts of super convolutional kernel and sub convolutional kernel are proposed inspired by the process that human observes objects.•A novel Parallel Crossing Deep Convolutional Neural Network (PC–DCNN) model is designed to simulate the human binocular mechanism for extracting richer information.•A framework named multi-scale PC–DCNN is deployed based on super convolutional kernel and sub convolutional kernel for image classification.