An Image Recognition Method Based on Cascaded Downsampling Convolutional Neural Networks

Abstract

The invention discloses an image recognition method based on a cascaded downsampling convolutional neural network, comprising: constructing an image recognition model based on a cascaded downsampling convolutional neural network; the cascaded downsampling based convolutional neural network includes a subject network and Two independent prediction networks; the subject network includes several convolutional layers and several cascaded down-sampling blocks; each of the independent prediction networks includes a class prediction sub-network and a bounding box prediction sub-network; the independent prediction network's The prediction result is obtained by non-maximum value suppression to obtain the image recognition result; the constructed image recognition model is trained, and image recognition is performed through the trained image recognition model. The invention can carry out real-time and accurate identification of images.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an image recognition method based on a cascaded downsampling convolutional neural network. Background technique [0002] With the continuous development of computer vision, the fields of industrial inspection, traffic counting and automatic driving have also developed. The most important technology in these fields is image recognition, that is, real-time detection of objects in images. Most current image recognition methods are based on deep convolutional neural networks, and use sliding windows to extract features from images. The earliest success of deep learning was Yann LeCun's successful application of deep learning to handwritten digit recognition. The image recognition method based on deep neural network has achieved good results on various data sets (for example, ImageNet, Pascal VOC), but the detection accuracy on the MSCOCO data set is still low. Scenes that...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an image recognition method based on cascaded downsampling convolutional neural network, to solve the technical problems in the prior art, and to be able to accurately recognize images in real time

Images