Unlock instant, AI-driven research and patent intelligence for your innovation.

An Image Classification Method Based on Binarized Image Classification Network

A technology of binarizing images and classification networks, applied in neural learning methods, biological neural network models, instruments, etc., to achieve the effects of enhancing representation capabilities, improving computing speed, and saving storage space overhead

Active Publication Date: 2022-05-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of image classification, and proposes an image classification method based on binary image classification network

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Image Classification Method Based on Binarized Image Classification Network
  • An Image Classification Method Based on Binarized Image Classification Network
  • An Image Classification Method Based on Binarized Image Classification Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0058] Such as figure 1 As shown, the present invention provides a kind of image classification method based on binary image classification network, comprises the following steps:

[0059] S1: collect the original image, and initialize the original image;

[0060] S2: Build an image classification network based on the initialized original image;

[0061] S3: Image classification using the softmax classifier of the image classification network.

[0062] In the embodiment of the present invention, such as figure 2 As shown, step S1 includes the following sub-steps:

[0063] S11: Collect an original image with a size of 224*224*3, and add 0 elements with a width of 3 around the original image to obtain a first output image with a size of 230*230*3;

[0064] S12: Use a convolution kernel with a size of 7*7 and a step size of 1 to perform a convolution ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an image classification method based on a binary image classification network, comprising the following steps: S1: collecting original images and initializing the original images; S2: building an image classification network according to the initialized original images; S3 : Image Classification Using the Softmax Classifier of Image Classification Networks. The image classification method binarizes the convolution kernel of the convolution operation module with the largest amount of computation in traditional image classification, and uses four binarized convolution kernels of the same specification for linear approximation, saving algorithm storage space overhead.

Description

technical field [0001] The invention belongs to the technical field of image classification, and in particular relates to an image classification method based on a binary image classification network. Background technique [0002] In recent years, Deep Neural Network (DNN) has brought revolutionary changes in the field of machine learning and pattern recognition. However, most of the existing DNN models are computationally expensive and memory intensive, which hinders their deployment in devices with low memory resources or in applications with strict latency requirements. [0003] Deep Neural Network (DNN) has brought revolutionary changes in the field of machine learning and pattern recognition. Take image classification as an example: LeNet, AlexNet, ResNet, VggNet and other classic network structures have been proposed one after another. These structures are mainly aimed at the server side. Both training and reasoning are performed in a hardware environment with suffic...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/764G06V10/28G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06F18/2415
Inventor 刘启和王钰涵周世杰张准董婉祾但毅严张豹
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA