Image classification and recognition method

A classification recognition and image technology, applied in the field of image recognition, can solve the problems of many calculation parameters, over-fitting, long running time, etc., and achieve the effect of improved classification and easy realization

Inactive Publication Date: 2018-09-14
HUBEI UNIV OF TECH
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional convolutional neural network, LeNet's image recognition accuracy is low, and the model is not stable enough
AlexNet still has obvious overfitting phenomenon after adding dropout, and there are many parameters to be calculated, and the running time is long

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
  • Image classification and recognition method
  • Image classification and recognition method
  • Image classification and recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0016] please see figure 1 and figure 2 , a method for image classification and recognition provided by the present invention is characterized in that it comprises the following steps:

[0017] Step 1: read local pictures;

[0018] This embodiment takes the detection pictures of lobsters as an example, and first reads 20,000 local pictures;

[0019] Step 2: Generate batches and scramble the sample data;

[0020] According to the order of the samples, every 32 batches are used as a batch, and the sample data is randomly disrupted, so as to enhance the sta...

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 and recognition method. The method includes the following steps that: local pictures are read; a batch is generated, and sample data are scrambled; an image classification and recognition model is constructed; parameters are trained until the image classification and recognition model reaches stability; and the image classification and recognition model is saved for related image recognition. According to the image classification and recognition method of the invention, traditional algorithms such as LeNet, AlexNet and GoogleNet are combined, sothat problems such as low recognition accuracy and over-fitting can be solved. The image classification and recognition method of the invention is obviously improved in image recognition and classification and is easier to implement compared with algorithms such as GoogleNet and R-CNN which have more layers and complex models; and the image classification and recognition method of the invention ismore practical in practical application, and can be used to classify various images as long as slightly modified.

Description

technical field [0001] The invention belongs to the technical field of image recognition, relates to an image classification and recognition method, in particular to an image classification and recognition method combined with traditional algorithms such as LeNet, AlexNet and GoogleNet. Background technique [0002] The active development of computer technology and digital image processing has made computer vision technology a research hotspot since the 20th century. At present, computer vision related technologies are becoming more and more mature, such as pattern recognition, image processing and machine learning. Every aspect of daily life, and play a significant value. As a branch of machine learning, deep learning is a derivative of neural network algorithms. Its advantages of "automatic data analysis" have achieved remarkable results in the classification and recognition of images, voices, texts, etc., and have attracted the attention of scholars at home and abroad. ...

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 Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/24
Inventor 舒军杨露涂杏沈开斌李鑫武蒋明威吴柯舒心怡潘健王淑青陈张言徐成鸿李志愧刘伟
Owner HUBEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap