Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image contour detection algorithm based on machine learning method

A contour detection and machine learning technology, applied in the field of image contour detection algorithms based on machine learning

Inactive Publication Date: 2015-02-18
TIANJIN POLYTECHNIC UNIV
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems in the prior art, the present invention provides a comprehensive feature, which further improves the accuracy of image contour acquisition, solves the problem of getting rid of the subjective judgment of people when judging the digital image contour, and is used for digital images. Image Contour Detection Algorithm Based on Machine Learning Method

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 contour detection algorithm based on machine learning method
  • Image contour detection algorithm based on machine learning method
  • Image contour detection algorithm based on machine learning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be described in detail below with reference to the accompanying drawings and embodiments.

[0018] A contour detection algorithm based on a machine learning method of the present invention, for each pixel in each image in the test set, while considering the gPb contour detection algorithm, the method utilizes a direction-oriented contour detection algorithm to eliminate gPb in the calculation The redundancy problem that arises when solving the problem, and then supplement the features of the trend direction between image pixels to form new features. All the pixel features obtained form the training samples of machine learning and input to the classifier, and after cross-validation, a linear model is obtained. After predicting the image pixel features of the newly input picture according to the model, the image contour ( figure 1 ). When processing images, this method gets rid of human participation in contour judgment activities through mach...

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 contour detection algorithm based on a machine learning method. According to three-layer characteristics obtained by the calculation of an image of a test set and image characteristics provided by gPb, a classifier is subjected to cross validation training by virtue of supervised learning to obtain a prediction model. The newly-input image can be predicted based on the model to obtain a precise contour of the image, and dependence on subjective setting of a person in a conventional image contour detection algorithm is eliminated. When an image contour is judged by virtue of the method, local characteristics under a plurality of channels of the image and global characteristics among pixels of the image are combined, so that the obtained image contour has excellent significance. Compared with a gPb contour detection algorithm, the image contour detection algorithm based on the machine learning method has high accuracy and recall rate, and the contour information of the image under a complicated environment can be effectively captured.

Description

technical field [0001] The invention relates to a technology for contour detection and division of digital images, especially the method of machine learning is added, so that the contour detection task of the image transitions from the past subjective dependence type to the independent judgment type, and no longer requires human participation as the main body The judgment activity of the contour realizes a breakthrough in the direction of intelligence. Background technique [0002] Recognizing the edge contour of an object is an indispensable ability in human visual function. An excellent contour detection algorithm has a lot of practical significance, and it can be applied in many different fields, including image segmentation, pattern recognition, artificial intelligence, and medical image analysis. It can be said that it is the cornerstone of the field of computer vision. Similar to concepts in the field of computer vision such as "texture" or "human face", the concept ...

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): G06K9/66G06T7/00
CPCG06T7/13G06T2207/20081
Inventor 陈科刘浩
Owner TIANJIN POLYTECHNIC UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com