Fruit image freshness attribute migration method based on adversarial network
A technology of attribute migration and freshness, applied in the field of computer vision, which can solve the problems of fuzzy attribute description and poor effect.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034] The present invention will be described in detail below in conjunction with the accompanying drawings and examples,
[0035] Step 1. Construct a training set;
[0036] The training set is a collection of marked fruit images, which can be crawled from the Internet with crawlers, downloaded from public image libraries, or prepared by yourself; in the end, normal fruit images need to be obtained and classified according to different degrees of freshness. Divided into four categories: surface fresh, surface dull color, surface wrinkled, surface partially rotted;
[0037] In the present embodiment, download and select high-quality fruit and the image of different freshness degree fruit from Imagenet website, utilize python crawler technology simultaneously, download the fruit image in different search engines;
[0038] Step 2, image file preprocessing;
[0039] Step 2.1, remove the wrong image file;
[0040] Use the method of program pre-reading to remove wrong images to ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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