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

Method and system for fruit and vegetable identification

A technology for fruit and vegetable recognition and fruit and vegetable recognition, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of large amount of calculation, cumbersome recognition steps, difficult real-time application, etc., and achieve the effect of improving work efficiency and saving costs

Inactive Publication Date: 2016-04-13
UNIV OF SCI & TECH OF CHINA
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] There are many problems faced by current image recognition: firstly, the recognition of an image needs to go through many different processes, and the recognition steps are relatively cumbersome; in addition, various current image recognition algorithms have certain limitations, and the amount of calculation Large, difficult to apply in real time

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
  • Method and system for fruit and vegetable identification
  • Method and system for fruit and vegetable identification
  • Method and system for fruit and vegetable identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] figure 1 The flow chart of a method for identifying fruits and vegetables provided in Embodiment 1 of the present invention mainly includes the following steps:

[0023] Step 101. Perform preprocessing on the fruit and vegetable images collected by the terminal.

[0024] After the terminal (for example, a mobile phone) collects the images of fruits and vegetables, it is sent to the server for identification through the network, or the terminal is directly identified after loading the database required for identification on the terminal.

[0025] Due to the variety of terminals and the influence of factors such as the user's shooting angle and distance, if the image is directly recognized, there will be a large error. Therefore, after receiving the image, the server needs to carry out standardized preprocessing, for example, extracting the fruit and vegetable graphics with closed edges, and correcting and unifying the size of the graphics.

[0026] Step 102 , extract f...

Embodiment 2

[0037] In order to facilitate understanding of the present invention, now in conjunction with the attached figure 2 The present invention is further introduced, such as figure 2 As shown, it mainly includes the following steps:

[0038] Step 201, receiving the fruit and vegetable images collected by the terminal.

[0039] The terminal can be a mobile phone or a camera with network function, so that it can be used for shooting anytime and anywhere, which is convenient for users; and the identification process and required data are stored on the server side, which can reduce the calculation amount and storage space of the terminal.

[0040] Step 202, preprocessing the fruit and vegetable images.

[0041] Due to the variety of terminals and the influence of factors such as the user's shooting angle and distance, if the image is directly recognized, there will be a large error. Therefore, the server needs to perform standardized preprocessing after receiving the image.

[00...

Embodiment 3

[0073] image 3 It is a schematic diagram of a fruit and vegetable identification system provided in Embodiment 3 of the present invention, the system mainly includes:

[0074] The preprocessing module 31 is used to preprocess the fruit and vegetable images collected by the terminal;

[0075] The difference degree scoring calculation module 32 is used to extract feature data from the preprocessed fruit and vegetable image and perform difference degree detection with the feature data corresponding to the fruit and vegetable image in the database to obtain a difference degree score;

[0076] The recognition result output module 33 is configured to select several fruit and vegetable images with the lowest difference scores and output them to the terminal as recognition results.

[0077] Described preprocessing module 31 comprises:

[0078] Closed graph acquisition module 311, used to find out the edge of the fruit and vegetable image through the edge detection operator canny op...

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 a method and a system for fruit and vegetable recognition. The method comprises the steps: carrying out pre-processing on fruit and vegetable images collected and obtained by a terminal; extracting feature data from the pre-processed fruit and vegetable images, carrying out detection on difference degrees between the feature data and feature data which are in a data bank and correspond to the fruit and vegetable images, and obtaining a grade of the difference degrees; selecting a plurality of fruit and vegetable images with the lowest grade on the difference degrees as a recognition result, and outputting the result to the terminal. Through the method, the fruit and vegetable recognition can be conveniently and fast conducted, working efficiency is improved, and cost is saved.

Description

technical field [0001] The invention relates to the technical field of computer image recognition, in particular to a method and system for fruit and vegetable recognition. Background technique [0002] The research goal of image recognition technology is to make a meaningful judgment on the object category in the observed image. That is to use modern information processing and computing technology to simulate and complete the process of human cognition and understanding. [0003] There are many methods of image recognition, which can be summarized into three types: statistical (or decision theory) method, structural (or syntax) method and neural network method. The statistical method is based on the mathematical decision theory, and a statistical recognition model is established according to this theory. Structural recognition is a supplement to statistical recognition methods. Statistical methods use numerical values ​​to describe the characteristics of images, while str...

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): G06K9/00
Inventor 朱明鲍天龙孙永录
Owner UNIV OF SCI & TECH OF CHINA
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