A preprocessing method for fruit and vegetable recognition based on visual subject detection

A fruit and vegetable recognition and preprocessing technology, applied in image data processing, character and pattern recognition, image analysis, etc.

Active Publication Date: 2020-11-13
NANJING XIAOZHUANG UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 1. Non-uniform scaling

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
  • A preprocessing method for fruit and vegetable recognition based on visual subject detection
  • A preprocessing method for fruit and vegetable recognition based on visual subject detection
  • A preprocessing method for fruit and vegetable recognition based on visual subject detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention collects 12 kinds of common fruit and vegetable images, a total of 1461, as shown in Table 1. These images were acquired under uncontrolled light source and uncontrolled background conditions. Segmentation and clipping using a single feature is relatively difficult, and the present invention uses a two-dimensional OTSU algorithm and an adaptive Canny algorithm for edge detection. The two-dimensional OTSU algorithm is an improved OTSU algorithm, which can divide the image into foreground color and background color according to color features. Because the environment of the image library used in the present invention is quite different, the image cannot be better segmented by using this method. The adaptive Canny algorithm is an improved algorithm of the Canny algorithm. This algorithm can extract image contour features, but if the image has many details, the algorithm obtains more contours, and it is not easy to segment according to the contours. ...

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 fruit and vegetable recognition preprocessing method based on visual subject detection. Aiming at the problem of difficult cropping and segmentation of fruit and vegetable images in complex environments due to factors such as uneven illumination and uncontrolled background, a method based on visual subject detection is proposed. preprocessing algorithm. Firstly, adjust image brightness and remove noise, then use manifold sorting to perform saliency detection to obtain a saliency image, and finally use gradient image and position weighting to fuse to obtain image cropping and complete image preprocessing. Through experiments, the fruit and vegetable images in complex environments can be correctly cropped, and better accuracy, robustness and real-time performance can be achieved.

Description

technical field [0001] The invention relates to the fields of food application and health, in particular to a fruit and vegetable recognition preprocessing method based on visual subject detection, which is used in the technical field of fruit recognition. Background technique [0002] With the continuous development of the field of artificial intelligence, people's lives are gradually becoming intelligent, and image recognition technology occupies an important position in the field of artificial intelligence. The invention studies the location technology of fruits and vegetables under complex environment and uncontrolled lighting conditions, uses the improved manifold sorting saliency detection algorithm, and integrates gradient energy and position information on the basis of the original technology to locate the fruits and vegetables. [0003] In the image processing stage, the original image cannot be directly applied to image recognition software due to factors such as a...

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): G06K9/40G06K9/46G06K9/48G06K9/62G06T7/12G06T7/564
CPCG06V10/30G06V10/478G06V10/473G06V10/46G06V10/56G06V10/751G06V20/68
Inventor 王燕清
Owner NANJING XIAOZHUANG UNIV
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