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

A Fast Matching Calculation Method for Fruit Images

A technology of matching calculation and fruit, applied in the field of image processing, can solve the problems of complex methods, long time, high speed requirements, etc.

Active Publication Date: 2016-10-12
杭州诺田智能科技有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the fruit detection and grading technology has high requirements on the speed of the method. Although the matching adaptability of the SIFT method is high, the method is complex, computationally intensive, and time-consuming.

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 Fast Matching Calculation Method for Fruit Images
  • A Fast Matching Calculation Method for Fruit Images
  • A Fast Matching Calculation Method for Fruit Images

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0137] Use the red snake fruit with spots as the implementation object, place the red red snake fruit on the fruit tray, make the calyx and fruit stem connection line of the red red snake fruit basically perpendicular to the horizontal plane, adjust the object distance between the red red snake fruit and the camera lens to 970mm, and adjust the zoom lens of the camera The focal length is 25mm, the camera CCD size is 1 / 3 inch, image acquisition is performed, and the region of interest is extracted from the image acquisition screen, and the left and right images have a width of 548 pixels and a height of 568 pixels. The rate is 0.146mm / pixel, such as figure 2 shown.

[0138] Such as image 3 As shown, the left image and the right image are subjected to background segmentation, and then the image is scanned from top to bottom, and the leftmost pixel and the rightmost pixel of the fruit contour are respectively recorded in the left image and the right image, and the most Subtra...

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 fast matching calculation method for fruit images. The fast matching of fruit images is realized through the extraction of effective matching areas and the improvement of SIFT method. Firstly, the side images of fruits are obtained, and the left and right boundary points of fruit contours are searched in the side images, and then the effective areas required for matching are extracted; then the effective areas are Feature point extraction: get the feature point set with feature point descriptors; then match the feature points by calculating the Euclidean distance between the feature point descriptors in the two feature point sets, and get the matching point set to be selected. The matching points are eliminated to obtain the correct matching point set. The present invention replaces the structure of the scale space in the SIFT method with a single-layer Gaussian difference image and cancels the rotation invariance, and reduces the dimensionality of the feature point descriptor, reducing redundant calculations in the fruit image feature point detection process; through the effective overlapping area Extraction removes unnecessary calculations and improves the calculation speed.

Description

technical field [0001] The invention relates to an image matching calculation method, in particular to a fast matching calculation method for fruit images in the technical field of image processing. Background technique [0002] Image matching refers to identifying the same point between two or more images through a certain matching method. In recent years, image matching has become a key technology and research hotspot in the fields of image analysis and processing such as object recognition, robot map perception and navigation, image stitching, 3D model building, gesture recognition, image tracking, and motion comparison. [0003] The acquisition of fruit surface information is the basis for the detection of fruit quality indicators such as size, shape, surface color and surface defects. The accuracy of surface color and surface defect detection depends on the acquisition of complete fruit surface images. Image mosaic technology is the key to achieve complete fruit surfac...

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): G06T7/00
Inventor 饶秀勤林文彬应义斌
Owner 杭州诺田智能科技有限公司
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