Fruit grader based on image processing

A fruit sorting and image processing technology, applied in the field of agricultural machinery, to avoid ghosting, improve sorting accuracy and sorting efficiency

Inactive Publication Date: 2013-05-22
SHANGHAI JIAO TONG UNIV
View PDF8 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims at the above-mentioned deficiencies existing in the prior art, and provides a fruit sorting device based on image processing, which can avoid image ghosting caused by the existence of camera exposure time and the movement of transported fruits in the prior art, and improve the quality of the collected images. Fruit image quality reduces the difficulty of image processing; RGB images and near-infrared images of multiple fruits are collected at one time, and the fruit mask image obtained by using the large brightness difference between the near

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
  • Fruit grader based on image processing
  • Fruit grader based on image processing
  • Fruit grader based on image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] like figure 1 As shown, this embodiment includes: intermittent multi-channel material transmission mechanism 1, continuous single-channel material transmission mechanism 2, classification box 3, feeding mechanism 4 and fruit information collection mechanism 6, wherein: intermittent multi-channel material transmission mechanism The front end of 1 is provided with feeding mechanism 4, and the top is provided with fruit information collection mechanism 6, and the tail is vertically connected with continuous single-channel material transmission mechanism 2, and the sorting box 3 is connected with continuous single-channel material transmission mechanism 2;

[0044] The fruit information collection mechanism 6 includes: a dome-shaped light source scattering device 5, a pair of triggers (not shown), several cameras 7 and light sources 20 connected to the computer, wherein: a pair of triggers are arranged on the intermittent multi- The channel material transmission mechanism 1...

Embodiment 2

[0058] like Figure 9 As shown, the steps of this embodiment include:

[0059] 1) Separate the NIR image of the fruit, and then threshold the image to obtain the mask image of the fruit image;

[0060] 2) Extract the G component image in the RGB image of the fruit;

[0061] 3) The mask image obtained by using the NIR image can remove the background in the G component image, and eliminate the background interference with the same brightness value as the defect;

[0062] 4) Complete the G component image after the background is segmented with a single threshold, and obtain the defect image of the fruit;

[0063] 5) Mark the location of the area where the fruit exists. The area is represented by 1, 2, ... n, and the same batch of fruit images are fused, which is the sum of the defect areas of different orientations of the fruit at the same label. According to the fruit classification criteria, complete each The grade division of the area, the grade is represented by 1, 2, ...i...

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

A fruit grader based on image processing belongs to the technical field of agricultural machinery and comprises a loading mechanism, a batch-type multi-channel material transport mechanism, a continuous single-channel material transport mechanism, a sorting box and a fruit information collecting mechanism. The front end of the batch-type multi-channel material transport mechanism is provided with the loading mechanism, the upper part of the batch-type multi-channel material transport mechanism is provided with the fruit information collecting mechanism, and the tail part of the batch-type multi-channel material transport mechanism is in vertical connection with the continuous single-channel material transport mechanism which is connected with the sorting box. Due to the effective machinery design, the fruit grader based on image process disclosed by the invention effectively avoids the ghost phenomenon when images are collected without lowering the grading efficiency and effectively improves the grading precision and the grading efficiency by combining with a schedule control method.

Description

technical field [0001] The invention relates to a sorting device in the technical field of agricultural machinery, in particular to a fruit sorting device based on image processing. Background technique [0002] At present, machine vision is widely used in the detection of fruit appearance quality. The camera collects the surface image of the fruit, and then transmits it to the computer. Through image processing, the external quality characteristics such as the size, color, and defect of the fruit image are obtained, and then the fruit is graded according to the national fruit grading standard. At present, the more common ones are single-channel sorter device and multi-channel fruit sorter device. The single-channel sorting machine is the most common sorting equipment. The fruit is automatically loaded by the feeding mechanism. During the feeding process, a mechanical device is used to arrange the fruit in a single row. A camera is installed above the assembly line. When th...

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
IPC IPC(8): B07C5/00B07C5/34B07C5/342B07C5/02B07C5/36
Inventor 张保华刘成良贡亮李彦明李子枫林昌建郭凯峰金理钻邵达
Owner SHANGHAI JIAO TONG 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