Image detection method for rotting oranges caused by penicillium infection

An image detection and indexing image technology, applied in the field of spectral detection, can solve the problems of ignoring feature expression, not suitable for automatic detection of Penicillium digitatum infected fruit, etc., to reduce postharvest losses, simple and effective image processing algorithm, and increase farmers' income Effect

Active Publication Date: 2016-03-23
BEIJING RES CENT OF INTELLIGENT EQUIP FOR AGRI
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, their research only focused on the extraction of complex features of the visible-near-infrared spectrum, ignoring the spatial information of the image to express the features of the region of interest, which is not suitable for the automatic detection of Penicillium digitatum-infected fruits

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
  • Image detection method for rotting oranges caused by penicillium infection
  • Image detection method for rotting oranges caused by penicillium infection
  • Image detection method for rotting oranges caused by penicillium infection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] The invention provides an image detection method of rotten citrus caused by Penicillium infection, which can visualize and image the infected area that is difficult to detect and provide an effective image processing and analysis method. Principal component clustering analysis was performed on the component spectra of the region and the component spectra of fungal infection regions of interest. Prepare 120 citrus fruit oranges. The 120 samples include 60 samples of normal fruit and 60 samples of fungal-infected fruit. The fungal-infected fruit is obtained by artificial inoculation. For the citrus peel tissue of Penicilliumdigitatum, disinfect with 75% medical alcohol for 1min, rinse the spores with sterile water, dissolve the spores in sterile water to form a spore solution, and then use a syringe to inoculate the spore solution into normal fruits, the inoculation depth is about 10mm under the citrus peel . Then place it in a plastic incubator (ambient temperature 25-2...

Embodiment 2

[0060] Based on the characteristic wavelength that embodiment 1 obtains, the method of the present invention comprises the following steps:

[0061] A: Use the visible-near-infrared hyperspectral imaging system (ImSpectorV10E, Spectral Imaging Ltd, Oulu, Finland) to acquire single-wavelength spectral images at four characteristic wavelengths of the citrus fruit to be tested. The four characteristic wavelengths are 575nm, 698nm, 810nm and 969nm ,Such as Figure 5 As shown, it can be seen from the figure that on the one hand, the brightness of the fruit surface is very uneven, and on the other hand, the contrast between the infected area and the normal peel area is very inconspicuous. Therefore, it is impossible to directly use single-wavelength images to extract the infected area.

[0062] B: Perform brightness unevenness correction on the 4 characteristic wavelength images. The brightness unevenness correction method is as follows:

[0063] 1) Add the 4 characteristic wavelen...

Embodiment 3

[0076] Example 3: Sample with the infected area at the edge of the fruit

[0077] As a special case, when the infected area is located at the edge of the fruit, it is the most difficult to perform image defect segmentation detection at this time. According to the same method as in Example 2, the detection results are as follows Figure 16 as shown, Figure 14 (original image in color) and Figure 15 represent the second indexed image and the R component of the indexed image, respectively, from Figure 16 It can be seen from the detection results that the method provided by the present invention will not be affected by the position of the infected area in the fruit image, and satisfactory results will be obtained even if the infected area is located at the edge of the fruit in the image.

[0078] Table 1 Sample Evaluation Results

[0079]

[0080] Using the above steps, the recognition results of 60 training set samples (30 normal fruit and 30 fungal infected fruit) and 6...

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 provides an image detection method for rotting oranges caused by penicillium infection, comprising the steps of: A, collecting the single wavelength spectrum images of four characteristic wave lengths of an orange fruit to be detected; B, correcting non-uniform surface brightness on the images; C, after correction, stacking the images to obtain a characteristic wavelength combination image I; D, converting the characteristic wavelength combination image I into an index image F1; E, extracting the R component image of the three primary color component in the index image F1 and preprocessing the image; F, converting into an index image F2 again and extracting the R component image of the three primary color component in the index image; and G, performing objective area division and circularity determination on the R component image obtained in step F. The method collects the single wavelength spectrum images of four characteristic wave lengths of an orange fruit to be detected, and realizes clear and visual display of an orange fungal infection area which is hard to perceive based on the combination of an image combination formula and an image processing method, thereby more effectively and accurately identifying rotting oranges caused by penicillium infection.

Description

technical field [0001] The invention belongs to the technical field of spectrum detection, and in particular relates to a detection method based on visible-near infrared spectrum. Background technique [0002] Citrus is a fruit with unique flavor and rich nutrition, which is deeply loved by consumers. my country is the world's largest citrus producer, and the citrus industry has a huge economic market both internationally and domestically. In order to improve the competitiveness of citrus fruit quality in the domestic and international markets, post-harvest automated rapid grading technology for citrus fruits has been prepared. attention. Compared with other common external defects such as scarring, rot caused by fungal infection is the most serious defect of citrus fruits. Fungal disease infection is the most important cause of fresh citrus rot during storage and transportation, and Penicilliumdigitatum infection is particularly important . In recent years, studies have f...

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 Applications(China)
IPC IPC(8): G06T7/00
CPCG06T7/0008G06T2207/10024G06T2207/20212
Inventor 李江波黄文倩田喜张驰王庆艳
Owner BEIJING RES CENT OF INTELLIGENT EQUIP FOR AGRI
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