Unlock instant, AI-driven research and patent intelligence for your innovation.

Loquat early bruise identification method based on OCT (optical coherence tomography) image processing

An image processing and loquat technology, which is applied in the field of automatic detection of the internal quality of fruits, can solve the problems of small contrast, inconspicuous features, and inability to distinguish bruises in OCT images of loquats, and achieves the effect of improving efficiency and accuracy and improving positioning accuracy.

Active Publication Date: 2017-05-31
ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Due to the low contrast and inconspicuous features of loquat OCT images in industrial applications, it is basically impossible to distinguish early bruises by manual discrimination
In the process of loquat OCT image application, there is no systematic report on the image processing algorithm, and the research is still in its infancy, and the existing technology lacks a method for early identification of loquat bruises

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
  • Loquat early bruise identification method based on OCT (optical coherence tomography) image processing
  • Loquat early bruise identification method based on OCT (optical coherence tomography) image processing
  • Loquat early bruise identification method based on OCT (optical coherence tomography) image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0043] Embodiments of the present invention and its implementation process are as follows:

[0044] 1) Using the TELSTO 1300V2 SD-OCT imager produced by Thorlabs to collect 40 SD-OCT image samples of loquat fruit, 20 of which contained bruising defects of varying degrees, and 20 were normal samples; figure 2 It is the OCT image of two typical loquat samples, in which (a) is a normal sample without defects, and (b) the sample pulp tissue has bruise defects. It can be seen that the normal non-defective tissue structure is dense and compact, while the tissue with bruises has sparse tissue with less density. The bruises cannot be judged with the naked eye alone.

[0045] 2) Enter such as Fig...

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 loquat early bruise identification method based on OCT (optical coherence tomography) image processing, comprising: acquiring an SD-OCT (spectral domain-OCT) image of a loquat fruit with cell image details, downsampling the image to reduce image resolution by means of bicubic interpolation algorithm, performing Gaussian fuzzy denoising to extract a boundary between the target loquat fruit and a background, using a highest point of the boundary as a reference point, deforming the boundary into a straight line along the reference point according to the reference point, performing average filtering on the image, binarizing the image, processing the binarized image to obtain cellular areas corresponding to cells, and analyzing and calculating the cellular areas to obtain bruise identification results. The method of the invention provides full-automatic detection for early bruise in loquat pulp, as well as identification and discrimination for subcutaneous cells of bruise tissues, detection efficiency is improved, and technical basis is laid for the online detection internal quality of loquat.

Description

technical field [0001] The invention belongs to the field of automatic detection of fruit internal quality, relates to an OCT image processing method, and in particular relates to a loquat early bruise identification method based on OCT image processing. Background technique [0002] Loquat is one of the unique fruit products in my country. The non-destructive and rapid detection method of its internal quality in the process of picking, selling, transporting and storing is the main technical problem faced by the development of loquat industry. During the sales process of various industries, loquats are easily damaged by external forces, resulting in later corruption and deterioration. The bruises of loquats may appear in various links such as picking, storage, transportation, packaging, etc., and are not easy to be noticed in the early stage of sales. The shelf life of bruised loquats is greatly shortened. Due to the damage of the cell structure, the tissue gradually browns...

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): G06T3/40G06T5/00
CPCG06T3/4023G06T2207/20024G06T2207/10101G06T2207/30188G06T2207/20152G06T5/70
Inventor 周扬陈正伟刘铁兵毛建卫王中鹏赵芸陈才施秧周武杰陈芳妮宋起文陶红卫吴茗蔚王建芬施祥郑卫红翁剑枫邱薇薇
Owner ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY