Identification method of overripe L. indigo fruit based on hyperspectral images

A hyperspectral image and fruit recognition technology, applied in the field of infrared spectrum recognition, can solve the problems of heavy workload, low efficiency, leakage of fruit pulp, etc., and achieve the effect of high preparation rate, strong technical advantages, and improved discrimination rate

Inactive Publication Date: 2016-08-31
NORTHWEST A & F UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, unripe red and cyan fruits can be judged by ordinary RGB image processing methods; overripe fruits have the same surface color as ripe fruits, and cannot be distinguished by the above method
However, overripe fruit is soft and easily damaged during transportation, resulting in the leakage of pulp and affecting other normal fruits, reducing its market value
At present, the commonly used method is to manually judge the hardness of the fruit with fingers, and pick out the soft fruit, which is a heavy workload and low efficiency.

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
  • Identification method of overripe L. indigo fruit based on hyperspectral images
  • Identification method of overripe L. indigo fruit based on hyperspectral images
  • Identification method of overripe L. indigo fruit based on hyperspectral images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0030] Such as figure 1 Shown, the method for identifying the overripe cyanocarpus fruit based on hyperspectral images of the present invention comprises:

[0031] Step S1, put the collected indigo fruit into a hyperspectral imaging device, and collect a hyperspectral image. The spectral wavelength range of this example is 369-1042nm, including 60 bands, and the range of each band is 11nm. The formula for calculating the central wavelength is:

[0032] w l =0.000324(8w n +1) 2 +1.273(8w n +1)+367.7

[0033] where w l is the central wavelength, w n is the band number, and the value of n is 0, 1, 2, ..., 59;

[0034] Step S2: Sampling the fruit pixels and background pixels in the hyperspectral image respectively to obtain the following figure 2 In the spectral characteristic curve shown, the frui...

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 present invention is a method for identifying overripe indigo fruit based on hyperspectral images, comprising the steps of: S1: collecting hyperspectral images of indigo fruit; S2: sampling fruit and background pixels in the hyperspectral image, analyzing and proposing methods for removing the background of the image Function model; S3: Remove the image background according to the function model established by S2; S4: Use median filtering, morphological filtering, spatial processing and threshold judgment to remove noise and determine the fruit position; S5: Overripe fruit and overripe fruit Sampling of the pixels, using the stepwise forward variable selection method to select the most discriminative band, and using the linear discriminant analysis method to establish a function model for distinguishing between overripe fruit pixels and overripe fruit pixels; S6: the discriminant model established based on S5 Classify each fruit pixel and mark it separately; S7: Classify each fruit using the majority principle. The method proposed by the invention not only utilizes the spectral information of the object, but also utilizes the spatial information of the fruit, thereby improving the discrimination rate.

Description

technical field [0001] The invention relates to the field of infrared spectrum identification, in particular to a hyper-spectral image-based identification method for overripe indigo fruit. Background technique [0002] Indigo fruit is a perennial deciduous shrub, and its fruit has high nutritional value, containing ash, protein, fat, tannin, pectin, volatile acid, vitamins and phosphorus and other elements, especially the high content of vitamin C, and it is also Contains 7 kinds of amino acids and various trace elements that humans must obtain from food. Fresh fruit can be eaten raw, and it is also a good raw material for brewing fruit wine and beverages, and is a rare natural pigment. Its berries can also be used as medicine, which has the effect of clearing away heat and detoxifying. The indigo fruit harvested by the mechanical vibrating picking device includes unripe red and cyan fruits, and just ripe and overripe dark blue fruits. Among them, unripe red and cyan fru...

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): G01N21/25
Inventor 傅隆生孙世鹏冯亚利彭俊李瑞
Owner NORTHWEST A & F 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