Muskmelon quality detection method based on hyperspectral image depth feature fusion

A hyperspectral image and depth feature technology, applied in the field of melon quality detection based on the fusion of hyperspectral image depth features, can solve the problems of high complexity of deep network models, failure to integrate low-level information, and ignore edge information extraction, etc., to overcome the model The effect of the overfitting problem

Active Publication Date: 2020-05-22
TIANJIN UNIV
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The method of using deep neural network to process hyperspectral images has greatly solved the shortcomings caused by traditional methods, but most of the existing deep learning methods have certain limitations: First, most deep learning methods need to determine A large number of parameters, so the existing deep network model has high complexity, which requires a large number of training samples
Second, the existing hyperspectral image classification or prediction only uses the deepest features for prediction or classification, and does not integrate low-level information
Third, the edge information of the image also has a great influence on the final prediction. The existing hyperspectral image prediction or classification ignores the extraction of edge information, so in the final prediction, the edge of the image is extremely inaccurate. Optimistic, unable to meet the needs of practical applications

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
  • Muskmelon quality detection method based on hyperspectral image depth feature fusion
  • Muskmelon quality detection method based on hyperspectral image depth feature fusion
  • Muskmelon quality detection method based on hyperspectral image depth feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] The embodiment of the present invention describes an end-to-end network structure based on deep multi-scale feature fusion, such as figure 1 shown.

[0037] It has two features: First, due to the end-to-end training strategy, all training processes are integrated into a neural network, which will make the learned features more discriminative. Second, unlike traditional frameworks that separate spectral and spatial features, spectral and spatial features are trained simultaneously in the proposed method. In this way, spectral and spatial information can be better fused. The main contributions of this method are summarized as follows.

[0038] 1. An end-to-end melon sweetness and firmness prediction framework (as an unsupervised network model) is proposed, which integrates the spectral and spatial features of melons into a unified neural network, which is divided into 2 branch:

[0039] The first branch is to feed the spectral data into an autoencoder to extract spect...

Embodiment 2

[0050] The scheme in embodiment 1 is verified below in conjunction with concrete experiment, see description below for details:

[0051] 1. Experimental settings

[0052] Datasets and evaluation metrics:

[0053] (1) In this study, the dataset is a total of 60 samples collected from vegetable growing areas in Tianjin. Three types of melons were selected: Elizabeth, Claw, and Emerald. The melons were cut lengthwise and measured for sweetness and firmness in the center.

[0054] Melon sweetness was measured with Brix-90 (refractometer PAL-1). The sweetness value of each sample was measured at 8 points on the melon half: head, tail and side, 4 points closer to the skin and 4 points closer to the pulp. Such as Figure 4 (a) shown. Each sample was tested for hardness values ​​using a texture detector. The firmness of each sample was measured around four locations where the sweetness value was measured. Such as Figure 4 (b) shown.

[0055] For the acquisition of hyperspec...

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 muskmelon quality detection method based on hyperspectral image depth feature fusion. The method comprises the following steps: constructing an end-to-end muskmelon sweetnessand hardness prediction framework, enabling the prediction framework to serve as an unsupervised network model, and enabling the framework to integrate the spectral features and spatial features of muskmelons into a unified neural network; carrying out 3 * 3 and 5 * 5 filling on the edge pixel points to ensure that the edge information of the image is rich; and constructing a small sample of correlation between characteristic pixels, calculating the distance between the characteristic pixels, taking the distance as a weight value, and then calculating the sweetness value and the hardness value of each pixel point in a measured area to estimate the sweetness and the hardness of the whole muskmelon. According to the method, the problem of model overfitting caused by too little annotation data is solved, and the edge information of the image is effectively extracted by filling the pixels of the edge neighborhood.

Description

technical field [0001] The invention relates to the field of melon quality detection, in particular to a method for melon quality detection based on deep feature fusion of hyperspectral images, which detects the sweetness and hardness of melon hyperspectral images through feature learning of spatial information and spectral information of images . Background technique [0002] The hyperspectral image has a high-resolution spectrum, and its spectral resolution can reach the nanometer level, which makes it have more spectral information than the visible light image, but there are two fundamental problems in the hyperspectral image, first: due to The spectral resolution is high, so the hyperspectral image has the disadvantages of huge data volume, serious data redundancy, and many bands; second: the spatial resolution of the hyperspectral image is limited, there are a large number of mixed pixels, and the detection accuracy will vary with the feature Hughes phenomenon in which...

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): G06T7/00G06T5/20G06T7/90G06T7/70
CPCG06T7/0002G06T5/20G06T7/90G06T7/70Y02A40/10
Inventor 王艳宁王征
Owner TIANJIN 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

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