Red date appearance quality classification method and device, apparatus and storage medium

A sorting method, jujube technology, applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problems of high cost, no classification of jujube appearance quality, low efficiency of manual sorting, etc., to speed up interaction and improve processing speed effect

Pending Publication Date: 2019-10-08
TIANJIN POLYTECHNIC UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, manual sorting is inefficient and costly, and there is no fixed standard for the quality classification of jujube appearance

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
  • Red date appearance quality classification method and device, apparatus and storage medium
  • Red date appearance quality classification method and device, apparatus and storage medium
  • Red date appearance quality classification method and device, apparatus and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] The specific framework schematic diagram of the present invention is as follows figure 1 As shown in the figure, the jujube image data is first collected by a 300,000-pixel industrial camera, and the collected images are preprocessed and screened, and then made into a training set and a test set, of which the training set contains 54,000 pictures, and the test set contains pictures. 6000 sheets; then, the 34-layer residual network is used as the main structure, and the channel weighting module and information aggregation mechanism are integrated. Through channel weighting, the network selectively enhances the features containing useful information, and suppresses useless features by learning global information. , a multi-channel information aggregation module is embedded at the end of each module to aggregate the features in various receptive fields to form a network structure; then the network model is obtained through training, and the data of the test set is tested to...

Embodiment 2

[0061] Figure 7 A schematic structural diagram of a device for classifying the appearance quality of red dates provided in the second embodiment of the present invention, such as Figure 7 As shown, the device for classifying the appearance and quality of red dates includes:

[0062] The original image acquisition module 710 is used to collect the original image of red dates;

[0063] The region-of-interest image extraction module 720 is used to preprocess the original image of the red jujube, extract the region of interest of the original image of the red jujube, and normalize the size of the region of interest to obtain the same size. The region of interest image of the jujube image;

[0064] The model training module 730 uses the optimized convolutional neural network to train the image of the region of interest of the red jujube image to obtain a trained jujube appearance quality classification model;

[0065] The image testing module 740 tests the red jujube images by...

Embodiment 3

[0075] Figure 8 A schematic structural diagram of a device provided in Embodiment 3 of the present invention, such as Figure 8 As shown, the device includes a processor 80, a memory 81, an input device 82 and an output device 83; the number of processors 80 in the device 8 can be one or more, Figure 8 Take a processor 80 as an example; the processor 80, the memory 81, the input device 82 and the output device 83 in the device 8 can be connected through a bus or other means, Figure 8 Take the connection through the bus as an example.

[0076] As a computer-readable storage medium, the memory 81 can be used to store software programs, computer-executable programs and modules, such as program instructions / modules corresponding to the method for classifying the appearance quality of red dates in the embodiment of the present invention (for example, the original image acquisition module 710 , a region of interest image extraction module 720, a model training module 730 and an...

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 embodiment of the invention discloses a red date appearance quality classification method and device, an apparatus and a storage medium. The method comprises the steps of collecting a red date original image; preprocessing the red date original image, extracting an region-of-interest of the red date original image, and performing size normalization operation on the region-of-interest to obtainan region-of-interest image of the red date image with the same size; using an optimized convolutional neural network to train the region-of-interest image of the red date image to obtain a trained red date appearance quality classification model; and testing the red date image by using the red date appearance quality classification model to obtain a classification result of the red date appearance quality. According to the embodiment of the invention, the accurate classification of the appearance quality of the red dates through the convolutional neural network combining a multi-channel weighting mechanism and an information aggregation mechanism is achieved, a problem that the classification grade positioning of the red dates is inaccurate is solved, and the classification efficiency ofthe appearance quality of the red dates is improved.

Description

technical field [0001] The embodiments of the present invention relate to the field of food safety testing, and in particular, to a method, device, equipment and storage medium for classifying the appearance and quality of red dates. Background technique [0002] Jujubes have been planted in China for more than 8,000 years. As a famous jujube-producing city in northern China, Cangzhou also has the largest jujube trading market in the country. In 2017, the transaction volume of jujubes in the Cangzhou jujube trading market was 38.2 billion yuan, and the total profit reached 6.56 billion yuan. With the expansion of the transaction radiation and the gradual increase in the transaction volume, traders have higher and higher requirements for the quality of jujubes. [0003] At present, the classification of the quality of red dates is carried out manually, and experienced workers can classify the four types of red dates: intact, dry, cracked and damaged skin. [0004] However, m...

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): G06K9/62G06K9/32
CPCG06V10/25G06F18/241
Inventor 耿磊马鸣帅肖志涛张芳吴骏刘彦北王雯
Owner TIANJIN POLYTECHNIC 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