Traditional Chinese medicinal material identification method and system based on a double-scale convolutional neural network

A technology of convolutional neural network and recognition method, which is applied in the field of Chinese medicinal material recognition and system based on double-scale convolutional neural network, can solve the problems of slow recognition speed and low recognition accuracy of convolutional neural network.

Active Publication Date: 2019-04-12
UNIV OF JINAN
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the patent can realize the identification of Chinese herbal medicines, the applicant believes that the artificial photography of the patent does not use special devices to take pictures, which cannot avoid the problems of insufficient light, reflections, and hand shakes when taking pictures that cannot accurately identify the type of medicinal materials. image, which will lead to low recognition accuracy of the convolutional neural network in the later stage; and the patent uses a common convolutional neural network algorithm, and the existing problem is that the recognition speed is not fast

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
  • Traditional Chinese medicinal material identification method and system based on a double-scale convolutional neural network
  • Traditional Chinese medicinal material identification method and system based on a double-scale convolutional neural network
  • Traditional Chinese medicinal material identification method and system based on a double-scale convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] like figure 1 As shown, the Chinese herbal medicine recognition method based on dual-scale image feature fusion includes the following steps:

[0074] Step S1: collect pictures of medicinal materials, and preprocess the pictures. In order to improve the accuracy of machine learning, in the process of collecting medicinal materials, take two shots of the same medicinal material at the same angle, one far and one near, and unify the size of the pictures to 500*500, and then send the far and near pictures of the same medicinal material to Into the image processing function, the image is processed by random cropping, random rotation or flipping, random hue transformation, random blurring, random light offset field, etc., and then outputs a picture with a size of 92*92 as the input of the convolutional neural network model.

[0075] Step S2: Since the data set is too large, 5 pictures are randomly selected from the far and near picture sets for training each time. It is nec...

Embodiment 2

[0110] This embodiment specifically introduces a Chinese herbal medicine recognition technology based on dual-scale image feature fusion and data enhancement from the preparation of medicinal material collection equipment, training models, and actual testing. The specific process is as follows:

[0111] 1. Preparation of medicinal material collection equipment

[0112] When artificially taking pictures and collecting medicinal material materials to be identified, uncertain factors such as lighting conditions, shooting angles, and hand tremors when people take pictures will affect the obtained pictures. Therefore, if this situation is not improved, even for the same medicinal material, the picture effects obtained by taking multiple photos may be different, which will greatly affect the accuracy of medicinal material identification. Therefore, in order to solve this problem, 3D printing technology is used to design and collect medicinal materials equipment.

[0113] like 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 traditional Chinese medicinal material recognition method and system based on a double-scale convolutional neural network. The method comprises the following steps: firstly,carrying out dual-scale image acquisition through a specially designed image acquisition device, sending a training image into a convolutional neural network for training, and carrying out multi-layerconvolutional pooling feature extraction and selection, and training to obtain a convolutional neural network model with relatively high identification precision; and sending the to-be-detected imageinto the trained convolutional neural network model for feature extraction, classifying the traditional Chinese medicinal materials based on the extracted features, and outputting a classification recognition result. The method is beneficial to improving the medicinal material recognition capability of ordinary people, and helps experts in the medicinal material field to identify medicinal materials more accurately and quickly.

Description

technical field [0001] The present disclosure relates to a method and system for identifying Chinese herbal medicines based on a dual-scale convolutional neural network. Background technique [0002] The statements in this section merely enhance the background related to the present disclosure and may not necessarily constitute prior art. [0003] With the growth of our country's economic level, the living standard of the people is getting higher and higher. In order to improve the quality of life, more and more people begin to pay attention to health preservation. Since ancient times, the culture of traditional Chinese medicine has been extensive and profound, containing the essence of the history of our country for thousands of years. It is the precious wealth accumulated in the long-term struggle of the Chinese nation against diseases and an important part of the excellent culture of the Chinese nation. made a great contribution to its prosperity. [0004] As a traditi...

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): G06K9/62
CPCG06F18/24G06F18/253G06F18/214
Inventor 王琳孙风阳孙润元杨华伟张晓雪倪庆瑞
Owner UNIV OF JINAN
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