A medicinal material or decoction piece identification method based on an image annotation deep learning algorithm model

A technology of deep learning and recognition methods, applied in the field of identification of Chinese herbal medicines, to achieve the effect of helping accuracy and objective evaluation

Pending Publication Date: 2021-10-22
CHENGDU UNIV OF TRADITIONAL CHINESE MEDICINE
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the defects in the existing artificial intelligence technology for identifying Fritillaria sichuan medicinal materials, the present invention provides a method for identifying medicinal materials of Fritillaria sichuanensis based on image annotation deep learning algorithm model

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
  • A medicinal material or decoction piece identification method based on an image annotation deep learning algorithm model
  • A medicinal material or decoction piece identification method based on an image annotation deep learning algorithm model
  • A medicinal material or decoction piece identification method based on an image annotation deep learning algorithm model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] In this embodiment, the identification of the category of Chuanbei samples is carried out, such as figure 1 As shown, including the following process:

[0038] 1. Data preprocessing

[0039] (1) Image data tag

[0040] 1) Mark the data in the Chuanbei picture, and mark the N+1 frame, which includes N local frames and 1 global frame; the N is an integer greater than or equal to 0;

[0041] 2) Extract N local images and 1 global image from the photo according to the marked frame;

[0042] 3) Extract feature data from the extracted local graph and global graph;

[0043] 4) Perform Faster RCNN model training according to the types and characteristic data of Fritillaria sichuanensis, and obtain the Faster RCNN model with the best performance.

[0044] (2) Word segmentation of text language

[0045] Artificially describe the properties of the decoction pieces according to the Pharmacopoeia and perform word segmentation, count and encode the words, and convert them into w...

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 belongs to the technical field of traditional Chinese medicinal material identification, and particularly relates to a medicinal material or decoction piece identification method based on an image annotation deep learning algorithm model. In order to overcome the defects in the existing technology for identifying medicinal materials or decoction pieces by artificial intelligence, the technical scheme of the invention is as follows: the method comprises the following steps: (1) image coding: acquiring a picture of a to-be-detected medicinal material or decoction piece, carrying out feature detection on the picture, and extracting to obtain feature data; (2) image decoding: converting the feature data obtained in the step (1) into feature description word vectors through a recurrent neural network model; and (3) identification: identifying the type of the to-be-detected medicinal material or decoction piece through the feature description word vector obtained in the step (2). The invention is suitable for identifying and classifying the types of the medicinal materials or the decoction pieces.

Description

technical field [0001] The invention belongs to the technical field of identification of traditional Chinese medicinal materials, and in particular relates to an identification method of medicinal materials and decoction pieces based on an image annotation deep learning algorithm model. Background technique [0002] Traditional Chinese medicine is an important means of clinical treatment of traditional Chinese medicine. There are many kinds of traditional Chinese medicine in my country, and identifying their authenticity is the basis for ensuring clinical efficacy. As the total demand for traditional Chinese medicine continues to rise, some authentic medicinal materials are in short supply, and lawbreakers often use unqualified medicinal materials to counterfeit precious medicinal materials or substandard medicinal materials as high-quality medicinal materials, which makes the Chinese medicinal material market flooded with a large number of counterfeit and inferior products. ...

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): G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06N3/045G06F18/23G06F18/2415
Inventor 吴纯洁谭超群陈虎黄永亮吴冲韦志强
Owner CHENGDU UNIV OF TRADITIONAL CHINESE MEDICINE
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