Tibetan medical urine feature classification method based on multi-scale convolution sparse coding

A convolutional sparse coding and feature classification technology, applied in the field of Tibetan medicine urine feature classification, can solve the problems of inability to meet clinical needs, inability to standardize, low repeatability, etc., to improve classification accuracy, simplify learning tasks, and complex models. degree-reducing effect

Inactive Publication Date: 2020-01-31
UNIV OF ELECTRONIC SCI & TECH OF CHINA +1
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The dry chemical method is semi-quantitative, the detection specificity is not high, and the detection results may appear false negative or false positive, which has certain limitations; the biggest problem of manual microscopic examination is that it is slow and cannot be standardized, and the technical methods of various inspectors are not uniform

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
  • Tibetan medical urine feature classification method based on multi-scale convolution sparse coding
  • Tibetan medical urine feature classification method based on multi-scale convolution sparse coding
  • Tibetan medical urine feature classification method based on multi-scale convolution sparse coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0056] like figure 1 As shown, the present invention provides a Tibetan medicine urine feature classification method based on multi-scale convolution sparse coding, and its implementation method is as follows:

[0057] S1. Urine image collection: use the camera to take images of floating and suspended objects in the urine temperature stage of Tibetan medicine, and extract multiple images as training samples to establish a training set of two types of urine features.

[0058] In this embodiment, a total of 2480 images of floating objects and suspended objects in the urine temperature stage are taken by the camera, and at the same time, 400 images of floating objects and suspended objects are selected as training samples according to different interference conditions such as illumination, shooting angle, and occlusion. Create a training set of 2 types of urine features.

[0059] S2. Urine Primary Feature Extraction: Extract the local features of the floating and suspended matte...

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 provides a Tibetan medical urine feature classification method based on multi-scale convolution sparse coding. The method comprises the following steps: collecting a urine image; performing urine primary feature extraction; performing urine feature multi-scale convolution sparse coding; and performing urine feature classification. The invention discloses a method for classifying characteristics of floaters and suspended solids in a urine temperature diagnosis stage of Tibetan medicine based on multi-scale convolution sparse coding. According to the method, the features do not need to be manually designed, filter banks of different scales can be automatically learned, objectification of Tibetan medical urine floating object and suspended matter characteristic classification isachieved, the classification accuracy is improved, and an auxiliary decision is provided for Tibetan medical urine diagnosis.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a Tibetan medicine urine feature classification method based on multi-scale convolution sparse coding. Background technique [0002] The effective inheritance of clinical experience and academic ideas of ethnic medicine has always been a key issue in the development and promotion of ethnic medicine in my country. The country has successively carried out "Demonstration Research on Key Technologies for Ethnic Medicine Development", "Ethnic Medicine Characteristic Therapy Efficacy Evaluation and Platform Technology Research", "Ethnic Medicine Literature Collection and Appropriate Technology Screening and Promotion Project", "National Famous Old Chinese Medicine Expert Inheritance Studio Construction projects (including some ethnic medicines)" and other projects have made a lot of achievements in the inheritance of ethnic medicines. However, due to the weak foun...

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): G06K9/46G06K9/62G06N3/04
CPCG06V10/50G06V10/462G06N3/045G06F18/2411
Inventor 刘勇国张艺华尔江泽翁拥忠降拥四郎杨尚明李巧勤杜春慧肖迪尹杜兆威
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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