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

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...

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 , has a certain degree of subjectivity

The accuracy of these detection methods is related to factors such as the level of physician's diagnosis and treatment skills and the external environment, lack of objective evaluation standards, and low repeatability

In the case of increasing specimens for current clinical examination, the clinical needs cannot be met

Images