Computer vision-based intelligent identification system for traditional Chinese medicinal material traits

By using an active optical projection device and polarization calculation technology, the problem of relying on subjective experience for the identification of traditional Chinese medicinal materials has been solved. This enables simultaneous quantitative analysis of the internal density and external microstructure of Chinese medicinal materials, thereby improving the accuracy and objectivity of identification.

CN121656261BActive Publication Date: 2026-06-09CHANGCHUN VOCATIONAL INST OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
CHANGCHUN VOCATIONAL INST OF TECH
Filing Date
2025-11-28
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Traditional identification of Chinese medicinal materials relies on subjective experience and lacks objective quantitative standards. Conventional machine vision technology cannot effectively distinguish between Chinese medicinal materials that look similar but have vastly different internal densities. Single optical measurement methods cannot simultaneously ensure the accuracy of macroscopic geometric depth and the fidelity of microscopic surface texture.

Method used

An active optical projection device is used to project a polarization-modulated variable frequency structured light field. The reflected light field is separated by a polarization solution and decoupling module. Combined with an internal density analysis module and a surface microstructure reconstruction module, the internal density and external microstructure of Chinese medicinal materials can be detected and quantitatively analyzed simultaneously.

Benefits of technology

It enables simultaneous detection of both the internal density and external microstructure of Chinese medicinal materials, providing objective digital evaluation indicators and improving the accuracy and reliability of Chinese medicinal material identification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121656261B_ABST
    Figure CN121656261B_ABST
Patent Text Reader

Abstract

The present application relates to the field of computer vision and optical measurement technology, and discloses a traditional Chinese medicinal material character intelligent identification system based on computer vision, which comprises an active optical projection device, an image acquisition device and a central control and processing device; the system projects a polarized modulation frequency-modulated structured light field and acquires multi-channel polarization data; a polarization solving and decoupling module separates the reflected light field into specular reflection and volume scattering components; an internal compactness analysis module uses the volume scattering component to analyze the compactness index based on the multi-frequency modulation amplitude contrast attenuation relationship; a surface micro-character reconstruction module fuses the macroscopic depth solved by the structured light and the microscopic normal field solved by the polarization analysis, generates a microscopic surface depth distribution and extracts roughness features; and an intelligent identification decision module constructs a standardized fingerprint vector by comprehensively considering the compactness and roughness indexes. The present application realizes the synchronous detection and objective quantitative identification of the internal compactness and surface microscopic morphology of traditional Chinese medicinal materials.
Need to check novelty before this filing date? Find Prior Art