Traditional Chinese medicine residue sorting and quality grading method based on machine vision recognition

By establishing a joint model of camera and light source response and performing state space scanning using an improved VMamba model, combined with the adaptive update of the TENT algorithm, the inconsistency problem in the sorting and quality grading of Chinese medicinal residues was solved, and stable sorting and grading were achieved under the condition of light source and camera drift.

CN122090426AActive Publication Date: 2026-05-26HEBEI UNIV OF TECH +3
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HEBEI UNIV OF TECH
Filing Date
2026-04-22
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing technologies struggle to maintain the stability and consistency of sorting and quality grading of medicinal herb residues without interrupting production, especially under conditions of light source aging and camera response drift, leading to inconsistent sorting and grading results.

Method used

By collecting a continuous sequence of images of Chinese medicinal residue on the conveying line, recording exposure, white balance gain, and light source driving quantity, a joint response function model of camera response and light source response is established, a frame-by-frame system transfer function sequence is generated, and transfer function inversion compensation and reflectivity uniformity are performed. Combined with the improved VMamba model, asymmetric state space scanning and cross-scale state transfer are carried out. The TENT algorithm is used for label-free adaptive updates, the parameter update amplitude is limited, and an adaptive normalized parameter set is generated for sorting and grading.

Benefits of technology

It improved the consistency of imaging photometric properties and batch-to-batch comparability, significantly enhanced the consistency and robustness of characterization of Chinese medicinal residues, strengthened the consistency and reliability of sorting category determination and quality grade determination, and improved the reliability of diversion control command generation and graded recording data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122090426A_ABST
    Figure CN122090426A_ABST
Patent Text Reader

Abstract

The invention discloses a traditional Chinese medicine residue sorting and quality grading method based on machine vision recognition. The method comprises the steps that an image sequence is collected, and exposure, white balance gain and light source driving quantity are recorded; a standardized image sequence is obtained through preprocessing, and a working condition drift tensor is constructed through batch difference; segmenting the target area, constructing an equivalent refraction-scattering weight map based on a particle size distribution parameter, a fiber orientation anisotropy parameter and a water-containing scattering indication parameter, and generating a physical token sequence; adopting improved VMama asymmetric scanning to obtain an anisotropic state characterization sequence; a prediction entropy is calculated, a physical consistency loss is constructed through a working condition drift tensor alignment residual error, and a self-adaptive normalized parameter set is obtained through TENT online updating; and reasoning to obtain a target sorting category and a target quality grade, and generating a shunting control instruction and grading record data for sorting and grading of a conveying line. According to the method, unmarked cross-working-condition sorting and consistent grading are achieved.
Need to check novelty before this filing date? Find Prior Art