Multispectral image recognition method, device and storage medium

By acquiring and fusing visible and non-visible light images of the oral cavity, and combining the image framework database and spectral feature parameters, automatic positioning of dental lesions is achieved, solving the shortcomings of manual identification in existing technologies and improving detection accuracy and efficiency.

CN114445388BActive Publication Date: 2025-09-05BEIJING KEEYOO TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202210109759.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-28
Publication Date
2025-09-05
Estimated Expiration
2042-01-28

AI Technical Summary

Technical Problem

In the existing technology, the site of tooth lesions cannot be automatically located and requires manual identification by oral medical staff. In addition, the multi-spectral information cannot be effectively integrated, resulting in low detection accuracy and easy misjudgment and omission.

Method used

A camera module is used to obtain visible light images and non-visible light images of the oral cavity, which are fused to generate multispectral images. Block matching and spectral feature parameter comparison are performed in combination with the image framework database to achieve automatic positioning of the lesion block.

Benefits of technology

It improves the accuracy and efficiency of dental lesion detection, can automatically identify specific lesion sites, and reduces false detection and missed detection rates.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114445388B_ABST
    Figure CN114445388B_ABST
Patent Text Reader

Abstract

The present invention discloses a multi-spectral image recognition method, device and storage medium. The method includes acquiring visible light images and non-visible light images of the oral cavity based on a camera module; fusing the visible light images and non-visible light images to generate a fused image; dividing the oral cavity into blocks based on the fused image; and locating the lesion area based on the lesion blocks in the division results. By implementing the present invention, a camera module is used to acquire visible light images and non-visible light images of the oral cavity; the visible light image and the non-visible light image are then fused to generate a fused image. The generated fused image contains the spectrum information of visible light and the spectrum information of non-visible light. Thus, detection is performed through the fused image, and the accuracy of detection can be improved through the multi-spectral information contained in the image. Finally, positioning is performed based on the detection results and the block division of the oral cavity image. The specific location of the diseased area is achieved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Caries observation instrument

    CN110200588A

  • Image processing method and device

    CN107644454A

  • Methods and apparatuses for forming a three-dimensional volumetric model of a subject's teeth

    US20190269485A1