A semantic segmentation-based embedded fingerprint module appearance detection method

By using a semantic segmentation-based deep learning neural network, combined with global fixed threshold and local dynamic threshold segmentation methods, the problem of low detection accuracy of adhesive overflow and bump defects in fingerprint modules in existing technologies has been solved, achieving high-precision defect detection and evaluation, and improving product stability and security.

CN115601332BActive Publication Date: 2026-07-07SHENZHEN JINGCHUANG TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN JINGCHUANG TECH CO LTD
Filing Date
2022-10-20
Publication Date
2026-07-07

AI Technical Summary

Technical Problem

Existing 2D visual positioning analysis technology cannot effectively detect excess adhesive and bump defects in fingerprint modules, resulting in low detection accuracy and poor stability, which affects the stability and security of the product.

Method used

A defect detection model is built by using a semantic segmentation-based deep learning neural network and combining global fixed threshold and local dynamic threshold segmentation methods. Through feature extraction and defect classification prediction networks, combined with a defect level quality assessment module, high-precision defect detection is achieved.

Benefits of technology

It improves the reliability and compatibility of fingerprint module appearance quality inspection, ensures product safety and reliability, can effectively identify and assess the level of excess glue and bump defects, and improves inspection accuracy and stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115601332B_ABST
    Figure CN115601332B_ABST
Patent Text Reader

Abstract

The application provides a kind of appearance detection method of embedded fingerprint module based on semantic segmentation, comprising: collecting fingerprint module sample image, positioning, labeling of glue overflow, bump;Defect semantic segmentation network model building;Establishing defect level quality evaluation module;And fingerprint module product defect online logic detection, collect actual fingerprint module product image to be detected, through global fixed threshold segmentation and local dynamic threshold positioning defect area to be detected product, call fingerprint module semantic segmentation detection model file, predict output glue overflow, bump defect, introduce defect level quality evaluation index to determine OK / NG product.The method comprehensively analyzes the characteristics of glue overflow and bump, builds a deep learning neural network segmentation network, extracts the occurrence area of glue overflow and bump with high precision, and finally applies the defect level quality evaluation module to comprehensively analyze the current product, improves the appearance quality safety stability of fingerprint module.
Need to check novelty before this filing date? Find Prior Art