TFT-LCD mura defect detection method based on ICA learning and multichannel fusion

Abstract

The invention discloses a TFT-LCD mura defect detection method based on ICA learning and multichannel fusion, belonging to the TFT-LCD display defect detection field. The TFT-LCD mura defect detection method based on ICA learning and multichannel fusion comprises steps of utilizing an FastICA algorithm to separate mutually independent image bases from massive sample images, using the image bases to construct a background image, maintaining background information as much as possible without being influenced by the object, performing thresholding on the difference image of a test image and a background difference image, reducing the interference on the object partitioning which is caused by a potential object area and noise through setting a plurality of threshold values, introducing a detection scheme of multi-color channel fusion while considering the color information of the mura defect and giving consideration to mura defect detection of different types. The TFT-LCD mura defect detection method based on ICA learning and multichannel fusion is applicable to the mura defect detection of various types and reduces the over-detection and lead detection.

Description

technical field [0001] The invention belongs to the technical field of TFT-LCD display defect detection, and in particular relates to a TFT-LCD mura defect detection method based on ICA learning and multi-channel fusion. Background technique [0002] TFT-LCD is currently the most popular display device, and its application fields involve industrial control, portable mobile products, desktop displays, televisions, aviation, medical and public display fields, etc. With the increasing complexity of TFT-LCD manufacturing technology, the probability of mura defects appearing in TFT-LCD screens increases accordingly. The mura defect is used to describe the brightness imbalance that people perceive when viewing a display. It is a low-contrast object with no fixed shape and blurred edges. The main reasons are defects in circuits or structures and uneven material properties. At present, most enterprises use the traditional manual method for mura defect detection, which has a series ...

AI Technical Summary

Problems solved by technology

[0008] In order to solve the problems in the prior art, the present invention proposes a TFT-LCDmura defect detection method based on ICA learning and multi-channel fusion; the present invention selects a large number of defect-free samples to construct a training sample set, and uses the FastICA algorithm to separate independent samples from the sample set. The image base, project the test image onto the image base, reconstruct the background image, and then use the thresholding model to accurately segment the mura area in the difference image, and fuse the detection results of the two channels of the gray domain and the S domain as the final The detection results solve the problem that the mura defect cannot be accurately segmented and the color spot mura information is lost due to the uneven brightness of the image background

Images