Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Partition-based method for shadow defect extraction from single-sided light guide plate

An extraction method and technology for light guide plates, which are applied in the fields of optical testing flaws/defects, material analysis, image analysis, etc., can solve the problems of shadow defects of light guide plates, detection accuracy, efficiency and stability of artificial shadows, which are difficult to adapt to enterprises.

Active Publication Date: 2018-12-21
杭州舜浩科技有限公司
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, shadow detection is mainly done manually. Under the light of the inspection fixture, the inspector visually checks whether there are dark areas in one or more places of the light guide plate. If there are dark areas, it means that the light guide plate has shadow defects.
The accuracy, efficiency, and stability of artificial shadow detection are difficult to meet the requirements of enterprises

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Partition-based method for shadow defect extraction from single-sided light guide plate
  • Partition-based method for shadow defect extraction from single-sided light guide plate
  • Partition-based method for shadow defect extraction from single-sided light guide plate

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] Embodiment 1. A partition-based method for extracting shadow defects of a single-side incident light guide plate, such as Figure 1-18 shown, including the following steps:

[0089] Step 1. Considering that the shadow image needs to be observed from an overall perspective, it is necessary to collect the image F of the light guide plate through the surface frame camera; perform step 2;

[0090] The image of the light guide plate collected by the surface frame camera is dense and dense, with different sizes and uniform light emission, which is suitable for the detection and identification of image defects.

[0091] Step 2, use the region growing method to partition the image; obtain the image of i regions, and perform step 3;

[0092] Since the image F of the light guide plate may be warped, and the brightness of each part of the image is uneven, if the global detection is performed directly, it is very likely to cause false detection. Carry out partition detection; the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a partition-based method for extracting shadow defects of a single-side incident light guide plate, a Gaussian filter is respectively designed for each area image of that lightguide plate, and the Gaussian filter is respectively carried out on the basis of the Fourier transform, the shadow defect is determined by calculating the shadow area, the shadow contour length and the eccentricity, external interference caused in the imaging process is avoided, and the accuracy of the shadow defects is effectively improved. Moreover, different shadow defects can be filtered by setting shadow area, shadow contour length and eccentricity to meet the quality inspection requirements of different manufacturers and different grades of products, and the adaptability of the algorithmis improved. The invention can automatically divide and detect shadows according to the gray level change of the light guide plate image, can effectively overcome the influence of uneven illumination, illumination change and the like on defect detection, and greatly improves the stability and robustness of the detection algorithm.

Description

technical field [0001] The invention relates to a method for detecting shadow defects by partitioning an image of a light guide plate, in particular to a partition-based method for extracting shadow defects of a single-side light incident type light guide plate. Background technique [0002] Light Guide Plate (LGP) uses optical-grade acrylic / PC sheet, and then uses high-tech materials with high reflectivity and no light absorption. Laser engraving and V-shaped cross grid are used on the bottom surface of the optical-grade acrylic sheet Engraving and UV screen printing technology to print light guide points. With its advantages of thin thickness, light weight, high brightness, good environmental protection and convenient maintenance, LGP has been widely used in advertising lights, flat panel lighting, liquid crystal displays, X-rays and other fields. Due to the limitations of actual production, many defects such as bright spots, black spots, scratches, scratches, shadows, an...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/187G01N21/88
CPCG01N21/8851G06T7/0004G06T7/11G06T7/187G06T2207/20024G06T2207/20032G06T2207/30108
Inventor 李俊峰卢彭飞楼小栋胡浩
Owner 杭州舜浩科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products