A FPC defect detection method based on improved mask RCNN

A defect detection and defect technology, applied in neural learning methods, image enhancement, instruments, etc., to achieve the effect of saving labor costs and facilitating re-judgment

Active Publication Date: 2021-10-26
NANCHANG INST OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a FPC defect detection method based on improved MASK RCNN, which realizes automatic detection, classification and segmentation of FPC main defects, saves labor costs of enterprises, and greatly improves Efficiency of defect detection

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
  • A FPC defect detection method based on improved mask RCNN
  • A FPC defect detection method based on improved mask RCNN
  • A FPC defect detection method based on improved mask RCNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] In this embodiment, based on the improved MASK RCNN FPC defect detection method, firstly, the collected original FPC image is pre-processed, and then the pre-processed image is data enhanced to expand the amount of FPC image data, and then the enhanced image The data is manually marked, and the marked data set is divided into a training set and a verification set according to a ratio of 4:1, and then the divided data set is sent to the model training, and finally the trained model is evaluated to determine whether the model meets the FPC testing requirements. Specific steps are as follows:

[0046] Step 1: ROI processing and image cropping, collect the target detection image of the industrial site, and preprocess the FPC original image data, including ROI processing and image cropping.

[0047] Step 2: Perform data enhancement processing on the preprocessed image. Data enhancement processing adopts traditional image processing methods: image rotation, image mirroring, ...

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 discloses an FPC defect detection method based on improved MASK RCNN, the steps are as follows: S1. ROI processing and image cutting, collecting target detection images, preprocessing the FPC original image data, and cutting into small images suitable for network input; S2 . Perform data enhancement processing on the preprocessed image to expand the data set for model training; S3. Manual labeling; S4. Determine the number N of horizontal stacking of feature map blocks, and determine the horizontal stacking of feature map blocks for the type and quantity of FPC defect detection Number of times N; S5. Model training, send the marked image data set into the improved MAKS RCNN network model for training; S6. Perform performance evaluation on the trained FPC defect detection model; S7. Parameter optimization and fine-tuning, combined with the evaluation results of S6 , to further optimize the model. The invention realizes the automatic detection of FPC defects, and the size of the defects can be obtained by segmenting the image defects through the mask, which is convenient for staff to re-judgment, and greatly reduces the detection cost of the enterprise.

Description

technical field [0001] The invention relates to the technical field of defect detection and image segmentation of flexible circuit boards, in particular to an FPC defect detection method based on improved MASKRCNN. Background technique [0002] Flexible printed circuit board is referred to as FPC (Flexible Printed Circuit Board), which has the characteristics of thin thickness, light weight, and free bending and folding. Compared with traditional circuit boards, FPC takes up less space and can greatly reduce package size and weight to meet the requirements of high integration and mobility of electronic products. It can realize three-dimensional space wiring of circuits and enhance product reliability. Reduce assembly costs. Because FPC materials are special, highly integrated, and the process is complex, the manufacturing process is easily affected by factors such as equipment, personnel, and the environment, resulting in defects. [0003] The MASK RCNN network is an impro...

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 Patents(China)
IPC IPC(8): G06T7/00G06K9/32G06K9/62G06N3/04G06N3/08
CPCG06T7/0004G06N3/08G06T2207/10004G06T2207/20132G06T2207/20081G06T2207/20084G06T2207/20021G06T2207/30141G06V10/25G06N3/045G06F18/241
Inventor 邓承志吴朝明罗林杰汪胜前徐晨光孙小惟
Owner NANCHANG INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap