An image segmentation algorithm for LED bracket's detection

The surface defect detection of LED bracket is an indispensable step to assure its product qualify. In this paper, an image segmentation algorithm method is proposed for LED bracket detection. Firstly, the basic principle and process of the proposed method is designed and presented, which combines t...

Full description

Saved in:

Bibliographic Details
Published in:	2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) pp. 1486 - 1490
Main Authors:	Xinjia Fang, Fupei Wu, Zhichao Zeng, Jintian Li
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-10-2016
Subjects:	Algorithm design and analysis boundary-based segmentation Copper Image edge detection Image segmentation LED bracket Light emitting diodes Object segmentation Plastics region-based segmentation segmentation algorithms threshold-based segmentation
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The surface defect detection of LED bracket is an indispensable step to assure its product qualify. In this paper, an image segmentation algorithm method is proposed for LED bracket detection. Firstly, the basic principle and process of the proposed method is designed and presented, which combines the use of threshold-based segmentation technique and boundary-based segmentation method. Secondly, the segmentation results and efficiencies of three methods, including threshold-based segmentation technique, region growing approach and the proposed method, are compared based on LED bracket' s image. In the end, the experiment results based on three mentioned methods show that the proposed segmentation approach has the most favorable segmentation results for LED brackets, and its efficiency is higher than the region growing technique, thus it can better meet the requirements of LED stent surface defect detection.
DOI:	10.1109/IMCEC.2016.7867463