Multi region segmentation algorithm based on edge preserving for molten pool image

2016 ◽  
Author(s):  
Fei Gao ◽  
Mingli Lu ◽  
Benlian Xu ◽  
Qian Zhang
Keyword(s):  
Molten Pool ◽  
Segmentation Algorithm ◽  
Edge Preserving ◽  
Region Segmentation ◽  
Pool Image

Based on the CO2 Gas Shielded Welding Molten Pool Image Edge Detection Algorithm

2013 ◽  
Vol 437 ◽  
pp. 840-844 ◽  
Author(s):  
Xiao Gang Liu ◽  
Bing Zhao
Keyword(s):  
Edge Detection ◽  
Molten Pool ◽  
High Speed ◽  
Vision System ◽  
Detection Algorithm ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Low Pass ◽  
Defect Recognition ◽  
Pool Image

This paper use the passive vision system through high-speed camera collects molten pool images; and then according to the frequency domain characteristics of the weld pool image Butterworth low-pass filter; gradient method for image enhancement obtained after pretreatment. Research Roberts, Sobel, Prewitt, Log, Zerocross, and Canny 6 both traditional differential operator edge detection processing results. Through comparison and analysis of choosing threshold for [0.1, 0. Canny operator can get the ideal molten pool edge character, for subsequent welding molten pool defect recognition provides favorable conditions.

Molten Pool Image Processing and Feature Extraction Based on Multiple Visions

2013 ◽  
Vol 753-755 ◽  
pp. 2131-2134
Author(s):  
Da Wei Wu ◽  
Zhen Yu Xiong ◽  
Wang Ping Gu ◽  
Jun Shan
Keyword(s):  
Image Processing ◽  
Feature Extraction ◽  
Molten Pool ◽  
Median Filtering ◽  
Threshold Method ◽  
Welding Arc ◽  
Image Processing Algorithms ◽  
Processing Algorithms ◽  
Composite Filter ◽  
Pool Image

A molten pool image gathering system is designed based on multiple visions. By using a composite filter, it can effectively overcome the interference of the welding arc and obtain a clear molten pool image. A series of image processing algorithms has been proposed based on the features of the molten pool image. A median filtering has been used to remove the noise of the molten pool image. A canny multi-threshold method has been used to extract the edge characteristics of the molten pool. Then the edge feature of the molten pool can be gotten after false edge removing and iterative fitting.

Anisotropic Dynamic-Morphological-Diffusion for Segmentation of Noisy Color Images

2014 ◽  
Vol 18 (2) ◽  
pp. 204-212
Author(s):  
Junji Maeda ◽  
◽  
Takehiro Harada ◽  
Sato Saga ◽  
Yukinori Suzuki ◽  
...  
Keyword(s):  
Anisotropic Diffusion ◽  
Color Images ◽  
Segmentation Algorithm ◽  
Morphological Filter ◽  
Smoothing Technique ◽  
Edge Preserving ◽  
Dynamic Selection ◽  
Small Image ◽  
Selection Of

In this paper, we propose a modified anisotropic diffusion algorithm using the dynamicmorphological filtering as a new precise edge-preserving smoothing technique for an accurate segmentation of color images with heavy noise. We incorporate a dynamic selection of multiple structuring elements for each pixel in the morphological filter before the anisotropic diffusion in order to improve the ability of edge-preserving smoothing. As a result, noise and unnecessary details of images are effectively smoothed while preserving small image structures before performing a segmentation algorithm. Several simulated examples are presented that demonstrate the effectiveness of the proposed technique.

Sign in / Sign up

Export Citation Format

Share Document