Seam Image Research Articles

Recognition of initial welding position for large diameter pipeline based on pulse coupled neural network

Purpose – The main purpose of this paper is to develop a method to recognize the initial welding position for large-diameter pipeline automatically, and introduce the image processing based on pulse-coupled neural network (PCNN) which is adopted by the proposed method. Design/methodology/approach – In this paper, a passive vision sensor is designed to capture weld seam images in real time. The proposed method contains two steps. The first step is to detect the rough position of the weld seam, and the second step is to recognize one of the solder joints from the local image and extract its centroid, which is regarded as the initial welding position. In each step, image segmentation and removal of small false regions based on PCNN are adopted to obtain the object regions; then, the traditional image processing theory is used for the subsequent processing. Findings – The experimental results show the feasibility and real time of the proposed method. Based on vision sensing technology and PCNN, it is able to achieve the autonomous recognition of initial welding position in large-diameter pipeline welding. Practical implications – The proposed method can greatly shorten the time of positioning the initial welding position and satisfy the automatic welding for large-diameter pipeline. Originality/value – In the proposed method, the image pre-processing is based on PCNN, which is more robust and flexible in the complex welding environment. After that, traditional image processing theory is adopted for the subsequent processing, of which the processing speed is faster.

Weld seam profile detection and feature point extraction for multi-pass route planning based on visual attention model

Automatic multi-pass route planning is one of key technologies for thick plate in robotic metal active gas (MAG) arc welding. In this research, a scheme for the extracting feature points of the weld seam profile to implement automatic multi-pass route planning, and guidance of the initial welding position in each layer during MAG arc welding, is presented. It consists of two steps: first a vision sensor based on structured light is employed to capture laser stripes and molten pools simultaneously within the same frame, and the laser stripe, forming the weld seam profile is detected by a visual attention model based on saliency. Then a methodology of polynomial fitting plus derivatives for feature point extraction of the weld seam profile is suggested. With respect to the effectiveness of highlighting the laser stripe, the proposed model is much better than the classic ones in this field, whereas the feature point extraction methodology in this paper outperforms typical template matching. Finally, the performance of the proposed scheme is demonstrated on different weld seam images captured in different layers and different welding experiments. New vision sensor captures laser stripes and molten pools simultaneously.A visual attention model for detecting weld seam profiles is proposed.Three kinds of feature points of weld seam profiles can be extracted.Different images captured in different layers validate the proposed methods.The extracted feature points can be used for multi-pass route planning.

Autonomous Detection of Weld Seam Profiles via a Model of Saliency-Based Visual Attention for Robotic Arc Welding

This paper presents a method of autonomously detecting weld seam profiles from molten pool background in metal active gas (MAG) arc welding using a novel model of saliency-based visual attention. First, a vision sensor based on structured light is employed to capture laser stripes and molten pools simultaneously in the same frame. Second, to effectively detect the weld seam profile from molten pool background for next autonomous guidance of initial welding positions and seam tracking, a model of visual attention based on saliency is proposed. With respect to the enhanced effect of saliency, the proposed model is much better than the classic models in the field. According to the comprehensive saliency map created by the proposed model, the weld seam profile can be extracted after threshold segmentation and clustering are applied to it in turn. Third, different weld seam images are used to demonstrate the robustness of the proposed methodology and last, to evaluate the performance of the proposed method, a measure called profile extraction rate (PER) is computed, which shows that the extracted weld seam profile can basically meet the requirements of seam tracking and the guidance of welding torches.

An efficient mosaic algorithm considering seasonal variation: application to KOMPSAT-2 satellite images.

As the aerospace industry grows, images obtained from Earth observation satellites have been successfully used in various fields. Specifically, the demand for a high-resolution (HR) optical images is gradually increasing, and hence the generation of a high-quality mosaic image is being magnified as an interesting issue. In this paper, we have proposed an efficient mosaic algorithm for HR optical images that are significantly different due to seasonal change. The algorithm includes main steps such as: (1) seamline extraction from gradient magnitude and seam images; (2) histogram matching; and (3) image feathering. Eleven Kompsat-2 images characterized by seasonal variations are used for the performance validation of the proposed method. The results of the performance test show that the proposed method effectively mosaics Kompsat-2 adjacent images including severe seasonal changes. Moreover, the results reveal that the proposed method is applicable to HR optic images such as GeoEye, IKONOS, QuickBird, RapidEye, SPOT, WorldView, etc.

Key Image Processing Techniques Used in Laser Welding

<div class=""abs_img""><img src=""[disp_template_path]/JRM/abst-image/00270001/03.jpg"" width=""500"" /> Welding image and weld pool edge</div> Machine vision techniques are widely used with automatic laser-welding robots. Existing systems acquire geometrical information on both the weld seams and molten pool by using a single camera and then processing a single image. The recognition of weld seams is thus obviously affected by the arc, plasma, spatter, etc. This study examined a novel, cost-effective weld image acquisition and processing system with real-time performance, which is based on an advanced RISC machine (ARM). The software and hardware platforms of a weld seam image processing system were designed, and theoretical and experimental studies were undertaken. A novel image-processing method for the laser welding molten pool, based on a quaternion and self-organizing feature map (SOFM) neural network is also proposed. The edge characteristic vector of the molten pool is acquired based on the rotational characteristic of the quaternion in a three-dimensional vector space. The geometric features of the molten pool image are acquired by the self-organizing feature map neural network. The measured results pointed to the possibility of improving the reliability and precision of the automatic laser welding system by combining the two machine vision systems. </span>

A Study on Modified Hough Algorithm for Image Processing in Weld Seam Tracking System

In modern market, achieving mechanical and automatic arc welding process is the key issue to be solved in welding industries. Because of the high complexity of the welding environment, manual detection of the weld line information is hard to be successful and time consuming. Therefore, this study aim at developing a new image processing algorithm for seam tracking system in Gas Metal Arc (GMA) welding by modified Hough algorithm based on the laser vision system. Firstly, noises in the captured weld seam images by CCD camera were effectively removed by noise filtering algorithm and then weld joint position were detected by the modified Hough algorithm to realize the automatic weld seam tracking. To verify the efficiency of the developed image processing model, a common image processing method was employed and the processed results were compared with the proposed algorithm. Statistical results proved that the modified Hough algorithm was able to acquire the weld information precisely with less computing time and memory cost, which also capable for industrial application.

A Study on Image Processing Algorithms for Seam Tracking System in GMA Welding

With the development of economy, the seam tracking technology for arc welding becomes one of the major research tasks in the manufacturing area with robots. In this study, the objectives aim to develop an intelligent and cost-effective algorithm based on the laser vision sensor for image processing in Gas Metal Arc (GMA) welding. Images of welded seam were captured from the CCD camera. These images were then processed by the algorithms in the proposed image processing. To optimize the effective image process, popular algorithms in use were verified, compared and finally selected for every step in the image processing. Moreover, owing to the simple interactive environment and abundant toolboxes, MATLAB was employed to realize those algorithms, which offer a sample for engineers to achieve the goal of algorithm developed by this new but easier approach. Finally, weld seam images obtained with different welding environments were processed to enhance the proposal validity, and it’s proved to have significant effect of getting rid of the variable noises to extract the feature points and centerline for seam tracking in GMA welding and is capable for industrial application.

Automated system for setting the seam coordinates in electron-beam welding facilities

Several facilities for electron-beam welding have been developed and fabricated at the Budker Institute of Nuclear Physics of the Russian Academy of Sciences. A prototype of the system designed for accurate determination of the welded seam position before the welding process and aiming of the electron beam during the welding process is described. For this purpose, the difference in scattering of electrons (and formation of secondary electrons) by the seam and by the surface of the welded workpiece is used, which allows recording the seam image by scanning with a low-current beam. A block diagram of the prototype and basic algorithms of its operation (both tested and proposed for the future) is given. Results of testing and trial operation of the first prototype of the electron-beam welding facility are considered.

Simulation of Data Processing for High-Performance Computers

As the non-uniformity of multi-channel output in ultra-high resolution CCD imaging system causes image seam problem, CCD multi-channel output non-uniformity correction method based on TDI read-out way is put forward. This method images only with image irradiance point, and with one image, a large amount of correction measuring points can be gained; on one hand, accuracy matching output characteristics can be ensured, and on the other hand, the influence of light source adjustment on correction outcomes can be erased. Experimental results show that, this method has high degree of correction accuracy, better than two-point method and multi-point method correction, and it can image only once.

Modeling of underwater wet welding process based on visual and arc sensor

Purpose – The purpose of this paper was to use visual and arc sensors to simultaneously obtain the underwater wet welding information, and a weld seam-forming model was made to predict the weld seam's geometric parameters. It is difficult to obtain a fine welding quality in underwater welding because of the intense disturbances of the water environment. To automatically control the welding quality, the weld seam-forming model should first be established. Thus, the foundation was laid for automatically controlling the underwater welding seam-forming quality. Design/methodology/approach – Visual and arc sensors were used simultaneously to obtain the weld seam image, current and voltage information; then signal algorithms were used to process the information, and the back propagation (BP) neural network was used to model the process. Findings – Experiment results showed that the BP neural network model could precisely predict the weld seam-forming parameters of underwater wet welding. Originality/value – A weld seam-forming model of underwater wet welding process was made; this laid the foundation for establishing a controller for controlling the underwater wet welding process automatically.

Shrink image by feature matrix decomposition

With the development of multimedia technology, image resizing has been raised as a question when the aspect ratio of an examined image should be displayed on a device with a different aspect ratio. Traditional nonuniform scaling for tackling this problem will lead to distortion. Therefore, content-aware consideration is mostly incorporated in the designing procedure. Such methods generally defines an energy function indicating the importance level of image content. The more important regions would be retained in the resizing procedure and distortion could be avoided consequently. The definition of the related energy function is thus the critical factor that directly influences the resizing results. In this work, we explore the definition of energy function from another aspect, matrix decomposition of Low-rank Representation. In our processing, a feature matrix that reflects the texture prior of object contour is firstly constructed. Then the matrix is decomposed into a low-rank one and sparse one. The energy function for resizing is then inferred from the sparse one. We illustrate the proposed method through seam carving framework and image shrinkage operation. Experiments on a dataset containing 1000 images demonstrate the effectiveness and robustness of the proposed method.

A New Method of Visual Recognition for Weld Appearance

The visual recognition methods of texture feature of welding seam have the important significances to realize the automatic tracking of welding seam in the steps of subsequent welding and cover welding of multi-layer welding. Starting from the point of view of making full use of texture feature of welding seam image, the method research and al- gorithm design are respectively carried out on the 2 steps (image processing and position identification) of visual recogni- tion of welding seam. In the image processing, the ±45°Sobel operators are used to carry out the edge detection. In the po- sition identification, the projection method and the regional integration method are combined so as to determine the posi- tion of middle lines of welding seams.The result shows that the proposed method is simple and easy in principal and can, at the same time, meet the timeliness and accuracy requirement.

A Review of Image Resizing Technology Based on Importance Index

This text discusses the feature of the existing methods relating to content-aware image resizing in detail, compares the performance and effect between different methods, and analyzes the merits and demerits about different algorithms. The basic process in contentaware image resizing are segmented into two steps: one of the steps is the identification of image content, which is generally computed by the product of image gradient and vision significance, and it reflects the different sensitivity that human eyes may feel towards different areas in image; Present articles regarding to content-aware image resizing mainly focus on the resizing technology that is the second step. According to the traits of different methods, this article divides the methods into three sorts: based on seam carving, image deformation and multi-operation.

A Study on Development of Optimal Noise Filter Algorithm for Laser Vision System in GMA Welding

In recent years, noise filter of image processing have been widely used in automated manufacturing processes in noisy environment, such as removal of noise in arc welding process, because such filters are robust even in the presence of extreme noise. Since arc, soot and splash etc., salt noise which has certain noise amplitude at random location was found in captured image. It is important to employ a noise filter to intensify the laser lines and ultimately remove or reduce the noise. In this study, the welding seam image captured from the CCD camera was processed by noise filters to remove the noise due to the complexity of welding environment. Comparison of three noise filters (Gaussian filter, Median filter and Wiener filter) was made to find out the optimal noise filtering algorithm. The result showed that the Median filter algorithm is the preferred method, as not only this algorithm performance provided lower MSE (Mean Square Error) and RMSE (Root Mean Square Error) values than those of Gaussian filter and Wiener filter, but also the values of the PSNR (Peak Signal-to-Noise Ratio) and SNR (Signal-to-Noise Ratio) were higher. Therefore, the Median filter can be considered to have a better enhancement effect than the other two filters.

Study on Stereo Vision for 3D Reconstruction of Welding Seam

The Monocular stereo vision sensor based on structured light is designed and invented for the detection of the weld seam. By incorporating the structured light, the corresponding points matching problem in the stereo vision has been solved effectively. Firstly, the built monocular stereo vision system is used to obtain the image information of seam surface. Then the image coordinate of the seam feature points in the two-dimensional plane can be identified and extracted, through the responding image processing and feature analysis of the seam image collected. After that, the three-dimensional coordinates are calculated by using the theory of projective geometry according to the positional relation between the CCD camera and structured light projected in the seam surface. By this way, the seam feature information such as the three-dimensional geometry sizes, the groove type, the angle, and the interval can be obtained. Finally, the algorithm performance is tested by the experiment of obtaining the three-dimensional coordinate for seams center points, and the results have proved the detection accuracy and reliability of the visual collection system.

Stereo Seam Carving a Geometrically Consistent Approach

Image retargeting algorithms attempt to adapt the image content to the screen without distorting the important objects in the scene. Existing methods address retargeting of a single image. In this paper, we propose a novel method for retargeting a pair of stereo images. Naively retargeting each image independently will distort the geometric structure and hence will impair the perception of the 3D structure of the scene. We show how to extend a single image seam carving to work on a pair of images. Our method minimizes the visual distortion in each of the images as well as the depth distortion. A key property of the proposed method is that it takes into account the visibility relations between pixels in the image pair (occluded and occluding pixels). As a result, our method guarantees, as we formally prove, that the retargeted pair is geometrically consistent with a feasible 3D scene, similar to the original one. Hence, the retargeted stereo pair can be viewed on a stereoscopic display or further processed by any computer vision algorithm. We demonstrate our method on a number of challenging indoor and outdoor stereo images.

Geometry seam carving

We present a novel approach to feature-aware mesh deformation. Previous mesh editing methods are based on an elastic deformation model and thus tend to uniformly distribute the distortion in a least-squares sense over the entire deformation region. Recent results from image resizing, however, show that discrete local modifications such as deleting or adding connected seams of image pixels in regions with low saliency lead to far superior preservation of local features compared to uniform scaling — the image retargeting analog to least-squares mesh deformation. Hence, we propose a discrete mesh editing scheme that combines elastic as well as plastic deformation (in regions with little geometric detail) by transferring the concept of seam carving from image retargeting to the mesh deformation scenario. A geometry seam consists of a connected strip of triangles within the mesh’s deformation region. By collapsing or splitting the interior edges of this strip, we perform a deletion or insertion operation that is equivalent to image seam carving and can be interpreted as a local plastic deformation. We use a feature measure to rate the geometric saliency of each triangle in the mesh and a well-adjusted distortion measure to determine where the current mesh distortion asks for plastic deformations, i.e., for deletion or insertion of geometry seams. Precomputing a fixed set of low-saliency seams in the deformation region allows us to perform fast seam deletion and insertion operations in a predetermined order such that the local mesh modifications are properly restored when a mesh editing operation is (partially) undone. Geometry seam carving hence enables the deformation of a given mesh in a way that causes stronger distortion in homogeneous mesh regions while salient features are preserved much better.

A New Algorithm of Weld Seam Detection Based on Mathematical Morphology

Weld seam tracking is the key technology of industrial robot. It satisfies accuracy and real-time demand. This paper presents a robust recognition algorithm for weld seam images based on mathematical morphology. This algorithm used the morphological filtering for image enhancement at first, and then applied Otsu threshold segmentation in local. Besides, it implemented region filling and morphological thinning operation to get the segmented weld seam. Finally, the Hough transform was adopted to detect the straight lines from the weld image. The results prove that this method not only can detect the seam tracking in real-time, but also can identify weld seam automatically.

Ripple Line Fillet Seam Tracking with Visual Sensors in Welding Process

To overcome the problems resulting from weldment trimming and assemble errors, thermal deformation, arc blow, etc., a set of new tracking system of fillet seam for automatic corrugated plate welding was put forward based on machine vision technology. The tracking system included two cameras: the precursor was set in front of the welding torch (a corrugation cycle far away), for capturing the linear laser projected on the side plate and the base plate; the another one was installed over the melting pool for capturing the image of welding torch tip and the seam. The processed image information from the precursor camera was used to track the fillet seam three-dimensional trajectory and the seam width, according to the information the welding motion controller and the welding power made preplanning; the processed torch tip and seam image information was sent to the motion controller and the welding power so that they could make real-time motion and welding parameter adjustment. Computer simulation proved that this new tracking system could work efficiently.

Depth-Aware Image Seam Carving

Image seam carving algorithm should preserve important and salient objects as much as possible when changing the image size, while not removing the secondary objects in the scene. However, it is still difficult to determine the important and salient objects that avoid the distortion of these objects after resizing the input image. In this paper, we develop a novel depth-aware single image seam carving approach by taking advantage of the modern depth cameras such as the Kinect sensor, which captures the RGB color image and its corresponding depth map simultaneously. By considering both the depth information and the just noticeable difference (JND) model, we develop an efficient JND-based significant computation approach using the multiscale graph cut based energy optimization. Our method achieves the better seam carving performance by cutting the near objects less seams while removing distant objects more seams. To the best of our knowledge, our algorithm is the first work to use the true depth map captured by Kinect depth camera for single image seam carving. The experimental results demonstrate that the proposed approach produces better seam carving results than previous content-aware seam carving methods.