Automatic recognition of welding defects in real-time radiography

This paper presents a new semi-automatic approach to extracting main road centrelines from high-resolution satellite images. The approach is based on active window line segment matching and an improved sequential similarity detection algorithm (SSDA). First, a user-specified point on the road centreline is selected as a reference central point to define a template window, and a thresholding operation is performed within the window. Then a best matched target window along the road is searched to determine the next central point in the road. To avoid the influence of noise, only the line segment of ‘interest’ in the window is matched. An improved SSDA searching strategy is proposed to increase the matching speed. When the best matched target window is found, its centre is used as the next central point in the road, and a new template window is generated. By repeating the matching process, a series of central points can be obtained automatically and the corresponding final road centreline from them is extracted. Our approach also allows some kinds of user interventions in case automatic tracking fails. Experimental results confirm that the proposed approach is capable of rapidly and accurately extracting main road centrelines and has good robustness against noise.

Based on analyzing the traditional image matching algorithms, a fast image matching method, which integrates improved sequential similarity detection algorithm (SSDA) and wavelet transformation, is presented in this paper. Firstly, some basic principles of SSDA image matching and wavelet transformation are introduced. Secondly, according to the shortcoming of traditional SSDA algorithm, a new SSDA algorithm is studied for improving the determining velocity of the threshold in SSDA searching match. By integrating wavelet transformation, an integrated matching algorithm is given out. Finally, the new method is compared with the traditional matching algorithms in experiments. The experimental results show that the new method has higher efficiency and accuracy in image matching and is suitable for the realization of real-time underwater navigation.

Template matching is a basic algorithm for image processing, and real-time is a crucial requirement of object tracking. For real-time tracking, a fast template matching algorithm based on grey prediction is presented, where computation cost can be reduced dramatically by minimizing search range. First, location of the tracked object in the current image is estimated by Grey Model (GM). GM(1,1), which is the basic model of grey prediction, can use some known information to foretell the location. Second, the precise position of the object in the frame is computed by template matching. Herein, Sequential Similarity Detection Algorithm (SSDA) with a self-adaptive threshold is employed to obtain the matching position in the neighborhood of the predicted location. The role of threshold in SSDA is important, as a proper threshold can make template matching fast and accurate. Moreover, a practical weighted strategy is utilized to handle scale and rotation changes of the object, as well as illumination changes. The experimental results show the superior performance of the proposed algorithm over the conventional full-search method, especially in terms of executive time.

An approach of fast image mosaic is presented, which involves image matching and image intensity smoothing. Image matching includes two procedures, i.e. rough matching and fine matching. In rough matching, the overlapped regions of two adjacent images to be mosaicked are segmented to binary image at first. Then the binary images are filtered by open operation of mathematic morphologic method. In the binary image region of the reference image, feature template is searched and extracted on a given rule. Via XOR operation of the feature template and search region, some possible matching positions in the overlapped region of the other image are got. In the fine matching, the sequential similarity detection algorithm (SSDA) is adopted to perform matching computation in the small regions near the positions got in the rough matching, and then the relative position offsets in X-orientation and Y-orientation between the two adjacent images are got. Based on the result of the image matching, the two images are stitched. An approach of seam-line smoothing is adopted to adjust the intensity of the overlapped area. Simulation experimental results show that the approach greatly improves the operation speed, while the precision remains fine, so it can be applied in real-time mosaicking.

In allusion to the colored image matching characteristic in the system of robot view navigation, SSDA (the sequential similarity detection algorithm) is improved and adaptive genetic algorithm is brought in; meanwhile, level-divided search strategy connective with rough and exact matching. The improved algorithm can enhance the image matching speed with no matching accuracy reduced, so that real-time requirements of robot view navigation can be met and robot view navigation will be of preferable robustness.

A supercomputer-based software which enables reconstruction of a three-dimensional shape without human assistance using a stereo-pair of scanning electron micrographs has been developed. It is based upon computer image processing and pattern recognition techniques, and can reconstruct a three-dimensional shape of a wide variety of fracture surfaces of corrosion fatigue as well as crack initiation sites in an aggressive environment line a corrosion pit. We discuss the optimum algorithm according to the morphology of the fracture surfaces. A sequential similarity detection algorithm is available in transgranular fatigued surfaces, whereas in the case of corrosion fatigue fracture surfaces and crack initiation sites, the mutual correlation coefficient technique is well suited. The shape and size of the window area, and the run time required in reconstruction are also discussed.

This paper visualizes the cutting mechanism of A1100–H18 and A1100–O of commercially pure aluminum for the measurement of the strain rate distribution near a cutting edge in orthogonal cutting. The distribution is measured using various methods in order. The methods are in-situ observation of cutting process in SEM, inputting image data, a computer image processing, calculating displacements by SSDA (Sequential Similarity Detection Algorithm) and calculating strain rates by FEM. The main results obtained are as follows: (1) It enables to measure a microscopic displacement near a cutting edge. (2) Cutting mechanism was made clear by measuring a strain rate distribution. (3) In cutting A1100–O, small fluctuations of the strain rate distribution were observed.

An approach of image mosaic based on binary image region matching is presented and applied in remote sensing serial image processing. Adopted the Nearest-neighbour interpolation, the original images are rectified on the basis of the values of external orientation elements of the camera installed on the unmanned aerial vehicle (UAV). Image matching includes two procedures, i.e. rough matching and fine matching. In rough matching, the area coverage of overlapped regions between two consecutive images to be stitched is determined approximately at first. Both of the overlapped regions of the two images are processed to binary image, and then the binary images are filtered by mathematic morphologic method. In the appointed binary image region of the former image, feature template is searched and extracted. Through the XOR operation of the feature template and search region, some possible matching positions in the overlapped region of the latter image are obtained. In the fine matching, the sequential similarity detection algorithm (SSDA) is adopted to perform matching computation in the some small regions near the positions extracted in the rough matching, and then the relative position offsets in X-orientation and Y-orientation between the two consecutive images are obtained. Based on the result of the image matching, the two images are stitched. Experimental results by simulation show that the approach presented in the paper greatly improves the operation speed, while the precision remains fine, than it can be applied in real-time mosaicking of serial images.

Based on analyzing current independent navigation methods, this paper presents a new underwater navigation system, which is integrated inertial navigation system (INS) and side scan sonar (SSS). Firstly we introduce the component of the underwater navigation system and the functions of each unit in the system. Then, we study the algorithm of the matching navigation used in the system. A fast image match method by integrating wavelet transform and improved sequential similarity detection algorithm (SSDA) is given out. Based on above researches, we implement simulation experiments. Experimental results show that the system presented in this paper can acquire high navigation accuracy under the background with characteristic seabed relief. Finally, some valuable conclusions and suggestions are given.

This paper presents an automatic visual inspection of exterior surface defects of oil tanks using unmanned aerial vehicles (UAVs) and image processing with two cascading fuzzy logic algorithms. Corrosion is one of the defects that has a serious effect on the safety of the surface of oil and gas tanks. At present, human inspection, and climbing robots inspection are the dominant approach for rust detection in oil and gas tanks. However, there are many shortcomings to this approach, such as taking longer, high cost, and covering less surface area inspection of the tank. The purpose of this research is to detect the rust in oil tanks by localizing visual inspection technology using UAVs, as well as to develop algorithms to distinguish between defects and noise. The study focuses on two basic aspects of oil tank inspection through the images captured by the UAV, namely, the detection of defects and the distinction between defects and noise. For the former, an image processing algorithm was developed to improve or remove noise, adjust the brightness of the captured image, and extract features to identify defects in oil tanks. Meanwhile, for the latter aspect, a cascading fuzzy logic algorithm and threshold algorithm were developed to distinguish between defects and noise levels and reduce their impact through three stages of processing: The first stage of fuzzy logic aims to distinguish between defects and low noise generated by the appearance of objects on the surface of the tank, such as trees or stairs, and reduce their impact. The second stage aims to distinguish between defects and medium noise generated by shadows or the presence of small objects on the surface of the tank and reduce their impact. The third stage of the thresholding algorithm aims to distinguish between defects and high noise generated by sedimentation on the surface of the tank and reduce its impact. The samples were classified based on the output of the third stage of the threshold process into defective or non-defective samples. The proposed algorithms were tested on 180 samples and the results show its superiority in the inspection and detection of defects with an accuracy of 83%.

PurposeHeritage is the latent part of a sustainable built environment. Conservation and preservation of heritage is one of the United Nations' (UN) sustainable development goals. Many social and natural factors seriously threaten heritage structures by deteriorating and damaging the original. Therefore, regular visual inspection of heritage structures is necessary for their conservation and preservation. Conventional inspection practice relies on manual inspection, which takes more time and human resources. The inspection system seeks an innovative approach that should be cheaper, faster, safer and less prone to human error than manual inspection. Therefore, this study aims to develop an automatic system of visual inspection for the built heritage.Design/methodology/approachThe artificial intelligence-based automatic defect detection system is developed using the faster R-CNN (faster region-based convolutional neural network) model of object detection to build an automatic visual inspection system. From the English and Dutch cemeteries of Surat (India), images of heritage structures were captured by digital camera to prepare the image data set. This image data set was used for training, validation and testing to develop the automatic defect detection model. While validating this model, its optimum detection accuracy is recorded as 91.58% to detect three types of defects: “spalling,” “exposed bricks” and “cracks.”FindingsThis study develops the model of automatic web-based visual inspection systems for the heritage structures using the faster R-CNN. Then it demonstrates detection of defects of spalling, exposed bricks and cracks existing in the heritage structures. Comparison of conventional (manual) and developed automatic inspection systems reveals that the developed automatic system requires less time and staff. Therefore, the routine inspection can be faster, cheaper, safer and more accurate than the conventional inspection method.Practical implicationsThe study presented here can improve inspecting the built heritages by reducing inspection time and cost, eliminating chances of human errors and accidents and having accurate and consistent information. This study attempts to ensure the sustainability of the built heritage.Originality/valueFor ensuring the sustainability of built heritage, this study presents the artificial intelligence-based methodology for the development of an automatic visual inspection system. The automatic web-based visual inspection system for the built heritage has not been reported in previous studies so far.

The main parts of automobiles are the piston rod of the shock absorber and the steering rack of the steering gear, and their quality control is critical in the product process. In the process line, these products are normally inspected through visual inspection, sampling, and simple tensile tests; however, if there is a problem or abnormality, it is difficult to identify the type and location of the defect. Usually, these defects are likely to cause surface cracks during processing, which in turn accelerate the deterioration of the shock absorber and steering, causing serious problems in automobiles. As a result, the purpose of this study was to present, among non-destructive methods, a shock response test method and an analysis method that can efficiently and accurately determine the defects of the piston rod and steering rack. A test method and excitation frequency range that can measure major changes according to the location and degree of defects were proposed. A defect discrimination model was constructed using machine and deep learning through feature derivation in the time and frequency domains for the collected data. The analysis revealed that it was possible to effectively distinguish the characteristics according to the location as well as the presence or absence of defects in the frequency domain rather than the time domain. The results indicate that it will be possible to quickly and accurately check the presence or absence of defects in the shock absorber and steering in the automobile manufacturing process line in the future. It is expected that this will play an important role as a key factor in building a smart factory.

Defect detection is a critical aspect of assuring the quality and reliability of silicon solar cells and modules. Luminescence imaging has been widely adopted as a fast method for analyzing photovoltaic devices and detecting faults. However, visual inspection of luminescence images is too slow for the expected manufacturing throughput. In this study, we propose a deep learning approach that identifies and localizes defects in electroluminescence images. Images are split into 16 tiles prior to training and treated as separate images for classification. The classified tiles provide both defect labels and their positions within the cell. We demonstrate the use of this novel approach to replace visual inspection of luminescence images in photovoltaic manufacturing lines to achieve fast and accurate defect detection.

Biaxially oriented polyester film (BOPET) defect is an important factor affecting the quality of the film. In view of identification of defects in the conventional film production process, this mathod resulted in the identification of defects inaccurate. and low labor efficiency and machine vision recognition on identification of specific defect. This paper presents a LVQ neural network-based BOPET film of defects detection and identification methods. In this algorithm, the film images were processed and the outlines of the membrane defects were obtained. Through extracting the aspect ration, circularity, complexity and elongation , projection histogram central moment and so on, the characteristic values of membrane defects, which from the image of film images after image processing, and then input to the defects recognition system based on LVQ neural network that had been trained, in order to achieve the film defects identification, classification and localization. Through the study of features of the defects in BOPET and extracted some quantities as character input of the LVQ neural network, then input some characteristic values as training value into the LVQ neural network to achieve the learning and prediction purpose, and the LVQ neural network was designed. The experiments show that, the proposed method can meet the requirements analysis of air defects in transparent film.

Automatic visual inspection has become an important application of pattern recognition, as it supports the human in this demanding and often dangerous work. Nevertheless, often missing abnormal or defective samples prohibit a supervised learning of defect models. For this reason, techniques known as one-class classification and novelty- or unusual event detection have arisen in the past years. This paper presents a new strategy to employ Hidden Markov models for defect localization in wire ropes. It is shown, that the Viterbi scores can be used as indicator for unusual subsequences. This prevents a partition of the signal into sufficient small signal windows at cost of the temporal context. Our results outperform recent time-invariant one-class classification approaches and depict a great advance for an automatic visual inspection of wire ropes.