Surface Defect Inspection System Research Articles

Cross-factory Polarizer Sheet Surface Defect Inspection System Based on Multi-Teacher Knowledge Amalgamation

Cross-factory Polarizer Sheet Surface Defect Inspection System Based on Multi-Teacher Knowledge Amalgamation

FDD: a deep learning-based steel defect detectors.

Surface defects are a common issue that affects product quality in the industrial manufacturing process. Many companies put a lot of effort into developing automated inspection systems to handle this issue. In this work, we propose a novel deep learning-based surface defect inspection system called the forceful steel defect detector (FDD), especially for steel surface defect detection. Our model adopts the state-of-the-art cascade R-CNN as the baseline architecture and improves it with the deformable convolution and the deformable RoI pooling to adapt to the geometric shape of defects. Besides, our model adopts the guided anchoring region proposal to generate bounding boxes with higher accuracies. Moreover, to enrich the point of view of input images, we propose the random scaling and the ultimate scaling techniques in the training and inference process, respectively. The experimental studies on the Severstal steel dataset, NEU steel dataset, and DAGM dataset demonstrate that our proposed model effectively improved the detection accuracy in terms of the average recall (AR) and the mean average precision (mAP) compared to state-of-the-art defect detection methods. We expect our innovation to accelerate the automation of industrial manufacturing process by increasing the productivity and by sustaining high product qualities.

Rail Surface Defect Detection Through Bimodal RSDINet and Three-Branched Evidential Fusion

Current state-of-the-art intensity and depth modal-based railway surface defect inspection system faces the dilemma between false alarming and miss detection. To overcome this challenge, a bimodal detection scheme using both feature-level fusion and (evidence theory-based) decision-level fusion is designed. Moreover, an improved evidential fusion algorithm is proposed, which adopts three-branched evidential weight structure and introduces the Transferable Belief Model to the improved decision functions, achieving outstanding performance on effectiveness and robustness analysis. Both theoretical justifications and experimental results validate the efficiency of the hybrid fusion-based detection scheme in solving rail surface defect problems.

Real-time batch inspection system for surface defects on circular optical filters.

Optical filters, one of the essential parts of many optical instruments, are used to select a specific radiation band of optical devices. There are specifications for the surface quality of the optical filter in order to ensure the instrument's regular operation. The traditional machine learning techniques for examining the optical filter surface quality mentioned in the current studies primarily rely on the manual extraction of feature data, which restricts their ability to detect optical filter surfaces with multiple defects. In order to solve the problems of low detection efficiency and poor detection accuracy caused by defects too minor and too numerous types of defects, this paper proposes a real-time batch optical filter surface quality inspection method based on deep learning and image processing techniques. The first part proposes an optical filter surface defect detection and identification method for seven typical defects. A deep learning model is trained for defect detection and recognition by constructing a dataset. The second part uses image processing techniques to locate the accurate position of the defect, determine whether the defect is located within the effective aperture, and analyze the critical eigenvalue data of the defect. The experimental results show that the method improves productivity and product quality and reduces the manual workload by 90%. The proposed model and method also compare the results of surface defect detection with the actual measurement data in the field, verifying that the method has good recognition accuracy while improving efficiency.

A UAV-Based Aircraft Surface Defect Inspection System via External Constraints and Deep Learning

A UAV-Based Aircraft Surface Defect Inspection System via External Constraints and Deep Learning

A deep learning-based surface defect inspection system using multi-scale and channel-compressed features

In machine vision-based surface inspection tasks, defects are typically considered as local anomalies in homogeneous background. However, industrial workpieces commonly contain complex structures, including hallow regions, welding joints, or rivet holes. Such obvious structural interference will inevitably cause a cluttered background and mislead the classification results. Moreover, the sizes of various surface defects might change significantly. Last but not least, it is extremely time-consuming and not scalable to capture large-scale defect data sets to train deep CNN models. To address the challenges mentioned earlier, we first proposed to incorporate multiple convolutional layers with different kernel sizes to increase the receptive field and to generate multiscale features. As a result, the proposed model can better handle the cluttered background and defects of various sizes. Also, we purposely compress the size of parameters in the newly added convolutional layers for better learning of defect-related features using a limited number of training samples. Evaluated in a newly constructed surface defect data set (images contain complex structures and defects of various sizes), our proposed model achieves more accurate recognition results compared with the state-of-the-art surface defect classifiers. Moreover, it is a lightweight model and can deliver real-time processing speed (>100 frames/s) on a computer equipped with a single NVIDIA TITAN X Graphics Processing Unit (12-GB memory).

An Automatic Surface Defect Inspection System for Automobiles Using Machine Vision Methods.

Automobile surface defects like scratches or dents occur during the process of manufacturing and cross-border transportation. This will affect consumers’ first impression and the service life of the car itself. In most worldwide automobile industries, the inspection process is mainly performed by human vision, which is unstable and insufficient. The combination of artificial intelligence and the automobile industry shows promise nowadays. However, it is a challenge to inspect such defects in a computer system because of imbalanced illumination, specular highlight reflection, various reflection modes and limited defect features. This paper presents the design and implementation of a novel automatic inspection system (AIS) for automobile surface defects which are the located in or close to style lines, edges and handles. The system consists of image acquisition and image processing devices, operating in a closed environment and noncontact way with four LED light sources. Specifically, we use five plane-array Charge Coupled Device (CCD) cameras to collect images of the five sides of the automobile synchronously. Then the AIS extracts candidate defect regions from the vehicle body image by a multi-scale Hessian matrix fusion method. Finally, candidate defect regions are classified into pseudo-defects, dents and scratches by feature extraction (shape, size, statistics and divergence features) and a support vector machine algorithm. Experimental results demonstrate that automatic inspection system can effectively reduce false detection of pseudo-defects produced by image noise and achieve accuracies of 95.6% in dent defects and 97.1% in scratch defects, which is suitable for customs inspection of imported vehicles.

A Water Polishing Process to Improve Ceria Abrasive Removal

This study details the improved ceria abrasive removal on SiO2 wafer during the post CMP water polishing (buff clean) process. Initially, the zeta potentials of the wafer and ceria abrasive were measured according to pH and compared with the zeta potential and pH change during water polishing. From these measurements, it was determined that the zeta potential difference between the ceria abrasive and the wafer decreased during water polishing. The electrical repulsion between them decreased as well. Additionally, ceria abrasive removal was measured using a surface defect inspection system. The abrasive removal increased when water polishing conditions such as pressure, rotation speed and processing time increased. Chemical enhancement and a pad cleaning process also increased the ceria abrasive removal. Consequently, the total defect counts were reduced by 91.8% with the optimized water polishing condition. These results provide useful data for determining optimal water polishing conditions for more effective post CMP cleaning.

열간 슬라브 표면결함 탐상 시스템

열간 슬라브 표면결함 탐상 시스템

A cost-effective and automatic surface defect inspection system for hot-rolled flat steel

Defective steel brings economic and commercial reputation losses to the hot-strip manufacturers, and one of the main difficulties in using machine-vision-based technique for steel surface inspection is time taken to process the massive images suffering from uneven illumination. This paper develops a modular and cost-effective AOI system for hot-rolled flat steel in real time. Firstly, a detailed system topology is constructed according to the design goals covering the vast majority of steel mills, lighting setup and typical defect patterns are presented as well. Secondly, the image enhancement method is designed to overcome the uneven-lighting, over- or under-exposure. Thirdly, the defect detection algorithm is developed based on variance, entropy and average gradient derived from non-overlapping 32×32 pixel blocks of steel surface images. Fourthly, the proposed algorithms are implemented on FPGA in parallel to improve the inspection speed. Finally, 18,071 contiguous images (4096×1024 pixel) acquired from 7 defective steel rolls have been inspected by the realized AOI system to evaluate the performance. The experimental results show that the proposed method is speedy and effective enough for real applications in the hot-rolled steel manufacturing, with 92.11% average accuracy while 5.54% false-negative rate. HighlightsDetailed system topology is constructed according to the design goals covering the vast majority of steel mills.A new dynamic image enhancement method is designed to overcome the uneven-lighting, over- or under-exposure.A defect detection algorithm with adaptive thresholding mechanism is developed based on image block variance, entropy and average gradient.The inspection speed of the proposed algorithms running on FPGA is evaluated.Testing procedures and evaluation results from the applied hot-rolling mill are discussed.

An automatic visual inspection system for cone surface defects

Limited to the impact of human visual sensitivity and individual subjective judgments, traditionally manual detection method is unable to accurately and reliably capture the cone surface defects, and will easily cause a lot of missing and false detection. In this paper, we propose a novel machine vision system for cone surface defect inspection. Specifically, we apply gradient and regional consistency detection algorithms to check the surface defects. And then the detection results will be sent via the serial port to the mechanical separation system, and the defective cones will be peeled off the production line by motor. The proposed system can improve the defect detection efficiency and product quality, also can reduce production costs. Experimental results demonstrate that the proposed approach can obtain superior performance over traditional manual method and has high detection efficiency.

Defect detection in slab surface: a novel dual Charge-coupled Device imaging-based fuzzy connectedness strategy.

To provide an accurate surface defects inspection system and make the automation of robust image segmentation method a reality in routine production line, a general approach is presented for continuous casting slab (CC-slab) surface defects extraction and delineation. The applicability of the system is not tied to CC-slab exclusively. We combined the line array CCD (Charge-coupled Device) traditional scanning imaging (LS-imaging) and area array CCD laser three-dimensional (3D) scanning imaging (AL-imaging) strategies in designing the system. Its aim is to suppress the respective imaging system's limitations. In the system, the images acquired from the two CCD sensors are carefully aligned in space and in time by maximum mutual information-based full-fledged registration schema. Subsequently, the image information is fused from these two subsystems such as the unbroken 2D information in LS-imaging and 3D depressed information in AL-imaging. Finally, on the basis of the established dual scanning imaging system the region of interest (ROI) localization by seed specification was designed, and the delineation for ROI by iterative relative fuzzy connectedness (IRFC) algorithm was utilized to get a precise inspection result. Our method takes into account the complementary advantages in the two common machine vision (MV) systems and it performs competitively with the state-of-the-art as seen from the comparison of experimental results. For the first time, a joint imaging scanning strategy is proposed for CC-slab surface defect inspection that allows a feasible way of powerful ROI delineation strategies to be applied to the MV inspection field. Multi-ROI delineation by using IRFC in this research field may further improve the results.

Automatic Inspection System for Surface Defect of Precision Steel Ball

Precision steel ball is one of the most critical components for rolling transmission. As precision ball affects the performance of precision transmission system, fully inspection of these balls is an urgent need for the industry. This paper is to develop a real-time inspection system for surface defects of precision steel ball with fast and robust method and mechanism. The developed system consists of an optical measurement module as well as a mechanism module for full surface inspecting of the steel ball. The minimum defect and area can be detected by the developed system are 0.1mm and 0.01 mm2 respectively. The developed system has been testified against the designed specifications at speed higher than 3pc/sec and less than 0.5% missing rate. It verified the resolution, accuracy and robustness of the developed system which is capable for final defect inspection of steel balls for grade 100 bearing.

Automatic inspection system of surface defects on optical IR-CUT filter based on machine vision

The paper presents an automatic surface defects inspection system for optical Infrared Cut-off (IR-CUT) filter, which is applied in all kinds of color cameras and video devices. The system involves illumination and imaging module, moving module, flipping module and machine vision algorithm. To highlight all the defected regions, the improved dark-field illumination technique is utilized in the imaging module. In order to accurately localize the region of optical IR-CUT filter in the captured image, stationary wavelet transform (SWT) is introduced to template matching algorithm. The introduction of SWT provides a more accurate estimate of the variances in the image and further facilitates the identification of the defected regions. The defects extraction method in this paper avoids the use of complicated learning process from a set of samples. Convexity theory is implemented on the algorithm of defects classification of edge crack. Experimental results on a variety of optical IR-CUT filter samples, including non-defective samples, samples with defects of stain, scratch and edge crack, have shown the efficiency (1.05s per sample) and accuracy (96.44%) of the proposed system. Moreover, defects extraction performances of different filters are compared in this paper. The research and application of the system will greatly liberate the human workforce and inspire ideas to detect the defects of some other small optical elements.

Research on Rail Surface Defect Inspection System

In order to realize the inspection of rail surface defects with high speed and high precision, an automatic detection system based on machine vision is presented. The hardware structure of the system consists of the mechanical system, control system and visual imaging system. The software structure using histogram threshold segmentation, multi-structural morphological edge detection and other image processing methods to detect and identify defects automatically, and also built the simulation rail detection platform. The experimental results show that the cracks, scars and other detects can be accurately detected and extracted in real time, and meet the requirement of the rail surface inspection.

A Real-Time Visual Inspection System for Discrete Surface Defects of Rail Heads

Discrete surface defects impact the riding quality and safety of a railway system. However, it is a challenge to inspect such defects in a vision system because of illumination inequality and the variation of reflection property of rail surfaces. This paper puts forward a real-time visual inspection system (VIS) for discrete surface defects. VIS first acquires a rail image by the image acquisition system, and then, it cuts the subimage of rail track by the track extraction algorithm. Subsequently, VIS enhances the contrast of the rail image using the local normalization (LN) method, which is nonlinear and illumination independent. At last, VIS detects defects using the defect localization based on projection profile (DLBP), which is robust to noise and very fast. Our experimental results demonstrate that VIS detects the Type-II defects with a recall of 93.10% and Type-I defects with a recall of 80.41%, and the proposed LN method and DLBP algorithm are better than the related well-established approaches. Furthermore, VIS is very fast with a linear computational time complexity, and it can be in real time to run on a 216-km/h test train under our experimental setup.

Development of a Surface Defect Inspection System for Cold Rolled Strip Based on Bright-Dark Filed Mode

Base on the study of the light reflectivity of steel surfaces, the interaction of CCD Camera and Illumination is investigated through experience. A new bright-dark filed defect recognition method which combines bright-filed mode and dark-filed mode is proposed. The bright-filed defect and dark-field defect on the surface of the strip steel can be detected at the same time through this new way, and the quantity of the defect information is increased. Therefore, the recognized defect type is twice the tradition way. A new algorithm of defect detection which is proper to bright-dark filed mode is proposed, too. This method is based on the image fusion. Experiment results show that detection rate of defects is more than 95% while classification rate of defects is over 85%.

Development of auto defect classification system on porosity powder metallurgy products

Automatic optical inspection (AOI) has been applied to many manufacturing fields for defect inspection of mass production parts, such as PCB and TFT-LCD, but it has never been applied to the production line of porous powder metallurgy. By its nature, the powder-formed part has inherent non-uniform porosity pattern on the metal substrate. The defect’s images are not easily separated from the substrate surface using the conventional binarization technique. This study develops a new image processing methodology and employs optical system design to build up an on-line surface defect inspection system for powder metallurgy parts. An analysis algorithm is also developed for the auto defect classification technique. It removes the noise signals from the porous image, detects the object edge and uses the hybrid-based method to sort out defects on the surface, such as crevice, scratch, broken corner and dent. Experimental tests show the maximum miss rate can be controlled to less than 5.65%.

An optimizing parameter selection method of neural network based on small sample

An optimized parameter selection method of neural network based on small sample was presented,and it was applied to online surface defect inspection system of cold rolled strips.Small sample of the method was utilized to train and test neural network by every possible combination of parameters to get a group of neural network parameters by plotting histogram of recognition rate under different parameter combinations.Experiments show that optimum recognition of surface defect of cold rolled strips can be accomplished by the parameters that are selected by the optimizing parameter selection method.

BMW to use automatic surface defect inspection system for sprayed car parts

BMW to use automatic surface defect inspection system for sprayed car parts