- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Automated Visual Inspection of Glass Bottle Bottom With Saliency Detection and Template Matching
摘要： Glass bottles are widely used as containers in the food and beverage industry, especially for beer and carbonated beverages. As the key part of a glass bottle, the bottle bottom and its quality are closely related to product safety. Therefore, the bottle bottom must be inspected before the bottle is used for packaging. In this paper, an apparatus based on machine vision is designed for real-time bottle bottom inspection, and a framework for the defect detection mainly using saliency detection and template matching is presented. Following a brief description of the apparatus, our emphasis is on the image analysis. First, we locate the bottom by combining Hough circle detection with the size prior, and we divide the region of interest into three measurement regions: central panel region, annular panel region, and annular texture region. Then, a saliency detection method is proposed for finding defective areas inside the central panel region. A multiscale filtering method is adopted to search for defects in the annular panel region. For the annular texture region, we combine template matching with multiscale filtering to detect defects. Finally, the defect detection results of the three measurement regions are fused to distinguish the quality of the tested bottle bottom. The proposed defect detection framework is evaluated on bottle bottom images acquired by our designed apparatus. The experimental results demonstrate that the proposed methods achieve the best performance in comparison with many conventional methods.
关键词： multiscale filtering,machine vision,template matching,saliency detection,Defect detection
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Ultrasonics Symposium (IUS) - Kobe, Japan (2018.10.22-2018.10.25)] 2018 IEEE International Ultrasonics Symposium (IUS) - High Frequency Optical Probe for BAW/SAW Devices
摘要： Optical properties of semiconductor devices for LED and OLED devices. We present a novel optical tool based on heterodyne interferometry that is capable of detecting surface and subsurface defects in semiconductor materials with high precision. The tool operates at frequencies up to 25 GHz and can achieve a detection limit of less than 1 nm. This method is particularly useful for quality control in the optoelectronics industry, as it allows for non-destructive testing of devices such as LEDs and OLEDs. Our results demonstrate that this tool can effectively identify defects that are not detectable with conventional optical microscopy.
关键词： non-destructive testing,defect detection,optoelectronics,semiconductor devices,LED,OLED,heterodyne interferometry
更新于2025-09-23 15:22:29
-
<i>(Invited)</i> Characterization of UV Excitation Accelerated Material Changes on as-Grown SiC Epitaxial Layers and Their Impact on Defect Detection
摘要： Both visible defects and crystal defects in Silicon Carbide (SiC) epitaxial layers are being scanned and identified by in-line production systems. All the modern detection systems use Ultra-Violet (UV) light exposure on the wafers followed by signal capture from topographic and photoluminescence (PL) channels. The repeatability and consistency of these measurements becomes very critical for both determining the quality and yield of the wafers and screening potential affected die for reliability issues. In this work, we present the effects of repeated and long-term UV exposure on the SiC wafers. We document the loss of measurement repeatability and determine the cause for this as a highly accelerated growth of a thin oxide layer. We further offer techniques to recover from this mechanism and offer a way to prevent this from happening. The results are further verified by recreating this mechanism and observing similar effects.
关键词： photoluminescence,UV excitation,epitaxial layers,Silicon Carbide,defect detection
更新于2025-09-23 15:21:21
-
[IEEE 2019 18th International Conference on Optical Communications and Networks (ICOCN) - Huangshan, China (2019.8.5-2019.8.8)] 2019 18th International Conference on Optical Communications and Networks (ICOCN) - Massive MIMO Precoding Based On Channel Condition Number
摘要： Titanium-coated surfaces are prone to tiny defects such as very small cracks, which are not easily observable by the naked eye or optical microscopy. In this study, two new thresholding methods, namely contrast-adjusted Otsu’s method and contrast-adjusted median-based Otsu’s method, are proposed for automated defect detection system for titanium-coated aluminum surfaces. The two proposed methods were compared with four existing thresholding techniques in terms of accuracy and speed of defect detections for images of 700, 900, and 1000 dpi obtained using high-resolution scanning. Experimental results have shown that the proposed contrast-adjusting methods have performance similar to minimum error thresholding (MET) and are generally better than Otsu’s method.
关键词： image processing,image analysis,mesoscopy,Coated surface inspection,defect detection,high-resolution scanning
更新于2025-09-23 15:21:01
-
[IEEE 2018 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA) - Singapore (2018.7.16-2018.7.19)] 2018 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA) - High Sensitivity Ultrasonic Inspection Technique Using Pulse Compression Method
摘要： We developed an ultrasonic inspection technique using a pulse compression method for detecting bonding defects with interfaces of stacked wafers. This technique can detect the minute echoes reflected from the bonding interfaces by computing the correlation function between transmitted and received signals. We designed a measurement condition for pulse compression with a transmitted signal and took an ultrasonic measurement of a 3-layer stacked sample. We compared the defect detection sensitivity of the pulse compression method with the ultrasonic inspection using pulse waves. The experimental results showed that the noise of an ultrasonic image was reduced and minute defects could be detected by applying developed method.
关键词： multi-layer staked sample,Correlation function,Defect detection,Ultrasonic inspection,Pulse compression
更新于2025-09-19 17:15:36
-
A wave-based optimization approach of curved joints for improved defect detection in waveguide assemblies
摘要： A wave-based numerical approach is proposed for the detection of defects in waveguide assemblies with curved joints. Within this framework, the wave finite element (WFE) method is used. It provides an efficient numerical means for computing waves in one-dimensional periodic structures (waveguides), and assessing the reflection and transmission coefficients of waves around defects and curved joints. A so-called apparent reflection matrix of the defects, which takes into account the influence of the joints on the reflected signals recorded at some measurement point at the beginning of a waveguide assembly, is proposed. This appears to be the relevant criterion for detecting defects. As it turns out, an optimization procedure for the design of curved joints can be proposed to magnify the amplitude of the reflected signals issued from defects. Numerical experiments are carried out on 2D waveguide assemblies, with one or two curved joints which are parameterized with respect to their radius and angle of curvature. Optimized values of these parameters can be found which magnify the reflected signals issued from several kinds of defects. Time response simulations are finally undertaken to highlight the relevance of the proposed approach.
关键词： defect detection,wave finite element method,optimization,curved joints,scattering matrix
更新于2025-09-19 17:13:59
-
Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning
摘要： With the rising use of photovoltaic and ongoing installation of large-scale photovoltaic systems worldwide, the automation of photovoltaic monitoring methods becomes important, as manual/visual inspection has limited applications. This research work deals with automatic detection of photovoltaic module defects in Infrared images with isolated deep learning and develop-model transfer deep learning techniques. An Infrared images dataset containing infrared images of normal operating and defective modules is collected and used to train the networks. The dataset is obtained from Infrared imaging performed on normal operating and defective photovoltaic modules with lab induced defects. An isolated learned model is trained from scratch using a light convolutional neural network design that achieved an average accuracy of 98.67%. For transfer learning, a base model is first developed (pre-trained) from electroluminescence images dataset of photovoltaic cells and then fine-tuned on infrared images dataset, that achieved an average accuracy of 99.23%. Both frameworks require low computation power and less time; and can be implemented with ordinary hardware. They also maintained real time prediction speed. The comparison shows that the develop-model transfer learning technique can help to improve the performance. In addition, we reviewed different kind of defects detectable from infrared imaging of photovoltaic modules, that can help in manual labelling for identifying different defect categories upon access to new huge data in future studies. Last of all, the presented frameworks are applied for experimental testing and qualitative evaluation.
关键词： Isolated deep learning,Develop-model transfer deep learning,Automatic defect detection,Thermography,Infrared images,Photovoltaic (PV) modules
更新于2025-09-19 17:13:59
-
CNN based automatic detection of photovoltaic cell defects in electroluminescence images
摘要： Automatic defect detection is gaining huge importance in photovoltaic (PV) field due to limited application of manual/visual inspection and rising production quantities of PV modules. This study is conducted for automatic detection of PV module defects in electroluminescence (EL) images. We presented a novel approach using light convolutional neural network architecture for recognizing defects in EL images which achieves state of the art results of 93.02 % on solar cell dataset of EL images. It requires less computational power and time. It can work on an ordinary CPU computer while maintaining real time speed. It takes only 8.07 milliseconds for predicting one image. For proposing light architecture, we perform extensive experimentation on series of architectures. Moreover, we evaluate data augmentation operations to deal with data scarcity. Overfitting appears a significant problem; thus, we adopt appropriate strategies to generalize model. The impact of each strategy is presented. In addition, cracking patterns and defects that can appear in EL images are reviewed; which will help to label new images appropriately for predicting specific defect types upon availability of large data. The proposed framework is experimentally applied in lab and can help for automatic defect detection in field and industry.
关键词： PV cell cracking,Automatic defect detection,Convolutional neural network (CNN),Electroluminescence,Deep learning,Photovoltaic (PV) modules
更新于2025-09-19 17:13:59
-
[IEEE 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) - Zaragoza, Spain (2019.9.10-2019.9.13)] 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) - Semi-automatic quality inspection of solar cell based on Convolutional Neural Networks
摘要： Quality control of solar cells is a very important part of the production process. A little crack or joint failure can cause bad performance of the cell in the future, partly because the defective areas can be electrically disconnected from the active zones. Nowadays, one of the techniques to carry out this control is electroluminescence (EL), which allows obtaining high-resolution images of the cells where a visual and non-invasive inspection of defects can be done. This inspection is mostly performed by trained human operators. However, as the eyes become tired after a working day and the subjectivity of the operators, the accuracy with which the defect detection is done may be compromised. In order to solve this problem, a method to assist the operator in the inspection of polycrystalline silicon solar cells surface from EL images based on Convolutional Neural Networks is proposed. The method would classify the cells as defective and non-defective, and suggest those cells that are defective for re-inspection. Also, it would propose a segmentation map of the defects in the cell. To compensate for the lack of image samples in the dataset, each cell image is divided into regions by a sliding window. Then, each region is classified as defective or non-defective. And finally, all classifications related to the cell are resembled obtaining a segmented image of defective areas in the cell.
关键词： Segmentation,Defect Detection,Classification,Electroluminescence,Convolutional Neural Networks
更新于2025-09-19 17:13:59
-
[IEEE 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) - Vancouver, BC, Canada (2019.10.17-2019.10.19)] 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) - 3D Shape Reconstruction based on Directional LED lights
摘要： A novel algorithm is presented in this paper for solder paste inspection. The proposed methodology is based on a specially designed directional LED lighting to highlight the geometrical features of the solder paste block. Solder paste inspection and shape reconstruction are then carried out based on the highlighted shape features. An algorithm for 3D reconstruction of solder paste is developed. The process is carried out by calculating a set of surface heights for the solder paste block. The estimated shape of the solder paste block is represented by the calculated set of surface heights. To improve the accuracy of the estimation, parameter optimization has been carried out to search for an optimal set of algorithm parameters using the actual solder paste shape.
关键词： LED,automation,automatic optical inspection,defect detection,shape reconstruction,solder paste inspection
更新于2025-09-16 10:30:52