|
|
Deployment of deep learning-based anomaly detection systems: challenges and solutions
Ježek, Štěpán ; Burget, Radim
Visual anomaly detection systems play an important role in various domains, including surveillance, industrial quality control, and medical imaging. However, the deployment of such systems presents significant challenges due to a wide range of possible scene setups with varying number of devices and high computational requirements of deep learning algorithms. This research paper investigates the challenges encountered during the deployment of visual anomaly detection systems for industrial applications and proposes solutions to address them effectively. We present a model use case scenario from real-world manufacturing quality control and propose an efficient distributed system for deployment of the defect detection methods in manufacturing facilities. The proposed solution aims to provide a general framework for deploying visual defect detection algorithms base on deep neural networks and their high computational requirements. Additionally, the paper addresses challenges related the whole process of automated quality control, which can be performed with varying number of camera devices and it mostly requires interaction with other factory services or workers themselves. We believe the presented framework can contribute to more widespread use of deep learning-based defect detection systems, which may provide valuable feedback for further research and development.
|
|
|
Automatic Tire Inspection Using Surface Scans
Toth Vaňo, Pavol ; Materna, Zdeněk (referee) ; Španěl, Michal (advisor)
This thesis deals with automatic detection of defects on tire treads using their depth scans. The approach proposed in the thesis doesn’t require a faultless reference tire for the inspected tire. The first step is the detection of anomalies, which is done using a modification of the PatchCore method proposed in the thesis, taking advantage of the repetition of patterns on the tire tread. Subsequently, anomalies corresponding to special elements on the tire are detected using the deep neural networks Faster R-CNN and Deep Hough transform, and they are filtered out. Applying the proposed approach on the prepared dataset, the value 0.584 of Average Precision metric for detection was obtained. The biggest weakness of the proposed method is its limited ability to detect defects with a very small depth.
|
|
|
Detection and Classification of Photovoltaic Power Plant Panel Defects from a Drone Thermal Imaging Camera
Haužvic, Filip ; Materna, Zdeněk (referee) ; Bambušek, Daniel (advisor)
The thesis describes the processing of thermal images of photovoltaic power plants captured by a drone. In contemporary solutions, the images are analyzed manually, where an expert in thermal imaging searches for defects in individual panels. This approach is very time-consuming, and introducing some level of automation could ease the process. Therefore, I trained and utilized a U-Net model that detects hot spots in the images. To visualize and present the defects to the user, I designed and created a web-based application that highlights them in a complete orthomosaic of the photovoltaic power plant. Within the application, a user can annotate PV panels in the power plant and manually remove, or add any defect. When the plant is wholly annotated, an export to a spreadsheet can be created, matching defects to the individual annotated panels.
|
|
|
Classification of board defects in semiconductor manufacturing
Jašek, Filip ; Vágner, Martin (referee) ; Dřínovský, Jiří (advisor)
This diploma thesis focuses on detecting defects in semiconductor wafer manufacturing. It explores methods for identifying faulty chips and controlling yield during production. To classify defects machine learning techniques are used. Initially, ResNet18 architecture was used for inference, but low accuracy was attributed to limited input data. Transfer learning with ResNet50v2 was then attempted, resulting in improved metric with different dataset. Hyperparameter tuning and data augmentations were also explored. The study found that autoencoders for data compression during inference increased speed but led to degraded evaluation metrics.
|
|
|
High data rate image processing using CUDA/OpenCL
Sedláček, Filip ; Klečka, Jan (referee) ; Honec, Peter (advisor)
The main objective of this research is to propose optimization of the defect detection algorithm in the production of nonwoven textile. The algorithm was developed by CAMEA spol. s.r.o. As a consequence of upgrading the current camera system to a more powerful one, it will be necessary to optimize the current algorithm and choose the hardware with the appropriate architecture on which the calculations will be performed. This work will describe a usefull programming techniques of CUDA software architecture and OpenCL framework in details. Using these tools, we proposed to implement a parallel equivalent of the current algorithm, describe various optimization methods, and we designed a GUI to test these methods.
|
|
|
Reliable visual systems
Honec, Peter ; Janáková, Ilona (advisor)
The Doctoral thesis demonstrates the design of reliable industrial visual systems. The special emphasis is dedicated to the detection of defects on webs in industrial applications based on line-scan cameras. This system makes possible detection and classification of defects originating during the real production conditions. This work covers a theoretical study of a visual system for the defect detection on endless bands as well as of appropriate lighting and the scene arrangement. Further to that have been selected, adjusted and designed key components of hardware. Following the design and optimization of algorithms a system prototype had been installed on non-woven textiles production line. Eight visual systems implemented into real-life industrial conditions based on this prototype
|
|
|
Deep Neural Networks for Defect Detection
Juřica, Tomáš ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The goal of this work is to bring automatic defect detection to the manufacturing process of plastic cards. A card is considered defective when it is contaminated with a dust particle or a hair. The main challenges I am facing to accomplish this task are a very few training data samples (214 images), small area of target defects in context of an entire card (average defect area is 0.0068 \% of the card) and also very complex background the detection task is performed on. In order to accomplish the task, I decided to use Mask R-CNN detection algorithm combined with augmentation techniques such as synthetic dataset generation. I trained the model on the synthetic dataset consisting of 20 000 images. This way I was able to create a model performing 0.83 AP at 0.1 IoU on the original data test set.
|
|
|
Inovation of system for electroluminiscence defect detection of solar cells
Lepík, Pavel ; Křivík, Petr (referee) ; Vaněk, Jiří (advisor)
This master thesis analyses the existing methods both practically and theoretically used to detect defected surface area in solar cells. Various methods were used but by using an upgraded CMOS camera without IR filter to implement the electroluminescence method, this has proven to have a very crucial impact on the results. Given the overall results and the acquired information, a procedure with a simple parameter can be setup to carry out the measurements. In addition to this a catalog was formed showing the defects occurring in mono and polycrystalline solar cells.
|
|
|
Response analysis of train track laboratory model
Heteš, Marek ; Věchet, Stanislav (referee) ; Kšica, Filip (advisor)
In terms of safety, railway tracks have to be kept in good condition. Early and accurate detection of track defects can save both time and money. This thesis deals with simulation of a passing train on laboratory apparatus, and the measurement of the generated response. Apparatus represents scaled down section of a railway track, and allows the simulation of defect formation. With the help of the obtained data, a suitable method for defect detection was created.
|
|
|
Classification of board defects in semiconductor manufacturing
Jašek, Filip ; Vágner, Martin (referee) ; Dřínovský, Jiří (advisor)
This diploma thesis focuses on detecting defects in semiconductor wafer manufacturing. It explores methods for identifying faulty chips and controlling yield during production. To classify defects machine learning techniques are used. Initially, ResNet18 architecture was used for inference, but low accuracy was attributed to limited input data. Transfer learning with ResNet50v2 was then attempted, resulting in improved metric with different dataset. Hyperparameter tuning and data augmentations were also explored. The study found that autoencoders for data compression during inference increased speed but led to degraded evaluation metrics.
|
guest ::
