Thesis Details
Hluboké neuronové sítě pro detekci anomálií při kontrole kvality
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.
Deep neural networks, anomaly detection, defect detection, quality control, Mask R-CNN
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Martínek Tomáš, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Vašíček Zdeněk, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Vojnar Tomáš, prof. Ing., Ph.D. (DITS FIT BUT), člen
Vranić Valentino, doc. Ing., Ph.D. (FIIT STU), člen
@mastersthesis{FITMT22149, author = "Tom\'{a}\v{s} Ju\v{r}ica", type = "Master's thesis", title = "Hlubok\'{e} neuronov\'{e} s\'{i}t\v{e} pro detekci anom\'{a}li\'{i} p\v{r}i kontrole kvality", school = "Brno University of Technology, Faculty of Information Technology", year = 2019, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/22149/" }