Detail výsledku s přesahem do praxe

Intelligent Defect and Anomaly Detection System - A Study in Tofu

HRADIŠ, M.

Originální název

Intelligent Defect and Anomaly Detection System - A Study in Tofu

Anglický název

Intelligent Defect and Anomaly Detection System - A Study in Tofu

Druh

Souhrnná výzkumná zpráva

Originální abstrakt

The report proposes an intelligent system for detection of defects in images based on a number of computer vision and pattern recognition methods: classification, segmentation, anomaly detection, and classification support visualization. 
The components were tested on real-life data from a food packaging plant.
The studied methods have to be able to detect physical defects and anomalies of various types of products and they should be able to adapt to new types of products and defects automatically or by users supervision. The user should be able to guide the detection system by providing examples of defects, by correcting wrong detections of the automated system, or by similar actions.

Anglický abstrakt

The report proposes an intelligent system for detection of defects in images based on a number of computer vision and pattern recognition methods: classification, segmentation, anomaly detection, and classification support visualization. 
The components were tested on real-life data from a food packaging plant.
The studied methods have to be able to detect physical defects and anomalies of various types of products and they should be able to adapt to new types of products and defects automatically or by users supervision. The user should be able to guide the detection system by providing examples of defects, by correcting wrong detections of the automated system, or by similar actions.

Klíčová slova

anomaly detection, defect detection, visual quality control, semi-supervised learning, active learning, convolutional neural networks

Klíčová slova v angličtině

anomaly detection, defect detection, visual quality control, semi-supervised learning, active learning, convolutional neural networks

Autoři

HRADIŠ, M.

Rok RIV

2016

Vydáno

30.12.2015

Nakladatel

Fingera s.r.o.

Místo

Brno

Strany od

1

Strany do

35

Strany počet

35

BibTex

@misc{BUT123629,
  author="Michal {Hradiš}",
  title="Intelligent Defect and Anomaly Detection System - A Study in Tofu",
  year="2015",
  pages="1--35",
  publisher="Fingera s.r.o.",
  address="Brno",
  note="Summary research report"
}