Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
GOLDMANN, T. ORSÁG, F. DRAHANSKÝ, M.
Originální název
Dataset generator for face detector training
Typ
článek ve sborníku mimo WoS a Scopus
Jazyk
angličtina
Originální abstrakt
Many classification algorithms depend on a training dataset to be able to find appropriate parameters. The training dataset can significantly affect the resulting quality of the classifier hence it is necessary to use as good dataset for given task as possible. Either there already is an available ready-to-use dataset or a new one must be created. It is rather tedious and time consuming process to create a~new dataset from scratch because many algorithms usually require a large amount of tagged data. For many specific tasks the only way is to create a new dataset simply because there are no sets available. For the purposes of training and testing face detection algorithms we created a generator producing large number of images containing human head in various poses and positions placed in a predefined background. We are using such datasets to test success rate of head detection algorithms in dependence on the rotation of the head. Based on the test results we designed a tool to classify suitability of a security camera placement based on its parameters and space it should watch.
Klíčová slova
identification, head pose, anthropometry
Autoři
GOLDMANN, T.; ORSÁG, F.; DRAHANSKÝ, M.
Vydáno
4. 6. 2018
Místo
Hersonissos
Strany od
1
Strany do
8
Strany počet
BibTex
@inproceedings{BUT168457, author="Tomáš {Goldmann} and Filip {Orság} and Martin {Drahanský}", title="Dataset generator for face detector training", booktitle="Proceedings 2019 International Conference on Biometrics", year="2018", pages="1--8", address="Hersonissos" }