Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Hierarchical grouping using gestalt assessments

: Michaelsen, Eckart; Arens, Michael

Fulltext urn:nbn:de:0011-n-4734057 (549 KByte PDF)
MD5 Fingerprint: 734f225862bb5c660d0b59502d4124c3
Created on: 14.11.2017

Ikeuchi, K. ; Institute of Electrical and Electronics Engineers -IEEE-:
IEEE International Conference on Computer Vision Workshops, ICCVW 2017 : 22-29 October 2017, Venice, Italy. Proceedings
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-5386-1034-3
ISBN: 978-1-5386-1035-0
International Conference on Computer Vision (ICCV) <2017, Venice>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Real images contain symmetric Gestalten with high probability. I.e. certain parts can be mapped on other certain parts by the usual Gestalt laws and are repeated there with high similarity. Moreover, such mapping comes in nested hierarchies – e.g. a reflection Gestalt that is made of repetition friezes, whose parts are again reflection symmetric compositions. This can be explicitly modelled by continuous assessment functions. Hard decisions on whether or not a law is fulfilled are avoided. Starting from primitive objects extracted from the input image successively aggregates are constructed: reflection pairs, rows, etc., forming a part-of-hierarchy and rising in scale. The work in this paper starts from super-pixel primitives, and the grouping ends when the Gestalten almost fill the whole image. Occasionally the results may not be in accordance with human perception. The parameters have not been adjusted specifically for the data at hand. Previous work only used the compulsory attributes location, scale, orientation and assessment for each object. A way to improve the recognition performance is utilizing additional features such as colors or eccentricity. Thus the recognition rates are a little better.