Gradient-DCT (G-DCT) descriptors
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F14%3A86093011" target="_blank" >RIV/61989100:27240/14:86093011 - isvavai.cz</a>
Result on the web
<a href="http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=7001946" target="_blank" >http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=7001946</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/IPTA.2014.7001946" target="_blank" >10.1109/IPTA.2014.7001946</a>
Alternative languages
Result language
angličtina
Original language name
Gradient-DCT (G-DCT) descriptors
Original language description
Many feature-based object detectors have shown that the use of gradient image information can be a very efficient way to describe the appearance of objects. Especially, the gradient sizes, directions and histograms are commonly used. In this area, the histogram of oriented gradients (HOG) is considered as the state-of-the-art method. The histograms and gradient orientations are used to encode the gradient information in HOG. Nevertheless, many works have proved that the feature vector dimensionality of HOG can be reduced; particularly, the information of the gradient directions is redundant and it can be reduced. This was the motivation to encode the gradient information with the least possible redundant information. In this paper, we propose the method in which the discrete cosine transform (DCT) is used to effectively encode the gradient information; using DCT, the gradient information can be encoded with a relatively small set of DCT coefficients in which the most important gradient information is preserved. We show the properties of presented method for the case of solving the problem of face and pedestrian detection.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2014 4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014
ISBN
978-1-4799-6461-1
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
134-139
Publisher name
Institute of Electrical and Electronics Engineers
Place of publication
New York
Event location
Paříž
Event date
Oct 14, 2014
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000380617200027