Reducing dimensions of the histogram of oriented gradients (HOG) feature vector

Autor:	A S Bondarchuk, S Poslavsky, Stanislav Shidlovskiy, M. V. Shikhman
Rok vydání:	2020
Předmět:	History Pixel Computer science business.industry Feature vector ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Computer Science Applications Education Support vector machine Histogram of oriented gradients Artificial intelligence business Classifier (UML)
Zdroj:	Journal of Physics: Conference Series. 1611:012072
ISSN:	1742-6596 1742-6588
DOI:	10.1088/1742-6596/1611/1/012072
Popis:	The article discusses the basic principles of a HOG-descriptor. A method is proposed for reducing dimensions of the feature vector obtained using the HOG-descriptor by applying the convolution operation and converting the resulting values of gradients and their directions. After using new feature vectors for training, the Support Vector Machine (SVM) classifier showed a 37-fold increase in performance when processing an image with a resolution of 282×159 pixels.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::5c942204b3ed2c5571a79c63a90bd5d0 https://doi.org/10.1088/1742-6596/1611/1/012072 Zobrazit plný text záznamu