Effective Feature Selection Method Using Hog-Family Feature for Human Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13440%2F14%3A43885982" target="_blank" >RIV/44555601:13440/14:43885982 - isvavai.cz</a>

Výsledek na webu

<a href="http://onlinepresent.org/proceedings/vol52_2014/23.pdf" target="_blank" >http://onlinepresent.org/proceedings/vol52_2014/23.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.14257/astl.2014.52.23" target="_blank" >10.14257/astl.2014.52.23</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Effective Feature Selection Method Using Hog-Family Feature for Human Detection

Popis výsledku v původním jazyce

Support Vector Machine (SVM) is one of powerful learning machine and has been applied to varying task with generally acceptable performance. The success of SVM for classification tasks in one domain is affected by fea-tures which represent the instance of specific class. Given the representative and discriminative features, SVM learning will give good generalization and consequently we can obtain good classifier. In this paper, we will assess the problem of feature choices for human detection tasks andmeasure the perfor-mance of each feature. Here we will consider HOG-family feature. We pro-posed the multi-scale HOG as a NEW family member in this feature group. We also combine SVM with Principal Component Analysis (PCA) to reduce di-mension of features and enhance the evaluation speed while retaining most of discriminative feature vectors.

Název v anglickém jazyce

Effective Feature Selection Method Using Hog-Family Feature for Human Detection

Popis výsledku anglicky

Support Vector Machine (SVM) is one of powerful learning machine and has been applied to varying task with generally acceptable performance. The success of SVM for classification tasks in one domain is affected by fea-tures which represent the instance of specific class. Given the representative and discriminative features, SVM learning will give good generalization and consequently we can obtain good classifier. In this paper, we will assess the problem of feature choices for human detection tasks andmeasure the perfor-mance of each feature. Here we will consider HOG-family feature. We pro-posed the multi-scale HOG as a NEW family member in this feature group. We also combine SVM with Principal Component Analysis (PCA) to reduce di-mension of features and enhance the evaluation speed while retaining most of discriminative feature vectors.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Advanced Science and Technology Letters

ISBN

—

ISSN

2287-1233

e-ISSN

—

Počet stran výsledku

10

Strana od-do

131-141

Název nakladatele

SERSC (Science & Engineering Research Support society)

Místo vydání

Budapešť

Místo konání akce

Budapešť, Maďarsko

Datum konání akce

14. 8. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—