Title :
A part-based rotational invariant hand detection
Author :
Jisu Kim ; Jeonghyun Baek ; Euntai Kim
Author_Institution :
Sch. of Electr. & Electron. Eng., Yonsei Univ., Seoul, South Korea
Abstract :
This paper proposes part-based rotational invariant hand detection in complicated environment. The proposed method consists with 4 steps: head detection, back projection, hand rotation and hand detection. To improve the hand detection performance, the human head information is used for generating effective hand ROIs. Generated hand ROIs are verified using Histogram of Oriented (HOG) feature and Support Vector Machine (SVM) classifier. In the experiment, the proposed method is compared with previous methods and detection performance and computational time are evaluated.
Keywords :
computer vision; feature extraction; gesture recognition; image classification; object detection; support vector machines; HOG; SVM; back projection; computer vision; hand ROI generation; hand detection performance improvement; hand gesture detection; hand rotation; head detection; histogram-of-oriented feature; human head information; part-based rotational invariant hand detection; region-of-interest; support vector machine classifier; Educational institutions; Feature extraction; Head; Image color analysis; Robustness; Skin; Support vector machines; HOG feature; Rotational invariant hand detection; SVM classifier;
Conference_Titel :
Fuzzy Theory and Its Applications (iFUZZY), 2013 International Conference on
Conference_Location :
Taipei
DOI :
10.1109/iFuzzy.2013.6825422
