DocumentCode
3253028
Title
Analysis of pixel level features in recognition of real life dual-handed sign language data set
Author
Lilha, Himanshu ; Shivmurthy, Devashish
Author_Institution
Dept. of Comput. Sci. & Eng., PES Sch. of Eng., Bangalore, India
fYear
2011
fDate
21-23 Dec. 2011
Firstpage
246
Lastpage
251
Abstract
This paper demonstrates the evaluation of various pixel level features for the dual handed sign language data set. Data sets are collected from the real life scenario. We compare the feature extraction methods like Histogram of Orientation Gradient (HOG), Histogram of Boundary Description (HBD) and the Histogram of Edge Frequency (HOEF). The accuracy of HOG and HBD found up to 71.4% and 77.3% whereas the accuracy of HOEF in real life data set is 97.3% and in ideal condition 98.1%.
Keywords
edge detection; feature extraction; gesture recognition; feature extraction methods; histogram of boundary description; histogram of edge frequency; histogram of orientation gradient; pixel level feature analysis; real life dual-handed sign language data set; sign language recognition; Feature extraction; Handicapped aids; Histograms; Image edge detection; Noise; Skin; HBD; HOEF; HOG; ISL; Sign language; dual-handed;
fLanguage
English
Publisher
ieee
Conference_Titel
Recent Trends in Information Systems (ReTIS), 2011 International Conference on
Conference_Location
Kolkata
Print_ISBN
978-1-4577-0790-2
Type
conf
DOI
10.1109/ReTIS.2011.6146876
Filename
6146876
Link To Document