Exploiting Depth Discontinuities for Vision-Based Fingerspelling Recognition

Authors:
Rogerio Feris;Matthew Turk;Ramesh Raskar;Karhan Tan;Gosuke Ohashi
Affiliations:
University of California, Santa Barbara;University of California, Santa Barbara;Mitsubishi Electric;University of Illinois, Urbana-Champaign;Shizuoka University
Venue:
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 10 - Volume 10
Year:
2004

Citing 0
Cited 10

Non-photorealistic camera: depth edge detection and stylized rendering using multi-flash imaging

ACM SIGGRAPH 2004 Papers
Non-photorealistic camera: depth edge detection and stylized rendering using multi-flash imaging

ACM SIGGRAPH 2006 Courses
Non-photorealistic camera: depth edge detection and stylized rendering using multi-flash imaging

SIGGRAPH '05 ACM SIGGRAPH 2005 Courses
Multiflash Stereopsis: Depth-Edge-Preserving Stereo with Small Baseline Illumination

IEEE Transactions on Pattern Analysis and Machine Intelligence
Using structured light for efficient depth edge detection

Image and Vision Computing
Efficiently capturing object contours for non-photorealistic rendering

SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Efficient depth edge detection using structured light

ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
Fingerspelling recognition through classification of letter-to-letter transitions

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
Turkish fingerspelling recognition system using axis of least inertia based fast alignment

AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Increasing the effect of fingers in fingerspelling hand shapes by thick edge detection and correlation with penalization

PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel method for automatic fingerspelling recognition which is able to discriminate complex hand configurations with high amounts of finger occlusions. Such a scenario, while common in most fingerspelling alphabets, presents a challenge for vision methods due to the low intensity variation along important shape edges in the hand image. Our approach is based on a simple and cheap modification of the capture setup: a multi-flash camera is used with flashes strategically positioned to cast shadows along depth discontinuities in the scene, allowing efficient and accurate hand shape extraction. We then use a shift and scale invariant shape descriptor for fingerspelling recognition, demonstrating great improvement over methods that rely on features acquired by traditional edge detection and segmentation algorithms.