2011 · 410 citations · 8 references
ComputingAmerican Sign LanguageComputer ScienceComputer VisionMachine VisionNatural Language ProcessingAction RecognitionLetter RecognitionMultimodal InteractionObject RecognitionOptical Character RecognitionPattern RecognitionHand TrackingHuman Shape DetectionRandom ForestsShape DetectionSign Language Recognition
The study introduces an interactive user interface for real‑time recognition of ASL fingerspelling. The system employs a Microsoft Kinect to capture appearance and depth images, uses OpenNI+NITE for hand detection and tracking, and classifies hand‑shapes with random forests, operating in real‑time within an interactive UI that lets users resolve ambiguities and consult an English dictionary. Combining appearance and depth images yields the best classification accuracy, as demonstrated on a dataset of four users.
This article presents an interactive hand shape recognition user interface for American Sign Language (ASL) finger-spelling. The system makes use of a Microsoft Kinect device to collect appearance and depth images, and of the OpenNI+NITE framework for hand detection and tracking. Hand-shapes corresponding to letters of the alphabet are characterized using appearance and depth images and classified using random forests. We compare classification using appearance and depth images, and show a combination of both lead to best results, and validate on a dataset of four different users. This hand shape detection works in real-time and is integrated in an interactive user interface allowing the signer to select between ambiguous detections and integrated with an English dictionary for efficient writing.
8
Leo Breiman · Machine Learning · 2001 · 126.2K citations · Full text
Shape Quantization and Recognition with Randomized Trees
Yali Amit, Donald Geman · Neural Computation · 1997 · 1.3K citations