Visual Gesture Character String Recognition by Classification-Based Segmentation with Stroke Deletion

• Published in: Proceedings - IEEE Computer Society Conference on Pattern Recognition and Image Processing pp. 120 - 124
• Main Authors: Xiao-Jie Jin, Qiu-Feng Wang, Xinwen Hou, Cheng-Lin Liu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2013
• Subjects: Character recognition; Context; Context modeling; deletion geometry model; Feature extraction; Handwriting recognition; Hidden Markov models; Kinect; over-segmentation; string recognition; Trajectory; Visual gesture character string
• ISSN: 0730-6512
• DOI: 10.1109/ACPR.2013.7

The recognition of character strings in visual gestures has many potential applications, yet the segmentation of characters is a great challenge since the pen lift information is not available. In this paper, we propose a visual gesture character string recognition method using the classification-based segmentation strategy. In addition to the character classifier and character geometry models used for evaluating candidate segmentation-recognition paths, we introduce deletion geometry models for deleting stroke segments that are likely to be ligatures. To perform experiments, we built a Kinect-based fingertip trajectory capturing system to collect gesture string data. Experiments of digit string recognition show that the deletion geometry models improve the string recognition accuracy significantly. The string-level correct rate is over 80%.