Speechreading using probabilistic models
Computer Vision and Image Understanding - Special issue on physics-based modeling and reasoning in computer vision
Image Sequence Analysis Using A Spatio-Temporal Coding For Automatic Lip-reading
ICIAP '99 Proceedings of the 10th International Conference on Image Analysis and Processing
Avatar-mediated face tracking and lip reading for human computer interaction
Proceedings of the 12th annual ACM international conference on Multimedia
Automatic Lipreading with Limited Training Data
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Colour and Geometric based Model for Lip Localisation: Application for Lip-reading System
ICIAP '07 Proceedings of the 14th International Conference on Image Analysis and Processing
Audio-visual speech modeling for continuous speech recognition
IEEE Transactions on Multimedia
| Hi-index | 0.00 |
This paper addresses the problem of isolate number recognition using visual information only. We utilize the intensity transformation and spatial filter to estimate the minimum enclosing rectangle of mouth in each frame. For each utterance, we obtain the two vectors composed of width and height of mouth, respectively. Then, we present a method to recognize the speech based on the polynomial fitting. Firstly, both width and height vectors are normalized and arranged into the constant length via interpolation. Secondly, least square method is utilized to produce two 3-order polynomials that can represent the main trend of the two vectors, respectively, and reduce the noise caused by the estimate error. Lastly, the positions of three crucial points (i.e. maximum, minimum, and right boundary point) in each 3-order polynomial curve are formed as a feature vector. For each utterance, we calculate the average of all vectors of training data to make a template, and utilize Euclidean distance between the template and testing data to perform the classification. Experiments show the promising results of the proposed approach in comparison with the existing methods.