Application of Directional Statistics to Gradient Based Lip Contour Extraction for Speechreading
نویسندگان
چکیده
In the relatively large class of lipreading algorithms based on lip contour analysis lip contour extraction is the rst step This refers to the de tection of lip contour in the rst frame of an audio visual sequence where no initial prediction of the lip contour is available This task is usually solved man ually or pseudo automatically requiring some manual human intervention Past attempts to contour extraction based on typical edge detection schemes failed in the case of frontal gray level natural mouth images due to the weak contrast of these images The proposed approach for lip contour extraction is still based on edge processing but instead of using the edge magnitude we process the edge direction Clear patterns of edge directions can be observed around the lip con tours and noisy directions in the remaining areas By using angular measures for edge following good results are obtained with little manual intervention
منابع مشابه
Pseudoautomatic Lip Contour Detection Based on Edge Direction Patterns
Detection and tracking of the lip contour is an important issue in speechreading. While there are solutions for lip tracking once a good contour initialization in the first frame is available, the problem of finding such a good initialization is not yet solved automatically, but done manually. Solutions based on edge detection and tracking have failed when applied on real world mouth images. In...
متن کاملAutomatic Extraction of Lip Feature Points
We present a novel algorithm for the robust and reliable automatic extraction of lip feature points for speechreading. The algorithm uses a combination of colour information in the image data and knowledge about the structure of the mouth area to find certain feature points on the inner lip contour. A new confidence measure quantifying how well the feature extraction process worked is introduce...
متن کاملA New Fuzzy C-means Based Segmentation Strategy. Applications to Lip Region Identification
The problem of lip contour detection is critical in the lipreading systems based on contour processing. The typical contour detection strategy based on image segmentation in homogeneous regions fails in the case when the mouth images available for lipreading are lowcontrast gray level images. Most of the solutions adopted require manual marking of some contour points. Here we propose a new solu...
متن کاملTowards speaker independent continuous speechreading
This paper describes recent speechreading experiments for a speaker independent continuous digit recognition task. Visual feature extraction is performed by a lip tracker which recovers information about the lip shape and information about the greylevel intensity around the mouth. These features are used to train visual word models using continuous density HMMs. Results show that the method gen...
متن کاملStatistical chromaticity-based lip tracking with B-splines
We present a statistical, colour-based technique for lip tracking intended to support personal veri cation. The lips are automatically localised in the original image by exploiting grey-level gradient projections as well as chromaticity models to nd the mouth area in an automatically segmented region corresponding to the face area. A B-spline, initially with an elliptic shape is then generated ...
متن کامل