Lirong Wang

Lip Detection and Tracking Using Variance Based Haar-Like Features and Kalman filter

Speaker lip motion stands out as the most linguistically relevant visual feature for speech recognition. Lip reading is an active field that receives much attention from computer scientists. Its applications take part not only in science, such as a speech recognition system, but also in social activities, such as teaching pronunciation for deaf children in order to recover their speaking ability, and combining visual features and audio features to increase the accuracy in noisy environments. In this paper, we aim to solve a narrower problem, the lip detection and tracking, which is an essential step to provide visual lip data for the lip-reading system. A new approach is proposed to perform the problem of real-time lip detection. The proposed method combines primitive Haar-Like feature and variance value to construct a new feature, so-called Variance based Haar-Like feature. Human face and lip can be represented with a small quantity of features using the new features. We used SVM for training and classification, combining kalman filter can realize lip real-time detection and tracking. Experiments showed that face and lip detection system using Variance based Haar-Like feature and SVM can be much more efficient than face and detection system by using primitive Haar-Like features.

The Research on Paper-Mediated Braille Automatic Recognition Method

The paper-mediated Braille automatic recognition method referred in this paper, for the scanned Braille images, pre-process the Braille images, convert into Braille binary image and then extract the Braille features by the fixed nature of Braille. Then grouping, locating, marking the Braille cells, establish a standard Braille Corpus according as one-to-one Correspondence between Braille cell and character contains Hanyu Pinyin, Arabic numerals and interpunction, then match the recognized Braille cells and finally output the sentences formed Hanyu Pinyin, Arabic numerals and interpunation. This method is simple convenient, and easy to operate. The paper introduces Braille extraction, Braille recognition, illuminates specific experimental approach in details. Experiments show that the method can effectively extract Braille, and accurately convert the Braille into Hanyu Pinyin.

Research on Local Image Navigation Method for Visual-Impaired Person

Due to no navigation in small area of the existing navigation system, we proposed an image-based matching navigation system for people with disabilities can walk in the designated area. Firstly, acquire and process the image captured from specified area by CCD digital video camera to establish Benchmark Image Library. And then pre-process the real-time image captured in walking to get Real-time Image Library. To match benchmark image with real-time image by fast scene matching algorithm based on SIFT feature. After that, match feature points for image that maybe rotation or change in scaling in different lighting and camera angles. Experimental results show that performance of the algorithm meet the requirements of high-performance of scene matching navigation systems.