International Journal of Mechanical & Mechatronics Engineering IJMME-IJENS Vol:14 No:02 48 146102-8585-IJMME-IJENS © April 2014 IJENS I J E N S Abstract— Lip reading is a technique of communication used by a hard hearing person in their conversation between themselves or with the normal person. Sometime the word they understand is not the same as what the other speaker talk. Computer-based lip reading system may help them to track those words based on the movement of the lips. When speak, lip make a movement that may differ between several words. For the computer to recognize the spoken word, feature from the lip need to be extracted and is stored in the database. A surface area of the lip is proposed as the feature of the lip movement. The horizontal and vertical distances of the lip are extracted to determine the surface area. Data from the lip feature then been resample to estimate some parameter and their reliability. Result from the resample then will be initialized to reduce memory usage in the database. In the experiments, several spoken words at the hospital have been chosen. The experimental results show that the ellipse feature could be employed to train the computer understands the spoken word from the human. Index Term— speech, image processing, lip tracking, ellipse I. INTRODUCTION Computer-based lip reading system is a system that may help deaf and hard hearing person to learn how to speak with the correct lip movement. Lip has a significant shape that may help in recognizing word speaking. In the conventional lip reading learning, instructor needs face to face with the hard hearing person to correct their lip movement for word been spoke. Paper submitted on 7 March 2014. This work is supported by Fundamental Research Grant Scheme by the Ministry of Education to Universiti Malaysia Perlis (FRGS 9003-00313). Kamil S. TALHA, Advanced Intelligent Computing and Sustainability Research Group, School of Mechatronic, Universiti Malaysia Perlis Kampus Pauh Putra, 02600 Arau, Perlis, MALAYSIA (e-mail: kamilsyahid89@gmail.com). KhairunizamWAN, Centre of Excellence for Unmanned Aerial System (COEUAS) and Advanced Intelligent Computing and Sustainability Research Group, School of Mechatronic, Universiti Malaysia Perlis KampusPauh Putra, 02600 Arau, Perlis, MALAYSIA (e-mail: khairunizam@unimap.edu.my). Zuradzman M. Razlan, Centre of Excellence for Unmanned Aerial System (COEUAS) Shahriman AB, Centre of Excellence for Unmanned Aerial System (COEUAS) S.K.Za’ba, Advanced Intelligent Computing and Sustainability Research Group, School of Mechatronic, Universiti Malaysia Perlis Kampus Pauh Putra, 02600 Arau, Perlis, MALAYSIA Viratt Chittawad, Advanced Intelligent Computing and Sustainability Research Group, School of Mechatronic, Universiti Malaysia Perlis Kampus Pauh Putra, 02600 Arau, Perlis, MALAYSIA M. Nasir Ayob, Advanced Intelligent Computing and Sustainability Research Group, School of Mechatronic, Universiti Malaysia Perlis Kampus Pauh Putra, 02600 Arau, Perlis, MALAYSIA When we speak our lips will make several horizontal and vertical movements. Many researches find out that detection of lip activities and movements may help to classified talking faces in television-content [1]. Piotr Dalka [2] in his research had developed a LipMouse to help paralyze people controlling mouse curser by using shape of the lips. Accurately tracking facial features requires coping with the large variation in appearance across subjects and the combination of a rigid and a non-rigid motion [3]. Lip region may sometime difficult to extract due to variation color of the lip. Lip tracking not a trivial task, since there are varieties in people in skin color, lip width and lip movement during speech [4]. In this work, the research objective is to detect the movement of lips based on the changes of the surface area of the ellipse. In [5] the researcher try to locate the lip region based on the whole face detection. The surface area is calculated based on the width and height of the tracking lip. This paper is structured as follows: In the methodologies, the fundamental of image processing employs in the research is briefly explain. In the experiments, the obtained results from ellipse tracking are discussed. II. LITERATURE REVIEW In the research of image processing, several researches had proposed various techniques for the purpose of vision sensing. Jamal Ahmad Dargham et al. [9] proposed a method for lips detection in color image in the normalized RGB color scheme. They proposed a new method called the maximum intensity normalization. The method successfully reduces the error in image segmentation compared to the pixel intensity normalization. Ying-li Tian et al. [10] described a method of tracking a feature of facial expression, in particular, lip contours, by using a multi-state mouth model and combining lip color, shape and motion information. They the lip and skin color by using Gaussian mixture. Yun-Long Lay [11] used principal component analysis and mouth changing rate for getting the feature of the moving lip. The author also states that in the pre-processing, several steps need to ensure first for getting the robust lip recognition. These steps include brightness adjustment, color space transforms, face color cutting, facial operation region and lip localization. Yonghong Xie [12] in his paper demonstrates a new method for ellipse detection. In his paper, the ellipse detected is based on the one-dimensional accumulator array to accumulate the length information for minor axis of the ellipse. This method Extracting Features Point of Lip Movement for Computer-based Lip Reading System Kamil S. TALHA, Khairunizam WAN, Viratt Chittawad, S.K.Za’ba and M. Nasir Ayob, Zuradzman M. Razlan, and Shahriman AB