Daleesha M Viswanathan & Sumam Mary Idicula International Journal of Image Processing (IJIP), Volume (9) : Issue (1) : 2015 32 SVM Based Recognition of Facial Expressions Used In Indian Sign Language Daleesha M Viswanathan daleesha_mv@address.com Department of Computer Science Cochin University of Science and Technology Kochi-22, Kerala, India Sumam Mary Idicula sumam@cusat.ac.in Department of Computer Science Cochin University of Science and Technology Kochi-22, Kerala, India Abstract In sign language systems, facial expressions are an intrinsic component that usually accompanies hand gestures. The facial expressions would modify or change the meaning of hand gesture into a statement, a question or improve the meaning and understanding of hand gestures. The scientific literature available in Indian Sign Language (ISL) on facial expression recognition is scanty. Contrary to American Sign Language (ASL), head movements are less conspicuous in ISL and the answers to questions such as yes or no are signed by hand. Purpose of this paper is to present our work in recognizing facial expression changes in isolated ISL sentences. Facial gesture pattern results in the change of skin textures by forming wrinkles and furrows. Gabor wavelet method is well-known for capturing subtle textural changes on surfaces. Therefore, a unique approach was developed to model facial expression changes with Gabor wavelet parameters that were chosen from partitioned face areas. These parameters were incorporated with Euclidian distance measure. Multi class SVM classifier was used in this recognition system to identify facial expressions in an isolated facial expression sequences in ISL. An accuracy of 92.12 % was achieved by our proposed system. Keywords: Indian Sign Language, Facial Expression, Gabor Wavelet, Euclidian Distance, SVM. 1. INTRODUCTION Facial expressions convey important synaptic information in sign language. For example, facial expression would modify the meaning of hand gesture sign for “you eat” in to “please eat”, “did you eat?” and “can you eat?” In ASL, the facial expressions and head movements are generally classified into expression of emotions, conversation regulator, expressions that modify the quality and quantity of a sign [1]. Similar to ASL, there are many occasions in ISL where facial expressions are used in sign language recognition. Whether a sentence is interrogative or simple sentence is decided by the associated facial expression [1]. As an example, “where are you going?” in ISL following “subject object verb” pattern is “you going where”, of which, ‘you’ and ‘going’ are signed by hand gesture but the question “where” is conveyed by facial expression [2]. In addition, the emotions such as anger, happiness, surprise and sadness are signed by facial expression in ISL [3]. In ASL, facial expression and head movement recognition systems have been standardized (Google Scholar and Web of Science citations) [1]. However, these works would not be directly applicable in ISL due to many reasons. Inherent difference exist between ASL and ISL [2]. Contrary to ASL, head movements are less conspicuous in ISL and there is clear variation in facial expressions between the two systems [3]. In addition, the answers to questions, such as yes or no are signed by hand in ISL