UNAFFECTED SERIAL PROPHECY BASED FILTER TECHNIQUE (USP-FT) FOR NOISE REMOVAL IN FACIAL EXPRESSION RECOGNITION IMAGES

Facial expression recognition is one of the key research area in the field of computer vision. Preprocessing the image is the first step while performing color facial expression images. This research work aims in design and development of unaffected serial prophecy based filter technique for noise removal in facial expression recognition images. Peak signal to noise ratio (PSNR), mean square error (MSE) and structural similarity index measure (SSIM) are the performance metrics and the proposed USP – FT is compared with MHFC [14] method and the results portrays that our method performs better.