title,doi,url,abstract,journal,publication_year,pmid,arxiv
Facial Expressions Detection and Recognition Using Neural Networks, https://doi.org/10.32628/IJSRCSEIT, https://ijsrcseit.com/CSEIT174425, Facial Expressions are one of the most robust way of non verbal information exchange in day-to-day life. Changes occurring in emotions of a human being directly efficate the behavior of a person. In this progressive world a numerous biometric have been evolved each having its own purport. However all these statistics play vital job to convey communication from one individual to another but 55% i.e a major part of communication transpire by facial expressions. Facial Expression recognition process concentrates on discerning the changes in expressions of facial muscles that automatically reflect switching of one’s mind from one state to another. Humans can recognize Expressions without any effort and almost instantaneously but that are not the case with a machine since its challenges are very dynamic like orientation lightening pose facial expressions etc.
So the process of wrenching out or extricating the facial feature points or landmarks is often very challenging. To recognize the fiducial points on the facial features and drawing out these points that generally lie on eyes corners chin eyebrows etc facial landmarking is done. Our landmarking technique combines Viola-Jones detection algorithm for feature detection with Harris corner detection and then coarse to fine strategy is implemented using an efficient algorithm. Using the Haar like features reduces the cost of brute force search also provides advantage of speed. Additional selection of sub-regions is also exploited using anthropometric constraints to limit the search region. This further reduces false detection rate and improves accuracy significantly. A sub- algorithm named Iterative best fit algorithm is used find a land mark exploiting its commonality and geometric configuration and can be used in other contexts as well. This method is then tested on JAFEE database Yale database AT&T database and the database constructed using my own images named as Smart database and this method provides the satisfactory accuracy.
, International Journal of Scientific Research in Computer Science Engineering and Information Technology, 2017, CSEIT174425