Computational intelligence techniques for hand gesture recognition

• Main Authors: Bilal, Sara Mohammed Osman Saleh, Akmeliawati, Rini
• Format: Book Chapter
• Language: English
• Published: IIUM Press 2011
• Subjects: TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
• Online Access: http://irep.iium.edu.my/21637/1/Chapter_10.pdf; http://irep.iium.edu.my/21637/; http://rms.research.iium.edu.my/bookstore/default.aspx

Hand gesture is an approach that ha~ gained much anenlion for real-time HUrTIlln 10 Computer llIleraction (1ICI) applications. In lhis chapter, we pro,-ide a survey on Computational Inlelligence Tedmiq""s (CID fot hand g~lIIre recognition for HCI applications in general and Hidden Markov Mood (HMM) in paruculat. Many tnlditional metlKxls exist in thc field of pallcm recognilion lO achieve hand POSlUre and geSlure rco:ognilion [I. 2] slJCh as artificial inlelligence lechniques and statislical algorithms. However OIher lypeS of self developed algorilhms also exisl. and an: often referre<lto as OOll-lIadiliona! algorilhrn.~. For mOle delails on bolh approaches used for "isual human aClion recognilion. readers can refcr to the slUdy by MiChael el al. in [3]. Artificial Neu...l Nelwork's (ANN) ability in finding palterns and versalilily in lraining makes il popular learning melhod in geSlure recognilion. ANN and its variation such as have be<:n used for SL geslure recognition in any forms as in [4]_ Two noticed research work for gesltlre recognilion using ANN where 3D Hopfield NN [5] and Time-Delay NN (TDNN) has been developed by [6]. Recently, A!'IIN has been less used in the: field of gestu<e recognition because of ilS greater computational burrlcn. susceptibilily to training data over·fining and the huge number database il requin:s.