Guest Editorial

Multimedia research has quite matured in the last couple of decades by contributing in almost every aspect of our life. Recent proliferation of audiovisual capturing devices is mostly due to the success of multimedia signal processing research that led to captivating technologies with applications ranging from image/audio/video signal processing to speech recognition and synthesis to multimedia communications to video surveillance and action recognition. Besides improving traditional image and audiovisual techniques, multimedia researchers are now increasingly focused on their innovative applications in other disciplines and this Special Issue of Journal of Multimedia is an excellent example to testify this. This Special Issue presents selected papers from the thirteenth conference of the series (ICCIT 2010) held during December 23-25, 2010 at Ahsanullah University of Science and Technology, Dhaka, Bangladesh. The first one was held in Dhaka, Bangladesh, in 1998. Since then the conference has grown to one of the largest computer and IT related research conferences in the South Asian region, with participation of academics and researchers from many countries around the world. Starting in 2008 the proceedings of ICCIT are included in IEEExplore. In 2010, a total of 410 full papers were submitted to the conference of which 136 were accepted after reviews conducted by an international program committee comprising 81 members from 16 countries with assistance from 83 reviewers. This was tantamount to an acceptance rate of 33%. From these 136 papers only nine highly ranked papers were invited for this Special Issue. The authors were invited to enhance their papers significantly and submit the same for review. Of those only four papers survived the review process and have been selected for inclusion in this Special Issue. These papers—covering four prominent domains namely, speech recognition, face recognition, machine vision, and video coding—truly represent the highly diversified nature of multimedia research. The first paper “Inhibition/Enhancement Network Based ASR using Multiple DPF Extractors” by F. Hassan, M. R. A. Kotwal, M. M. Hasan, G. Muhammad, and M. N. Huda investigates the effectiveness of Inhibition/Enhancement (In/En) networks for robust automatic speech recognition. Experimental results on Japanese speech database have shown that In/En networks not only improve phoneme recognition but also reduces mixture components in Hidden Markov Models. The next paper “Performance of PCA Based Semi-supervised Learning in Face Recognition Using MPEG-7 Edge Hi