Dictionary Learning in Visual Computing

The last few years have witnessed fast development on dictionary learning approaches for a set of visual computing tasks, largely due to their utilization in developing new techniques based on sparse representation. Compared with conventional techniques employing manually defined dictionaries, such as Fourier Transform and Wavelet Transform, dictionary learning aims at obtaining a dictionary adaptively from the data so as to support optimal sparse representation of the data. In contrast to conventional clustering algorithms like K-means, where a data point is associated with only one cluster center, in a dictionary-based representation, a data point can be associated with a small set of dictionary atoms. Thus, dictionary learning provides a more flexible representation of data and may have the potential to capture more relevant features from the original feature space of the data. One of the early algorithms for dictionary learning is K-SVD. In recent years, many variations/extensionsof K-SVD and other new algorithms have been proposed, with some aiming at adding discriminative capability to the dictionary, and some attempting to model the relationship of multiple dictionaries. One prominent application of dictionary learning is in the general field of visual computing, where long-standing challenges have seen promising new solutions based on sparse representation with learned dictionaries. With a timely review of recent advances of dictionary learning in visual computing, covering the most recent literature with an emphasis on papers after 2008, this book provides a systematic presentation of the general methodologies, specific algorithms, and examples of applications for those who wish to have a quick start on this subject.

Acknowledgments.- Figure Credits.- Introduction.- Fundamental Computing Tasks in Sparse Representation.- Dictionary Learning Algorithms.- Applications of Dictionary Learning in Visual Computing.- An Instructive Case Study with Face Recognition.- Bibliography.- Authors' Biographies .

Qiang Zhang received his B.S. degree in electronic information and technology from Beijing Normal University, Beijing, China in 2009 and his Ph.D. degree in Computer Science from Arizona State University, Tempe, Arizona in 2014. Since 2014, he has been with Samsung, Pasadena, CA as a staff research scientist in computer vision and machine learning. His research interests include image/video processing, computer vision and machine vision, specialized in sparse learning, face recognition, and motion analysis.Baoxin Li received his Ph.D. in electrical engineering from the University of Maryland, College Park, in 2000. He is currently a professor of computer science and engineering and a graduate faculty in computer science, electrical engineering and computer engineering programs at Arizona State University, Tempe. From 2000 to 2004, he was a Senior Researcher with SHARP Laboratories of America, Camas, Washington, where he was a technical lead in developing SHARPs HiMPACT Sports technologies. From 2003-2004, he was also an Adjunct Professor with the Portland State University, Oregon. He holds sixteen issued U.S. patents and his current research interests include computer vision and pattern recognition, multimedia, social computing, machine learning, and assistive technologies. He won twice the SHARP Laboratories President Award, in 2001 and 2004 respectively. He also won the SHARP Laboratories Inventor of the Year Award in 2002. He was a recipient of the National Science Foundations CAREER Award.