Dr K.T. Lo

Dr Lo has published over 180 papers in various international journals and conference proceedings. In 2007, one of his papers on digital video processing won the Most Cited Paper Award for the Journal of Visual Communication and Image Representation. In 2012, his other paper on an analysis of multimedia encryption scheme was awarded the First Prize of the Natural Science Paper Award by Xiang Tan City, Hunan Province, P.R. China. His current research interests are in the areas of multimedia content protection, image and video coding, privacy preserving image retrieval, intelligent content distribution and Internet applications.

Research highlights:

Multimedia Content Protection: Dr Lo has been working on multimedia content protection for years. He has made contribution to the area of cryptanalysis of many different multimedia encryption techniques. Based on the findings of his cryptanalysis work, a number of image encryption techniques have been developed. Recently, he has derived a content adaptive joint image compression and encryption technique. Extensive experiments and security analysis are conducted to show the good compression and encryption performance of the group’s proposed encryption scheme. Currently, Dr Lo is working on developing encryption schemes for dedicated applications areas such as encrypted domain image processing schemes and privacy preserving image retrieval systems.

Privacy Preserving Image Retrieval System: In order to preserve the privacy of the owners of images, people tend to convert the multimedia data into unrecognizable data before uploading it to the cloud so that the content of the plain images will not be exposed to others even when the server is hacked. However, this arrangement is not compliant with plain-text based conventional information retrieval techniques. The relevant research work is trying to apply machine learning techniques to derive an effective way in measuring image features in encrypted domain and developing similarity measures for different features so as to facilitate efficient image retrieval for two classes of images: one requires high compression and computational efficiency but light protection like those images shared in various social networks, and the other class emphasizes on high security level for those high sensitive images like medical and military images.