Digital Image Computing: Techniques and Applications 

Abstract: There are many applications such as stereo matching, mo- tion tracking and image registration that require so called 'corners' to be detected across image sequences in a reliable manner. The Harris cor- ner detector is widely used for this purpose. However, the response from the Harris operator, and other corner operators, varies considerably with image contrast. This makes the setting of thresholds that are appropri- ate for extended image sequences difficult, if not impossible. This paper describes a new corner and edge detector developed from the phase con- gruency model of feature detection. The new operator uses the principal moments of the phase congruency information to determine corner and edge information. The resulting corner and edge operator is highly local- ized and has responses that are invariant to image contrast. This results in reliable feature detection under varying illumination conditions with fixed thresholds. An additional feature of the operator is that the corner map is a strict subset of the edge map. This facilitates the cooperative use of corner and edge information.

Abstract: In public venues, crowd size is a key indicator of crowd safety and stability. Crowding levels can be detected using holistic image features, however this requires a large amount of training data to capture the wide variations in crowd distribution. If a crowd counting algorithm is to be deployed across a large number of cameras, such a large and burdensome training requirement is far from ideal. In this paper we propose an approach that uses local features to count the number of people in each foreground blob segment, so that the total crowd estimate is the sum of the group sizes. This results in an approach that is scalable to crowd volumes not seen in the training data, and can be trained on a very small data set. As a local approach is used, the proposed algorithm can easily be used to estimate crowd density throughout different regions of the scene and be used in a multi-camera environment. A unique localised approach to ground truth annotation reduces the required training data is also presented, as a localised approach to crowd counting has different training requirements to a holistic one. Testing on a large pedestrian database compares the proposed technique to existing holistic techniques and demonstrates improved accuracy, and superior performance when test conditions are unseen in the training set, or a minimal training set is used.

Abstract: Mass detection from mammograms plays a crucial role as a pre- processing stage for mass segmentation and classification. The detection of masses from mammograms is considered to be a challenging problem due to their large variation in shape, size, boundary and texture and also because of their low signal to noise ratio compared to the surrounding breast tissue. In this paper, we present a novel approach for detecting masses in mammograms using a cascade of deep learning and random forest classifiers. The first stage classifier consists of a multi-scale deep belief network that selects suspicious regions to be further processed by a two-level cascade of deep convolutional neural networks. The regions that survive this deep learning analysis are then processed by a two-level cascade of random forest classifiers that use morphological and texture features extracted from regions selected along the cascade. Finally, regions that survive the cascade of random forest classifiers are combined using connected component analysis to produce state-of-the-art results. We also show that the proposed cascade of deep learning and random forest classifiers are effective in the reduction of false positive regions, while maintaining a high true positive detection rate. We tested our mass detection system on two publicly available datasets: DDSM-BCRP and INbreast. The final mass detection produced by our approach achieves the best results on these publicly available datasets with a true positive rate of 0.96 ± 0.03 at 1.2 false positive per image on INbreast and true positive rate of 0.75 at 4.8 false positive per image on DDSM-BCRP.

Abstract: Mobile Cloud Computing (MCC) which combines mobile computing and cloud computing, has become one of the industry buzz words and a major discussion thread in the IT world since 2009. As MCC is still at the early stage of development, it is necessary to grasp a thorough understanding of the technology in order to point out the direction of future research. With the latter aim, this paper presents a review on the background and principle of MCC, characteristics, recent research work, and future research trends. A brief account on the background of MCC: from mobile computing to cloud computing is presented and then followed with a discussion on characteristics and recent research work. It then analyses the features and infrastructure of mobile cloud computing. The rest of the paper analyses the challenges of mobile cloud computing, summary of some research projects related to this area, and points out promising future research directions.