Skin detection is used in applications ranging from face detection, tracking body parts and hand gesture analysis, to retrieval and blocking objectionable content. In this paper, we investigate and evaluate (1) the effect of color space transformation on skin detection performance and finding the appropriate color space for skin detection, (2) the role of the illuminance component of a color space, (3) the appropriate pixel based skin color modeling technique and finally, (4) the effect of color constancy algorithms on color based skin classification. The comprehensive color space and skin color modeling evaluation will help in the selection of the best combinations for skin detection. Nine skin modeling approaches (AdaBoost, Bayesian network, J48, Multilayer Perceptron, Naive Bayesian, Random Forest, RBF network, SVM and the histogram approach of Jones and Rehg [15]) in six color spaces (IHLS, HSI, RGB, normalized RGB, YCbCr and CIELAB) with the presence or absence of the illuminance component are compared and evaluated. Moreover, the impact of five color constancy algorithms on skin detection is reported. Results on a database of 8991 images with manually annotated pixel-level ground truth show that (1) the cylindrical color spaces outperform other color spaces, (2) the absence of the illuminance component decreases performance, (3) the selection of an appropriate skin color modeling approach is important and that the tree based classifiers (Random forest, J48) are well suited to pixel based skin detection. As a best combination, the Random Forest combined with the cylindrical color spaces, while keeping the illumi- nance component outperforms other combinations, and (4) the usage of color constancy algorithms can improve skin detection performance.

Interest point detection is an important research area in the field of image processing and computer vision. In particular, image retrieval and object categorization heavily rely on interest point detection from which local image descriptors are computed for image matching. In general, interest points are based on luminance, and color has been largely ignored. However, the use of color increases the distinctiveness of interest points. The use of color may therefore provide selective search reducing the total number of interest points used for image matching.

No abstract

We detect and arrange events in private photo archives by putting these photos into context. The problem is seen as a fully automated mining in one's personal life and behavior. To this end, we build a contextual meaningful hierarchy of events based on personal photos. With the analysis of very simple cues of time, space and perceptual visual appearance we are refining and validating the event borders and their relation in an iterative way. Beginning with discriminating between routine and unusual events, we are able to robustly recognize the basic nature of an event. Further combination of the given cues efficiently gives a hierarchy of events that coincides with the given ground-truth at an F-measure of 0.83 for event detection and 0.70 for its hierarchical representation. We process the given task in a fully unsupervised and computationally inexpensive manner. Using standard clustering and machine learning techniques, sparse events in the collection would tend to be neglected by automated approaches. Opposed to these methods, the proposed approach is invariant to the distribution of the photo collection regarding the sparsity and denseness in time, space and visual appearance. This is improved by introducing a momentum of attraction measure for a meaningful representation of personal events.