Elena Sikudova

Color-based descriptors for image fingerprinting

Typically, content-based image retrieval (CBIR) systems receive an image or an image description as input and retrieve images from a database that are similar to the query image in regard to properties such as color, texture, shape, or layout. A kind of system that did not receive much attention compared to CBIR systems, is one that searches for images that are not similar but exact copies of the same image that have undergone some transformation. In this paper, we present such a system referred to as an image fingerprinting system, since it aims to extract unique and robust image descriptors (in analogy to human fingerprints). We examine the use of color-based descriptors and provide comparisons for different quantization methods, histograms calculated using color-only and/or spatial-color information with different similarity measures. The system was evaluated with receiver operating characteristic (ROC) analysis on a large database of 919 original images consisting of randomly drawn art images and similar images from specific categories, along with 30 transformed images for each original, totaling 27570 images. The transformed images were produced with attacks that typically occur during digital image distribution, including different degrees of scaling, rotation, cropping, smoothing, additive noise and compression, as well as illumination contrast changes. Results showed a sensitivity of 96% at the small false positive fraction of 4% and a reduced sensitivity of 88% when 13% of all transformations involved changing the illuminance of the images. The overall performance of the system is encouraging for the use of color, and particularly spatial chromatic descriptors for image fingerprinting

Dynamic range compression by differential zone mapping based on psychophysical experiments

In this paper we present a new technique for the display of High Dynamic Range (HDR) images on Low Dynamic Range (LDR) displays. The described process has three stages. First, the input image is segmented into luminance zones. Second, the tone mapping operator (TMO) that performs better in each zone is automatically selected. Finally, the resulting tone mapping (TM) outputs for each zone are merged, generating the final LDR output image. To establish the TMO that performs better in each luminance zone we conducted a preliminary psychophysical experiment using a set of HDR images and six different TMOs. We validated our composite technique on several (new) HDR images and conducted a further psychophysical experiment, using an HDR display as reference, that establishes the advantages of our hybrid three-stage approach over a traditional individual TMO.

Investigation of the beat rate effect on frame rate for animated content

Knowledge of the Human Visual System (HVS) may be exploited in computer graphics to significantly reduce rendering times without the viewer being aware of any resultant image quality difference. Furthermore, cross-modal effects, that is the influence of one sensory input on another, for example sound and visuals, have also recently been shown to have a substantial impact on viewer perception of image quality. In this paper we investigate the relationship between audio beat rate and video frame rate in order to manipulate temporal visual perception. This represents an initial step towards establishing a comprehensive understanding for the audio-visual integration in multisensory environments.

EXTRACTING SEMANTIC INFORMATION FROM ART IMAGES

This paper presents a method for automatic annotation of portraits in art image databases and discusses the extraction of semantic information from portraits. The proposed method segments images into candidate regions and fits an ellipse and a bounding box to them. Their extracted features serve as input to a neural network, which is trained to distinguish between face and non-face regions. Paintings containing face regions are classified as portraits. The method evaluation is done on a set of 188 digital paintings using ROC curves as performance measures. The results show that the method is very efficient in locating the face regions and in the recognition of portrait paintings. The performance of the algorithm is encouraging for its further development, which includes the extraction of portrait-specific semantic information.

Perceptually guided high-fidelity rendering exploiting movement bias in visual attention

A major obstacle for real-time rendering of high-fidelity graphics is computational complexity. A key point to consider in the pursuit of “realism in real time” in computer graphics is that the Human Visual System (HVS) is a fundamental part of the rendering pipeline. The human eye is only capable of sensing image detail in a 2ˆ foveal region, relying on rapid eye movements, or saccades, to jump between points of interest. These points of interest are prioritized based on the saliency of the objects in the scene or the task the user is performing. Such “glimpses” of a scene are then assembled by the HVS into a coherent, but inevitably imperfect, visual perception of the environment. In this process, much detail, that the HVS deems unimportant, may literally go unnoticed. Visual science research has identified that movement in the background of a scene may substantially influence how subjects perceive foreground objects. Furthermore, recent computer graphics work has shown that both fixed viewpoint and dynamic scenes can be selectively rendered without any perceptual loss of quality, in a significantly reduced time, by exploiting knowledge of any high-saliency movement that may be present. A high-saliency movement can be generated in a scene if an otherwise static objects starts moving. In this article, we investigate, through psychophysical experiments, including eye-tracking, the perception of rendering quality in dynamic complex scenes based on the introduction of a moving object in a scene. Two types of object movement are investigated: (i) rotation in place and (ii) rotation combined with translation. These were chosen as the simplest movement types. Future studies may include movement with varied acceleration. The objects geometry and location in the scene are not salient. We then use this information to guide our high-fidelity selective renderer to produce perceptually high-quality images at significantly reduced computation times. We also show how these results can have important implications for virtual environment and computer games applications.

A Gamut-Mapping Framework for Color-Accurate Reproduction of HDR Images.

An integrated gamut- and tone-management framework for color-accurate reproduction of high dynamic range images can prevent hue and luminance shifts while taking gamut boundaries into consideration. The proposed approach is conceptually and computationally simple, parameter-free, and compatible with existing tone-mapping operators.

Comparison of color spaces for face detection in digitized paintings

In our paper we investigate the annotation of digitized paintings. We use single Gaussian distribution model to classify image areas as skin colored. After detecting the skin colored regions, the geometrical information about each region is used to verify the face. Then we focus on the comparison of the fitness of chosen color spaces in skin pixel detection. We use three methods of region classification a feed forward neural network (NN), linear discriminant analysis (LDA) and learning vector quantization (LVQ). At the end we briefly discuss the results achieved.

Multiple Instances Detection in RGBD Images

Object instances detection and registration is the area closely connected to augmented reality. Only correctly detected and registered real world object can be used to register the real and virtual world for the purpose of displaying the augmented information. Although detection and registration methods are well studied, little attention is paid to the situation where multiple instances of objects are present in the scene and need to be augmented (e.g. a table full of fliers, several exemplars of historical coins in the museum, etc.). In this paper we propose a new method for multiple instances of object detection in cluttered scenes using local features and Hough-based voting.

Combination of Global and Local Features for Efficient Classification of Paintings

Since the beginning of the new century an increasing amount of smartphones sold every year causes a strong interest in the interactive mobile guides (travel, museum guides) utilizing the visual recognition of interesting objects. In our paper we focus on a special class of objects -- fine art paintings. We introduce new pipeline of visual recognition employing both local and global image features. In the recognition process we firstly sort the database of Originals, the high quality paintings based on the global feature extracted from the photograph of a painting and then match the local feature descriptors for efficient recognition. Our approach achieves the speed up of the recognition process by minimizing the number local feature comparisons.

Schola ludus, serious games, and measurement of interestingness

We propose a novel engagement measurement (establihed originally in virtual museum theory) for serious games. The key idea is to measure the user input in terms of time spent. The output is given by the recorded user behavior. We discuss the implications for edutainment, e-learning, and serious games.