Ioannis Pitas

Bio: Ioannis Pitas is an academic researcher from Aristotle University of Thessaloniki. The author has contributed to research in topics: Facial recognition system & Digital watermarking. The author has an hindex of 76, co-authored 795 publications receiving 24787 citations. Previous affiliations of Ioannis Pitas include University of Bristol & University of York.

Neural Networks for Digital Media Analysis and Description

Abstract: In this paper a short overview on recent research efforts for digital media analysis and description using neural networks is given. Neural networks are very powerful in analyzing, representing and classifying digital media content through various architectures and learning algorithms. Both unsupervised and supervised algorithms can be used for digital media feature extraction. Digital media representation can be done either in a synaptic level or at the output level. The specific problem that is used as a case study for digital media analysis is the human-centered video analysis for activity and identity recognition. Several neural network topologies, such as self organizing maps, independent subspace analysis, multi-layer perceptrons, extreme learning machines and deep learning architectures are presented and results on human activity recognition are reported.

Monocular Weakly-Supervised Camera-Relative 3D Human Pose Estimation

Abstract: This paper presents a 3D human pose estimation framework based on Deep Neural Networks (DNNs). It builds upon existing weakly-supervised methods that predict 2D-3D correspondences and improves them by introducing a geometrical-alignment pre-processing step and a 3D skeleton-refinement post-processing step. The geometrical-alignment pre-processing step is applied on the ground-truth 3D human poses and transforms them, in order to enable the utilized 2D-to-3D skeleton mapping DNN to be efficiently trained in a weakly-supervised manner. The 3D skeleton-refinement post-processing step acts on the DNN outputs and enables the proposed 3D human pose estimation framework to predict the camera-relative 3D human poses. Experiments on the widely used public showed that the proposed framework managed to predict camera-relative 3D human poses with increased accuracy.

Incremental Label Propagation on Facial Images

Abstract: The increasing computational complexity of label propagation-based facial image annotation when applied on multimedia data whose cardinality increases over the time (e.g., when analyzing video or movie content on-line), can be reduced by using an incremental approach. In this paper, a method for incremental label propagation on facial images is described. The similarity matrix is incrementally constructed by employing the kd-tree nearest neighbor algorithm. Furthermore, the matrix inversion, which is included in the label propagation solution, is calculated with a block-wise inversion formula involving the Woodbury matrix identity. Experiments show significant computational savings when the incremental approach is applied on a dataset of three full length movies. Moreover, the classification accuracy was improved in most cases.

Fast Free-Vibration Modal Analysis of 2-D

Abstract: This paper presents an accurate, very fast approach for the deformations of two-dimensional physically based shape models representing open and closed curves. The introduced models are much faster than other deformable models (e.g., fi- nite-element methods). The approach relies on the determination of explicit deformation governing equations that involve neither eigenvalue decomposition, nor any other computationally intensive numerical operation. The approach was evaluated and compared with another fast and accurate physics-based deformable shape model, both in terms of deformation accuracy and computation time. The conclusion is that the introduced model is completely accurate and is deformed very fast on current personal computers (Pentium III), achieving more than 380 contour deformations per second.

Tracing on heterogeneous grids to improve the concavity performance of snake algorithms

Abstract: Existing contour tracing algorithms operate on binary images at pixel level to traverse the boundary of an object. However, if the original grayscale image has obscure edge transitions, it can be very challenging to extract binary objects properly for pixelwise tracing. A more reliable approach can be to consider a rough approximation of the objects and perform tracing on that, followed by a final adjustment. We can use e.g. the quadtree representation which belongs to the family of heterogeneous grid representations. In this paper, we show how a contour tracing algorithm operating at pixel level can be extended to a heterogeneous grid representation. The robustness of our method is demonstrated in snake algorithms to improve their concavity performance.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Face recognition: A literature survey

Abstract: As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially during the past several years. At least two reasons account for this trend: the first is the wide range of commercial and law enforcement applications, and the second is the availability of feasible technologies after 30 years of research. Even though current machine recognition systems have reached a certain level of maturity, their success is limited by the conditions imposed by many real applications. For example, recognition of face images acquired in an outdoor environment with changes in illumination and/or pose remains a largely unsolved problem. In other words, current systems are still far away from the capability of the human perception system.This paper provides an up-to-date critical survey of still- and video-based face recognition research. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. To provide a comprehensive survey, we not only categorize existing recognition techniques but also present detailed descriptions of representative methods within each category. In addition, relevant topics such as psychophysical studies, system evaluation, and issues of illumination and pose variation are covered.

Detecting faces in images: a survey

Abstract: Images containing faces are essential to intelligent vision-based human-computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face, regardless of its 3D position, orientation and lighting conditions. Such a problem is challenging because faces are non-rigid and have a high degree of variability in size, shape, color and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future research.