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 …

I and i

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

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.

Face recognition: A literature survey

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

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.

/pdf/detecting-faces-in-images-a-survey-4yhbbns6mr.pdf

Detecting faces in images: a survey

In this paper we investigate the potential benefits of combining, within a classification task, a discriminant linear subspace feature extraction technique, namely Discriminant Nonnegative Matrix Factorization (Discriminant NMF or DNMF), with a Support Vector Machine (SVM) classifier. The aim was to investigate whether this combination provides better classification results compared to a template matching method operating on the DNMF space or on the raw data and an SVM classifier operating on the raw data, when applied on the frontal facial pose recognition problem. The latter is a two-class problem (frontal and non-frontal facial images). DNMF is based on a supervised training procedure and works by imposing additional criteria on the NMF objective function that aim at increasing class seperability in the lower dimensionality space. Results on face images extracted from the XM2VTS dataset show that feeding the DNMF subspace data into the SVM is the approach that provides the best results.

Studying the effectiveness of using linear subspace techniques to improve SVM classifiers in facial image classification

Color-Based Video Shot Boundary Detection

This paper focuses on the application of 2D visual object tracking in Unmanned Aerial Vehicles (UAV) for the coverage of live outdoor events, by filming moving targets (e.g., athletes, boats, cars etc.). In this application scenario, a 2D target tracker visually assists the UAV pilot (or cameraman) to maintain proper target framing, or it is employed for autonomous UAV operation. It should be expected that in such scenarios, the 2D tracker may fail due to target occlusions, illumination variations, fast 3D target motion, etc., thus, the 2D tracker should be able to recover from such situations. The proposed long-term 2D tracking algorithm solves exactly this problem, by detecting occlusions from the 2D tracker responses. Moreover, according to the immensity of the occlusion, the tracker may stop updating the tracker model or try to re-detect the target in a broader frame region. Experimental results indicate that our proposed tracking algorithm outperforms state-of-the art correlation filter trackers in UAV orientated visual tracking benchmarks, as well as in realistic UAV cinematography applications.

On Detecting and Handling target occlusions in Correlation-filter-based 2D tracking

Three simple speaker verification techniques based on vector quantization, sphericity models and dynamic time warping, respectively, are developed and tested using the same experimental protocol. Two types of feature vectors, the linear prediction derived cepstral coefficients and the melfrequency cepstral coefficients are considered. The efficiency of the combination of the type of acoustic analysis and the verification technique is quantitatively measured through the achieved equal error rate.

Comparative study of speaker verification techniques based on vector quantization, sphericity models

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.

Ioannis Pitas

Papers

Studying the effectiveness of using linear subspace techniques to improve SVM classifiers in facial image classification

Color-Based Video Shot Boundary Detection

On Detecting and Handling target occlusions in Correlation-filter-based 2D tracking

Comparative study of speaker verification techniques based on vector quantization, sphericity models

Neural Networks for Digital Media Analysis and Description