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 propose a novel class of learning vector quantizers (LVQ) based on multivariate data ordering. Linear LVQ is not the optimal estimator for non-Gaussian multivariate data distributions. Furthermore, it is not robust either in the case of outliers or in the case of erroneous decisions. The novel LVQs use multivariate ordering in order to obtain location estimators that are robust and that provide superior and, in certain cases, optimal performance for non-Gaussian multivariate distributions. A special case of the novel LVQ class is the marginal median LVQ (MM LVQ), which uses the marginal median as multivariate estimator of location.

Median learning vector quantizer

The paper statistically analyzes the behaviour of a simple blind copyright protection watermarking system based on chaotic watermark signals generated by n-way Bernoulli shift maps. The analysis involves theoretic evaluation of the system detection reliability, when a correlator detector is used. The effect of simple distortions on the detection reliability is also theoretically investigated. The aim of the paper is twofold: (i) to introduce the n-way Bernoulli shift generated chaotic watermarks and theoretically contemplate their properties with respect to detection reliability and (ii) to theoretically establish their potential superiority against the widely used pseudorandom watermarks.

https://link.springer.com/content/pdf/10.1007%2F978-0-387-35413-2_7.pdf

Theoretic Performance Analysis of a Watermarking System based on Bernoulli Chaotic Sequences

When linear discriminant analysis (LDA) is employed, the correct classification of a sample heavily depends on having an adequately large training set. This is often not possible in practical applications, such as person verification, where the lack of sufficient training samples causes improper estimation of a linear separation hyper-plane between the two classes. To overcome this shortcoming a novel algorithm that can handle the verification problem more efficiently than traditional LDA is presented. The dimensionality of the samples is reduced by breaking them down, thus creating subsets of smaller dimensionality feature vectors, and applying discriminant analysis on each subset. The resulting discriminant weight sets are themselves weighted under a normalization criterion, making the discriminant functions continuous in this sense. A series of simulations that formulate the face verification problem illustrate the cases for which our method outperforms traditional LDA and various statistical observations are made about the discriminant coefficients that are generated.

/pdf/face-verification-using-locally-linear-discriminant-models-29xoldopdd.pdf

Face Verification using Locally Linear Discriminant Models

Camera-equipped Unmanned Aerial Vehicles (UAVs, or drones) have revolutionized several application domains, with a steadily increasing degree of cognitive autonomy in commercial drones paving the way for unprecedented robotization of daily life. Dynamic cooperation of UAV s with human collaborators is typically necessary during a mission; a fact that has led to various solutions for high-level UAV-operator interaction. Hand gestures are an effective way of facilitating this remote drone handling, giving rise to new gesture languages for visual communication between operators and autonomous UAV s. This paper reviews all the available languages which could be used or have been created for this purpose, as well as relevant gesture recognition datasets for training machine learning models. Moreover, a novel, generic, base gesture language for handling camera-equipped UAV s is proposed, along with a corresponding, large-scale, publicly available video dataset. The presented language can easily and consistently be extended in the future to more specific scenarios/profiles, tailored for particular application domains and/or additional UAV equipment (e.g., aerial manipulators/arms). Finally, we evaluate: a) the performance of state-of-the-art gesture recognition algorithms on the proposed dataset, in a quantitative and objective manner, and b) the intuitiveness, effectiveness and completeness of the proposed gesture language, in a qualitative and subjective manner.

An Overview of Hand Gesture Languages for Autonomous UAV Handling

In this paper, an overview of watermarking schemes based on chaotic generators and correlation detection is presented. Statistical properties of watermark sequences generated by piecewise-linear Markov maps are exploited for both additive and multiplicative watermark embedding. Correlation/spectral properties of such sequences are easily controllable, a fact that reflects on the watermarking system performance. A family of chaotic maps, namely the skew tent map family, is used in temporal and transform-domain watermarking schemes. The chaotic watermarking framework is applied successfully to audio signals, demonstrating its superiority with respect to both robustness and inaudibility.

Ioannis Pitas

Papers

Median learning vector quantizer

Theoretic Performance Analysis of a Watermarking System based on Bernoulli Chaotic Sequences

Face Verification using Locally Linear Discriminant Models

An Overview of Hand Gesture Languages for Autonomous UAV Handling

Chaoticwatermark sequences for correlation-based schemes