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 introduce segmentation-based L-filters, that is, filtering processes combining segmentationand (nonadaptive) optimum L-filtering, and we use them for the suppression of speckle noise in ultrasonic (US)images. With the aid of a suitable modification of the Learning Vector Quantizer (LVQ) self-organizing neuralnetwork, the image is segmented in regions of approximately homogeneous first-order statistics. For each suchregion a minimum mean-squared error (MMSE) L-filter is designed on the basis of a multiplicative noise modelby using the histogram of grey values as an estimate of the parent distribution of the noisy observations and asuitable estimate of the original signal in the corresponding region. Thus, we obtain a bank of L-filters that arecorresponding to and are operating on different image regions. Simulation results on a simulated US B-mode imageof a tissue mimicking phantom are presented which verify the superiority of the proposed method as compared toa number of conventional filtering strategies in terms of a suitably defined signal-to-noise ratio (SNR) measure anddetection theoretic performance measures.

Segmentation-based L-filtering of speckle noise in ultrasonic images

A major issue that arises from mass visual media distribution in modern video sharing, social media and cloud services, is the issue of privacy. Malicious users can use these services to track the actions of certain individuals and/or groups thus violating their privacy. As a result the need to hinder automatic facial image identification in images and videos arises. In this paper we propose a method for de-identifying facial images. Contrary to most de-identification methods, this method manipulates facial images so that humans can still recognize the individual or individuals in an image or video frame, but at the same time common automatic identification algorithms fail to do so. This is achieved by projecting the facial images on a hypersphere. From the conducted experiments it can be verified that this method is effective in reducing the classification accuracy under 10%. Furthermore, in the resulting images the subject can be identified by human viewers.

/pdf/de-identifying-facial-images-using-projections-on-3mgeva11lo.pdf

De-identifying facial images using projections on hyperspheres

In this paper we propose a novel algorithm for face clustering using spectral graph clustering in order to split and merge a similarity graph. The proposed method makes use of the mutual information-based image similarity. Face clusters are formed based on spectral graph clustering in a two step process. We begin by partitioning the dataset into clusters. A novel adaptive way is proposed for spectral clustering. Then merge is performed using spectral graph clustering on the partitioned clusters, by considering merging only two clusters at a time. Experiments on various video databases containing actors' facial images are conducted. The evaluation of the face clustering provided very good results.

Face clustering in videos based on spectral clustering techniques

The Kernel k-Means algorithm for clustering extends the classic k-Means clustering algorithm. It uses the kernel trick to implicitly calculate distances on a higher dimensional space, thus overcoming the classic algorithm's inability to handle data that are not linearly separable. Given a set of n elements to cluster, the n × n kernel matrix is calculated, which contains the dot products in the higher dimensional space of every possible combination of two elements. This matrix is then referenced to calculate the distance between an element and a cluster center, as per classic k-Means. In this paper, we propose a novel algorithm for zeroing elements of the kernel matrix, thus trimming the matrix, which results in reduced memory complexity and improved clustering performance.

/pdf/kernel-matrix-trimming-for-improved-kernel-k-means-9baebcricn.pdf

Kernel matrix trimming for improved Kernel K-means clustering

Social network sites, like Facebook, Tweeter and Flickr provide users the opportunity to share their media content, such as videos, music tracks or photos. Beyond the fact that they can share information the users can also vote or comment on information posted by other users. Social networks take advantage of this activity and create groups and communities of users with similar interests. This categorization helps social network systems to support users with data, e.g. videos, photos or users profiles, that are relevant to their interests. In order to increase the effectiveness of navigation, analysis of social media content graphs needs to be done. In this paper, an analysis of the Youtube social media graph is presented. Graphs of 2D and 3D videos are considered in this analysis. Well known properties of web and social networks analysis, like the power-law distribution are discussed. Moreover, clustering methods are applied in order to study the existence of media content groups. Finally, the results of our analysis are discussed and directions of future work are presented.

/pdf/a-statistical-and-clustering-study-on-youtube-2d-and-3d-57cg7c7cdj.pdf

Ioannis Pitas

Papers

Segmentation-based L-filtering of speckle noise in ultrasonic images

De-identifying facial images using projections on hyperspheres

Face clustering in videos based on spectral clustering techniques

Kernel matrix trimming for improved Kernel K-means clustering

A statistical and clustering study on Youtube 2D and 3D video recommendation graph