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

Motion estimation is a very important topic in computer vision and image sequence compression. However, most commonly used motion estimation algorithms do not take into consideration any motion invariances that a certain local motion might possess. In this paper, a technique for estimating the invariant motion parameters of non-translational motion fields is proposed, which leads to more efficient estimation, smoothing or coding of the motion field. It is shown that the algorithm performs well, even in high noise levels, i.e., in the case of noisy output of the motion estimator.

Parameter estimation of non-translational motion fields

Event detection is a very important task in geophysics. It encompasses the detection of wave sources (earthquakes, subsurface explosions) and the detection of wave reflectors (interfaces between rock layers having different velocities and/or different densities). The latter application is very important in seismic oil prospecting. Seismic events release energy which propagates toward the earth surface as waves which are recorded by arrays of sensors. The data recorded are usually corrupted by noise, which sometimes is much stronger than the weak events. The aim of this paper is to couple wave theory and detection theory to detect seismic events in an optimal way. A statistical model of the earth is proposed. This model combined with the wave equation describes sufficiently well the wave propagation in the stratified earth. Optimal and suboptimal receivers for event detection, based on this earth model, are proposed. The validity of our approach is demonstrated by simulation examples.

Detection of wave reflectors and wave sources in the earth subsurface

Optimal image mosaicing has large computational complexity, that becomes prohibitive as the number of sub-images increases. Two methods are proposed, which require less computation time by performing mosaicing in pairs of two sub-images at a time, without significant reconstruction losses, as evidenced by simulation results.

/pdf/computationally-efficient-image-mosaicing-using-spanning-mw2oue4ia8.pdf

Computationally efficient image mosaicing using spanning tree representations

Recent technical and jurisdictional advances, together with the availability of low-cost platforms, have facilitated the implementation of unmanned aerial vehicles (UAVs) in individual tree detection (ITD) applications. UAV-based photogrammetry or structure from motion is an example of such a low-cost technique, but requires detailed pre-flight planning in order to generate the desired 3D-products needed for ITD. In this study, we aimed to find the most optimal flight parameters (flight altitude and image overlap) and processing options (smoothing window size) for the detection of taxus trees in Belgium. Next, we tested the transferability of the developed marker-controlled segmentation algorithm by applying it to the delineation of olive trees in an orchard in Greece. We found that the processing parameters had a larger effect on the accuracy and precision of ITD than the flight parameters. In particular, a smoothing window of 3 × 3 pixels performed best (F-scores of 0.99) compared to no smoothing (F-scores between 0.88 and 0.90) or a window size of 5 (F-scores between 0.90 and 0.94). Furthermore, the results show that model transferability can still be a bottleneck as it does not capture management induced characteristics such as the typical crown shape of olive trees (F-scores between 0.55 and 0.61).

/pdf/effects-of-flight-and-smoothing-parameters-on-the-detection-2be9ysz5.pdf

Effects of Flight and Smoothing Parameters on the Detection of Taxus and Olive Trees with UAV-Borne Imagery

A novel method is introduced for label propagation on similarity tensors. The proposed method operates on data with multiple representations. A higher order similarity matrix is constructed for describing the relationship between the data representations in different modalities. Then, label propagation is performed on the above mentioned similarity matrix, by extending the state of the art label propagation method with local and global consistency to the case of higher order similarity graphs. The evaluation of the proposed method was performed on two classification tasks: person recognition on facial images extracted from three stereo movies and human action recognition on two data sets consisting of videos downloaded from YouTube. Experimental results showed that the proposed label propagation approach achieves either competitive or better classification accuracy from the state of the art in all classification tasks.

Ioannis Pitas

Papers

Parameter estimation of non-translational motion fields

Detection of wave reflectors and wave sources in the earth subsurface

Computationally efficient image mosaicing using spanning tree representations

Effects of Flight and Smoothing Parameters on the Detection of Taxus and Olive Trees with UAV-Borne Imagery

Multi-modal label propagation based on a higher order similarity matrix