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

Vertical search engines and web portals are gaining ground over the general-purpose engines due to their limited size and their high precision for the domain they cover. The number of vertical portals has rapidly increased over the last years, making the importance of a topic-driven (focused) crawler evident. In this paper, we develop a latent semantic indexing classifier that combines link analysis with text content in order to retrieve and index domain specific web documents. We compare its efficiency with other well-known web information retrieval techniques. Our implementation presents a different approach to focused crawling and aims to overcome the size limitations of the initial training data while maintaining a high recall/precision ratio.

Focused crawling using latent semantic indexing – an application for vertical search engines

The catastrophic impact of wildfires on the economy and ecosystems of Mediterranean countries in recent years, along with insufficient policies that favor disproportionally high funding for fire suppression, demand a more comprehensive understanding of fire regimes. Satellite remote sensing products support the generation of relevant burned-area (BA) information, since they provide the means for the systematic monitoring of large areas worldwide at low cost. This research study assesses the accuracy of the two publicly available MODIS BA products, MCD64A1 C6 and FireCCI51, at a national scale in a Mediterranean country. The research period covered four fire seasons, and a comparison was conducted against a higher-resolution Sentinel-2 dataset. The specific objectives were to assess their performance in detecting fire events occurring primarily in forest and semi-natural lands and to investigate their spatial and temporal uncertainties. Monthly fire observations were processed and analyzed to derive a comprehensive set of accuracy metrics. We found that fire size has an impact on their detection accuracy, with higher detection occurring in fires larger than 100 ha. Detection of smaller (<100 ha) fires was favored by the 250 m FireCCI51 product, but not from MCD64A1 C6, which exhibited less than 50% detection probability in the same range. Their spatial estimates of burned area exhibited a fairly satisfactory agreement with the reference data, reaching an average of 78% in detection rate. MCD64A1 C6 exhibited a more consistent spatial performance overall and better temporal accuracy, whereas FireCCI51 did not substantially outperform the former despite its finer resolution. Additional research is required for a more rigorous assessment of the variability of these burned area products, yet this research provides further insight and has implications for their use in fire-related applications at the local to the national scale.

https://www.mdpi.com/2072-4292/14/3/602/pdf?version=1643271213

Assessing the Accuracy of MODIS MCD64A1 C6 and FireCCI51 Burned Area Products in Mediterranean Ecosystems

This paper describes a method for the accurate and computationally efficient registration of 3-D shapes. The method is based on the iterative closest point (ICP) algorithm and improves it by dramatically decreasing the computational cost of the algorithm's most inefficient step, namely the implementation of the closest point operator. The decrease is achieved with the help of a 3-D volume containing the points to be registered. Prior to the implementation of the ICP algorithm, the Voronoi diagram of the "model" points is constructed in the volume, by means of the morphological Voronoi tesselation method with respect to the Euclidean distance metric. The use of the tesselated volume renders the calculation of the closest point operator extremely fast and speeds up the ICP algorithm tremendously.

Morphological techniques in the iterative closest point algorithm

This paper presents an accurate, computationally efficient, fast, and fully automated algorithm for the alignment of two-dimensional (2-D) serially acquired sections forming a 3-D volume. The approach relies on the determination of interslice correspondences. The features used for correspondence are extracted by a 2-D physics-based deformable model parameterizing the object shape. Correspondence affinities and global constrains render the method efficient and reliable. The method accounts for one of the major shortcomings of 2-D slices alignment of a 3-D volume, namely variable and nonuniform thickness of the slices. Moreover, no particular alignment direction is privileged, avoiding global offsets, biases, and error propagation. The method was evaluated on real images and the experimental results demonstrated its accuracy, as reconstruction errors were smaller than I degree in rotation and smaller than 1 pixel in translation.

/pdf/reconstruction-of-serially-acquired-slices-using-physics-2giqne7ie7.pdf

Reconstruction of serially acquired slices using physics-based modeling

In this paper, we propose a method for video summarization based on human activity description. We formulate this problem as the one of automatic video segment selection based on a learning process that employs salient video segment paradigms. For this one-class classification problem, we introduce a novel variant of the One-Class Support Vector Machine (OC-SVM) classifier that exploits subclass information in the OC-SVM optimization problem, in order to jointly minimize the data dispersion within each subclass and determine the optimal decision function. We evaluate the proposed approach in three Hollywood movies, where the performance of the proposed SOC-SVM algorithm is compared with that of the OC-SVM. Experimental results denote that the proposed approach is able to outperform OC-SVM-based video segment selection.

/pdf/exploiting-subclass-information-in-one-class-support-vector-4fovtqhxqx.pdf

Ioannis Pitas

Papers

Focused crawling using latent semantic indexing – an application for vertical search engines

Assessing the Accuracy of MODIS MCD64A1 C6 and FireCCI51 Burned Area Products in Mediterranean Ecosystems

Morphological techniques in the iterative closest point algorithm

Reconstruction of serially acquired slices using physics-based modeling

Exploiting subclass information in one-class support vector machine for video summarization