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

Robust Spatial 3D Image Watermarking

In this paper, we investigate the effectiveness of the Extreme Learning Machine (ELM) network in facial image classification. In order to enhance performance, we exploit knowledge related to the human face structure. We train a multi-view ELM network by employing automatically created facial regions of interest to this end. By jointly learning the network parameters and optimized network output combination weights, each facial region appropriately contributes to the final classification result. Experimental results on three publicly available databases show that the proposed approach outperforms facial image classification based on a single facial representation and on other facial region combination schemes.

Enhancing ELM-based Facial Image Classification by Exploiting Multiple Facial Views

This paper introduces the discrete modal transform (DMT), a 1D and 2D discrete, non-separable transform for signal processing, which, in the mathematical sense, is a generalization of the well-known discrete cosine transform (DCT). A 3D deformable surface model is used to represent the image intensity and the introduced discrete transform is a by-product of the explicit surface deformation governing equations. The properties of the proposed transform are similar to those of the DCT. To illustrate these properties, the proposed transform is applied to lossy image compression and the obtained results are compared to those of a DCT-based compression scheme. Experimental results show that DMT, which includes an embedded compression ratio selection mechanism, has excellent energy compaction properties and achieves comparable compression results to DCT at low compression ratios, while being in general better than DCT at high compression ratios.

The discrete modal transform and its application to lossy image compression

Ex-vivo evaluation of the detectability of vertical root fractures (VRFs) using digital subtraction radiography (DSR) and conventional digital periapical radiography (CDPR); investigation of the effect of root canal filling, x-ray angulation, and thickness of the VRF in the diagnostic accuracy. Sixty root canals were mechanically prepared and radiographed either with a gutta-percha root canal filling or without, at 0o and ± 10o. VRFs were introduced with a universal testing machine. The width and angulation of the fracture line with the radiographic beam were calculated. DSR was performed comparing radiographs obtained prior to and after the VRF induction. Five examiners evaluated the resultant images and analysis was performed using receiver operator characteristic (ROC) statistics and binary logistic regression tests. No significant differences in sensitivity, specificity, and the areas under the ROC curves (AUC) between the CDPR and DSR were detected (p > 0.05), except for root canal filled teeth where the AUC for DSR was higher (p < 0.05). Using DSR, a VRF was 1.3 times more likely to be diagnosed [95% confidence intervals (CI): 1.045–1.59; p = 0.018]. A correct diagnosis was 2.399 times more likely to occur in non-filled teeth regardless of the radiographic technique (95% CI 1.940–2.965; p = 0). The regression coefficients were positive for width and negative for angle. DSR showed a better diagnostic accuracy of VRFs compared with CDPR, in single root canal filled teeth. The angulation, the width, and the presence of a root canal filling affected the diagnostic potential. DSR is a cost- and time-effective imaging technique that could contribute in early diagnosis of VRFs.

Digital subtraction radiography in detection of vertical root fractures: accuracy evaluation for root canal filling, fracture orientation and width variables. An ex-vivo study

The segmentation of ultrasonic images using self-organizing neural networks (NN) is investigated. A modification of learning vector quantizer (called L/sub 2/ LVQ) is proposed so that the weight vectors of the output neurons correspond to the L/sub 2/ mean instead of the sample arithmetic mean of the input observations. The convergence in the mean and in the mean square of the proposed variant of LVQ is studied. Experimental results show that L/sub 2/ LVQ outperforms other segmentation techniques that employ thresholding a filtered ultrasonic image with respect to the probability of detection for the same probability of false alarm in all cases. >

Ioannis Pitas

Papers

Robust Spatial 3D Image Watermarking

Enhancing ELM-based Facial Image Classification by Exploiting Multiple Facial Views

The discrete modal transform and its application to lossy image compression

Digital subtraction radiography in detection of vertical root fractures: accuracy evaluation for root canal filling, fracture orientation and width variables. An ex-vivo study

A variant of learning vector quantizer based on the L/sub 2/ mean for segmentation of ultrasonic images