Information Processing and Pattern Recognition

The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled with a wide variability of scale, pose, illumination, and expressions, and also may be partially occluded. We develop a recognition method based on a cascade of processing steps that normalize for the effects of the changing imaging environment. In particular there are three areas of novelty: (i) we suppress the background surrounding the face, enabling the maximum area of the face to be retained for recognition rather than a subset; (ii) we include a pose refinement step to optimize the registration between the test image and face exemplar; and (iii) we use robust distance to a sub-space to allow for partial occlusion and expression change. The method is applied and evaluated on several feature length films. It is demonstrated that high recall rates (over 92%) can be achieved whilst maintaining good precision (over 93%).

Users are still waiting for accurate optical character recognition solutions for Arabic handwritten scripts. This research explores best sets of feature extraction techniques and studies the accuracy of well-known classifiers for Arabic letters. Depending on their position in the word, Arabic letters are drawn in four forms: Isolated, Initial, Medial, and Final. The principal component analysis technique is used to select best subset of features out of a large number of extracted features. We used parametric and non-parametric classifiers and found out that a subset of 25 features is needed to get 84% recognition accuracy using a linear discriminant classifier, and using more features does not substantially improve this accuracy. However, for features fewer than 25 features, a quadratic discriminant classifier is more accurate than the linear classifier. Classifiers that are parameterized for the individual four forms score better accuracy than classifiers that do not make use of this input information.

This paper addresses the problem of tracking moving objects of variable appearance in challenging scenes rich with features and texture. Reliable tracking is of pivotal importance in surveillance applications. It is made particularly difficult by the nature of objects encountered in such scenes: these too change in appearance and scale, and are often articulated (e.g. humans). We propose a method which uses fast motion detection and segmentation as a constraint for both building appearance models and their robust propagation (matching) in time. The appearance model is based on sets of local appearances automatically clustered using spatio-kinetic similarity, and is updated with each new appearance seen. This integration of all seen appearances of a tracked object makes it extremely resilient to errors caused by occlusion and the lack of permanence of due to low data quality, appearance change or background clutter. These theoretical strengths of our algorithm are empirically demonstrated on two hour long video footage of a busy city marketplace.

In this paper we consider face recognition from sets of face images and, in particular, recognition invariance to illumination. The main contribution is an algorithm based on the novel concept of Maximally Probable Mutual Modes (MMPM). Specifically: (i) we discuss and derive a local manifold illumination invariant and (ii) show how the invariant naturally leads to a formulation of "common modes" of two face appearance distributions. Recognition is then performed by finding the most probable mode, which is shown to be an eigenvalue problem. The effectiveness of the proposed method is demonstrated empirically on a challenging database containing the total of 700 video sequences of 100 individuals.

In this paper we address the problem of matching sets of vectors embedded in the same input space. We propose an approach which is motivated by canonical correlation analysis (CCA), a statistical technique which has proven successful in a wide variety of pattern recognition problems. Like CCA when applied to the matching of sets, our extended canonical correlation analysis (E-CCA) aims to extract the most similar modes of variability within two sets. Our first major contribution is the formulation of a principled framework for robust inference of such modes from data in the presence of uncertainty associated with noise and sampling randomness. E-CCA retains the efficiency and closed form computability of CCA, but unlike it, does not possess free parameters which cannot be inferred directly from data (inherent data dimensionality, and the number of canonical correlations used for set similarity computation). Our second major contribution is to show that in contrast to CCA, E-CCA is readily adapted to match sets in a discriminative learning scheme which we call discriminative extended canonical correlation analysis (DE-CCA). Theoretical contributions of this paper are followed by an empirical evaluation of its premises on the task of face recognition from sets of rasterized appearance images. The results demonstrate that our approach, E-CCA, already outperforms both CCA and its quasi-discriminative counterpart constrained CCA (C-CCA), for all values of their free parameters. An even greater improvement is achieved with the discriminative variant, DE-CCA.

Our aim in this paper is to robustly match frontal faces in the presence of extreme illumination changes, using only a single training image per person and a single probe image. In the illumination conditions we consider, which include those with the dominant light source placed behind and to the side of the user, directly above and pointing downwards or indeed below and pointing upwards, this is a most challenging problem. The presence of sharp cast shadows, large poorly illuminated regions of the face, quantum and quantization noise and other nuisance effects, makes it difficult to extract a sufficiently discriminative yet robust representation. We introduce a representation which is based on image gradient directions near robust edges which correspond to characteristic facial features. Robust edges are extracted using a cascade of processing steps, each of which seeks to harness further discriminative information or normalize for a particular source of extra-personal appearance variability. The proposed representation was evaluated on the extremely difficult YaleB data set. Unlike most of the previous work we include all available illuminations, perform training using a single image per person and match these also to a single probe image. In this challenging evaluation setup, the proposed gradient edge map achieved 0.8% error rate, demonstrating a nearly perfect receiver-operator characteristic curve behaviour. This is by far the best performance achieved in this setup reported in the literature, the best performing methods previously proposed attaining error rates of approximately 6-7%.

Linear subspace representations of appearance variation are pervasive in computer vision. In this paper we address the problem of robustly matching them (computing the similarity between them) when they correspond to sets of images of different (possibly greatly so) scales. We show that the naïve solution of projecting the low-scale subspace into the high-scale image space is inadequate, especially at large scale discrepancies. A successful approach is proposed instead. It consists of (i) an interpolated projection of the low-scale subspace into the high-scale space, which is followed by (ii) a rotation of this initial estimate within the bounds of the imposed “downsampling constraint”. The optimal rotation is found in the closed-form which best aligns the high-scale reconstruction of the low-scale subspace with the reference it is compared to. The proposed method is evaluated on the problem of matching sets of face appearances under varying illumination. In comparison to the naïve matching, our algorithm is shown to greatly increase the separation of between-class and within-class similarities, as well as produce far more meaningful modes of common appearance on which the match score is based.

Over the course of the last decade, infrared (IR) and particularly thermal IR imaging based face recognition has emerged as a promising complement to conventional, visible spectrum based approaches which continue to struggle when applied in the real world. While inherently insensitive to visible spectrum illumination changes, IR images introduce specific challenges of their own, most notably sensitivity to factors which affect facial heat emission patterns, e.g.\ emotional state, ambient temperature, and alcohol intake. In addition, facial expression and pose changes are more difficult to correct in IR images because they are less rich in high frequency detail which is an important cue for fitting any deformable model. In this paper we describe a novel method which addresses these major challenges. Specifically, to normalize for pose and facial expression changes we generate a synthetic frontal image of a face in a canonical, neutral facial expression from an image of the face in an arbitrary pose and facial expression. This is achieved by piecewise affine warping which follows active appearance model (AAM) fitting. This is the first publication which explores the use of an AAM on thermal IR images; we propose a pre-processing step which enhances detail in thermal images, making AAM convergence faster and more accurate. To overcome the problem of thermal IR image sensitivity to the exact pattern of facial temperature emissions we describe a representation based on reliable anatomical features. In contrast to previous approaches, our representation is not binary; rather, our method accounts for the reliability of the extracted features. This makes the proposed representation much more robust both to pose and scale changes. The effectiveness of the proposed approach is demonstrated on the largest public database of thermal IR images of faces on which it achieved 100% identification rate, significantly outperforming previously described methods.

Shape matching and point correspondence recovering play a fundamental role in applications like pattern and object recognition, shape classification, image alignment and registration, visual information data mining, and many other computer vision related areas, which recently became active research disciplines due to the increasing needs in many practical fields. This article introduces the Contour-Point Signature (CPS), a novel technique that produces features that are invariant to translation, scaling, and rotation. The approach make use of CPS to find the correspondences of points extracted from the contours of two similar shapes and to establish a relation to map arbitrary points from one shape to another.

Illumination invariance remains one of the most researched, yet the most challenging aspect of automatic face recognition. In this paper the discriminative power of colour-based invariants is investigated in the presence of large illumination changes between training and query data, when appearance changes due to cast shadows and non-Lambertian effects are significant. Specifically, there are three main contributions: (i) a general photometric model of the camera is described and it is shown how its parameters can be estimated from realistic video input of pseudo-random head motion, (ii) several novel colour-based face invariants are derived for different special instances of the camera model, and (iii) the performance of the largest number of colour-based representations in the literature is evaluated and analysed on a database of 700 video sequences. The reported results suggest that: (i) colour invariants do have a substantial discriminative power which may increase the robustness and accuracy of recognition from low resolution images in extreme illuminations, and (ii) that the non-linearities of the general photometric camera model have a significant effect on recognition performance. This highlights the limitations of previous work and emphasizes the need to assess face recognition performance using training and query data which had been captured by different acquisition equipment.

Some low-IQ savants can give the day of the week corresponding to decades’ worth of dates, but cannot state the number of dates in a week or solve a simple addition or subtraction problem. This divergence seems paradoxical because we divide the world into  conscious, complex, “high-level” cognitive processes and unconscious, simple, “low-level” perceptual-motor ones.  Yet savant abilities fit neither category: savants’ abilities, though not fully conscious, involve more than rote memory.  Indeed, savants eventually come to resemble neurotypical experts, and may even become creative.  Unsupervised neural network models may illustrate how savants learn: through unconscious, yet very high-level, pattern recognition.  Savants seek out domains that have meaningful structural regularities, e.g. calendars, math, or music, and spend a great deal of time and attention on such domains.  They may implicitly learn these regularities through a sort of pattern recognition.  This theory implies that pattern recognition is more than just a low-level perceptual process, and more importantly, that complex cognitive processes can be unconscious.

In this paper we are interested in analyzing behaviour in crowded public places at the level of holistic motion. Our aim is to learn, without user input, strong scene priors or labelled data, the scope of "normal behaviour" for a particular scene and thus alert to novelty in unseen footage. The first contribution is a low-level motion model based on what we term tracklet primitives, which are scene-specific elementary motions. We propose a clustering-based algorithm for tracklet estimation from local approximations to tracks of appearance features. This is followed by two methods for motion novelty inference from tracklet primitives: (a) an approach based on a non-hierarchial ensemble of Markov chains as a means of capturing behavioural characteristics at different scales, and (b) a more flexible alternative which exhibits a higher generalizing power by accounting for constraints introduced by intentionality and goal-oriented planning of human motion in a particular scene. Evaluated on a 2h long video of a busy city marketplace, both algorithms are shown to be successful at inferring unusual behaviour, the latter model achieving better performance for novelties at a larger spatial scale.

Subliminal information theory proposes that information is not only processed without awareness, but that it is also acted upon without awareness. Some research suggests such information is even prioritized over other forms of information processing. Where there remains some controversy over the extent or nature of the behavior that can be influenced by subliminal messages, there is little doubt that properly presented subliminal information is processed, retained, and acted upon. Contrary to popular opinion, the literature and evidence supporting subliminal information theory is robust. Indeed, meta-analysis clearly demonstrates very strong statistical support for this modality of care. There are many areas of research remaining to further enable taking advantage of subliminal information process- ing; however, because of the mis- and dis-information in the public domain, many scientists avoid this area, because of either a lack of knowledge or a fear of the kind of criticism that can influence careers.

The paper focuses on an overview of the different existing methods in content-based video retrieval. During the last decade there was a~rapid growth of video posted on the Internet. This imposes urgent demands on video retrieval. Video has a complex structure and can express the same idea in different ways. This makes the task of searching for video more complicated. Video titles and text descriptions cannot give the hole information about objects and events in the video. This creates a need for content-based video retrieval. There is a semantic gap between low-level video features, that can be extracted, and the users' perception. Complex content-based video retrieval can be regarded as the bridge between traditional retrieval and semantic-based video retrieval.

Keywords: frames; near-duplicates video; scenes; shots; video annotation; video classification; video mining; video reranking; video retrieval.

В статье предлагается обзор различных существующих методов ассоциативного поиска по видео. В течение прошлого десятилетия наблюдался стремительный рост количества видео размещаемых в Интернете, что создало острую необходимость в появлении поиска по видео. Видео имеет сложную структуру. Одна и та же информация может быть выражена различными способами. Это серьёзно усложняет задачу видео-поиска. Заголовки и описания видео не могут дать полного представления о самом видео, что влечет за собой необходимость использования ассоциативного поиска по видео. Существует семантический разрыв между низкоуровневыми характеристиками видео и восприятием пользователей. Комплексный ассоциативный видео-поиск может рассматриваться как связующее звено между обычным поиском и смысловым поиском по видео.

Ключевые слова: анализ видео; аннотирование видео; видео-поиск; кадры; классификация видео; нечеткие дубликаты видео; ранжирование видео; сцены; съёмки.

Никитин И. К. Элементы ассоциативного поиска по видео [Текст] / И. К. Никитин // Новое слово в науке: перспективы развития : материалы междунар. науч.–практ. конф. (Чебоксары, 10 сент. 2014 г.) / редкол.: О. Н. Широков [и др.]. – Чебоксары: ЦНС «Интерактив плюс», 2014. – С. 223–230. – ISBN 978-5-906626-37-0.

За последние несколько лет объем носителей мультимедийной информации вырос в несколько раз. В сложившейся ситуации необходим простой и гибкий поиск неструктурированным мультимедийных данных. В статье предлагается обзор  существующих методов ассоциативного поиска по видео.

Shape matching and point correspondence recovering play a fundamental role in applications like pattern and object recognition, shape classication, image alignment and regis- tration, visual information data mining, and many other computer vision related areas, which recently became active research disciplines due to the increasing needs in many practical elds. This article introduces the Contour-Point Signature (CPS), a novel technique

Abstract: Shape matching and point correspondence recovering play a fundamental role in applications like pattern and object recognition, shape classification, image alignment and registration, visual information data mining, and many other computer vision related areas, ...