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

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

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

On robust estimation of the location parameter

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

We are interested in Greek folk music genre classification by resorting to canonical correlation analysis (CCA). Here, the genre is related to the place of origin of the song. The CCA learns a linear transformation of the song lyrics descriptors that is highly correlated with their genre labels as well as another linear transformation of the audio features extracted from music recordings, which is maximally correlated with their genre labels. In the latter task, thanks to the deep CCA (DCCA), deep nonlinear transformations of the audio features are learnt, which are maximally correlated with the genre labels. Experimental findings are disclosed for a two-class genre recognition problem, employing folk songs originated from Pontus and Asia Minor. It is demonstrated that the CCA achieves an average accuracy of 97.02% across the 5 folds, when the term frequency-inverse document frequency features model the song lyrics. By modeling the music signal of each song with 28 mel-frequency cepstral coefficients (MFCCs) extracted from each frame and averaged over all frames, the average accuracy of the CCA drops to 72.9% across the 5 folds. The DCCA yields an accuracy of 69% for audio-based genre recognition.

Greek folk music classification into two genres using lyrics and audio via canonical correlation analysis

Automatic music tagging is addressed by resorting to auditory temporal modulations and Parallel Factor Analysis 2 (PARAFAC2). The starting point is to represent each music recording by its auditory temporal modulations. Then, an irregular third order tensor is formed. The first slice contains the vectorized training temporal modulations, while the second slice contains the corresponding multi-label vectors. The PARAFAC2 is employed to effectively harness the multi-label information for dimensionality reduction. Any vectorized test auditory representation of temporal modulations is first projected onto the semantic space derived via the PARAFAC2 and the coefficient vector is obtained. Then, the annotation vector is obtained by multiplying this coefficient vector by the left singular vectors of the second slice (i.e., the slice associated to the label vector). The proposed framework, outperforms the state-of-the-art auto-tagging systems, when applied to the CAL500 dataset in a 10-fold cross-validation experimental protocol.

/pdf/automatic-music-tagging-via-parafac2-3ll7pfrcjd.pdf

Automatic music tagging via PARAFAC2

Two novel adaptive nonlinear filter structures are proposed which are based on linear combinations of order statistics. These adaptive schemes are modifications of the standard LMS (least mean square) algorithm and have the ability to incorporate constraints imposed on coefficients in order to permit location invariant and unbiased estimation of a constant signal in the presence of additive white noise. The convergence properties of the proposed filters are considered. Both of them can adapt well to a variety of noise probability distributions ranging from short-tailed to long-tailed ones. Simulation examples are given. >

/pdf/constrained-adaptive-lms-l-filters-55tkdywov8.pdf

Constrained adaptive LMS L-filters

Adaptive order statistic filters for noise smoothing in digital images are presented. Two classes of adaptive filters are studied, namely, the least mean squares (LMS)-based adaptive order statistic filters and the signal-adaptive filters. The filter structures in the first class require a noise-free image to be used as a reference image, whereas those in the second class do not require a reference image. Two filter structures from the former class are examined: the adaptive locationinvariant L-filter and the adaptive Ll -filter. A novel signal-adaptive filter, namely, the morphological signal-adaptive median (MSAM) filter is proposed in the second class. It employs an anisotropic window adaptation procedure based on mathematical morphology operations. The noisesmoothing capabilities and the computational complexity of the LMSbased adaptive order statistic filters studied serves as a baseline in the assessment of the properties of the proposed MSAM filter. Quantitative criteria (e.g., the SNR, the peak SNR, the mean absolute error, and the mean squared error) as well as qualitative criteria (e.g., the perceived visual quality of the processed images) are employed to assess the performance of the filters in various corruption cases by different noise models.

/pdf/adaptive-order-statistic-filters-for-the-removal-of-noise-2gzs1qhmn2.pdf

Adaptive order statistic filters for the removal of noise from corrupted images

Anunsupervisedapproachforautomaticmusicstructureanalysis is proposed resorting to the following assumption: If the feature vectors extracted from a specific music segment are drawn from a single subspace, then the sequence of feature vectors extracted from a music recording will lie in a union of as many subspaces as the music segments in this recording are. It is well known that each feature vector stemming from a union of independent linear subspaces admits a sparse representation with respect to a dictionary formed by all other feature vectors with nonzero coefficients associated only to feature vectors that stem from its own subspace. Such sparse representation reveals the relationships among the feature vectors and it is used to construct a similarity graph, the so-called l1-graph. Accordingly, the segmentation of audio features is obtained by applying spectral clustering to the l1-graph. The performance of the just described approach is assessed by conducting experiments on the PopMusic and the UPF Beatles benchmark datasets. Promising results are reported.

/pdf/l1-graph-based-music-structure-analysis-1phi9t3vo5.pdf

Constantine Kotropoulos

Papers

Greek folk music classification into two genres using lyrics and audio via canonical correlation analysis

Automatic music tagging via PARAFAC2

Constrained adaptive LMS L-filters

Adaptive order statistic filters for the removal of noise from corrupted images

ℓ1-GRAPH BASED MUSIC STRUCTURE ANALYSIS