The rapid evolution of satellite imaging systems has resulted in sharp increases of image archive volumes. Multitemporal images constitute a sizeable portion of these time-series databases. Accordingly, development of accurate content based time-series retrieval (CBTSR) methods in massive archives of RS images attracts much research interest. Given a user-defined query time series, CBTSR aims at identifying within a massive archive image time series that show characteristics similar to those of the query time series. In this paper, we focus our attention to CBTSR in pairs of RS images, aiming to search and retrieve bi-temporal image pairs containing changes similar to those modeled in the query. To this end, we introduce two deep learning-based methods in the framework of CBTSR. The first method, called deep change vector retrieval (DVCR), is based on selected deep features extracted from the change vector analysis. The second method, called autoencoder with early fusion (AEEF) uses an autoencoder architecture to recreate the time difference images and the latent codes produced by this network. Experimental results show the effectiveness of the proposed methods for CBTSR problems. The code of the proposed methods is available at: https://github.com/OnatV/ChangeRetrieval.

Recent advances in intelligent surveillance systems have enabled a new era of smart monitoring in a wide range of applications from health monitoring to homeland security. However, this boom in data gathering, analyzing and sharing brings in also significant privacy concerns. We propose a Compressive Sensing (CS) based data encryption that is capable of both obfuscating selected sensitive parts of documents and compressively sampling, hence encrypting both sensitive and non-sensitive parts of the document. The scheme uses a data hiding technique on CS-encrypted signal to preserve the one-time use obfuscation matrix. The proposed privacy-preserving approach offers a low-cost multi-tier encryption system that provides different levels of reconstruction quality for different classes of users, e.g., semi-authorized, full-authorized. As a case study, we develop a secure video surveillance system and analyze its performance.

This paper presents a novel content based remote sensing (RS) image retrieval system that consists of: i) a spatial and spectral image description scheme; and ii) a sparsity based supervised retrieval method. Spatial image description is based on the scale invariant feature transform (SIFT), while a novel descriptor defined based on the bag of spectral values is proposed to express spectral features. With the conjunction of these two feature vectors RS image retrieval is instrumented via a sparse reconstruction-based approach. These sparse reconstructions are used to estimate the likelihood of a scene to contain a land-cover class label. Applying this method separately for each land-cover class, one achieves retrieval in the framework of multi-label remote sensing image retrieval. Experimental results obtained on an archive of hyperspectral images show the effectiveness of the proposed system.

We propose to model the image differentials of astrophysical source maps by Student's t-distribution and to use them in the Bayesian source separation method as priors. We introduce an efficient Markov Chain Monte Carlo (MCMC) sampling scheme to unmix the astrophysical sources and describe the derivation details. In this scheme, we use the Langevin stochastic equation for transitions, which enables parallel drawing of random samples from the posterior, and reduces the computation time significantly (by two orders of magnitude). In addition, Student's t-distribution parameters are updated throughout the iterations. The results on astrophysical source separation are assessed with two performance criteria defined in the pixel and the frequency domains.

We propose an adaptive Monte Carlo Markov Chain (MCMC) simulation for the Bayesian source separation problem and apply it to the unmixing of astrophysical components. In this method, we use the Langevin stochastic equation for transitions, which enables parallel drawing of random samples from the posterior, and which reduces the computation time significantly (by two orders of magnitude). In addition to this, the parameters of the Markov Random Field (MRF) model are updated via Maximum Likelihood (ML) throughout the iterations.

We address content-based retrieval of complete 3D object models by a probabilistic generative description of local shape properties. The proposed shape description framework characterizes a 3D object with sampled multivariate probability density functions of its local surface features. This density-based descriptor can be efficiently computed via kernel density estimation (KDE) coupled with fast Gauss transform. The non-parametric KDE technique allows reliable characterization of a diverse set of shapes and yields descriptors which remain relatively insensitive to small shape perturbations and mesh resolution. Density-based characterization also induces a permutation property which can be used to guarantee invariance at the shape matching stage. As proven by extensive retrieval experiments on several 3D databases, our framework provides state-of-the-art discrimination over a broad and heterogeneous set of shape categories.

We investigate the source separation problem of random fields within a Bayesian framework. The Bayesian formulation enables the incorporation of prior image models in the estimation of sources. Due to the intractability of the analytical solution, we resort to numerical methods for the joint maximization of the a posteriori distribution of the unknown variables and parameters. We construct the prior densities of pixels using Markov random fields based on a statistical model of the gradient image, and we use a fully Bayesian method with modified-Gibbs sampling. We contrast our work to approximate Bayesian solutions such as Iterated Conditional Modes (ICM) and to non-Bayesian solutions of ICA variety. The performance of the method is tested on synthetic mixtures of texture images and astrophysical images under various noise scenarios. The proposed method is shown to outperform significantly both its approximate Bayesian and non-Bayesian competitors.

In this paper, a new scaling-based image-adaptive watermarking system has been presented, which exploits human visual model for adapting the watermark data to local properties of the host image. Its improved robustness is due to embedding in the low-frequency wavelet coefficients and optimal control of its strength factor from HVS point of view. Maximum likelihood (ML) decoder is used aided by the channel side information. The performance of the proposed scheme is analytically calculated and verified by simulation. Experimental results confirm the imperceptibility of the proposed method and its higher robustness against attacks compared to alternative watermarking methods in the literature.

In this paper, we focus on the reliable detection of facial fiducial points, such as eye, eyebrow and mouth corners. The proposed algorithm aims to improve automatic land-marking performance in challenging realistic face scenarios subject to pose variations, high-valence facial expressions and occlusions. We explore the potential of several feature modalities, namely, gabor wavelets, independent component analysis (ICA), non-negative matrix factorization (NMF), and discrete cosine transform (DCT), both singly and jointly. We show that the selection of the highest scoring face patch as the corresponding landmark is not always the best, but that there is considerable room for improvement with the cooperation among several high scoring candidates and also using a graph-based post-processing method. We present our experimental results on Bosphorus face database, a new challenging database.

The various image-processing stages in a digital camera pipeline leave telltale footprints, which can be exploited as forensic signatures. These footprints consist of pixel defects, of unevenness of the responses in the CCD sensor, black current noise, and may originate from proprietary interpolation algorithms involved in color filter array [CFA]. Various imaging device (camera, scanner etc.) identification methods are based on the analysis of these artifacts. In this work, we set to explore three sets of forensic features, namely binary similarity measures, image quality measures and higher order wavelet statistics in conjunction with SVM classifier to identify the originating camera. We demonstrate that our camera model identification algorithm achieves more accurate identification, and that it can be made robust to a host of image manipulations. The algorithm has potential to discriminate camera units within the same model.

In this paper, we present an extensive study of 3-D face recognition algorithms and examine the benefits of various score-, rank-, and decision-level fusion rules. We investigate face recognizers from two perspectives: the data representation techniques used and the feature extraction algorithms that match best each representation type. We also consider novel applications of various feature extraction techniques such as discrete Fourier transform, discrete cosine transform, nonnegative matrix factorization, and principal curvature directions to the shape modality. We discuss and compare various classifier combination methods such as fixed rules voting- and rank-based fusion schemes. We also present a dynamic confidence estimation algorithm to boost fusion performance. In identification experiments performed on FRGC v1.0 and FRGC v2.0 face databases, we tried to find the answers to the following questions: 1) the relative importance of the face representation technique vis-à-vis the types of features extracted; 2) the impact of the gallery size; 3) the conditions, under which subspace methods are preferable, and the compression factor; 4) the most advantageous fusion level and fusion methods; 5) the role confidence votes in improving fusion and the style of selecting experts in the fusion; and 6) the consistency of the conclusions across different databases.

We present an identification and authentication system based on hand modality which is part of a reference system for all modalities developed within the biosecure consortium. It relies on simple geometric features extracted from hand boundary. The different steps of this system are detailed, namely: pre-processing, feature extraction and hand matching. This system has been tested on the biosecure hand database which consists of 4500 hand images of 750 individuals. Results are detailed with respect to different enrolment conditions such as population size, enrolment size, and image resolution.

We address the 3D object retrieval problem using multivariate density-based shape descriptors. Considering the fusion of first and second order local surface information, we construct multivariate features up to five dimensions and process them by the kernel density estimation methodology to obtain descriptor vectors. We can compute these descriptors very efficiently using the fast Gauss transform algorithm. We also make use of descriptor level information fusion by concatenating descriptor vectors to increase their discrimination power further. To render the resulting descriptors storage-wise efficient, we develop two analytical tools, marginalization and probability density suppression, for descriptor dimensionality reduction. The experiments on two different databases, Princeton Shape Benchmark and Sculpteur, show that, boosted with both feature level and descriptor level information fusion, and powered with fast computational schemes, the density-based shape description framework enables effective and efficient 3D object retrieval.

The problem of person recognition and verification based on their hand images has been addressed. The system is based on the images of the right hands of the subjects, captured by a flatbed scanner in an unconstrained pose at 45 dpi. In a pre-processing stage of the algorithm, the silhouettes of hand images are registered to a fixed pose, which involves both rotation and translation of the hand and, separately, of the individual fingers. Two feature sets have been comparatively assessed, Hausdorff distance of the hand contours and independent component features of the hand silhouette images. Both the classification and the verification performances are found to be very satisfactory as it was shown that, at least for groups of about five hundred subjects, hand-based recognition is a viable secure access control scheme.

Identification and verification of a video clip via its fingerprint find applications in video browsing, database search and security. For this purpose, the video sequence must be collapsed into a short fingerprint using a robust hash function based on signal processing operations. We propose two robust hash algorithms for video based both on the discrete cosine transform (DCT), one on the classical basis set and the other on a novel randomized basis set (RBT). The robustness and randomness properties of the proposed hash functions are investigated in detail. It is found that these hash functions are resistant to signal processing and transmission impairments, and therefore can be instrumental in building database search, broadcast monitoring and watermarking applications for video. The DCT hash is more robust, but lacks security aspect, as it is easy to find different video clips with the same hash value. The RBT based hash, being secret key based, does not allow this and is more secure at the cost of a slight loss in the receiver operating curves

We present a compression technique that provides progressive transmission as well as lossless and near-lossless compression in a single framework. The proposed technique produces a bit stream that results in a progressive, and ultimately lossless, reconstruction of an image similar to what one can obtain with a reversible wavelet codec. In addition, the proposed scheme provides near-lossless reconstruction with respect to a given bound, after decoding of each layer of the successively refinable bit stream. We formulate the image data-compression problem as one of successively refining the probability density function (pdf) estimate of each pixel. Within this framework, restricting the region of support of the estimated pdf to a fixed size interval then results in near-lossless reconstruction. We address the context-selection problem, as well as pdf-estimation methods based on context data at any pass. Experimental results for both lossless and near-lossless cases indicate that the proposed compression scheme, that innovatively combines lossless, near-lossless, and progressive coding attributes, gives competitive performance in comparison with state-of-the-art compression schemes.

The payload increase of watermarking channels via the use of low-density parity check (LDPC) codes is considered. The bit error rate and payload size problem is addressed in the light of the performance of typical transform-domain spread-spectrum watermarking techniques. Simulation results indicate that the information payload can be doubled via judicious use of LDPC codes vis-a/spl grave/-vis the performance of the Bose-Chaudhuri-Hochquenghem and repetition codes.

We propose measures to evaluate quantitatively the performance of video object segmentation and tracking methods without ground-truth (GT) segmentation maps. The proposed measures are based on spatial differences of color and motion along the boundary of the estimated video object plane and temporal differences between the color histogram of the current object plane and its predecessors. They can be used to localize (spatially and/or temporally) regions where segmentation results are good or bad; and/or they can be combined to yield a single numerical measure to indicate the goodness of the boundary segmentation and tracking results over a sequence. The validity of the proposed performance measures without GT have been demonstrated by canonical correlation analysis with another set of measures with GT on a set of sequences (where GT information is available). Experimental results are presented to evaluate the segmentation maps obtained from various sequences using different segmentation approaches.

A new multilevel thresholding method is proposed using sample moment function (SMF). For the binary case the method can make use of the a priori information on whether the target object is found on the darker or lighter part of the scene. Extensive comparisons using a database of NDT images show that the proposed method outperforms in competition 40 other thresholding methods from the literature M. Sezgin et al. (2001) (2003), based upon both objective scores and subjective evaluation.

Presents a scalable object tracking framework, which is capable of tracking the contour of nonrigid objects in the presence of occlusion. The framework consists of open-loop boundary prediction and closed-loop boundary correction parts. The open-loop prediction block adaptively divides the object contour into subcontours, and estimates the mapping parameters for each subsegment. The closed-loop boundary correction block employs a suitably weighted combination of low-level features such as color edge, color segmentation, motion models, and motion segmentation for each subcontour. Performance evaluation measures are used in a feedback loop to evaluate the goodness of the segmentation/tracking in order to adjust the weights assigned to each of these low-level features for each subcontour at each frame. The framework is scalable because it can be adapted to track a coarse estimate of the boundary of selected objects in real-time, as well as pixel-accurate boundary tracking in off-line mode. The proposed method does not depend on any single motion or shape model, and does not need training. Experimental results demonstrate that the algorithm is able to track the object boundaries under significant occlusion and background clutter.

We present techniques for steganalysis of images that have been potentially subjected to steganographic algorithms, both within the passive warden and active warden frameworks. Our hypothesis is that steganographic schemes leave statistical evidence that can be exploited for detection with the aid of image quality features and multivariate regression analysis. To this effect image quality metrics have been identified based on the analysis of variance (ANOVA) technique as feature sets to distinguish between cover-images and stego-images. The classifier between cover and stego-images is built using multivariate regression on the selected quality metrics and is trained based on an estimate of the original image. Simulation results with the chosen feature set and well-known watermarking and steganographic techniques indicate that our approach is able with reasonable accuracy to distinguish between cover and stego images.

We present a novel technique for steganalysis of images that have been subjected to least significant bit (LSB) type steganographic algorithms. The seventh and eighth bit planes in an image are used for the computation of several binary similarity measures. The basic idea is that the correlation between the bit planes as well the binary texture characteristics within the bit planes differs between a stego-image and a cover-image. These telltale marks can be used to construct a steganalyzer, that is, a multivariate regression scheme to detect the presence of a steganographic message in an image.

A novel image compression technique is presented that incorporates progressive transmission and near-lossless compression in a single framework. Experimental performance of the proposed coder proves to be competitive with the state-of-the-art compression schemes.

We present a scalable object tracking framework which is capable of tracking the contour of rigid and non-rigid objects in the presence of occlusion. The method adaptively divides the object contour into sub-contours, and employs several low-level features such as color edge, color segmentation, motion models, motion segmentation, and shape continuity information in a feedback loop to track each sub-contour. We also introduce some novel performance evaluation measures to evaluate the goodness of the segmentation and tracking. The results of these performance measures are utilized in a feedback loop to adjust the weights assigned to each of these low-level features for each sub-contour at each frame. The framework is scalable because it can be adapted to roughly track simple objects in real-time as well as pixel-accurate tracking of more complex objects in offline mode. The proposed method does not depend on any single motion or shape model, and does not need training. Experimental results demonstrate that the algorithm is able to track the object boundaries accurately under significant occlusion and background clutter.

We present metrics to evaluate the performance of video object segmentation and tracking methods quantitatively when ground-truth segmentation maps are not available. The proposed metrics are based on the color and motion differences along the boundary of the estimated video object plane and the color histogram differences between the current object plane and its temporal neighbors. These metrics can be used to localize (spatially and/or temporally) regions where segmentation results are good or bad; or combined to yield a single numerical measure to indicate the goodness of the boundary segmentation and tracking results. Experimental results are presented to evaluate the segmentation map of the "Man" object in the "Hall Monitor" sequence both in terms of a single numerical measure, as well as localization of the good and bad segments of the boundary.

In nondestructive testing (NDT) applications based on image analysis, image segmentation is the most important step in the extraction of defective regions of materials. An effective and very simple method of image segmentation, especially in NDT applications, is image thresholding. In an effort to present a quantitative evaluation of image thresholding methods NDT applications, 41 thresholding algorithms are compared. They are grouped in six categories based on the information they are exploiting, such as histogram shape, object attribute or clustering behavior, etc. Performance assessment is based on the weighted combination of four complementary objective metrics. Based on the results of such NDT images as defective thermal, ultrasonic, eddy current, etc., the thresholding algorithms that perform well over the majority of cases are established and a mixture thresholding scheme is proposed.

We present techniques for steganalysis of images that have been potentially subjected to a watermarking algorithm. We show that watermarking schemes leave statistical evidence or structure that can be exploited for detection with the aid of proper selection of image features and multivariate regression analysis. We use some image quality metrics as the feature set to distinguish between watermarked and unwatermarked images and furthermore distinguish between different watermarking techniques. To identify specific quality measures that provide the best discriminative power, we use analysis of variance (ANOVA) techniques. Multivariate regression analysis is then used on the selected quality metrics to build an optimal classifier using a set of test images and their blurred versions. Simulation results with a specific feature set and some well-known and publicly available watermarking techniques indicate that our approach is able to accurately distinguish with high accuracy between images marked by different watermarking techniques.

An automatic system for the person identification based on comparison of a camera image and a document photo presents several design difficulties. The main complication arises from the fact that the document photo may represent quite a different appearance of the test person, i.e., an older version, sometimes by years, or with a different hairstyle, facial expression and lighting conditions. In addition the scanned photo is usually of a much lower quality. In this paper elements of a system for a face comparison between camera images and archival photo albums are discussed and experimental results are given. Such a system may be instrumental for document control or for police investigations.

This paper provides a generalization of non-reducible descriptors. Non-reducible descriptors are used in supervised pattern recognition problems when the patterns descriptions consist of Boolean variables. This generalization extends the concept of distance between patterns of different classes. A mathematical model to construct generalized non-reducible descriptors, a computational procedure, and numerical examples are discussed.

An improved segmentation algorithm is proposed, which implements the MAP estimation of the label field using a Constraint Satisfaction Neural Network (CSNN). It uses the advantages of stochastic relaxation with those of Gauss-Markov Random Field (GMRF) models. The performance of the algorithm is compared vis-a-vis alternate relaxation schemes using both synthetic and real images.

The thresholding technique used can critically affect the performance of subsequent operations such as page segmentation and character recognition. A taxonomy of thresholding methods has been proposed where the major categories are listed as entropy-based, histogram shape-based, object attribute-based, clustering based, adaptive, and object similarity-based. Furthermore a comprehensive performance evaluation of thresholding algorithms in the context of document analysis and character recognition systems has been performed. A large class of thresholding algorithms have been comparatively evaluated using shape distortion, false alarm and missprobability, and edge discrepancy measures. Both simulated documents and bitmaps of ground-truthed documents are used.

We develop a technique to perform efficient and accurate matching to detect the occurence(s) of a template in a scene. The template may describe an object or a textured surface. Representative binary features such as edge points for objects and a set of intensity extrema for textured surfaces are extracted from both test and template images. The search is based on a three-stage "coarse-fine-final" matching. First, we match with the binarized template skipping positions in horizontal and vertical directions and find a number of highest ranking matching positions. Second, we search in neighborhoods centered at the stated positions and find improved matching positions. Finally, some error measure between the original, i.e. gray level or color, test and template images is computed at the fine positions as the final matching. It is demonstrated that the proposed scheme achieves significant reduction in computational complexity with virtually no loss of detection performance.

Two new design techniques for adaptive orthogonal block transforms based on vector quantization (VQ) codebooks are presented. Both techniques start from reference vectors that are adapted to the characteristics of the signal to be coded, while using different methods to create orthogonal bases. The resulting transforms represent a signal coding tool that stands between a pure VQ scheme on one extreme and signal-independent, fixed block transformation-like discrete cosine transform (DCT) on the other. The proposed technique has superior compaction performance as compared to DCT both in the rendition of details of the image and in the peak signal-to-noise ratio (PSNR) figures.

The paper presents performance evaluation of thresholding algorithms in the context of document analysis and character recognition systems. Several thresholding algorithms are comparatively evaluated on the basis of the original bitmaps of characters. Different distance measures such as Hausdorff, Jaccard, and Yule are used to measure the similarity between thresholded bitmaps and original bitmaps of characters.

An object-oriented codec for video transmission at very low bit rates is proposed. The object motion is modeled by quadratic transform for which the coefficients are estimated by the nonlinear quasi-Newton method. The segmentation problem is put forward as a constrained optimization problem which interacts with the motion estimation process in the course of region growing. A context-based shape coding method which takes into account the image synthesis error as well as the geometric distortion, is also proposed. Quantitative and subjective performance results of the codec on various test sequences are included.

This paper addresses the problem of object based image coding for the purpose of video transmission at very low bit rates (below 32 kbit/s). Each frame of an image sequence is first segmented into temporally unchanged (background) and changed regions via a change detector. Then the changed regions are subdivided into arbitrarily shaped model failure and model compliance regions so as to satisfy the chosen quadratic transform motion model. Our work brings in two original contributions: (1) the use of region growing motion segmentation, and (2) joint use of quadratic transform with optical flow motion estimation.

In this correspondence, the problem of directional and multiscale edge detection is considered. Orthogonal and linear-phase M-band wavelet transform is used to decompose the image into MxM channels. These channels are then combined such that each combination, which we refer to as decomposition filter, results in zero-crossings at the locations of edges corresponding to different directions and resolutions, and inherently performs regularization against noise. By applying a zero-crossing detector on the outputs of the decomposition filters, edge maps of desired resolution and direction are obtained. In addition, with the application of the Teager's energy operator at the analysis stage, it is possible to obtain a reduction in unwanted zero-crossings. Final edge maps of images are obtained through simple combinations of directional edge maps.

The problem of directional and multiscale edge detection is considered. Orthogonal and linear-phase M-band wavelet transform is used to decompose the image into channels which correspond to different directions and resolution levels. "Meaningful" combinations of the synthesis filter outputs at the selected channels yield edge maps with desired properties. In addition, with the application of energy operators at the analysis stage, it is possible to obtain a reduction in unwanted zero-crossings. Final edge maps of images are obtained through simple combinations of directional edge maps.>

A new classification method based on the multiresolution decomposition analysis of nonstationary signals is proposed. The signal is decomposed into (M+1) octave bands in order to reduce the degree of nonstationarity. A separate feature vector is extracted from each band and a "time-frequency feature matrix" is formed using these vectors. This feature matrix is then inputted to the first stage of a two-stage classifier including (M+1) individual classifiers where a generalized version of the k-nearest neighbor classification rule and soft decision method is used. Final decision is given at the second stage by combining the decisions of the (M+1) classifiers using a decision combination function. The intended application of the method is the classification of respiratory sound signals into healthy and pathological classes.

Accurate modeling and adaptation of scene objects play a crucial role in model-based coding schemes. In this paper a method is presented which transforms a general model of a face to the actual face viewed in the scene. The transformation is based on the facial contours (face border, eyes and mouth) and consists of an affine transformation (for all vertices) and local transformations for each individual vertex. Local transformations are executed taking into consideration the elastic properties of the model.>

The performance of the maximum likelihood spectral estimate is compared vis-à-vis the classical Bartlett spectrum. Special cases such as single tone harmonic analysis and asymptotic behaviour have been considered.

Various asynchronous delta modulation algorithms are considered. The statistical distribution of interbit intervals is analyzed and the signal-to-noise ratio behaviour is compared vis-a-vis linear and adaptive delta modulation algorithms. The problem of transmission of nonuniform samples through synchronous channels has also been treated. Quantization and runlength encoding characteristics of interbit intervals are studied. The optimal size and the statistical properties of buffer memory are determined and trade-offs between various system parameters such as runlength constraint, overflow and underflow probabilities and synchronization words are investigated.

The design and evaluation of real-time implementable coding schemes for Gaussian multisource-multichannel communication systems are considered. The problem is to transmit the output from ann-dimensional Gaussian source over a memorylessm-dimensional Gaussian channel with power constraint and a mean-squared error distortion measure. Shannon performance bounds are obtained for this system through the optimum performance theoretically attainable (OPTA) relationship between the source distortion level\betaand the channel input power level\alpha. The optimum encoder is determined within the class of linear memoryless transformations, in which case the optimum decoder transformation becomes a least-mean-square estimator. The optimum linear encoder-decoder pair either coincides with or is very close to the Shannon bound in a number of significant cases.