Shlomo Greenberg

Fingerprint image enhancement using filtering techniques

Extracting minutiae from fingerprint images is one of the most important steps in automatic fingerprint identification and classification. Minutiae are local discontinuities in the fingerprint pattern, mainly terminations and bifurcations. In this work we propose two methods for fingerprint image enhancement. The first one is carried out using local histogram equalization, Wiener filtering, and image binarization. The second method use a unique anisotropic filter for direct grayscale enhancement. The results achieved are compared with those obtained through some other methods. Both methods show some improvement in the minutiae detection process in terms of either efficiency or time required.

New Error-Resilient Scheme Based on FMO and Dynamic Redundant Slices Allocation for Wireless Video Transmission

Video quality suffers significant degradation when transmitted over error-prone channel, due to packet loss, errors caused by fading in wireless channel and due to the video codec prediction mechanisms. The H.264/AVC standard suggests some new error-resilient features to enable reliable transmission of compressed video signal over lossy packet networks. Two of those new features are the Redundant Slices and the Flexible Macro-Block Ordering (FMO). In this paper we propose a new error-resilient scheme which merges the H.264/AVC FMO feature with a new technique for dynamic allocation of redundant slices depending on the wireless channel fading parameters. We suggest using a unique smart dynamic redundant slices allocation scheme which considers the dynamic wireless channel parameters rather than using the classical standard static allocation. The proposed redundant slice allocation algorithm is based on both Average Fade Duration (AFD), and Level Cross Rate (LCR) channels characteristics. Moreover, we propose a new Explicit Spiral-Interleaved (ESI) flexible macroblocks ordering technique, which outperforms all other FMO types. The new ESI ordering results in effective error scattering which maximize the number of correctly received macroblocks located around corrupted macroblocks, leading to better error concealment. The proposed scheme greatly improves video transmission quality over lossy wireless transmission channels. Simulations results for wireless channel characterized by Rayleigh fading indicate that the proposed method improves the standard static allocation of redundant slices in terms of PSNR by about 2.5dB. Performance evaluations show that our approach is especially suited for applications such as video conferencing and mobile TV, where typically a specific main important Region of Interest should be more carefully protected

Improved structure-adaptive anisotropic filter

Most adaptive smoothing approaches damage image fidelity. In this paper we propose to improve the structure-adaptive anisotropic filtering approach using an elliptical kernel, a non-linear filtering function, and a more robust-to-noise technique for oriented pattern direction estimation. The proposed filter outperforms some others known filters and is more robust to noisy images.

Region-of-interest-based algorithm for automatic target detection in infrared images

We present a region-of-interest-based segmentation (ROI-S) algorithm and apply it for automatic target detection. The proposed algorithm requires no templates or a priori knowledge of the targets. An automatic ROI extraction approach based on localized texture and statistical features is used to locate targets in an IR scene without any prior knowledge of their type, exact size, and orientation. Two locally adaptive histogram-based segmentation techniques are applied to extract the target signature. The Bayes decision rule is applied for a bimodal histogram while entropic correlation is used for all other cases. Geometric and statistical features are automatically extracted for each suspected ROI. We suggest a unique variance-based metric for discriminating targets from clutter and for evaluating the probability of correct detection. The proposed system is successfully tested on several hundred single-frame IR images that contain multiple examples of military vehicles, with various sizes and brightness levels and in various background scenes and orientations. A high probability of correct detection (greater than 90%) with a low false alarm rate is achieved.

Statistical multiplexing and admission control policy for smoothed video streams using e-PCRTT algorithm

Improvements in telecommunication and computer technologies have made integrated services packet-switched networks possible. It is expected that a significant portion of future networks will carry prerecorded video and that traffic in applications such as video on demand (VoD) will include high-fidelity audio, short multimedia clips, and full-length movies. In this paper we study the effect of video rate smoothing, of prerecorded VBR sources, on network utilization and admission control of a VoD system, such that the end users receive a satisfactory service. The enhancement piecewise constant rate transmission and transport (e-PCRTT) algorithm is used as the smoothing algorithm, which utilizes equal size intervals. The effect of smoothing on the statistical characteristics of multiplexed video streams is explored. We found that synchronization between the smoothing intervals can significantly improve the efficiency of the smoothing process by reducing the number of bandwidth changes and the rate variability of the multiplexed stream. In this paper we propose an admission control policy in which a bandwidth rate-plan is negotiated at stream initiation. The algorithm is evaluated via simulation for the VoD scenario.

Neural-network classifiers for automatic real-world aerial image recognition.

We describe the application of the multilayer perceptron (MLP) network and a version of the adaptive resonance theory version 2-A (ART 2-A) network to the problem of automatic aerial image recognition (AAIR). The classification of aerial images, independent of their positions and orientations, is required for automatic tracking and target recognition. Invariance is achieved by the use of different invariant feature spaces in combination with supervised and unsupervised neural networks. The performance of neural-network-based classifiers in conjunction with several types of invariant AAIR global features, such as the Fourier-transform space, Zernike moments, central moments, and polar transforms, are examined. The advantages of this approach are discussed. The performance of the MLP network is compared with that of a classical correlator. The MLP neural-network correlator outperformed the binary phase-only filter (BPOF) correlator. It was found that the ART 2-A distinguished itself with its speed and its low number of required training vectors. However, only the MLP classifier was able to deal with a combination of shift and rotation geometric distortions.

New hybrid error concealment for digital compressed video

Transmission of a compressed video signal over a lossy communication network exposes the information to losses and errors, which leads to significant visible errors in the reconstructed frames at the decoder side. In this paper we present a new hybrid error concealment algorithm for compressed video sequences, based on temporal and spatial concealment methods. We describe spatial and temporal techniques for the recovery of lost blocks. In particular, we develop postprocessing techniques for the reconstruction of missing or damaged macroblocks. A new decision support tree is developed to efficiently choose the best appropriate error concealment method, according to the spatial and temporal characteristics of the sequence. The proposed algorithm is compared to three error concealment methods: spatial, temporal, and a previous hybrid approach using different noise levels. The results are evaluated using four quality measures. We show that our error concealment scheme outperforms all the other three methods for all the tested video sequences.

Video rate smoothing and statistical multiplexing using the e-PCRTT algorithm

Rapid advantages in computer and telecommunication technologies have made integrated services packet-switched networks possible. It is expected that a significant portion of future networks will carry prerecorded video. Traffic in applications such as Video on Demand (VoD), will include high-fidelity audio, short multimedia clips, and full-length movies. In this paper we study the effect of video rate smoothing of a prerecorded VBR sources, on network utilization and statistical multiplexing gain, such that the end users receive satisfactory service. The enhancement piecewise constant rate transmission and transport (e-PCRTT) algorithm is used as the smoothing algorithm which utilizes equal size intervals and its effect on the statistical characteristics of the multiplexed video is explored. We found that synchronization between the smoothing intervals can significantly improve the efficiency of the smoothing process by reducing the number of bandwidth changes and the rate variability of the multiplexed stream. We investigate how synchronized smoothing intervals influence the potential for statistical gain, as compared to unsynchronized streams and present several examples to illustrate the advantage of synchronized streams over unsynchronized streams.

EPCRTT-based smoothing and multiplexing of VBR video traffic

Applying video smoothing techniques to real-time video transmission can significantly reduce the peak rate and rate variability of compressed video streams. Moreover, statistical multiplexing of the smoothed traffic can substantially improve network utilization. In this paper we propose a new smoothing scheme, which exploits statistical multiplexing gain that can be obtained after smoothing of individual video streams. We present a new bandwidth allocation algorithm that allows for responsive interactivity. The local re-smoothing algorithm is carried out using an iterative process. In the proposed scheme the smoothed video streams are divided into fixed intervals and then a new transmission schedule for each interval is calculated. The problem of applying an optimal transmission schedule for aggregated smoothing video streams is shown to be NP-hard problem. Partitioning the whole stream into sections enables parallel processing of the smoothing algorithm in real-time before transmission. This approach allows partial transmission of the multiplexed stream while smoothing other intervals. The simulation results show a significant reduction in peak rate and rate variability of the aggregated stream, compared to the non-smoothing case. Therefore the proposed scheme allows us to increase the number of simultanusally-served video streams.

Structure-adaptive anisotropic filter applied to fingerprints

We propose a modified structure-adaptive anisotropic filter, which uses local intensity orientation and an anisotropic measure to control the shape of the filter kernel, and apply it to fingerprints. The modification is made in the frequency domain by converting the common structure-adaptive anisotropic filter from a low-pass filter to a band-pass one. We show that the modified structure-adaptive anisotropic filter can be effectively applied to applications, such as fingerprint image enhancement, in which the oriented patterns in local neighborhood form a sinusoidal-shaped plane wave with a well-defined frequency and orientation. The performance of the proposed structure-adaptive anisotropic filter is compared to some other filters used for minutiae detection. The proposed filter shows some improvement in terms of computational time and efficiency.