Successful blind image deconvolution algorithms require the exact estimation of the Point Spread Function size, PSF. In the absence of any priori information about the imagery system and the true image, this estimation is normally done by trial and error experimentation, until an acceptable restored image quality is obtained. This paper, presents an exact estimation of the PSF size that yields the optimum restored image quality. The paper also describes a least squares PSF estimation, instead of the slowly iterative update, that is commonly used in Iterative Blind Deconvolution software, IBD. Moreover, a technique is also proposed to improve the sharpness of the de-convolved images using Independent Component Analysis techniques (ICA). Simulation examples are given to show that the proposed technique manages to accurately estimate the PSF size apart from competing very well with the existing approaches.

Temporal shape variations intuitively appear to provide a good cue for human activity modeling. In this paper, we lay out a novel framework for human action recognition based on fuzzy log-polar histograms and temporal self-similarities. At first, a set of reliable keypoints are extracted from a video clip (i.e., action snippet). The local descriptors characterizing the temporal shape variations of action are then obtained by using the temporal self-similarities defined on the fuzzy log-polar histograms. Finally, the SVM classifier is trained on these features to realize the action recognition model. The proposed method is validated on two popular and publicly available action datasets. The results obtained are quite encouraging and show that an accuracy comparable or superior to that of the state-of-the-art is achievable. Furthermore, the method runs in real time and thus can offer timing guarantees to real-time …

Automatic face detection and localization is a key problem in many computer vision tasks. In this paper, a simple yet effective approach for detecting and locating human faces in color images is proposed. The contribution of this paper is twofold. First, a particular reference to face detection techniques along with a background to neural networks is given. Second, and maybe most importantly, an adaptive cubic-spline neural network is designed to be used to detect and locate human faces in uncontrolled environments. The experimental results conducted on our test set show the effectiveness of the proposed approach and it can compare favorably with other state-of-the-art approaches in the literature.

An essential part of any activity recognition system claiming be truly real-time is the ability to perform feature extraction in real-time. We present, in this paper, a quite simple and computationally tractable approach for real-time human activity recognition that is based on simple statistical features. These features are simple and relatively small, accordingly they are easy and fast to be calculated, and further form a relatively low-dimensional feature space in which classification can be carried out robustly. On the Weizmann publicly benchmark dataset, promising results (i.e. 97.8%) have been achieved, showing the effectiveness of the proposed approach compared to the-state-of-the-art. Furthermore, the approach is quite fast and thus can provide timing guarantees to real-time applications.

NULL

Total variation (TV) regularization is popular in image restoration and reconstruction due to its ability to preserve image edges. This paper, describes a new total variation based de-noising scheme. The proposed technique optimally finds the threshold level of the noisy image wavelet decomposition that minimizes the energy of the error between the restored and the noisy image. The minimization algorithm is regularized by including 1st as well as 2nd order derivatives effects of the noisy image, into the minimization scheme. Next, the problem of blind deconvolution of noisy images is addressed. First, the order of the blurring Point Spread Function (PSF), is accurately estimated using a de-noised version of the noisy blurred image. Then, the deconvolution algorithm is modified by including the effects of the 1 st as well as 2nd order derivatives of the blurred noisy images into the image update algorithm. Simulation …

This paper, presents an exact estimation of the PSF size for both noisy and noiseless images that is essential for good quality image restoration. Having accurately estimated the PSF, the paper also proposes a fast double updating algorithm for improving the quality of the restored image. It is based on minimizing some largest errors between the blurred image and its equivalent computed as the 2-D convolution of the estimated restored image and the estimated PSF. Simulation results have been given to verify that the proposed technique manages to correctly estimate the PSF size for noisy and noiseless cases as well as yielding a sharpened image with higher PSNR than classical approaches.

Different guard interval techniques for the Orthogonal Frequency Division Multiplexing (OFDM) transmission are suggested to reduce the interference between successive symbols (i.e. Inter-Symbol Interference, ISI) and interference between different carriers within the same symbol (i.e. Inter-Carrier Interference, ICI). In this paper, the impact of replacing the Cyclic Prefix (CP) by zeros insertion (ZI) before the Inverse Fast Fourier Transform (IFFT) process on OFDM is studied. Associated with each OFDM symbol, the zeros will be added in the transmitter before the IFFT process. For symmetry of the OFDM symbol, the zeros will be inserted with the same length among the OFDM frames. The ZI acts as a buffer region where delayed information from the previous symbols can get stored. The receiver has to exclude samples from the ZI which got corrupted by the previous symbol when choosing the samples for an OFDM …

Despite their high stability and compactness, chord-length shape features have received relatively little attention in the human action recognition literature. In this paper, we present a new approach for human activity recognition, based on chord-length shape features. The most interesting contribution of this paper is twofold. We first show how a compact, computationally efficient shape descriptor; the chord-length shape features are constructed using 1-D chord-length functions. Second, we unfold how to use fuzzy membership functions to partition action snippets into a number of temporal states. On two benchmark action datasets (KTH and WEIZMANN), the approach yields promising results that compare favorably with those previously reported in the literature, while maintaining real-time performance.

NULL