1:00, IMDSP-P4.1
A NEW CONSTRAINT FOR THE REGULARIZED ENHANCEMENT OF COMPRESSED VIDEO
C. SEGALL, A. KATSAGGELOS
A novel fidelity constraint to the image enhancement problem is presented. With this constraint, we exploit the motion vectors of a compressed video bit-stream. These vectors establish a correspondence between image pixels across a series of frames, and we guarantee that processing the decoded sequence does not violate this correspondence. We develop the constraint within the context of MPEG-2 and incorporate the constraint into a regularized enhancement algorithm. Simulations are then performed. Quantitative and qualitative results illustrate an improvement in visual quality.

1:00, IMDSP-P4.2
IMAGE ENHANCEMENT USING MULTISCALE DIFFERENTIAL OPERATORS
Y. WANG, Q. WU, K. CASTLEMAN, Z. XIONG
Differential operators have been widely used for multiscale geometric descriptions of images. The efficient computation of these differential operators is available by taking advantage of the spline techniques. In this paper, we make use of a special class of these operators for image enhancement, with a particular application to chromosome image enhancement. These operators constitute a translation invariant wavelet transform well suited for the structural description of the chromosome geometry. Based on the fact that the geometrical features like edges are correlated between different scales in the representation, a novel algorithm is designed to enhance the salient features of the image. Comparisons of this algorithm with other approaches are given.

1:00, IMDSP-P4.3
IMAGE INTERPOLATION USING ACROSS-SCALE PIXEL CORRELATION
T. CHEN, H. WU, B. QIU
In this paper, a novel method is proposed for image interpolation. It is assumed that the pixel correlation between local regions across scales would remain similar. In addition, this a priori similarity could be extracted from a set of available image data that have the same content but different resolutions. A simple architecture is devised to estimate the correlation efficiently, which is then used to predict the unknown pixel values in a high-resolution image. Evaluation shows a promising performance of the proposed algorithm.

1:00, IMDSP-P4.4
NONLINEAR SMOOTHING FILTER USING ADAPTIVE RADIAL CLUSTERING.
I. GU, V. GUI
A novel adaptive nonlinear filter is proposed aimed at smoothing homogenous regions while maintaining image structures. The filter can be utilized as a pre-processing tool in image segmentation and edge estimation for improving the results. Several special features are introduced to the filter, including using local adaptive radial clustering and pixel filtering to exclude the influence of outliers and to maintain image structures; using steepest-descent method to iteratively update pixels to the nearest clusters obtained by mean-shift; and introducing highly parallel processing by using random seed samples and their associated data blocks which enables fast processing and the global optimum solution of the nonlinear filter. Experiments were done on images of various complexities, and good results were obtained. Evaluations of the filter were also done in terms of edge preserving and image segmentation.

1:00, IMDSP-P4.5
EDGE-PRESERVING IMAGE RESIZING USING MODIFIED B-SPLINES
A. GOTCHEV, K. EGIAZARIAN, J. VESMA, T. SARAMÄKI
A method for image resizing (decimation and interpolation) is proposed in the present paper. The decimation is considered as an orthogonal projection with respect to the chosen interpolation basis. The latter is formed in a spline-like manner as a linear combination of B-splines of different degrees. The combination is optimized in such a way that preserves the small image details. Considering the strongest edges as step edges, a segmentation procedure preceding the decimation, is proposed. It leads to resized images with clearly outlined borders.

1:00, IMDSP-P4.6
ADAPTIVE WINDOW SIZE IMAGE DENOISING BASED ON ICI RULE
K. EGIAZARIAN, V. KATKOVNIK, J. ASTOLA
An algorithm for image noise-removal based on local adaptive window size filtering is developed in this paper. Two features to use into local spatial/transform-domain filtering are suggested. First, filtering is performed on images corrupted not only by additive white noise, but also by image-dependent (e.g. film-grain noise) or multiplicative noise. Second, used transforms are equipped with a varying adaptive window size obtained by the intersection of confidence intervals (ICI) rule. Finally, we combine all estimates available for each pixel from neighboring overlapping windows by weighted averaging these estimates. Comparison of the algorithm with the known techniques for noise removal from images shows the advantage of the new algorithm, both quantitatively and visually.

1:00, IMDSP-P4.7
INTERPOLATION OF SCRATCHES IN MOTION PICTURE FILMS
T. BRETSCHNEIDER, C. MILLER, O. KAO
Movie films are often damaged through ageing, chemical changes and contact with mechanical parts of a film projector. In this paper a method for the removal of scratches and un-de-sirable lines in digitised film sequences is discussed. The method assumes the prior knowledge about the position and orientation of the scratches and utilises an iterative method to interpolate the affected pixels. The convergence of the algorithm is guaranteed for the noise free case and the optimal choice of the involved relaxation parameter is demonstrated. The method was validated using sampled movies and proved to be stable even in the pres-ence of noise. Remarkable is the reconstruction result in com-parison to standard interpolation techniques like cubic splines.

1:00, IMDSP-P4.8
NONLINEAR CUMULANT BASED ADAPTIVE FILTER FOR SIMULTANEOUS REMOVAL OF GAUSSIAN AND IMPULSIVE NOIESES IN IMAGES
H. IBRAHIM, R. GHARIEB, A. IBRAHIM
This paper presents an edge-preserving higher order statistics (HOS) based filter called Nonlinear Cumulant Based Adaptive Filter (NCBAF)for noise suppression in images. The NCBAF algorithm combines the linear (Averging) characteristics of the Two-Dimensional Cumulant Based Adaptive Enhancer (2DCBAE) and the nonlinear characteristics of the median filter. The proposed algorithm allows the simultaneous removal of impulsive and Gaussian noise types in images, processed in a single filtering pass. The performance of the proposed method is compared to the commonly used median filter and the 2DCBAE.

1:00, IMDSP-P4.9
SUPPRESSION OF ATMOSPHERIC TURBULENCE IN VIDEO USING AN ADAPTIVE CONTROL GRID INTERPOLATION APPROACH
D. FRAKES, J. MONACO, M. SMITH
Atmospheric turbulence is a naturally occurring phenomenon that can severely limit the resolution of long distance optical and infrared sensors. Because atmospheric turbulence can degrade the appearance of video captured by these sensors, many of which are already deployed in the field, there is much interest in employing enhancement/restoration processing to improve data quality after acquisition. This paper presents a signal processing approach to suppressing atmospheric turbulence effects in sensor video using an adaptive control grid interpolation method. In this method a dense dynamic motion vector field is derived from the characteristics of the atmospheric turbulence as seen in the data. The vector field is used in turn as part of the distortion compensation process, while preserving naturally occurring motion, such as that associated with the movement of objects within the scene. The resulting algorithm is shown to produce enhanced video with quality significantly higher than that of the original.

1:00, IMDSP-P4.10
SPATIAL AND TEMPORAL FILTERING IN A LOW-COST MPEG BIT-RATE TRANSCODER
A. MOREL, A. BOURGE
The MPEG bit-rate transcoder with motion compensation, MC-BRT, that exactly derives from a simplified synchronized decoder/encoder cascade, is considered. Such a transcoder is cost effective but lacks features such as spatial and temporal filtering. These features are known to improve the encoder performance at low bit-rates reducing quantization artifacts. Such features would be highly desirable in the MC-BRT since most applications now involve critical bit-rates. This paper shows that spatial and motion compensated temporal filtering can be implemented in the MC-BRT at a negligible cost. The filters are analyzed and control variables are given. Simulations reveal the efficiency of the method in terms of noise reduction as well as its great impact on image quality.

1:00, IMDSP-P4.11
SPACE-SCALE ADAPTIVE NOISE REDUCTION IN IMAGES BASED ON THRESHOLDING NEURAL NETWORK
X. ZHANG
Noise reduction has been a traditional problem in image processing. Recent wavelet thresholding based denoising methods proved promising, since they are capable of suppressing noise while maintaining the high frequency signal details. However, the local space-scale information of the image is not adaptively considered by standard wavelet thresholding methods. In this paper, a new type of thresholding neural networks (TNN) is presented with a new class of smooth nonlinear thresholding functions being the activation function. Unlike the standard soft-thresholding function, these new nonlinear thresholding functions are infinitely differentiable. Then a new nonlinear 2-D space-scale adaptive filtering method based on the wavelet TNN is presented for noise reduction in images. The numerical results indicate that the new method outperforms the Wiener filter and the standard wavelet thresholding denoising method in both peak-signal-to-noise-ratio (PSNR) and visual effect.