A discrete denoising algorithm estimates the input sequence to a discrete memoryless channel (DMC) based on the observation of the entire output sequence. For the case in which the DMC is known and the quality of the reconstruction is evaluated with a given single-letter fidelity criterion, we propose a discrete denoising algorithm that does not assume knowledge of statistical properties of the input sequence. Yet, the algorithm is universal in the sense of asymptotically performing as well as the optimum denoiser that knows the input sequence distribution, which is only assumed to be stationary and ergodic. Moreover, the algorithm is universal also in a semi-stochastic setting, in which the input is an individual sequence, and the randomness is due solely to the channel noise.

Abstract not found

The performance of unsupervised learning models for natural images is evaluated quantitatively by means of information theory. We estimate the gain in statistical independence (the multi-information reduction) achieved with independent component analysis (ICA), principal component analysis (PCA), zero-phase whitening, and predictive coding. Predictive coding is translated into the transform coding framework, where it can be characterized by the constraint of a triangular filter matrix. A randomly sampled whitening basis and the Haar wavelet are included into the comparison as well. The comparison of all these methods is carried out for different patch sizes, ranging from 2x2 to 16x16 pixels. In spite of large differences in the shape of the basis functions, we find only small differences in the multi-information between all decorrelation transforms (5% or less) for all patch sizes. Among the second-order methods, PCA is optimal for small patch sizes and predictive coding performs best for large patch sizes. The extra gain achieved with ICA is always less than 2%. In conclusion, the `edge filters‘ found with ICA lead only to a surprisingly small improvement in terms of its actual objective.

Abstract not found

(TO ACCOMMODATE DUPLEX PRINTING).

In this paper we present a new lossless image compression algorithm. To achieve the high compression speed we use a linear prediction, modified Golomb–Rice code family, and a very fast prediction error modeling method. We compare the algorithm experimentally with others for medical and natural continuous tone grayscale images of depths of up to 16 bits. Its results are especially good for big images, for natural images of high bit depths, and for noisy images. The average compression speed on Intel Xeon 3.06 GHz CPU is 47 MB/s. For big images the speed is over 60 MB/s, i.e., the algorithm needs less than 50 CPU cycles per byte of image. KEY WORDS: lossless image compression; predictive coding; adaptive modeling; medical imaging; Golomb–Rice codes 1

We present our new low-complexity compression algorithm for lossless coding of video sequences. This new coder produces better compression ratios than lossless compression of individual images by exploiting temporal as well as spatial and spectral redundancy. Key features of the coder are a pixel-neighborhood backward-adaptive temporal predictor, an intra-frame spatial predictor and a differential coding scheme of the spectral components. The residual error is entropy coded by a context-based arithmetic encoder. This new lossless video encoder outperforms state--of--the-- art lossless image compression techniques, enabling more efficient video storage and communications.

Abstract — In this paper, we propose a novel wavelet-based-CMAC (WCMAC) network for predictive image coding. The Gaussian functions of traditional CMAC are replaced by wavelet functions. In addition, properties and advantages of fuzzy TSK- model are used to modify the activation functions of CMAC for obtaining high approximation accuracy and convergent rate. The WCMAC is employed to predict differential pulse code modulation (DPCM) of image compression. The WCMAC predictor can not only have accurate prediction, but also rather study and adapt to various and constant changing data. Experimental results and comparisons with other state-of-the-art lossless predictors are given to highlight the advantages of the proposed approach. Index Terms—CMAC, wavelet, image compression, lossless image coding.

Abstract—Data compression is used operationally to reduce bandwidth and storage requirements. An efficient method for achieving lossless weather radar data compression is presented. The characteristics of the data are taken into account and the optical linear prediction is used for the PPI images in the weather radar data in the proposed method. The next PPI image is identical to the current one and a dramatic reduction in source entropy is achieved by using the prediction algorithm. Some lossless compression methods are used to compress the predicted data. Experimental results show that for the weather radar data, the method proposed in this paper outperforms the other methods.