Stefano Fioravanti

A multifractal-based approach to natural scene analysis

An approach to natural surface analysis and characterization that is based on multifractals is presented. Such an approach presents many interesting peculiarities in the extraction of textural features from an image. A new method to compute such features is suggested, together with their use in the image segmentation process. Comparative results on SAR (synthetic aperture radar) images, by applying a data-fusion segmentation module, are presented and discussed.<<ETX>>

DCRVQ: a new strategy for efficient entropy coding of vector-quantized images

This paper presents a novel predictive coding scheme for image-data compression by vector quantization (VQ). On the basis of a prediction, further compression is achieved by using a dynamic codebook-reordering strategy that allows a more efficient Huffman encoding of vector addresses. The proposed method is lossless, for it increases the compression performances of a baseline vector quantization scheme, without causing any further image degradation. Results are presented and a comparison with Cache-VQ is made.

Morphological analysis of textured images for identification of thin structures

The paper addresses the problem of a real time approach for thin structures identification. The proposed method make use of adaptive morphological operators in which the normal textural properties are brought to bear on the filter design in order to enhance the output related to anomalous structures. The authors discuss how the introduction of adaptivity criteria is useful to reduce the sensitivity of morphological filtering to local variations typical of textures and to noise. In addition, theoretical investigations related to the problem of the optimization algorithm are presented and discussed. Experimental results have been carried out both on classical natural textures and on ceramic tile images and prove the efficiency of the proposed approach in many practical applications.

Spectral and rank order approaches to texture analysis

There are two major approaches to texture analysis, both supported by physiological evidence: those based on the spatial statistics, and those based on its spectral properties. One of the most sophisticated spectral approaches to texture is that based on the Wigner distribution where the attributes computed for each pixel encapsulate both the local spectral and phase properties of the local Fourier transform in a unique real spectrum. On the other hand, some of the most efficient methods which operate in the spatial domain alone, are those based on rank order functions. Before one embarks on the use of the sophisticated methods, it is worth exploring the efficient ones to the limit of their performance. In this paper we investigate these two major approaches and compare their performance both in terms of quality of results and efficiency. The problem we consider is that of detecting defective blobs and cracks on complex textural backgrounds. We show that in most cases rank order approaches can perform well, although no unique method can be employed for both types of defects. On the other hand, the Wigner approach with a very small modification can cope with both types of defects and handle even the identification of very subtle cracks. Thus, it seems that for any real time performance inspection system, the rank order approaches should form the front end with the more sophisticated methods coming in play when necessary.

SAR image filtering using wavelet transform

This paper presents a novel multiresolution wavelet-based algorithm for filtering SAR images in order to remove speckle noise. The basic idea is to apply to the wavelet coefficients a size-decreasing half-interpolated median filter. The size of the median filter is adapted to the noise energy reduction between the image pyramid levels and different filter shapes are used in each wavelet subbands according to the dominant frequencies. Experimental results showed, that the proposed algorithm results in significant noise removal while the edges are preserved in the images.

An edge-based splitting criterion for adaptive transform coding

A novel splitting strategy for variable block-size image coding based on edge information is presented, which makes it possible to reduce the number of blocks to be encoded while maintaining an in-depth split in edge areas. This approach has been applied to a standard transform coding algorithm, and results have been compared with those obtained by a classical splitting structure. Tests showed a notable increase in the compression factor under the same SNR conditions. Reconstructed images are affected by the blocking effect to a smaller extent, as the problem of generating a large number of small blocks in the uniform areas surrounding an edge is overcome by the proposed split topology.<<ETX>>

Adaptive image coding using multilayer neural networks

A data compression technique based on neural networks is presented. The schema consists of multiple multilayer perceptron networks, which produce a transformation of the original image with a reduced redundancy. A perceptron with a hidden layer is used; the input and output layers have the same number of nodes, while in the middle the number is reduced, thus producing a data compression of the original information. The transformation is carried out by the neural networks in an adaptive way. A split segmentation, based on spatial activities of regions, is applied to the original image in order to locate uniform blocks. A higher ratio between the input and the hidden nodes is used with large blocks and a lower one with smaller blocks; details are then retained in a good way. Major advantages of the proposed approach lie in its good performance, even with images outside the training set.<<ETX>>

ON COMPUTING MULTIFRACTALITY FOR TEXTURE DISCRIMINATION

A methodology for texture analysis and discrimination is presented. A technique, based on the estimation of the multifractal features of a surface, i.e., the, function D(q) of each texture patch, has been developed and is described. Its, performances are reported, both on synthetic and real Brodatz textures.

Texture representation through multifractal analysis of optical mass distributions

The paper addresses the analysis of singular distributions defined on a fractal support, called fractal measures. In general, a fractal measure has an infinite number of singularities of infinitely many types. The term multifractals expresses the fact that points, corresponding to a given type of singularity, typically form a fractal subset whose dimensions depend on the type of singularity. The theory of the q-th order generalized fractal dimensions supplies a tool for the characterization of such multifractal measures. This theory results from an extension of the fractal dimension to different-order statistics. The paper exploits such concepts in order to face the problem of texture recognition. In particular the fractal measure taken into account is the 2D distribution of the optical mass of an image; some theoretical aspects related to this problem are addressed. Results on real images are presented and discussed.

An efficient neural prediction for vector quantization

A novel predictive coding scheme for VQ is presented, called dynamic codebook reordering VQ (DCRVQ). Residual correlations between neighboring codevectors are exploited by a nonlinear prediction, that is a neural one. As a matter of fact, on the basis of the previously decoded codevectors, a multilayer neural network makes a prediction, and this result is used to reorganize the codebook in a dynamic way. This allows for efficient Huffman compression of codevector addresses after reordering.<<ETX>>