Conference Paper

Space-color quantization of multispectral images in hierarchy of scales

Univ. of Montenegro, Podgorica
DOI: 10.1109/ICIP.2001.959195 Conference: Image Processing, 2001. Proceedings. 2001 International Conference on, Volume: 1
Source: IEEE Xplore

ABSTRACT

In this paper a novel model for multiscale space-color
quantization of multispectral images, is described. The approach is
based on the hierarchical clustering technique, derived from the
statistical physics model of free energy (Jovovic 1996, Jovovic et al.
1999). The group vectors for image color are computed on the adaptively
selected windows of computation, as contrasted to the block-size
windows, optimizing the accuracy of the computation of the group vectors
with the density of sampling an image by the group windows. The
algorithm is suitable for implementation in parallel computer
architectures. The results of quantization of color images by our
algorithm are compared with 3 image compression techniques: 1) wavelets,
2) discrete cosine transform (DCT), and, 3) quad tree (QT). Contextual
information of spatial coherency of the data is used in the segmentation
process, in our algorithm. As a result, much better spatial resolution
and small size of compressed images are obtained by our algorithm, as
compared to the other techniques, for any error level of compression
selected. Major spatial features are optimally color-coded along the
hierarchy of scales of computation. The images quantized with our
algorithm are suitable for the run-length encoding scheme of the
hierarchy of binary images

Download full-text

Full-text

Available from: Milan Jovovic
  • Source
    • "A multifractal model formalism is derived in the " Thalweg ARC. " project report [12], to explain the decomposition of image sequences into the singular data sets. The partition function describes the probabilistic model of data clusters and is analyzed as a multifractal measure in the method. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this report a multi-dimensional data scaling approach is proposed in data mining and knowledge discovery applications. We derive the method based on an analogy to the physical computation of signal distortion. A dynamical cascade computation diagrams result from the statistical physics model computation in the free energy decomposition. We assess the scale invariance of various data sets, such as with the image motion sequences, and with the high dimensional chemical data sets. Theoretical model of error propagation is given by the numerical computational schemes. Statistical mapping of the data is analyzed through dynamical cascades, as a way of approaching its coding and control data structure. We show how it correlates by segmenting set of chemical compounds observations in a high dimensional property space. The proposed algorithm, also, is suitable for the implementation in parallel computer architectures. An example implementation on the multicore processors is given in the end of this report. A multifractal model formalism is derived in the "Thalweg ARC." project report (12), to explain the decomposition of image sequences into the singular data sets. The partition function describes the probabilistic model of data clusters and is analyzed as a multifractal measure in the method. Singularity analysis of computational maps of clustering vectors is derived to describe the computational means of decomposing the image information into different singular sets. We show also that the propagation of information in image sequences is governed by the scale-space wave equation, therefore enabling us to treat singular frequencies of data clusters in an unified way, both in space and in time. Contextual information of the spatial coherency of data is used in the segmentation process in the hierarchical scale computation of feature vectors. The spatial segmentation of images is performed while using the Green's function, parameterized with the scale parameter, as the integration function in the segmentation process. The scale information is evaluated by conjoining the two parameters: the scale parameter β of the signal distortion, and the spatial scale parameter r. A larger extent of spatial integration of the motion information is used on a larger scale, while it becomes effectively more local in space as we decrease the scale of segmentation. Distinct singular features are segmented on a certain scale and the least singular feature become segmented in two spatial windows with the Laplacian system regularity constraints, in the hierarchical scale computation. Accordingly, the reconstruction formula is derived based on the Laplacian system of the diffusion of the residual information from the most singular sets. This gives us an effective way of compressing and progressive coding of the information in image sequences. The binary tree data structure of the clustering parameters is suitable in the coding schemes that use the hierarchical structure of the binary images of the spatial distribution of cluster windows, along with the feature vectors and residual image information that make up for the point feature vector estimation. We give here a derivation of the computational scheme for a 2- dimensional case, like in image sequences. We then consider a dynamical coupling and the energy exchange between 3 clusters computed. Corresponding statistical maps are analyzed w.r.t. the dimensionality of the eigenvalue decomposition of the clusters" covariances. The results are shown for the chemical compounds in the 155 properties dimensional data set. Projections along the most singular components are computed in 1 and dimensional statistical maps. 2. METHOD
    Full-text · Article · Jan 2007
  • Source
    • "is applied as in [12]. The 5th image in sequence is shown in figure 4 (a), for which the spectral singular sets are shown in 4 (b). "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we propose a method for image analysis, processing and coding, based on physical computation of signal distortion. A binary tree data structure of coupled system of data sets was initially proposed in [9, 10], derived from the statistical physics model of free energy. We assess the scale invariance, in the method, by hierarchically clustering data. Theoretical model of error propagation is given in such a computational scheme. This decomposition of image information is analyzed by multifractal model formalism. We study how it correlates with the convective structure in clouds, that is associated with rain. The results are shown for MeteoSat IR images, provided by Thalweg ARC. project. The regularity constraints of data are used in the hierarchical scale decomposition of images. Accordingly, the reconstruction formula is derived based on the Laplacian system of diffusion of the residual information from the most singular sets. This gives us an effective way of compressing and progressive coding of information in image sequences. The proposed algorithm, also, is suitable for the implementation in parallel computer architectures.
    Full-text · Article · Jan 2003
  • Source
    • "In fact, we want to incorporate color and spatial correlation information into the design of the transform in order to outperform a usual decorrelating transform such as the Karhunen-Love transform (KLT) across color planes [1]– [3]. We are concerned with color transforms and not as much with space-color transforms such as those in [4],[5] "
    [Show abstract] [Hide abstract]
    ABSTRACT: In the compression of color or multispectral imagery, intra pixel color transforms are usually employed to decorrelate planes. It is usually thought that plane decorrelation (such as provided by the Karhunen-Love transform (KLT)) may lead to higher compression. Spatial correlation, however, is usually not considered. We developed a method to devise a pixel-wise color transform that takes into account spatial correlation and outperforms the KLT. This is done by considering space-color correlation. We aim at decorrelating the data across color planes, but at correlating the data spatially, so that spatial transforms can more easily decorrelate each of the color planes. Experiment results are shown to demonstrate the gains of the propose transform.
    Preview · Conference Paper · Feb 2002
Show more