Results 1  10
of
12
Fast Non Rigid Matching by Gradient Descent: Study and Improvements of the "Demons" Algorithm
, 1999
"... Most iconic methods for rigid matching consist in finding and minimizing a registration criterion specifically chosen to solve a given problem. For nonrigid matching, attention has rather focussed on the type of smoothing or physical model of deformation to be used. In this report, we propose to pl ..."
Abstract

Cited by 27 (10 self)
 Add to MetaCart
Most iconic methods for rigid matching consist in finding and minimizing a registration criterion specifically chosen to solve a given problem. For nonrigid matching, attention has rather focussed on the type of smoothing or physical model of deformation to be used. In this report, we propose to place the nonrigid matching problem into a minimization framework. We have developped our theoretical idea in the case of the least squares criterion, corresponding to the assumption that the intensities of points do not change over time, and we have implemented a first order gradient descent which, along with a multiresolution approach, minimizes this criterion. We also prove that the idemonsj algorithm, thought of until now as an as hoc matching technique, can be seen as an approximation of a second order gradient descent on this criterion. Analysis of the mechanisms of this gradient descent incites us to introduce two different weightings into the filters used to smooth the solution, which we ca...
Compact Unstructured Representations for Evolutionary Topological Optimum Design
 APPLIED INTELLIGENCE
, 2002
"... This paper proposes a few steps to escape structured extensive representations for evolutionary solving of Topological Optimum Design (TOD) problems: early results have shown the ability of Evolutionary methods to find numerical solutions to yet unsolved TOD problems, but those approaches were l ..."
Abstract

Cited by 19 (6 self)
 Add to MetaCart
This paper proposes a few steps to escape structured extensive representations for evolutionary solving of Topological Optimum Design (TOD) problems: early results have shown the ability of Evolutionary methods to find numerical solutions to yet unsolved TOD problems, but those approaches were limited because the complexity of the representation was that of a fixed underlying mesh. Different compact unstructured representations are introduced, the complexity of which is selfadaptive, i.e. is evolved by the algorithm itself. The Voronoi based representations are variable length lists of alleles that are directly decoded into shapes, while the IFS representation, based on fractal theory, involves a much more complex morphogenetic process.
Individual GP: an Alternative Viewpoint for the Resolution of Complex Problems.
"... An unususal GP implementation is proposed, based on a more "economic" exploitation of the GP algorithm: the "individual" approach, where each individual of the population embodies a single function rather than a set of functions. The nal solution is then a set of individuals. Exa ..."
Abstract

Cited by 11 (5 self)
 Add to MetaCart
(Show Context)
An unususal GP implementation is proposed, based on a more "economic" exploitation of the GP algorithm: the "individual" approach, where each individual of the population embodies a single function rather than a set of functions. The nal solution is then a set of individuals. Examples are presented where results are obtained more rapidly than with the conventional approach, where all individuals of the nal generation but one are discarded.
Manipulation of nonlinear ifs attractors using genetic programming
 Congress on Evolutionary Computation (CEC'99
, 1999
"... Nonlinear Iterated Function Systems (IFSs) are very powerful mathematical objects related to fractal theory, that can be used in order to generate (or model) very irregular shapes. We investigate in this paper how Genetic Programming techniques can be efficiently exploited in order to generate rand ..."
Abstract

Cited by 7 (2 self)
 Add to MetaCart
(Show Context)
Nonlinear Iterated Function Systems (IFSs) are very powerful mathematical objects related to fractal theory, that can be used in order to generate (or model) very irregular shapes. We investigate in this paper how Genetic Programming techniques can be efficiently exploited in order to generate randomly or interactively artistic “fractal” 2D shapes. Two applications are presented for different types of nonlinear IFSs: interactive generation of Mixed IFSs attractors using a classical GP scheme, random generation of Polar IFSs attractors based on an “individual ” approach of GP. 1
Evolutionary lossless compression with GPzip
, 2008
"... In recent research we proposed GPzip, a system which uses evolution to find optimal ways to combine standard compression algorithms for the purpose of maximally losslessly compressing files and archives. The system divides files into blocks of predefined length. It then uses a linear, fixedlength ..."
Abstract

Cited by 6 (4 self)
 Add to MetaCart
In recent research we proposed GPzip, a system which uses evolution to find optimal ways to combine standard compression algorithms for the purpose of maximally losslessly compressing files and archives. The system divides files into blocks of predefined length. It then uses a linear, fixedlength representation where each primitive indicates what compression algorithm to use for a specific data block. GPzip worked well with heterogonous data sets, providing significant improvements in compression ratio compared to some of the best standard compression algorithms. In this paper we propose a substantial improvement, called GPzip*, which uses a new representation and intelligent crossover and mutation operators such that blocks of different sizes can be evolved. Like GPzip, GPzip * finds what the best compression technique to use for each block is. The compression algorithms available in the primitive set of GPzip* are: Arithmetic coding (AC), LempelZivWelch (LZW), Unbounded Prediction by Partial Matching (PPMD), Run Length Encoding (RLE), and Boolean Minimization. In addition, two transformation techniques are available: the BurrowsWheeler Transformation (BWT) and Move to Front (MTF). Results show that GPzip* provides improvements in compression ratio ranging from a fraction to several tens of percent over its predecessor.
Evolution of humancompetitive lossless compression algorithms with GPzip2
 GENET PROGRAM EVOLVABLE MACH
, 2011
"... We propose GPzip2, a new approach to lossless data compression based on Genetic Programming (GP). GP is used to optimally combine wellknown lossless compression algorithms to maximise data compression. GPzip2 evolves programs with multiple components. One component analyses statistical features ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
We propose GPzip2, a new approach to lossless data compression based on Genetic Programming (GP). GP is used to optimally combine wellknown lossless compression algorithms to maximise data compression. GPzip2 evolves programs with multiple components. One component analyses statistical features extracted by sequentially scanning the data to be compressed and divides the data into blocks. These blocks are projected onto a twodimensional Euclidean space via two further (evolved) program components. Kmeans clustering is then applied to group similar data blocks. Each cluster is labelled with the optimal compression algorithm for its member blocks. After evolution, evolved programs can be used to compress unseen data. The compression algorithms available to GPzip2 are: Arithmetic coding, LempelZivWelch, Unbounded Prediction by Partial Matching, Run Length Encoding, and Bzip2. Experimentation shows that the results produced by GPzip2 are humancompetitive, being typically superior to wellestablished humandesigned compression algorithms in terms of the compression ratios achieved in heterogeneous archive files.
Learning Markov Chains in Fractal Compression of Image Data
, 2001
"... In a recent paper ([17]) we proposed a stochastic algorithm which generates optimal probabilities for the decompression of an image represented by the xed point of an IFS system (SAOP). We show here that such an algorithm is in fact a non trivial example of Generalized Random System with Comple ..."
Abstract
 Add to MetaCart
(Show Context)
In a recent paper ([17]) we proposed a stochastic algorithm which generates optimal probabilities for the decompression of an image represented by the xed point of an IFS system (SAOP). We show here that such an algorithm is in fact a non trivial example of Generalized Random System with Complete Connections. We also exhibit a generalization which could represent the solution to the inverse problem for an image with grey levels, if a xed set of contraction maps is available.
A Stochastic Algorithm to Compute Optimal Probabilities in the ChaosGame
, 2001
"... We present a stochastic algorithm which generates optimal probabilities for the ChaosGame to decompress an image represented by the xed point of an IFS operator. The algorithm can be seen as a sort of time inhomogeneous rigenerative process. We prove that optimal probabilities exist and, by ma ..."
Abstract
 Add to MetaCart
(Show Context)
We present a stochastic algorithm which generates optimal probabilities for the ChaosGame to decompress an image represented by the xed point of an IFS operator. The algorithm can be seen as a sort of time inhomogeneous rigenerative process. We prove that optimal probabilities exist and, by martingale methods, that the algorithm converges almost surely. The method holds for IFS operators associated to any arbitrary number of possibly overlapping ane contraction maps on the pixels space.
Proposal of Some Stochastic Algorithms in Fractal Image Compression
, 2001
"... In this paper we review some recently proposed stochastic algorithms which compute optimal probabilities in generating images compressed by IFS or IFSP systems ([12], [13]). We also propose new algorithms, called selection algorithms, which in principle compress an arbitrary image with grey leve ..."
Abstract
 Add to MetaCart
(Show Context)
In this paper we review some recently proposed stochastic algorithms which compute optimal probabilities in generating images compressed by IFS or IFSP systems ([12], [13]). We also propose new algorithms, called selection algorithms, which in principle compress an arbitrary image with grey levels on the pixels space, by means of an IFSP system that is somehow optimal for a given random generator of ane contraction maps.