Model-based image interpretation using genetic algorithms

doi:10.1016/0262-8856(92)90045-5

Image and Vision Computing

Volume 10, Issue 5, June 1992, Pages 295-300

https://doi.org/10.1016/0262-8856(92)90045-5 Get rights and content

Abstract

We describe the application of genetic algorithms in model-based image interpretation. The delineation of left ventricular boundaries in apical 4-chamber echocardiograms is used as an illustrative exemplar. The suitability of genetic algorithms for the modellobjective-function/search procedure is presented.

References (11)

H Yamada et al.
Recognition of echocardiograms by a dynamic programming matching method
Patt. Recogn.
(1991)
W.E.L. Grimson
Object Recognition by Computer: The Role of Geometric Constraints
(1990)
J.H. Holland
Adaptation in Natural and Artificial Systems
(1975)
L Davis
Genetic Algorithms and Simulated Annealing
(1987)
D.E. Goldberg
Genetic Algorithms in Search, Optimization and Machine Learning
(1989)

There are more references available in the full text version of this article.

Cited by (102)

A survey on image segmentation using metaheuristic-based deformable models: State of the art and critical analysis
2016, Applied Soft Computing Journal
Citation Excerpt :
Therefore, the entire algorithm can be viewed as a parallel simulated annealing with competition. In [170,171] a standard genetic algorithm is used to optimize shape models (using one-point crossover and bit string mutation). The remainder stochastic independent sampling algorithm [188] is used as selection operator.
Deformable models are segmentation techniques that adapt a curve with the goal of maximizing its overlap with the actual contour of an object of interest within an image. Such a process requires the definition of an optimization framework whose most critical issues include: choosing an optimization method which exhibits robustness with respect to noisy and highly-multimodal search spaces; selecting the optimization and segmentation algorithms’ parameters; choosing the representation for encoding prior knowledge on the image domain of interest; and initializing the curve in a location which favors its convergence onto the boundary of the object of interest.
All these problems are extensively discussed within this manuscript, with reference to the family of global stochastic optimization techniques that are generally termed metaheuristics, and are designed to solve complex optimization and machine learning problems. In particular, we present a complete study on the application of metaheuristics to image segmentation based on deformable models. This survey studies, analyzes and contextualizes the most notable and recent works on this topic, proposing an original categorization for these hybrid approaches. It aims to serve as a reference work which proposes some guidelines for choosing and designing the most appropriate combination of deformable models and metaheuristics when facing a given segmentation problem.
After recalling the principles underlying deformable models and metaheuristics, we broadly review the different hybrid approaches employed to solve image segmentation problems, and conclude with a general discussion about methodological and design issues as well as future research and application trends.
A morphological assessment system for 'show quality' bovine livestock based on image analysis
2011, Computers and Electronics in Agriculture
Morphological assessment is one important parameter considered in conservation and improvement programs for bovine livestock. This assessment process consists of scoring an animal based on its morphology and is normally carried out by highly qualified staff. These animals are all of agreed ‘show quality’ and hence they are morphologically very similar.
This paper presents a system designed to provide an assessment based on a lateral image of the cow. The system consists of two main parts: a feature extraction stage, to reduce the information on the cow in the image to a set of parameters, and a neural network stage to provide a score based on that set of parameters. For the image analysis section, a model of the animal is constructed by means of the point distribution model (PDM) technique. Later, that model is used in the searching process within each image, which is implemented using genetic algorithms (GAs). As a result of this stage, the vector of weights that describe the deviation of the given shape from the mean is obtained. This vector is used in the second stage, where a multilayer perceptron is trained to provide the desired assessment, using the scores given by experts for selected cows.
The system has been tested with 138 images corresponding to 44 individuals of a special rustic breed, with very promising results, given that the information contained in only one view of the cow can not be considered complete.
Hierarchical vibrations for part-based recognition of complex objects
2010, Pattern Recognition
Citation Excerpt :
Such deterministic approaches are of limited use if—as it is often the case—the solution space is of high dimensionality and/or non-convex, such that multiple local optima may be found. Our shape search therefore uses an evolutionary strategy, which is inspired by the genetic algorithm Hill and Taylor employed for model-based segmentation of medical data [40]. It combines aspects from [13,43,42] in a knowledge-driven model-fitting strategy, where randomness is introduced in the direction of the search using stochastic sampling.
We propose a technique for the recognition and segmentation of complex shapes in 2D images using a hierarchy of finite element vibration modes in an evolutionary shape search. The different levels of the shape hierarchy can influence each other, which can be exploited in top-down part-based image analysis. Our method overcomes drawbacks of existing structural approaches, which cannot uniformly encode shape variation and co-variation, or rely on training. We present results demonstrating that by utilizing a quality-of-fit function the model explicitly recognizes missing parts of a complex shape, thus allowing for categorization between shape classes.
Statistical shape models for 3D medical image segmentation: A review
2009, Medical Image Analysis
Citation Excerpt :
After several iterations/generations, the best-rated chromosome in the population is regarded as the final solution. Hill and Taylor (1992) were the first to employ genetic algorithms for the model-based segmentation of echocardiogram images, optimizing four pose and six shape parameters (all encoded in one chromosome) of a custom-built model. They also presented an extension called niches and species to the algorithm in order to detect several candidate shapes at once.
Statistical shape models (SSMs) have by now been firmly established as a robust tool for segmentation of medical images. While 2D models have been in use since the early 1990s, wide-spread utilization of three-dimensional models appeared only in recent years, primarily made possible by breakthroughs in automatic detection of shape correspondences. In this article, we review the techniques required to create and employ these 3D SSMs. While we concentrate on landmark-based shape representations and thoroughly examine the most popular variants of Active Shape and Active Appearance models, we also describe several alternative approaches to statistical shape modeling. Structured into the topics of shape representation, model construction, shape correspondence, local appearance models and search algorithms, we present an overview of the current state of the art in the field. We conclude with a survey of applications in the medical field and a discussion of future developments.
Tunneling descent for m.a.p. active contours in ultrasound segmentation
2007, Medical Image Analysis
Active contours that evolve in ultrasound images under gradient descent are often trapped in spurious local minima. This paper presents an evolution strategy called tunneling descent, which is capable of escaping from such minima. The key idea is to evolve the contour by a sequence of constrained minimizations that move the contour in to, and out of, local minima. This strategy is an extension of classical gradient descent.
Because tunneling descent does not terminate at a local minima an explicit stopping rule is required. Model-based and model-free stopping rules are presented and formulae for choosing the stopping threshold are given.
The algorithm is used to segment the endocardium in 44 short axis cardiac ultrasound images. The energy function of the active contour is derived from a m.a.p. formulation. All segmentations are achieved without tweaking either the energy function or numerical parameters. Experimental evaluation of the segmentations show that the algorithm overcomes multiple local minima to find the endocardium. The accuracy of the algorithm is comparable to that of manual segmentations and significantly better than classical gradient descent active contours. The sensitivity of the segmentation to initialization is also evaluated and it is shown that segmentations from quite different initializations are close to each other. Finally, some limitations of the m.a.p. formulation are discussed.
A distributed hierarchical genetic algorithm for efficient optimization and pattern matching
2007, Pattern Recognition
In this paper we propose a new approach in genetic algorithm called distributed hierarchical genetic algorithm (DHGA) for optimization and pattern matching. It is eventually a hybrid technique combining the advantages of both distributed and hierarchical processes in exploring the search space. The search is initially distributed over the space and then in each subspace the algorithm works in a hierarchical way. The entire space is essentially partitioned into a number of subspaces depending on the dimensionality of the space. This is done in order to spread the search process more evenly over the whole space. In each subspace the genetic algorithm is employed for searching and the search process advances from one hypercube to a neighboring hypercube hierarchically depending on the convergence status of the population and the solution obtained so far. The dimension of the hypercube and the resolution of the search space are altered with iterations. Thus the search process passes through variable resolution (coarse-to-fine) search space. Both analytical and empirical studies have been carried out to evaluate the performance between DHGA and distributed conventional GA (DCGA) for different function optimization problems. Further, the performance of the algorithms is demonstrated on problems like pattern matching and object matching with edge map.

View all citing articles on Scopus

View full text

Model-based image interpretation using genetic algorithms

Abstract

Patt. Recogn.

Object Recognition by Computer: The Role of Geometric Constraints

Adaptation in Natural and Artificial Systems

Genetic Algorithms and Simulated Annealing

Genetic Algorithms in Search, Optimization and Machine Learning