A Stereo Matching Algorithm based on Genetic Algorithm with Propagation Stratagem

Zhang, Zhuoyun; Hou, Chunping; Yang, Jiachen

doi:10.1109/iwisa.2009.5072678

Cited by 6 publications

(5 citation statements)

References 12 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A. Genetic Algorithm Holland J. in 1975 gives the idea ofGenetic algorithm which isworked on the theory of evolution [5].Population is the method of genetic algorithm [6]. In the search space each particle is giving a solution in the population which is encoded as chromosome and the algorithm will repeat the step to calculate the fitness of each particle and choose the particle with good result as the parents of next generation,now the two process which are known as crossover andmutation are performed to reproduce the next generation.…”

Section: Different Soft Computing Techniquesmentioning

confidence: 99%

Edge Detection of Different Images using Soft Computing Techniques

Dagar¹,

Dahiya²

2019

IJRTE

View full text Add to dashboard Cite

The technique by which an image or photograph is divided into several number of parts in order to analyze the segmented components such as colors, textures grey scale and edges/boundaries of the entities which are present in the image is called as image segmentations. Images obtained by segmentation methods are more understandable as compared to the original images. In the digital snap shot segmentation is essentially used to detect object boundaries present in the image. The paper presents the comparative analysis of image segmentation using soft computing methods.In this paper, we included genetic algorithm, ant colony algorithm, neural network, neuro-fuzzy genetic and adaptive neuro-fuzzy inference system. The techniques are tested on six standard test images. The peak signal to noise ratio (PSNR)is calculated for GA and ACO techniques. The results which are obtained by the above techniques prove that the value of PSNR for GA is much more as compared to the ACO technique

show abstract

Section: Different Soft Computing Techniquesmentioning

confidence: 99%

Edge Detection of Different Images using Soft Computing Techniques

Dagar¹,

Dahiya²

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…Recently, (Dai et al, 2008) use an adaptive crossover and mutation while their fitness function do not include any smoothing term. Finally, (Zhang et al, 2009) use a pyramidal propagation stratagem for solution representation and (Nie et al, 2009) implement a stereo correspondence genetic algorithm in GPU for performance enhancement. Genetic algorithms have also been used for matching sparse features, for instance in (Issa et al, 2002) a genetic algorithm is employed to match edges.…”

Section: Genetic Algorithms In Stereomentioning

confidence: 99%

Genetic Algorithm for Stereo Correspondence with a Novel Fitness Function and Occlusion Handling

Arranz

Sánchez-Miralles

Boal

et al. 2013

Proceedings of the International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

This paper proposes a genetic algorithm for solving the stereo correspondence problem. Applied to stereo, genetic algorithms are flexible in the cost function and permit global reasoning. The main contribution of this paper is a new crossover and a mutation operator which accounts for occlusion management and a new fitness function which considers occluded pixels and photometric derivatives. Both left and right disparity images are analysed in order to classify occluded pixels correctly. The proposed fitness function is compared to the traditional energy function based in the framework of the Markov Random Fields. The results show that a 32% bad-pixel error reduction can be achieved on average using the proposed fitness function. The results have been uploaded to the Middlebury ranking webpage, as the first evolutionary algorithm evaluated.

show abstract

“…GA is applied in a variety of significant problems, such as customizable FPGA IP core, the traveling salesman problem, network routing problems, stereo matching and clustering data [12][13][14][15]. The GA has four steps as follows:…”

Section: Genetic Algorithmmentioning

confidence: 99%

An Improved Signal Segmentation Method using Genetic Algorithm

Azami¹,

Mohammadi²,

Hassanpour³

2011

IJCA

View full text Add to dashboard Cite

In many signal processing application, the signal of interest is often divided into epochs. In these applications, the segmented signal is preferred to have no change on the statistical characteristics of the epochs. Modified Varri is among the segmentation methods with an acceptable accuracy. There are three parameters affecting on the accuracy of this method. These parameters are set experimentally. Hence, they may not be optimal for any signal segmentation application. We have used Genetic Algorithm (GA) in this research to choose appropriate values for these parameters in any signal segmentation application. The proposed technique was applied on both synthetic signal and Electroencephalography (EEG) to evaluate its performance. The results indicate superiority of the proposed method in signal segmentation compared to the original approach.

show abstract

A Stereo Matching Algorithm based on Genetic Algorithm with Propagation Stratagem

Cited by 6 publications

References 12 publications

Edge Detection of Different Images using Soft Computing Techniques

Edge Detection of Different Images using Soft Computing Techniques

Genetic Algorithm for Stereo Correspondence with a Novel Fitness Function and Occlusion Handling

An Improved Signal Segmentation Method using Genetic Algorithm

Contact Info

Product

Resources

About