Discovery of Human-Competitive Image Texture Feature Extraction Programs Using Genetic Programming

Lam, Brian T.; Ciesielski, Victor

doi:10.1007/978-3-540-24855-2_121

Cited by 19 publications

(23 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It incorporates implementation of Fourier and wavelet transforms, along with a covariance matrix and statistical momentum as features. (Further relevant details can be found in [22], [6], [17], [1], [3], [23], [5], [7], [10], [12], [31], [24], [19]. )…”

Section: A Past Workmentioning

confidence: 99%

Painter classification using genetic algorithms

Levy

David

Netanyahu

2013

2013 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

Abstract-This paper describes the problem of painter classification. We propose solving the problem by using genetic algorithms, which yields very promising results. The proposed methodology combines dimensionality reduction (via image preprocessing) and evolutionary computation techniques, by representing preprocessed data as a chromosome for a genetic algorithm (GA). The preprocessing of our scheme incorporates a diverse set of complex features (e.g., fractal dimension, Fourier spectra coefficients, and texture). The training phase of the GA employs a weighted nearest neighbor (NN) algorithm. We provide initial promising results for the 2-and 3-class cases, which offer significant improvement in comparison to a standard nearest neighbor classifier.

show abstract

Section: A Past Workmentioning

confidence: 99%

Painter classification using genetic algorithms

Levy

David

Netanyahu

2013

2013 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…Aurnhammer [23] and Lam et al [24] described the use of genetic programming to generate texture features and reported very promising results on image classification problems. Li et al [25] proposed a hybrid of a co-evolutionary genetic programming and expectation maximisation algorithm applied on partially labelled data.…”

Section: Evolutionary Feature Synthesismentioning

confidence: 99%

Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis

Ballerini

Fisher

et al. 2010

Applications of Evolutionary Computation

View full text Add to dashboard Cite

Abstract. This paper gives an example of evolved features that improve image retrieval performance. A content-based image retrieval system for skin lesion images is presented. The aim is to support decision making by retrieving and displaying relevant past cases visually similar to the one under examination. Skin lesions of five common classes, including two non-melanoma cancer types, are used. Colour and texture features are extracted from lesions. Evolutionary algorithms are used to create composite features that optimise a similarity matching function. Experiments on our database of 533 images are performed and results are compared to those obtained using simple features. The use of the evolved composite features improves the precision by about 7%.

show abstract

“…features to evolve the classification rules [7]. Inspired by the psycho visual study, multi-scale processing Keywords -Classification, Genetic Programming, Texture is a promising way to deal with texture analysis.…”

mentioning

confidence: 99%

A Genetic Programming Approach for Classification of Textures Based on Wavelet Analysis

Chen

2007

2007 IEEE International Symposium on Intelligent Signal Processing

View full text Add to dashboard Cite

-In this paper, we propose a method for classifying Fractal Models, not only describe texture but also synthesize it textures using Genetic Programming (GP). Texture features are using a specific model. extracted from the energy of subimages of the wavelet Genetic Programming (GP) [4], which is an evolutionary decomposition. The GP is then used to evolve rules, which are method that lends itself naturally to the development of arithmetic combinations of energy features, to identify whether a program with the ability of automatically constructing texture image belongs to certain class. Instead of using only one rule to discriminate the samples, a set of rules are used to vappropriate structures for the solution as well as selectig the perform the prediction by applying the majority voting variables, has been applied to extract features from textures in technique. In our experiment results based on Brodatz dataset, the past. A GP method iS proposed based on raw pixel data the proposed method has achieved 99.6% test accuracy on an using dynamic range selection [5][6]. Gray level histogram, average. In addition, the experiment results also show that which is reported to outperform raw pixel features in the classification rules generated by this approach are robust to some cluster accuracy and convergence speed, is also used as noises on textures.features to evolve the classification rules [7].

show abstract

Discovery of Human-Competitive Image Texture Feature Extraction Programs Using Genetic Programming

Cited by 19 publications

References 11 publications

Painter classification using genetic algorithms

Painter classification using genetic algorithms

Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis

A Genetic Programming Approach for Classification of Textures Based on Wavelet Analysis

Contact Info

Product

Resources

About