Genetic Programming for Automatic Global and Local Feature Extraction to Image Classification

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@InProceedings{Bi:2018:CEC,

• author = "Ying Bi and Mengjie Zhang and Bing Xue",
• title = "Genetic Programming for Automatic Global and Local Feature Extraction to Image Classification",
• booktitle = "2018 IEEE Congress on Evolutionary Computation (CEC)",
• year = "2018",
• editor = "Marley Vellasco",
• address = "Rio de Janeiro, Brazil",
• month = "8-13 " # jul,
• publisher = "IEEE",
• keywords = "genetic algorithms, genetic programming",
• URL = "https://openaccess.wgtn.ac.nz/articles/conference_contribution/Genetic_Programming_for_Automatic_Global_and_Local_Feature_Extraction_to_Image_Classification/13884998",
• DOI = "doi:10.1109/CEC.2018.8477911",
• size = "8 pages",
• abstract = "Feature extraction is an essential process to image classification. Existing feature extraction methods can extract important and discriminative image features but often require domain expert and human intervention. Genetic Programming (GP) can automatically extract features which are more adaptive to different image classification tasks. However, the majority GP-based methods only extract relatively simple features of one type i.e. local or global, which are not effective and efficient for complex image classification. In this paper, a new GP method (GP-GLF) is proposed to achieve automatically and simultaneously global and local feature extraction to image classification. To extract discriminative image features, several effective and well-known feature extraction methods, such as HOG, SIFT and LBP, are employed as GP functions in global and local scenarios. A novel program structure is developed to allow GP-GLF to evolve descriptors that can synthesise feature vectors from the input image and the automatically detected regions using these functions. The performance of the proposed method is evaluated on four different image classification data sets of varying difficulty and compared with seven GP based methods and a set of non-GP methods. Experimental results show that the proposed method achieves significantly better or similar performance than almost all the peer methods. Further analysis on the evolved programs shows the good interpretability of the GP-GLF method.",
• notes = "WCCI2018",

}

Genetic Programming entries for Ying Bi Mengjie Zhang Bing Xue

Citations