Abstract
Many image-related operators, including image descriptors, filtering operators and pooling operators, can be employed as functions in GP to achieve effective feature learning. However, this has not been extensively investigated in GP due to the limitations of the current GP representations. This chapter proposes a new GP-based approach with a flexible program structure and a number of image-related operators for feature learning in image classification. In this new approach, a new program structure, a new function set with many image-related operators, a new terminal set are developed. The performance of the proposed approach is examined on 12 benchmark datasets, including seven datasets with a large number of instances, and compared with a large number of effective algorithms. An in-depth analysis is conducted to deeply analyse the proposed approach to understand why it can achieve good performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The training and test sets can be downloaded from http://www.iro.umontreal.ca/~lisa/twiki/bin/view.cgi/Public/PublicDatasets.
References
Al-Sahaf H, Song A, Neshatian K, Zhang M (2012) Two-tier genetic programming: towards raw pixel-based image classification. Expert Syst with Appl 39(16):12291–12301
Al-Sahaf H, Zhang M, Al-Sahaf A, Johnston M (2017) Keypoints detection and feature extraction: a dynamic genetic programming approach for evolving rotation-invariant texture image descriptors. IEEE Trans Evolu Comput 21(6):825–844
Atkins D, Neshatian K, Zhang M (2011) A domain independent genetic programming approach to automatic feature extraction for image classification. In: Proceedings of IEEE congress on evolutionary computation, pp 238–245
Bi Y, Xue B, Zhang M (2018) A gaussian filter-based feature learning approach using genetic programming to image classification. In: Proceedings of Australasian joint conference on artificial intelligence. Springer, pp 251–257
Bi Y, Xue B, Zhang M (2020) An effective feature learning approach using genetic programming with image descriptors for image classification [research frontier]. IEEE Comput Intell Mag 15(2):65–77
Bruna J, Mallat S (2013) Invariant scattering convolution networks. IEEE Trans Pattern Anal Mach Intell 35(8):1872–1886
Cai L, Zhu J, Zeng H, Chen J, Cai C, Ma KK (2018) Hog-assisted deep feature learning for pedestrian gender recognition. J Frankl Inst 355(4):1991–2008
Chan TH, Jia K, Gao S, Lu J, Zeng Z, Ma Y (2015) Pcanet: a simple deep learning baseline for image classification? IEEE Trans Image Process 24(12):5017–5032
Chollet F et al. (2015) Keras. https://keras.io
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 1:886–893
Fei-Fei L, Perona P (2005) A bayesian hierarchical model for learning natural scene categories. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2:524–531
Fortin FA, De Rainville FM, Gardner MA, Parizeau M, Gagné C (2012) DEAP: Evolutionary algorithms made easy. J Mach Learn Res 13(Jul):2171–2175
Hassaballah M, Abdelmgeid AA, Alshazly HA (2016) Image features detection, description and matching. In: Image feature detectors and descriptors. Springer, pp 11–45
Iqbal M, Xue B, Al-Sahaf H, Zhang M (2017) Cross-domain reuse of extracted knowledge in genetic programming for image classification. IEEE Trans Evolut Comput 21(4):569–587
Larochelle H, Erhan D, Courville A, Bergstra J, Bengio Y (2007) An empirical evaluation of deep architectures on problems with many factors of variation. In: Proceedings of the 24th International Conference on Machine Learning. ACM, pp 473–480
Li H, Gong M (2017) Self-paced convolutional neural networks. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp 2110–2116
Liu C, Wechsler H (2002) Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Trans Image Process 11(4):467–476
Liu L, Shao L, Li X, Lu K (2016) Learning spatio-temporal representations for action recognition: a genetic programming approach. IEEE Trans Cybernet 46(1):158–170
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Lvd Maaten, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9:2579–2605
Mallikarjuna P, Targhi AT, Fritz M, Hayman E, Caputo B, Eklundh JO (2006) The kth-tips2 database. Computational Vision and Active Perception Laboratory (CVAP), Stockholm, Sweden. http://www.nada.kth.se/cvap/databases/kth-tips
Montana DJ (1995) Strongly typed genetic programming. Evolut Comput 3(2):199–230
Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830
Qian G, Zhang L (2018) A simple feedforward convolutional conceptor neural network for classification. Appl Soft Comput 70:1034–1041
Rifai S, Vincent P, Muller X, Glorot X, Bengio Y (2011) Contractive auto-encoders: explicit invariance during feature extraction. In: Proceedings of international conference on machine learning. Omnipress, pp 833–840
Roberts ME (2003) The effectiveness of cost based subtree caching mechanisms in typed genetic programming for image segmentation. In: Proceedings of workshops on applications of evolutionary computation. Springer, pp 444–454
Samaria FS, Harter AC (1994) Parameterisation of a stochastic model for human face identification. In: Proceedings of 1994 IEEE workshop on applications of computer vision, pp 138–142
Shao L, Liu L, Li X (2014) Feature learning for image classification via multiobjective genetic programming. IEEE Trans Neural Netw Learn Syst 25(7):1359–1371
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Sun Y, Xue B, Zhang M, Yen GG (2019) Evolving deep convolutional neural networks for image classification. IEEE Trans Evolut Comput 24(2):1–14
Thomaz CE (2012) Fei face database. http://fei.edu.br/~cet/facedatabase.html
Vedaldi A, Fulkerson B (2010) Vlfeat: an open and portable library of computer vision algorithms. In: Proceedings of the 18th ACM international conference on multimedia, pp 1469–1472
Young S, Abdou T, Bener A (2018) Deep super learner: a deep ensemble for classification problems. In: Proceedings of Canadian conference on artificial intelligence. Springer, pp 84–95
Yu T, Guo C, Wang L, Xiang S, Pan C (2018) Self-paced autoencoder. IEEE Signal Process Lett 25(7):1054–1058
Zhou ZH, Feng J (2018) Deep forest. Natl Sci Rev 6(1):74–86
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Bi, Y., Xue, B., Zhang, M. (2021). GP with Image-Related Operators for Feature Learning. In: Genetic Programming for Image Classification. Adaptation, Learning, and Optimization, vol 24. Springer, Cham. https://doi.org/10.1007/978-3-030-65927-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-65927-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65926-4
Online ISBN: 978-3-030-65927-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)