Measuring the Effect of Data Augmentation Methods for Improving the Success of Convolutional Neural Network

With the intensive work done, deep learning finds many use areas. However, obtaining a sufficient amount of data required by deep learning is not always an easy task. To overcome this difficulty, deep network trainers prefer to develop their datasets by using a set of algorithms. With the increased amount of data, deep networks can be trained more successfully. Data augmentation (DA) is one of the most widely used methods of increasing the amount of data. With DA, the number of sounds and images that a convolutional neural network (CNN) can classify can be increased. In this study, the number of images belonging to 6 classes that do not have enough images to train the CNN successfully enough was increased by DA methods. First, the amount of data was increased by applying three different DA methods separately and all three together. The original dataset and created datasets in which DA methods were used are used to train 15 CNNs with different parameters. Then, their effects on CNN have been investigated. As a result, a success increase of over 5% was observed by increasing the data.

Anahtar Kelimeler:

Classification rate, Convolutional Neural Network, Data augmentation, Deep learning

PDF

___

Reference1 Y. Q. Lv, K. Liu, F. Cheng, and W. Li, “Visual tracking with tree-structured appearance model for online learning,” Iet Image Processing, vol. 13, no. 12, pp. 2106–2115, 2019, doi: 10.1049/iet-ipr.2018.6517.
Reference2 F. Özyurt, T. Tuncer, E. Avci, M. Koç, and İ. Serhatlioğlu, “A novel liver image classification method using perceptual hash-based convolutional neural network,” Arabian Journal for Science and Engineering, vol. 44, no. 4, pp. 3173–3182, 2019.
Reference3 L. Perez and J. Wang, “The effectiveness of data augmentation in image classification using deep learning,” arXiv preprint arXiv:1712.04621, 2017.
Reference4 Q. Lin et al., “Classifying functional nuclear images with convolutional neural networks: a survey,” IET Image Processing, vol. 14, no. 14, pp. 3300–3313, 2020.
Reference5 H. Alhichri, Y. Bazi, and N. Alajlan, “Assisting the Visually Impaired in Multi-object Scene Description Using OWA-Based Fusion of CNN Models,” Arabian Journal for Science and Engineering, vol. 45, no. 12, pp. 10511–10527, 2020.
Reference6 A. Khémiri, A. K. Echi, and M. Elloumi, “Bayesian versus convolutional networks for Arabic handwriting recognition,” Arabian Journal for Science and Engineering, vol. 44, no. 11, pp. 9301–9319, 2019.
Reference7 F. Zhou, Y. Hu, and X. Shen, “MSANet: multimodal self-augmentation and adversarial network for RGB-D object recognition,” The Visual Computer, vol. 35, no. 11, pp. 1583–1594, 2019.
Reference8 A. Fawzi, H. Samulowitz, D. Turaga, and P. Frossard, “Adaptive data augmentation for image classification,” in 2016 IEEE international conference on image processing (ICIP), 2016, pp. 3688–3692.
Reference9 D. A. Van Dyk and X.-L. Meng, “The art of data augmentation,” Journal of Computational and Graphical Statistics, vol. 10, no. 1, pp. 1–50, 2001.
Reference10 C. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, no. 1, pp. 1–48, 2019.
Reference11 Y. LeCun et al., “Handwritten digit recognition with a back-propagation network,” Advances in neural information processing systems, vol. 2, 1989.
Reference12 C. Affonso, A. L. D. Rossi, F. H. A. Vieira, and A. C. P. de Leon Ferreira, “Deep learning for biological image classification,” Expert Systems with Applications, vol. 85, pp. 114–122, 2017.
Reference13 A. Arora, P. Chakraborty, and M. P. S. Bhatia, “Analysis of Data from Wearable Sensors for Sleep Quality Estimation and Prediction Using Deep Learning,” Arabian Journal for Science and Engineering, vol. 45, no. 12, pp. 10793–10812, 2020.
Reference14 X. Jiang, S. C. Satapathy, L. Yang, S.-H. Wang, and Y.-D. Zhang, “A Survey on Artificial Intelligence in Chinese Sign Language Recognition,” Arabian Journal for Science and Engineering, pp. 1–36, 2020.