Preprocessing for image classification by convolutional neural networks
Published in 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), 2016
Recommended citation: K. K. Pal and K. S. Sudeep, 'Preprocessing for image classification by convolutional neural networks', 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), Bangalore, 2016, pp. 1778-1781. doi: 10.1109/RTEICT.2016.7808140 https://ieeexplore.ieee.org/document/7808140
Abstract
In recent times, the Convolutional Neural Networks have become the most powerful method for image classification. Various researchers have shown the importance of network architecture in achieving better performances by making changes in different layers of the network. Some have shown the importance of the neuron’s activation by using various types of activation functions. But here we have shown the importance of preprocessing techniques for image classification using the CIFAR10 dataset and three variations of the Convolutional Neural Network. The results that we have achieved, clearly shows that the Zero Component Analysis(ZCA) outperforms both the Mean Normalization and Standardization techniques for all the three networks and thus it is the most important preprocessing technique for image classification with Convolutional Neural Networks.