A Study on Deep Learning Techniques for Digital Image Processing

Deep Learning models are more appropriate for image processing jobs because they utilize neural networks, which are significantly more accurate and reliable. Furthermore, we observed that machine learning algorithms perform far better on data-driven sets than on big, complicated datasets. We also explored  the several stages involved in deep learning techniques for image processing. By examining specific phases and layers, we discovered why DL is far more accurate in nature.  We may discover more resources and opportunities to learn more about the topic as time goes on because the field is always evolving.  

1.                Rao, Kschandra & Srinivas, Y & Krishna, M. (2020). Study on image processing using deep learning techniques. Materials Today: Proceedings. 10.1016/j.matpr.2020.09.536. 2.                I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016. 3.                A. Krizhevsky, I. Sutskever, G. Hinton, ImageNet classification with deep volutional neural networks, NIPS (2012). 4.                J. Deng, A. Berg, S. Satheesh, H. Su, A. Khosla, and L. FeiFei. ImageNet Large Scale Visual Recognition Competition 2012 (ILSVRC2012). 5.                S. Ren, K. He, R. Girshick, J. Sun, Faster r-cnn: Towards real-time object detection with region proposal networks, NIPS (2015). 6.                M. A. Abbas, ‘‘Improving deep learning performance using random forest HTM cortical learning algorithm,” 2018 First International Workshop on Deep and Representation Learning (IWDRL), Cairo, 2018, pp. 13-18. 7.                J. Wu, Yinan Yu, Chang Huang and Kai Yu, ‘‘Deep multiple instances learning for image classification and auto-annotation,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, 2015, pp. 3460-3469. 8.                L. Shao, D. Wu, X. Li, Learning Deep and Wide: A Spectral Method for Learning Deep Networks, IEEE Transactions on Neural Networks and Learning Systems 25 (12) (Dec. 2014) 2303–2308. 9.                K. Nguyen, C. Fookes and S. Sridharan, ‘‘Improving deep convolutional neural networks with unsupervised feature learning,” 2015 IEEE International Conference on Image Processing (ICIP), Quebec City, QC, 2015, pp. 2270-2274. 10.             Y. Wang, ‘‘Deep reasoning and thinking beyond deep learning by cognitive robots and brain-inspired systems,” 2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC), Palo Alto, CA, 2016, pp. 3-3.