• Sonal Borase
• Dr. Anupama Deshpande
• Dr. Javed Shaikh

Convolutional Neural Network (CNN) is subset of artificial neural networks. It has become prominent in many computer vision applications. CNN is designed in such a way that it should learn automatically. Spatial hierarchies of features are used in algorithms through backpropagation by using multiple building blocks such as convolution layers, pooling layers, and fully connected layers. This article offers a perspective on the basic concepts of CNN and its applications in image processing domain. Convolution neural network have been successful in identifying faces, objects and traffic signs apart from powering vision in robots and self-driving cars. CNN provides a very exciting alternatives and other application which can play important role in today's computer science field. There are some Limitations also which are mentioned.

Artificial Neural Network, ANN, Convolutional Neural Network, CNN, LeNet-5 Structure, AlexNet Structure, VGG-16 Structure, Inception-v.

"Convolution Neural Networks in Image Processing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 7, page no.604-608, July-2020, Available :http://www.jetir.org/papers/JETIR2007071.pdf

"Convolution Neural Networks in Image Processing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 7, page no. pp604-608, July-2020, Available at : http://www.jetir.org/papers/JETIR2007071.pdf