CARTOON IMAGE RECOGNITION BASED ON TENSORFLOW DEEP LEARNING TECHNOLOGY

Jiang Xichun, Yao Yan, Shen Qi

The article is devoted to the consideration of the features of recognizing cartoon images on the basis of deep learning technology TensorFlow. In the process of research the distinctive features and capabilities of TensorFlow technology are outlined. Also formalized algorithm for recognizing images from cartoons on the basis of convolutional neural network. Separately described is the code that uses Python and TensorFlow to implement neural networks designed to recognize hand-drawn cartoon images. In addition, the paper summarizes the basic steps required for neural networks to recognize hand-drawn expressions.

Keywords:image, cartoon, deep learning, recognition, performance