Recognition of Labels for Hand Drawn Images
Keywords:
Component, Formatting, Style, Styling, InsertAbstract
Freehand sketch drawings are highly abstract and sparse in structures. Due to the diversity, highly iconic and intra-class deformations of these sketches, automatic recognition is more a challenging task. This paper, sheds light on developing an efficient recognition scheme of freehand sketch, based on Convolutional Neural Networks (CNNs). Furthermore, this paper seek to classify Google's 'Quick, Draw!' dataset sketches which contains more than 50 million drawings across 345 categories by creating a Keras model. It aim to integrate a custom model to an Android app using Tensor flow Lite. Such a system will outperform for variety of applications, such as human-computer interaction, sketch-based search, game design, and education.
References
- M. Eitz, J. Hays, and M. Alexa. How do humans sketch objects ACM Trans. Graph. (Proc. SIGGRAPH), 31(4):44:1– 44:10, 2012
- K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition, 2016.
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105, 2012.
- R. G. Schneider and T. Tuytelaars. Sketch classification and classification-driven analysis using fisher vectors. ACM Transactions on Graphics (TOG), 33(6):174, 2014
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.