CSL Net: Convoluted SE and LSTM Blocks Based Network for Automatic Image Annotation
Vijayarani. A1, Lakshmi Priya G. G.2
1Vijayarani.A, School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India.
2Lakshmi Priya G.G., School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India.
Manuscript received on December 01, 2019. | Revised Manuscript received on December 08, 2019. | Manuscript published on December 30, 2019. | PP: 47-54 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3276129219/2019©BEIESP | DOI: 10.35940/ijeat.B3276.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Due to advancement of multimedia technology, availability and usage of image and video data is enormous. For indexing and retrieving those data, there is a need for an efficient technique. Now, Automatic keyword generation for images is a focussed research which has lot of attractions. In general, conventional auto annotation methods having lesser performance over deep learning methods. The annotation is transformed as captioning in deep learning models. In this paper, we propose a new model CSL Net (CSLN) as a combination of convoluted squeeze and excitation block with Bi-LSTM blocks to predict tags for images. The proposed model is evaluated using the various benchmark datasets like CIFAR10, Corel5K, ESPGame and IAPRTC12. It is observed that, the proposed work yields better results compared to that of the existing methods in term of precision, recall and accuracy.
Keywords: Automatic image annotation, Image captioning, Deep learning, Convolution, Squeeze and Excitation Block, Long – short term memory block.