Image Description using Encoder and Decoder LSTM Methods: Some Issues
Nirmala1, Gopalkrishna Joshi2, P S Hiremath3
1Mrs. Nirmala, Department of Computer Science & Engineering, Nitte Meenakshi Institute of Technology, Bangalore, Karnataka, India.
2Dr. Gopalkrishna Joshi, Dean Director, Centre for Engineering Education Research B. V. Bhoomaraddi College of Engg. & Technology, Hubli, Karnataka, India.
3Dr. P S Hiremath, Professor, Department of Computer Science, BVB College of Engineering & Technology, Hubli Karnataka, India.
Manuscript received on August 13, 2020. | Revised Manuscript received on September 03, 2020. | Manuscript published on September 10, 2020. | PP: 167-172 | Volume-9 Issue-11, September 2020 | Retrieval Number: 100.1/ijitee.K77290991120 | DOI: 10.35940/ijitee.K7729.0991120
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: Description of images has an important role in image mining. The description of images provides an insight into the location, its surroundings and other information related to it. Different procedures of describing the images exist in literature. However, a well trained description of images is still a tedious task to achieve. Several researchers have come up with solutions to this problem using various techniques. Herein, the concept of LSTM is used in generating a trained description of images. The said process is achieved through encoders and decoders. Encoders use techniques of maxpooling and convolution, while the decoders use the concept of recurrent neural networks. The combined architecture of encoders and decoders result in trained classifiers, which enable reliable description of images. The working has been implemented by considering a sample image. It has been found that slight variations with regard to accuracy, naturalness, missing concepts, deficiency of sufficient semantics and incomplete description of image still exist. Hence, it can be inferred that, with reasonable amount of enhancement in the technique and using the techniques of natural language processing, more accuracy in image descriptions could be achieved.
Keywords: Convolution Neural Network, Data Processing, Decoder, Encoder, LSTM, Maxpooling.
Scope of the Article: Deep Learning