Image Captioning: Transcribing Image into Words |
Author(s): |
| Adesh S. Vaidya , Karmaveer Dadasaheb Kannamwar Engineering College; Proff. Abhishek Nachankar, Karmaveer Dadasaheb Kannamwar Engineering College |
Keywords: |
| Image Caption Generation, LSTM, Deep Learning, Natural Language Processing, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Text Generation, Transcript Generation |
Abstract |
|
In the past few years, generating descriptive sentences by the machine of any image data gained an immense curiosity in computer vision and natural language processing research. Captioning the image is a basic job which requires the understanding of image data and potential to generate descriptive sentence with the correct structure. Image captioning models follow the conventional encoder-decoder architecture which uses the features of the image data as input and generates transcription. Image captioning needs to identify the important entities, their attributes, and their connection in an image data. It is also primely important that the model can make the sentence semantically and systematically. The deep learning-based model is proficient to manage these complications and challenges of image captioning. |
Other Details |
|
Paper ID: IJSRDV9I10083 Published in: Volume : 9, Issue : 1 Publication Date: 01/04/2021 Page(s): 102-104 |
Article Preview |
|
|
|
|
