- Version
- Download 169
- File Size 1.16 MB
- File Count 1
- Create Date 17/05/2022
- Last Updated 17/05/2022
Image Caption Generator
Saurav Pandey1, Sudhir Kumar2, Shailesh Kumar Gupta3, Ritik Shukla4
Department of Computer Science and Engineering, Babu Banarasi Das Institute of Technology and
Management, Lucknow, India
ABSTRACT
Wouldn’t be great if blind people can know what is going around them without depending on anyone, or we can know if something suspicious is going in our house or place.
These all things can be achieved by state of the art machine learning and deep learning techniques. Our machine learning model tries to solve this problem by providing caption for image. It takes image as input and output text describing it.
It is comparatively challenging task than any image recognition or face-recognition, classification task. We have used several exciting deep learning concepts and tools. We have used tensorflow, CNN for image processing and state of the art Transformers for text processing.
KEYWORDS : Deep learning, CNN, Transformers, Tensorflow