Image Captioning System
Amita Goel Vasudha Bahl and Nidhi Sengar Gaurav Joshi · International Journal for Modern Trends in Science and Technology · 2020
Deep Learning is relatively a new field and it has grabbed a lot of attention because it provides higher level of accuracy in recognizing objects than ever earlier. NLP is also one field that has created a huge impact in our life. NLP has come a long way from producing a readable summary of the texts to analysis of mental illness, it shows the impact of NLP. Image captioning task combines both NLP and Deep Learning. Describing images in a meaningful way can be done using Image captioning. Describing an image don’t just mean recognizing objects, to describe an image properly we first need to identify objects present in the image and then the relationship between those objects. In this study we have used CNN-LSTM based framework. CNN will be used to extract features of the image while with the help of LSTM we will try to generate meaningful sentences. This study also discusses applications of Image captioning and major challenges faced in achieving this task.