https://doi.org/10.26706/ijceae.3.2.arset4383

---

Abstract:-

This project entitled “Image Caption Generator Using CNN and LSTM” is a work that demonstrates the automated generation of captions for a wide variety of images. This technology is used by major tech-giants like Google, Microsoft, IBM, etc. to generate captions for the huge dataset of images produced over various platforms and social media websites. This project embodies the use of various Artificial Neural Networks namely CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks) and LSTM (Long Short-Term Memory) Units. The functionality of the model developed using these neural nets. has been rendered to an interactive Web Application for the users to understand the methodology.

Index Terms:-

Convolutional Neural Networks, Recurrent Neural Networks, Long Short-Term Memory, Computer Vision, Natural Language Processing.

---

REFERENCES

1. J. D. Kelleher, Deep Learning, The MIT Press, 2019.
   Online
   

---

2. P. Kim, "Convolutional Neural Network," MATLAB Deep Learning, p. 121–147, 2017.
   Crossref
   

---

3. U. Karn, "An Intuitive Explanation of Convolutional Neural Networks," 2016.
   Online
   

---

4. M. Glossary, "Activation Functions," 2017.
   Online
   

---

5. A. L. Caterini and D. Chang, "Recurrent Neural Networks," Deep Neural Networks in a Mathematical Framework, pp. 59-79, 2018.
   Online
   

---

6. Van Houdt, G., Mosquera, C. & Nápoles, G. A review on the long short-term memory model. Artif Intell Rev, Volume 53, 5929–5955, 2020.
   Crossref
   

---

7. A. Gulli and S. Pal, Deep Learning with Keras, Packt Publishing Ltd., 2017.
   Online
   

---

To view full paper, Download here

---