https://github.com/scionoftech/image_caption_generation

Image caption generation using Deep Learning-LSTM
https://github.com/scionoftech/image_caption_generation

caption-generation cnn rnn

Last synced: 2 months ago
JSON representation

Image caption generation using Deep Learning-LSTM

• Host: GitHub
• URL: https://github.com/scionoftech/image_caption_generation
• Owner: scionoftech
• Created: 2019-12-23T17:42:31.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2019-12-23T18:10:38.000Z (about 6 years ago)
• Last Synced: 2024-12-27T17:23:42.400Z (about 1 year ago)
• Topics: caption-generation, cnn, rnn
• Language: Jupyter Notebook
• Size: 1.32 MB
• Stars: 1
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Image Caption Generation

Caption generation is a challenging artificial intelligence problem where a textual description must be generated for a given photograph.

It requires both methods from computer vision to understand the content of the image and a language model from the field of natural language processing to turn the understanding of the image into words in the right order. Recently, deep learning methods have achieved state-of-the-art results on examples of this problem.

Deep learning methods have demonstrated state-of-the-art results on caption generation problems. What is most impressive about these methods is a single end-to-end model can be defined to predict a caption, given a photo, instead of requiring sophisticated data preparation or a pipeline of specifically designed models.

### Steps:

* Photo and Caption Dataset

* Prepare Photo Data

* Prepare Text Data

* Build Deep Learning Model

* Train Model

* Evaluate Model

* Generate New Captions

### Model 

![image_cap.png](image_cap.png)

The Flickr 8k dataset is used for image caption generation, which you can download by filling [this](https://forms.illinois.edu/sec/1713398) form provided by the University of Illinois at Urbana-Champaign. 

This dataset contains 8000 images each with 5 captions

Other Datasets,

* [COCO 2015 Image Captioning](http://cocodataset.org/#captions-2015)

* [Google Conceptual Captions](https://ai.google.com/research/ConceptualCaptions/download)