Image-Caption-Generator
Image Caption Generator is a project that involves computer vision and natural language processing concepts to recognize the context of an image and describe them in a natural language like English. For implementing the project, techniques used are CNN with LSTM. The image features will be extracted using a CNN model trained on the imagenet dataset and then we feed the features into the LSTM model which will be responsible for generating the image captions.
Flickr_8K : Flicker8k_Dataset – Dataset folder which contains 8091 images. Flickr_8k_text – Dataset folder which contains text files and captions of images. link to download dataset- https://paperswithcode.com/task/image-captioning
Steps for Project:
- Importing all the necessary packages.
- Getting and performing data cleaning.
- Extracting the feature vector from all images.
- Loading dataset for Training the model.
- Tokenizing the vocabulary.
- Creating a data generator.
- Defining the CNN-RNN model.
- Training the model.
- Testing the model.
Output Images