Image Screening Project

• Tech Stack: Python, TensorFlow, Keras, NumPy, NLTK, Transfer Learning, Javascript, HTML
• Github URL: Project Link

The model is trained using a dataset of images and corresponding captions. The image features are extracted using the pre-trained VGG16 model, and the captions are processed and fed into the LSTM network.

Given a new input image, the trained model generates captions by first extracting the image features using the CNN and then using the LSTM to generate a sequence of words based on the image features.