Description

app.py

@@ -10,8 +10,8 @@ warnings.filterwarnings('ignore')
 
 # Define problem statement
 problem_statement = """
-### Overview
-This project aims to generate descriptive spoken captions for images, leveraging CNNs and RNNs for feature extraction and sequence generation, respectively. The model is trained on the Flickr8K dataset and extended with an attention mechanism for enhanced accessibility.
+### Problem Statement
+This project aims to develop a deep learning model to verbally describe image contents for the visually impaired using caption generation with an attention mechanism on the Flickr8K dataset. Inspired by the "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention" paper, the model utilizes a CNN-RNN architecture to extract image features and generate captions, facilitating accessibility. The Kaggle dataset comprises 8,000 images, each paired with five descriptive captions, enabling comprehensive understanding of image content.
 """
 
 # Define solution overview