Urdu Image Caption Generation

Overview

An attention-based LSTM model that generates Urdu-language captions for input images. The project required building a custom dataset of images paired with native Urdu captions, then training and deploying the model as an online service. Outcome: First-of-its-kind plug-and-play Urdu captioning model, available online for direct use.

Architecture & Pipeline

flowchart LR
    n0["
Image Input
Custom Urdu-caption dataset
"] n1["
CNN Encoder
Visual features
"] n2["
Attention LSTM Decoder
TensorFlow
"] n3["
Urdu Caption
Online inference
"] n0 --> n1 n1 --> n2 n2 --> n3 classDef step0 fill:#f1f5f9,stroke:#64748b,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step1 fill:#ecfeff,stroke:#06b6d4,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step3 fill:#ecfdf5,stroke:#10b981,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step4 fill:#fffbeb,stroke:#f59e0b,color:#1e293b,stroke-width:2px,rx:10,ry:10; class n0 step0; class n1 step1; class n2 step3; class n3 step4;

End-to-end flow derived from this project's scope and tech stack. Tap View Fullscreen for a larger view, or scroll horizontally on small screens.

Key Features

  • Attention-based LSTM architecture
  • Custom Urdu image-caption dataset
  • Trained and deployed for online inference
  • Tech Stack:** Python, TensorFlow