PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Major Project
Image Caption Generator with CNN & LSTM
Writes a sentence describing a photo with an encoder-decoder model
3-4 weeks build
Overview
A pretrained InceptionV3 encodes each Flickr8k image into features, and an LSTM decoder with Bahdanau attention generates the caption word by word. Greedy and beam search decoding are compared, BLEU scores are reported on the test split, and attention maps show which part of the image each word came from.
What makes it stand up
- 01CNN encoder with an attention-based LSTM decoder
- 02Caption cleaning, tokenisation and vocabulary pruning
- 03Greedy and beam search decoding compared
- 04Attention heatmaps for every generated word
- 05BLEU-1 to BLEU-4 reported on the Flickr8k test split
Module breakdown
- 01
Text pipeline
Caption cleaning, tokeniser and padded sequences.
- 02
Encoder
Cached InceptionV3 features for every image.
- 03
Decoder
LSTM with Bahdanau attention and teacher forcing.
- 04
Inference
Greedy and beam search caption generation.
- 05
Web app
Flask upload that shows the caption and attention map.
After this, you will be able to
- Explain how attention lets the decoder focus on image regions
- Defend BLEU as a metric and discuss its weaknesses
- Demo captions on photos taken during the viva
Technology stack
- Python
- TensorFlow
- NLTK
- Flask
- NumPy
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 3-4 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support