CV · NLP

📄 Intelligent Data Extraction from Documents

Document Scanner Web App with custom Named Entity Recognizer (NER) for business card extraction. Built end-to-end pipeline: data labeling (BIO tagging), text parsing, Displacy rendering, and bounding box annotations.

Python spaCy OCR NER
View Details
NLP · Transformers

🛍️ Product Categorization with Transformers

Ranked 9th of 400+ teams at IndoML 2024 (BITS Pilani Goa). Multi-task classification using BERT, LLaMa-2-7B, and GPT-J. Integrated FAISS-based data augmentation with adaptive learning for real-world e-commerce.

BERT LLaMA-2 GPT-J FAISS
View Details
NLP · Healthcare

🏥 Medical Abstract Sequence Classification

Major Project. Implemented Bi-ANN, Bi-LSTM, and BERT for sequential classification of medical abstracts. Achieved 92% accuracy via fine-tuning and optimization. Full preprocessing & feature extraction pipeline.

BERT LSTM TensorFlow NLTK
View Details
Robotics · CV

🤖 3D Robotic Arm Color Sorting

Built at AMURoboclub. Designed a 3D robotic arm to sort objects by color. Used OpenCV for robust hue-based classification and Raspberry Pi for precise mechanical control of arm movements.

OpenCV Raspberry Pi Python Robotics
View Details
ML · Web

🏠 House Price Prediction Web App

Intuitive web app to predict housing prices. Trained a regression model on real estate features, deployed via pickle for fast inference. Designed a clean front-end using HTML/CSS for smooth UX.

Scikit-learn Flask HTML/CSS Pandas
View Details
CV · Deep Learning

🍱 FoodVision: Food Classification System

Deep learning model with transfer learning for food image classification. Enables accurate recognition of diverse foods — applicable for diet tracking, calorie estimation, and nutrition analysis.

EfficientNet Transfer Learning TensorFlow Keras
View Details
Wireless · Research

📡 Trans-REM: Radio Environment Mapping

Two-agent CNN-Transformer for indoor REM. Combines local feature extraction (CNN) with global context (Transformer). Auxiliary LoS and antenna pattern inputs. 15%+ improvement over SOTA in MSE.

CNN Transformer PyTorch Wireless
View Publication
CV · Smart City

🚗 Vehicle Detection for Traffic Management

Published at IEEE MASS 2024 (Seoul). Real-time vehicle detection with YOLOv8s for adaptive traffic light control. Achieves mAP@0.5 of 85.8% across 5 vehicle categories.

YOLOv8 OpenCV PyTorch Real-time
View Publication