🎨 Transform photos into stunning cartoon artwork using OpenCV! Features advanced edge detection, color quantization & bilateral filtering. Includes Gradio web interface for easy use, Jupyter notebooks for exploration, and modular Python architecture. Perfect for learning computer vision concepts.

🏥 AI-powered breast cancer classification using Logistic Regression with 95% accuracy. Features interactive Gradio web interface for real-time predictions on 30 diagnostic parameters from Wisconsin dataset. Includes comprehensive Jupyter notebooks for model training, evaluation metrics, and deployment-ready architecture for healthcare application.

Semantic book recommendation system leveraging vector embeddings (sentence-transformers), approximate nearest neighbor search (FAISS), and generative AI (Google Gemini/Vertex AI) for personalized analysis and content generation, wrapped in an interactive Gradio web UI.

This project predicts used car prices using a feedforward neural network regression model implemented in PyTorch. Features include car age, mileage, and other attributes. The pipeline supports feature normalization, train/validation/test splitting, and visualization of training and validation loss curves.

This project develops a semantic book recommender system leveraging the power of Large Language Models (LLMs). It allows users to input a book description and receive recommendations for similar books, classified by categories and emotional tones.

This project classifies SMS messages as spam or ham using a feedforward neural network in PyTorch with a bag-of-words representation. It includes train/validation/test splits, performance evaluation (accuracy, sensitivity, specificity, precision), and saving the trained model and vectorizer for reuse in inference.

Tire condition classification using ResNet and transfer learning. This project applies deep learning to identify whether a tire is in good or bad condition based on image data.

an intelligent book recommendation system using llms and python. vibe code-free.

Gradio-powered semantic Q&A app using Sentence Transformers

2025 휴먼 IT Deep Learning + LLM 개인 프로젝트

A helpful assistant that provides information to users who want to explore the city of Uppsala, in Sweden. Powered by Google Search-based Grounding, Vector Similarity Search (Qdrant + google/embeddinggemma-300m) and OCR-extracted documents from tourism brochure (DestinationUppsala) as context.

Comparador visual de documentos (PDF, DOCX, TXT) que resalta diferencias usando colores. Compara el primer archivo con el segundo y opcionalmente con un tercero. Ideal para contratos, informes y propuestas.

This project predicts loan approval outcomes (Approved/Rejected) using a PyTorch neural network. It includes data preprocessing, train/validation/test split, model training with BCEWithLogitsLoss, and inference with probability-based classification.