A high-performance text plagiarism detection pipeline using KMP and Rabin-Karp exact matching, robust Winnowing fingerprinting, and sub-linear time candidate screening via MinHash + Locality-Sensitive Hashing (LSH), built with a unified Streamlit analytical dashboard.
python algorithms scikit-learn data-structures kmp-algorithm minhash locality-sensitive-hashing text-processing rabin-karp string-matching plagiarism-detector portfolio-project streamlit winnowing-algorithm full-stack-dsa tfidf-similarity
-
Updated
Jun 8, 2026 - Python