Date of Award

2025

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

Committee Chair

Tathagata Mukherjee

Committee Member

Farbod Fahimi

Committee Member

Jacob Hauenstein

Research Advisor

Tathagata Mukherjee

Subject(s)

Pattern recognition systems, Computer vision, Deep learning (Machine learning), Scrabble (Game)

Abstract

The scope of this thesis is to present an AI-powered system for automati- cally scoring real-world Scrabble games using computer vision and deep learning. To achieve this purpose a DeepLabv3 model is trained to segment the board from top- down images, while an EfficientNet-B0 classifier identifies individual tile characters, including blank and empty tiles. The system continuously tracks the gameplay by detecting newly placed tiles and applies official Scrabble rules to compute scores, in- cluding crosswords, bonus tiles, and bingo logic simultaneously. The scoring engine supports multi-move gameplay, player turns, and endgame handling. All moves are visualized with a color-coded board and logged for transparency. The system was tested on over 25 real moves and consistently matched the expected scores. Unlike traditional OCR methods, this approach works efficiently in a wide array of lighting, angle, and tile variations. Additionally, the system offers a hands-free alternative for educational and recreational Scrabble settings.

Available for download on Wednesday, August 05, 2026

Share

COinS