Augmented Reality Chess Analyzer (ARChessAnalyzer): In-Device Inference of Physical Chess Game Positions through Board Segmentation and Piece Recognition using Convolutional Neural Network

Abstract

Chess game position analysis is important in improving ones game. It requires entry of moves into a chess engine which is, cumbersome and error prone. We present ARChessAnalyzer, a complete pipeline from live image capture of a physical chess game, to board and piece recognition, to move analysis and finally to Augmented Reality (AR) overlay of the chess diagram position and move on the physical board. ARChessAnalyzer is like a scene analyzer - it uses an ensemble of traditional image and vision techniques to segment the scene (ie the chess game) and uses Convolution Neural Networks (CNNs) to predict the segmented pieces and combine it together to analyze the game. This paper advances the state of the art in the first of its kind end to end integration of robust detection and segmentation of the board, chess piece detection using the fine-tuned AlexNet CNN and chess engine analyzer in a handheld device app. The accuracy of the entire chess position prediction pipeline is 93.45\% and takes 3-4.5sec from live capture to AR overlay. We also validated our hypothesis that ARChessAnalyzer, is faster at analysis than manual entry for all board positions for valid outcomes. Our hope is that the instantaneous feedback this app provides will help chess learners worldwide at all levels improve their game.