Restricted Set Classification with prior probabilities: A case study on chessboard recognition

Research output: Contribution to journalArticlepeer-review

Standard Standard

Restricted Set Classification with prior probabilities: A case study on chessboard recognition. / Kuncheva, Ludmila; Constance, James.
In: Pattern Recognition Letters, Vol. 111, 08.2018, p. 36-42.

Research output: Contribution to journalArticlepeer-review

HarvardHarvard

APA

CBE

MLA

VancouverVancouver

Kuncheva L, Constance J. Restricted Set Classification with prior probabilities: A case study on chessboard recognition. Pattern Recognition Letters. 2018 Aug;111:36-42. Epub 2018 Apr 12. doi: 10.1016/j.patrec.2018.04.018

Author

Kuncheva, Ludmila ; Constance, James. / Restricted Set Classification with prior probabilities: A case study on chessboard recognition. In: Pattern Recognition Letters. 2018 ; Vol. 111. pp. 36-42.

RIS

TY - JOUR

T1 - Restricted Set Classification with prior probabilities: A case study on chessboard recognition

AU - Kuncheva, Ludmila

AU - Constance, James

PY - 2018/8

Y1 - 2018/8

N2 - In the Restricted Set Classification approach (RSC), a set of instances must be labelled simultaneously into a given number of classes, while observing an upper limit on the number of instances from each class. In this study we expand RSC by incorporating prior probabilities for the classes and demonstrate the improvement on the classification accuracy by doing so. As a case-study, we chose the challenging task of recognising the pieces on a chessboard from top view images, without any previous knowledge of the game. This task fits elegantly into the RSC approach as the number of pieces on the board is limited, and each class (type of piece) may have only a fixed number of instances. We prepared an image dataset by sampling from existing competition games, arranging the pieces on the chessboard, and taking top-view snapshots. Using the grey-level intensities of each square as features, we applied single and ensemble classifiers within the RSC approach. Our results demonstrate that including prior probabilities calculated from existing chess games improves the RSC classification accuracy, which, in its own accord, is better than the accuracy of the classifier applied independently.

AB - In the Restricted Set Classification approach (RSC), a set of instances must be labelled simultaneously into a given number of classes, while observing an upper limit on the number of instances from each class. In this study we expand RSC by incorporating prior probabilities for the classes and demonstrate the improvement on the classification accuracy by doing so. As a case-study, we chose the challenging task of recognising the pieces on a chessboard from top view images, without any previous knowledge of the game. This task fits elegantly into the RSC approach as the number of pieces on the board is limited, and each class (type of piece) may have only a fixed number of instances. We prepared an image dataset by sampling from existing competition games, arranging the pieces on the chessboard, and taking top-view snapshots. Using the grey-level intensities of each square as features, we applied single and ensemble classifiers within the RSC approach. Our results demonstrate that including prior probabilities calculated from existing chess games improves the RSC classification accuracy, which, in its own accord, is better than the accuracy of the classifier applied independently.

KW - Classification methodology, Restricted Set Classification, Simultaneous classification, Image recognition, Chess piece recognition

U2 - 10.1016/j.patrec.2018.04.018

DO - 10.1016/j.patrec.2018.04.018

M3 - Article

VL - 111

SP - 36

EP - 42

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -