Share Email Print

Proceedings Paper

Segmentation and classification of offline hand drawn images for the BGT neuropsychological screening test
Author(s): Momina Moetesum; Imran Siddiqi; Uzma Masroor; Nicole Vincent; Florence Cloppet
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Shape drawing tests are widely used by practitioners to assess the neuropsychological conditions of patients. Most of these neuropsychological figure drawing tests comprise a set of figures drawn on a single sheet of paper which are inspected to analyze the presence or absence of certain properties and are scored accordingly. An automated scoring system for such a test requires the extraction and identification of a particular shape from the set of figures as a vital preprocessing step. This paper presents a system for effective segmentation and recognition of shapes for a well-known clinical test, the Bender Gestalt Test (BGT). The segmentation is based on connected component analysis, morphological processing and spatial clustering while the recognition is carried out using shape context matching. Experiments carried out on offline images of hand drawn samples contributed by different subjects realize promising segmentation and classification results validating the ideas put forward in this study.

Paper Details

Date Published: 29 August 2016
PDF: 5 pages
Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100334N (29 August 2016); doi: 10.1117/12.2244139
Show Author Affiliations
Momina Moetesum, Bahria Univ. (Pakistan)
Imran Siddiqi, Bahria Univ. (Pakistan)
Uzma Masroor, Bahria Univ. (Pakistan)
Nicole Vincent, Paris Descartes Univ. (France)
Florence Cloppet, Paris Descartes Univ. (France)

Published in SPIE Proceedings Vol. 10033:
Eighth International Conference on Digital Image Processing (ICDIP 2016)
Charles M. Falco; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top