TY - JOUR
T1 - Two step convolutional neural network for automatic glottis localization and segmentation in stroboscopic videos
AU - Belagali, Varun
AU - Achuth Rao, M. V.
AU - Gopikishore, Pebbili
AU - Krishnamurthy, Rahul
AU - Ghosh, Prasanta Kumar
N1 - Publisher Copyright:
© 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement.
PY - 2020
Y1 - 2020
N2 - Precise analysis of the vocal fold vibratory pattern in a stroboscopic video plays a key role in the evaluation of voice disorders. Automatic glottis segmentation is one of the preliminary steps in such analysis. In this work, it is divided into two subproblems namely, glottis localization and glottis segmentation. A two step convolutional neural network (CNN) approach is proposed for the automatic glottis segmentation. Data augmentation is carried out using two techniques : 1) Blind rotation (WB), 2) Rotation with respect to glottis orientation (WO). The dataset used in this study contains stroboscopic videos of 18 subjects with Sulcus vocalis, in which the glottis region is annotated by three speech language pathologists (SLPs). The proposed two step CNN approach achieves an average localization accuracy of 90.08% and a mean dice score of 0.65.
AB - Precise analysis of the vocal fold vibratory pattern in a stroboscopic video plays a key role in the evaluation of voice disorders. Automatic glottis segmentation is one of the preliminary steps in such analysis. In this work, it is divided into two subproblems namely, glottis localization and glottis segmentation. A two step convolutional neural network (CNN) approach is proposed for the automatic glottis segmentation. Data augmentation is carried out using two techniques : 1) Blind rotation (WB), 2) Rotation with respect to glottis orientation (WO). The dataset used in this study contains stroboscopic videos of 18 subjects with Sulcus vocalis, in which the glottis region is annotated by three speech language pathologists (SLPs). The proposed two step CNN approach achieves an average localization accuracy of 90.08% and a mean dice score of 0.65.
UR - http://www.scopus.com/inward/record.url?scp=85090056591&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090056591&partnerID=8YFLogxK
U2 - 10.1364/BOE.396252
DO - 10.1364/BOE.396252
M3 - Article
AN - SCOPUS:85090056591
SN - 2156-7085
VL - 11
SP - 4695
EP - 4713
JO - Biomedical Optics Express
JF - Biomedical Optics Express
IS - 8
ER -