TY - GEN
T1 - Efficient optic cup localization based on superpixel classification for glaucoma diagnosis in digital fundus images
AU - Xu, Yanwu
AU - Liu, Jiang
AU - Cheng, Jun
AU - Yin, Fengshou
AU - Tan, Ngan Meng
AU - Wong, Damon Wing Kee
AU - Cheng, Ching Yu
AU - Tham, Yih Chung
AU - Wong, Tien Yin
PY - 2012
Y1 - 2012
N2 - Optic cup is the primary image indicator clinically used for identifying glaucoma. To automatically localize the optic cup in fundus images, an effective and efficient superpixel classification based approach is proposed in this work, which maintains both advantages of existing pixel and window based approaches. This method provides three major contributions. First, it proposes processing of the fundus images at the superpixel level, which leads to more descriptive and effective features than those employed by pixel based approaches, without additional computational cost. Second, a feature normalization method is proposed to reduce the influence of illumination variations across the training and testing images, which greatly elevates superpixel classification accuracy. Third, a refinement scheme that utilizes both retinal structural priors and local context information is adopted to further improve the accuracy. Tested on the ORIGA-light clinical dataset, which comprises of 325 images from a population-based study, the proposed method achieves an accuracy that is comparable to or higher than the state-of-the-art techniques, with a speedup factor of tens or hundreds.
AB - Optic cup is the primary image indicator clinically used for identifying glaucoma. To automatically localize the optic cup in fundus images, an effective and efficient superpixel classification based approach is proposed in this work, which maintains both advantages of existing pixel and window based approaches. This method provides three major contributions. First, it proposes processing of the fundus images at the superpixel level, which leads to more descriptive and effective features than those employed by pixel based approaches, without additional computational cost. Second, a feature normalization method is proposed to reduce the influence of illumination variations across the training and testing images, which greatly elevates superpixel classification accuracy. Third, a refinement scheme that utilizes both retinal structural priors and local context information is adopted to further improve the accuracy. Tested on the ORIGA-light clinical dataset, which comprises of 325 images from a population-based study, the proposed method achieves an accuracy that is comparable to or higher than the state-of-the-art techniques, with a speedup factor of tens or hundreds.
UR - http://www.scopus.com/inward/record.url?scp=84874562864&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84874562864
SN - 9784990644109
T3 - Proceedings - International Conference on Pattern Recognition
SP - 49
EP - 52
BT - ICPR 2012 - 21st International Conference on Pattern Recognition
T2 - 21st International Conference on Pattern Recognition, ICPR 2012
Y2 - 11 November 2012 through 15 November 2012
ER -