Paper
8 June 2005 Image analysis of contact lens grading scales for objective grade assignment of ocular complications
Author Affiliations +
Abstract
Ocular complications in contact lens wearers are usually graded by specialists using visual inspection and comparing with a standard reference. The standard grading scales consist of either a set of illustrations or photographs ordered from a normal situation to a severe complication. Usually, visual inspection based on comparison with standards yields results that may differ from one specialist to another due to contour conditions or personal appreciation, causing a lack of objectiveness in the assessment of an ocular disorder. We aim to develop a method for an objective assessment of two contact lens wear complications: conjunctiva hyperemia and papillary conjunctivitis. In this work, we start by applying different image processing techniques to two standard grading scales (Efron and Cornea and Contact Lens Research Unit-CCLRU grading scales). Given a set of standard illustrations or pictures, image pre-processing is needed to compare equivalent areas. Histogram analysis allows segmenting vessel and background pixel populations, which are used to determine features, such as total area of vessels and vessel length, in the measurement of contact lens effects. In some cases, the colour content of standard series can be crucial to obtain a correct assessment. Thus, colour image analysis techniques are used to extract the most relevant features. The procedure to obtain an automatic grading method by digital image analysis of standard grading scales is described.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Elisabet Perez-Cabre, Maria S. Millan, Hector C. Abril, and Edison Valencia "Image analysis of contact lens grading scales for objective grade assignment of ocular complications", Proc. SPIE 5827, Opto-Ireland 2005: Photonic Engineering, (8 June 2005); https://doi.org/10.1117/12.610226
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Photography

Image segmentation

Image analysis

RGB color model

Objectives

Optical inspection

Feature extraction

Back to Top