Automated study of ocular thermal images: Comprehensive analysis of corneal health with different age group subjects and validation

• Published in: Digital signal processing Vol. 20; no. 6; pp. 1579 - 1591
• Main Authors: Tan, Jen-Hong, Ng, E.Y.K., Acharya U, Rajendra, Chee, C.
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.12.2010
• Subjects: Age; Algorithms; Automated; Cornea; Genetic algorithm; Infrared; Infrared radiation; Mathematical analysis; Snake; Surface temperature; Target tracing function; Thermogram; Cornea; Thermogram; Infrared; Target tracing function; Snake; Genetic algorithm
• ISSN: 1051-2004; 1095-4333
• DOI: 10.1016/j.dsp.2010.03.014

Thermography using infrared (IR) imaging is a non-invasive imaging technique widely used in medical and engineering arena nowadays. This technique is capable of detecting temperature changes in the vascular tissues, and plays an important role in the study of ocular surface temperature and ocular diseases. In this study the performance of an automated algorithm which acquires corneal surface temperature was studied for normal IR thermograms of different age groups. The automated algorithm consists of algorithms intelligently localizing cornea and removing eye lashes, reading in temperature values within the localized cornea without any human intervention for further analysis. Its performance was compared against the results of manual corneal delineation. Our studies showed that the automated algorithm performed as good as the tedious and laborious manual method with the calculated average corneal temperature of 34.01 ± 0.64 ° C (automated) and 33.99 ± 0.63 ° C for manual method.