Translator Disclaimer
29 May 2014 Detection of exudates in fundus imagery using a constant false-alarm rate (CFAR) detector
Author Affiliations +
Diabetic retinopathy is the leading cause of blindness in adults in the United States. The presence of exudates in fundus imagery is the early sign of diabetic retinopathy so detection of these lesions is essential in preventing further ocular damage. In this paper we present a novel technique to automatically detect exudates in fundus imagery that is robust against spatial and temporal variations of background noise. The detection threshold is adjusted dynamically, based on the local noise statics around the pixel under test in order to maintain a pre-determined, constant false alarm rate (CFAR). The CFAR detector is often used to detect bright targets in radar imagery where the background clutter can vary considerably from scene to scene and with angle to the scene. Similarly, the CFAR detector addresses the challenge of detecting exudate lesions in RGB and multispectral fundus imagery where the background clutter often exhibits variations in brightness and texture. These variations present a challenge to common, global thresholding detection algorithms and other methods. Performance of the CFAR algorithm is tested against a publicly available, annotated, diabetic retinopathy database and preliminary testing suggests that performance of the CFAR detector proves to be superior to techniques such as Otsu thresholding.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Manish Khanna and Elina Kapoor "Detection of exudates in fundus imagery using a constant false-alarm rate (CFAR) detector", Proc. SPIE 9077, Radar Sensor Technology XVIII, 90771T (29 May 2014);


Back to Top