A Computationally Efficient Retina Detection and Enhancement Image Processing Pipeline for Smartphone-Captured Fundus Images

Yaroub Elloumi (1, 2) , Mohamed Akil (3) , Nasser Kehtarnavaz (4)

1 LIGM - Laboratoire d'Informatique Gaspard-Monge
2 TIM - Laboratoire Technologie et Imagerie Médicale [Monastir]
3 Algorithms, architectures, image analysis and computer graphics
4 ECE - Department of Electrical and Computer Engineering - University of Texas

Due to the handheld holding of smartphones and the presence of light leakage and non-balanced contrast, the detection of the retina area in smartphone-captured fundus images is more challenging than angiography-captured fundus images. This paper presents a computationally efficient image processing pipeline in order to detect and enhance the retina area in smartphone-captured fundus images. The developed pipeline consists of the five image processing components of point spread function parameter estimation, deconvolution, contrast balancing, circular Hough transform, and retina area extraction. The results obtained indicate a typical fundus image captured by a smartphone through a D-EYE lens is processed in less than 1 second.

Domaines: Imagerie médicale

Yaroub Elloumi, Mohamed Akil, Nasser Kehtarnavaz. A Computationally Efficient Retina Detection and Enhancement Image Processing Pipeline for Smartphone-Captured Fundus Images. Journal of Multimedia Information System, 2018, 5 (2), pp.79-82. ⟨10.9717/JMIS.2018.5.2.79⟩. ⟨hal-01796763⟩