bob.ip.binseg.data.rimoner3

RIM-ONE r3 (training set) for Cup Segmentation

The dataset contains 159 stereo eye fundus images with a resolution of 2144 x 1424. The right part of the stereo image is disregarded. Two sets of ground-truths for optic disc and optic cup are available. The first set is commonly used for training and testing. The second set acts as a “human” baseline. A third set, composed of annotation averages may also be used for training and evaluation purposes.

  • Reference: [RIMONER3-2015]

  • Original resolution (height x width): 1424 x 1072

  • Split reference: [MANINIS-2016]

  • Protocols optic-disc-exp1, optic-cup-exp1, optic-disc-exp2, optic-cup-exp2, optic-disc-avg and optic-cup-avg:

    • Training: 99

    • Test: 60

bob.ip.binseg.data.rimoner3.dataset = <bob.ip.binseg.data.dataset.JSONDataset object>

RIM-ONE r3 dataset object