Search Results for author: Hiroshi Ishikawa

Found 15 papers, 2 papers with code

Dueling Deep Q-Network for Unsupervised Inter-frame Eye Movement Correction in Optical Coherence Tomography Volumes

no code implementations3 Jul 2020 Yasmeen M. George, Suman Sedai, Bhavna J. Antony, Hiroshi Ishikawa, Gadi Wollstein, Joel S. Schuman, Rahil Garnavi

We also compare our model with elastix intensity based medical image registration approach, where significant improvement is achieved by our model for both noisy and denoised volumes.

Image Registration Medical Image Registration

Inference of visual field test performance from OCT volumes using deep learning

no code implementations5 Aug 2019 Stefan Maetschke, Bhavna Antony, Hiroshi Ishikawa, Gadi Wollstein, Joel Schuman, Rahil Garnavi

Visual field tests (VFT) are pivotal for glaucoma diagnosis and conducted regularly to monitor disease progression.

A feature agnostic approach for glaucoma detection in OCT volumes

1 code implementation12 Jul 2018 Stefan Maetschke, Bhavna Antony, Hiroshi Ishikawa, Gadi Wollstein, Joel S. Schuman, Rahil Garnavi

Optical coherence tomography (OCT) based measurements of retinal layer thickness, such as the retinal nerve fibre layer (RNFL) and the ganglion cell with inner plexiform layer (GCIPL) are commonly used for the diagnosis and monitoring of glaucoma.

BIG-bench Machine Learning

Joint Gap Detection and Inpainting of Line Drawings

no code implementations CVPR 2017 Kazuma Sasaki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa

We evaluate our method qualitatively on a diverse set of challenging line drawings and also provide quantitative results with a user study, where it significantly outperforms the state of the art.

Mastering Sketching: Adversarial Augmentation for Structured Prediction

no code implementations27 Mar 2017 Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa

Our approach augments a simplification network with a discriminator network, training both networks jointly so that the discriminator network discerns whether a line drawing is a real training data or the output of the simplification network, which in turn tries to fool it.

Structured Prediction

Higher-Order Clique Reduction Without Auxiliary Variables

no code implementations CVPR 2014 Hiroshi Ishikawa

While the method does not reduce all terms, it can be used with existing techniques that transformsarbitrary terms (by introducing auxiliary variables) and improve the speed.

Cannot find the paper you are looking for? You can Submit a new open access paper.