jizhihang Goto Github PK

In this work, we present an extensive description and evaluation of our method for blood vessel segmentation in fundus images based on a discriminatively trained, fully connected conditional random field model. Standard segmentation priors such as a Potts model or total variation usually fail when dealing with thin and elongated structures. We overcome this difficulty by using a conditional random field model with more expressive potentials, taking advantage of recent results enabling inference of fully connected models almost in real-time. Parameters of the method are learned automatically using a structured output support vector machine, a supervised technique widely used for structured prediction in a number of machine learning applications. Our method, trained with state of the art features, is evaluated both quantitatively and qualitatively on four publicly available data sets: DRIVE, STARE, CHASEDB1 and HRF. Additionally, a quantitative comparison with respect to other strategies is included. The experimental results show that this approach outperforms other techniques when evaluated in terms of sensitivity, F1-score, G-mean and Matthews correlation coefficient. Additionally, it was observed that the fully connected model is able to better distinguish the desired structures than the local neighborhood based approach. Results suggest that this method is suitable for the task of segmenting elongated structures, a feature that can be exploited to contribute with other medical and biological applications.

fundus-vessel-segmentation-tmbe

One of the first steps in automatic fundus image analysis is the segmentation of the retinal vasculature, which provides valuable information related to several diseases. In this work, we present an extensive description and evaluation of our method for blood vessel segmentation in fundus images based on a discriminatively trained, fully connected conditional random field model. This task remains a challenge largely due to the desired structures being thin and elongated, a setting that performs particularly poorly using standard segmentation priors, such as a Potts model or total variation. We overcome this difficulty by using a conditional random field model with more expressive potentials, taking advantage of recent results enabling inference of fully connected models almost in real-time. Parameters of the method are learned automatically using a structured output support vector machine, a supervised technique widely used for structured prediction in a number of machine learning applications. The evaluation of our method is performed both quantitatively and qualitatively on DRIVE, STARE, CHASEDB1 and HRF, showing its ability to deal with different types of images and outperforming other techniques, trained using state of the art features.

fvcore

Collection of common code that's shared among different research projects in FAIR computer vision team.

fvkit

FVKit: Matlab code to extract Fisher Vectors

fwgrid

Deprecated code for managing jobs on ucsd's FWgrid

gan-vis

Visualization of GAN training process

gaussianprocesses

Gaussian Processes regression with gaussian kernel implementation.

gcn

Implementation of Graph Convolutional Networks in TensorFlow

gdal-segment

GDAL Segment

general-descriptors-in-cv

general-pooling

Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree

generalized-pooling-for-robust-object-tracking

Generalized pooling for robust object tracking

generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

geo-blur

In this code, re-implementation of geometric blur was done. The code is primarily in python with an invocation to C. David Lowe's sift keypoint detection is used. (His binary was used. For liecense agreement of sift refer http://people.cs.ubc.ca/~lowe/)

jizhihang Goto Github PK

jizhihang's Projects

Recommend Projects

Recommend Topics

Recommend Org