Guoliang Fan

Learn More
This paper presents an efficient method for automatic detection and extraction of blood vessels in retinal images. Specifically, we also delineate vascular intersections/crossovers. The proposed algorithm is composed of four steps: matched filtering, local entropy thresholding, length filtering, and vascular intersection detection. The purpose of matched(More)
This work studies retinal image registration in the context of the National Institutes of Health (NIH) Early Treatment Diabetic Retinopathy Study (ETDRS) standard. The ETDRS imaging protocol specifies seven fields of each retina and presents three major challenges for the image registration task. First, small overlaps between adjacent fields lead to(More)
This paper presents efficient methods for automatic detection and extraction of blood vessels and optic disc (OD) both of which are two prominent anatomical structures in ocular fundus images. The blood vessel extraction algorithm is composed of four steps, i.e., matched filtering, local entropy-based thresholding, length filtering, and vascular(More)
In this paper, a joint multi-context and multiscale (JMCMS) approach to Bayesian image segmen-tation is proposed. In addition to the multiscale framework, the JMCMS applies multiple context models to jointly use their distinct advantages, and we use a heuristic multi-stage problem solving technique to estimate sequential maximum a posteriori of the JMCMS.(More)
Video segmentation has been an important and challenging issue for many video applications. Usually there are two different video segmentation approaches, i.e., shot-based segmentation that uses a set of key-frames to represent a video shot and object-based segmentation that partitions a video shot into objects and background. Representing a video shot at(More)
We propose a hybrid body representation that represents each typical pose by both template-like view information and part-based structural information. Specifically, each body part as well as the whole body are represented by an off-line learned shape model where both region-based and edge-based priors are combined in a coupled shape representation.(More)
In this paper, we propose a new postprocessing method for low bit-rate wavelet-based image coding which uses the technique of wavelet modulus maximum representation (WMMR). The edge degradation from wavelet-based coding is discussed under the overcomplete wavelet expansion, and interpreted as the distortion of wavelet modulus maxima, i.e. magnitude decays.(More)
We propose a new statistical generative model for spatiotemporal video segmentation. The objective is to partition a video sequence into homogeneous segments that can be used as "building blocks" for semantic video segmentation. The baseline framework is a Gaussian mixture model (GMM)-based video modeling approach that involves a six-dimensional(More)