Baisheng Dai

Learn More
Retinal microaneurysms (MAs) are the earliest clinically observable lesions of diabetic retinopathy. Reliable automated MAs detection is thus critical for early diagnosis of diabetic retinopathy. This paper proposes a novel method for the automated MAs detection in color fundus images based on gradient vector analysis and class imbalance classification,(More)
Reliable localization of the optic disc (OD) is important for retinal image analysis and ophthalmic pathology screening. This paper presents a novel method to automatically localize ODs in retinal fundus images based on directional models. According to the characteristics of retina vessel networks, such as their origin at the OD and parabolic shape of the(More)
Diabetic retinopathy (DR) is one of the common causes of blindness, and hard exudates (HEs) are the primary and early clinical signs of DR. Thus, a reliable detection of HEs is significant for clinical diagnosis and preventing vision loss of patients. In this paper, a novel method is presented to detect HEs automatically in color retinal images. The method(More)
Intrapapillary hemorrhage with adjacent peripapillary subretinal hemorrhage (IHAPSH) is a clinical syndrome most commonly affecting myopic eyes with tilted discs that usually resolves spontaneously without treatment. Subretinal hemorrhage usually occurs peripapillary on the nasally adjacent side near the optic disc. The etiology of this condition is still(More)
In this paper, a multiscale line filter is proposed which is integrated with phase congruency to detect the network of vessels in retinal images. The proposed line filter can reduces the influence of step edges compared with Gaussian matched filter, and the post process use the phase congruency demonstrated a substantial improvement in detecting vessels(More)
This paper used the STEP AP203 files as the input information, an 3D reconstruction module was developed on the basis of Open CASCADE 3D modeling platform by using the Visual C++. The data structure of STEP neutral file was analyzed and the correspondent C++ class of its geometry and topology information was designed. By using the STEP-Based attributed(More)