A Novel Efficient Approach for the Screening of New Abnormal Blood Vessels in Color Fundus Images

Abstract

Reliable detection of abnormal vessels in color fundus image is still a great issue in medical image processing. An Efficient and robust approach for automatic detection of abnormal blood vessels in digital color fundus images is presented in this paper. First, the fundus images are preprocessed by applying a 3x3 median filter. Then, the images are segmented using a novel morphological operation. To classify these segmented image into normal and abnormal, seven features based on shape, contrast, position and density are extracted. Finally, these features are classified using a non-linear Support Vector Machine (SVM) Classifier. The average computation time for blood vessel detection was less than 2.4sec with a success rate of 99%. The performance of our proposed method is measured on publically available DRIVE and STARE database.

A Non-invasive Optimized System for rapid detection of Gilomas Brain Tumor using Machine Learning

“…An effective machine-learning method for the detection and classification of the kind of terminal disease in cerebral images obtained by magnetic resonance imaging (MRI) [16] Due to their superior resistance to rotation, scaling, and noise issues, KAZE and SURF are used to extract the image's gaussian features, while KAZE is used to recover the image's non-linear features. The suggested untargeted lipidomic [17] was initially conducted using a finding group (n = 107). The data were analysed by a differentiating model that focuses on classifiers to provide a list of possible indicators.…”

Efficient approach for the automatic detection of haemorrhages in colour retinal images

“…The filtered L-component is then enhanced by applying CLAHE algorithm [16,17]. Finally, the enhanced L-component is added with chromaticity layer (a and b components) and it is converted back to original RGB colour space.…”