Detecting blood vessels is a vital task in retinal image analysis. The task is more challenging with the presence of bright and dark lesions in retinal images. Here, a method is proposed to detect vessels in both normal and abnormal retinal fundus images based on their linear features. First, the negative impact of bright lesions is reduced by using K-means segmentation in a perceptive space. Then, a multi-scale line operator is utilized to detect vessels while ignoring some of the dark lesions, which have intensity structures different from the line-shaped vessels in the retina. The proposed algorithm is tested on two publicly available STARE and DRIVE databases. The performance of the method is measured by calculating the area under the receiver operating characteristic curve and the segmentation accuracy. The proposed method achieves 0.9483 and 0.9387 localization accuracy against STARE and DRIVE respectively.

This paper presents a hybrid approach by a combination of particle swarm optimization (PSO) and parallel simulated annealing (PSA). PSO is a population based heuristic method that sometimes traps in local maximum. To cope with this problem, we used simulated annealing. However, since SA is extremely greedy regarding the number of iterations, a parallel approach can be used to decrease total iterations. In this article, we used discrete PSO to achieve a good local maximum. Then parallel SA (PSA) is employed to escape from this locality. Study on the n-queens problem shows that PSO-PSA is promising in solving constraint satisfaction problems.

No abstract