Search

Diabetic Retinopathy is an eye disease caused in patients with diabetic which leads to blindness. So, detection of Diabetic retinopathy at early stage prevents loss of vision. In this paper, we proposed an effective segmentation method that combines modified Fuzzy C Means (FCM) clustering with spatial features and Inertia Weight Particle Swarm optimization (IWPSO) for detection of Diabetic Retinopathy. The input human retinal fundus images are filtered by a median filter to reduce speckle noise and then contrast enhancement is done by Adaptive Histogram Equalization. Then segmented by various methods like Chaotic Particle Swarm optimization (CPSO), Inertia Weight Particle Swarm optimization (IWPSO) and our proposed method. The performance of these methods is analyzed using the metrics Accuracy, True Positive Rate (Sensitivity), True Negative Rate (Specificity), False Positive Rate and False Negative Rate. A comparative analysis has been made for the above said segmentation algorithms and the results proved that our proposed method achieved the best than the other methods.

Curiosity to know the unknown and desire to behold what we need are important reasons for advancement in technology. Humans had the ability of vision to know what the world is like and through which we were able to explore and visualize the unknown and the needed respectively. As its result, computer vision was introduced to the world at late 1970's which was a field which consists of various discipline. This was developed to automate the process of what human visual system can perform. It concentrates on the theory of artificial intelligence which uses images as source of information. There are multiple forms to represent image data such as video sequence, views from multiple camera or multi-dimensional data from the medical scanner etc. In this article, the video which has been used for surveillance and entertainment has been studied in various perspective of its application. Thus, under computer vision the video could be explicitly used for newer implementation and experiments where they could be enhanced to a lot more than just a visual source.

Voronoi diagram (VD) is an extensively studied geometric entity since it has applications in fields such as computer graphics, computer vision, geometric modeling etc. In this paper, an algorithm for computing the VD of a set of planar freeform closed convex curves has been developed, without approximating the curves using points or lines. Algorithms for VD predominantly lie on computing the bisectors, a geometrically complex and a high degree curve even for inputs of low degree. Hence, a lot of processing is required to compute bisector segments that contribute to VD as well as in the computation of branch points. In this paper, it has been shown that computation of a branch point is possible without first computing either the bisector or segments of it. The algorithm uses the minimum antipodal discs (MADs) for all pairs of curves. Three touch discs (TTD) (circles touching three curves) are computed only for a specific set of three curves. Decision criteria for a TTD to become a branch disc (BD, i.e. empty TTD) have been addressed without using explicit curve containment check. Local computations of Voronoi segments are then done. The algorithm gives all branch points via centers of the branch discs along with the segments of curves that will contribute to VD. Results of implementation are provided along with analysis of the algorithm.

GPS receivers have a major drawback: they don't work properly under multi-storey concrete structures, for e.g. in underground car parks, University buildings, shopping malls, factory complexes etc. A navigation system for such huge enclosed spaces, which does not rely on a GPS is very desirable for visitors to such places who do not know the layout of the place. This paper presents the design and development of a low-cost GPS-less navigation system based on TI Stellaris-LM3S3748, which could help visitors find their way around such places.