Browsing by Author "Sinha, N."

Filter results by typing the first few letters
Now showing 1 - 6 of 6
  • No Thumbnail Available
    Item
    An Integrated Method for Realtime 2D Hand Pose Detection
    (Association for Computing Machinery, 2020) Rao, N.; Sinha, N.
    We present an integrated, real-time approach for 2D hand pose detection from a monocular RGB image, with a common backbone shared between the bounding box detector and the keypoint detector subnets. This is in contrast to traditional methods which use two separate models for hand localization and keypoint detection with no sharing of features. We build on the popular RetinaNet architecture for object detection and introduce an integrated model which performs both hand localization and keypoint detection in real-time. We evaluate our approach on two different datasets and show evidence that our model obtains accurate results. © 2021 Owner/Author.
  • No Thumbnail Available
    Item
    Automatic Optic Disc segmentation using maximum intensity variation
    (2013) Kumar, V.; Sinha, N.
    Optic disc (OD) segmentation is an important step in automating eye screening for pathological conditions. In this paper, we propose an intensity-based approach to detect the OD boundary, given OD center. OD center is utilized to crop the sub-image that encloses the OD, within which candidate contour points are obtained. Points of maximum intensity variation, both horizontally and vertically, are chosen as candidate contour points. Iterative curve fitting is carried out, incorporating smoothness constraints. The area within the contour is checked for values of mean intensity, variance and compactness. The algorithm is applied on 152 images taken from two public datasets, DIARETDB1 and MESSIDOR. The validation criteria used are common area overlapping between automated segmentation and true OD region (score), sensitivity and Mean Distance to Closest Point (MDCP). The algorithm renders, on an average, a score value of 90%, sensitivity of 93% and MDCP of 8.3 pixels. � 2013 IEEE.
  • No Thumbnail Available
    Item
    Automatic Optic Disc segmentation using maximum intensity variation
    (2013) Kumar, V.; Sinha, N.
    Optic disc (OD) segmentation is an important step in automating eye screening for pathological conditions. In this paper, we propose an intensity-based approach to detect the OD boundary, given OD center. OD center is utilized to crop the sub-image that encloses the OD, within which candidate contour points are obtained. Points of maximum intensity variation, both horizontally and vertically, are chosen as candidate contour points. Iterative curve fitting is carried out, incorporating smoothness constraints. The area within the contour is checked for values of mean intensity, variance and compactness. The algorithm is applied on 152 images taken from two public datasets, DIARETDB1 and MESSIDOR. The validation criteria used are common area overlapping between automated segmentation and true OD region (score), sensitivity and Mean Distance to Closest Point (MDCP). The algorithm renders, on an average, a score value of 90%, sensitivity of 93% and MDCP of 8.3 pixels. © 2013 IEEE.
  • No Thumbnail Available
    Item
    Cuckoo search for influence maximization in social networks
    (2016) Sinha, N.; Annappa, B.
    In a social network, the influence maximization is to find out the optimal set of seeds, by which influence can be maximized at the end of diffusion process. The approaches which are already existing are greedy approaches, genetic algorithm and ant colony optimization. Eventhough these existing algorithms take more time for diffusion, they are not able to generate a good number of influenced nodes. In this paper, a Cuckoo Search Diffusion Model (CSDM) is proposed which is based on a metaheuristic approach known as the Cuckoo Search Algorithm. It uses fewer parameters than any other metaheuristic approaches. Therefore parameter tuning is an easy task for this algorithm which is the main advantage of the Cuckoo Search algorithm. Experimental results show that this model gives better results than previous works. � Springer India 2016.
  • No Thumbnail Available
    Item
    Cuckoo search for influence maximization in social networks
    (Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2016) Sinha, N.; Annappa, B.
    In a social network, the influence maximization is to find out the optimal set of seeds, by which influence can be maximized at the end of diffusion process. The approaches which are already existing are greedy approaches, genetic algorithm and ant colony optimization. Eventhough these existing algorithms take more time for diffusion, they are not able to generate a good number of influenced nodes. In this paper, a Cuckoo Search Diffusion Model (CSDM) is proposed which is based on a metaheuristic approach known as the Cuckoo Search Algorithm. It uses fewer parameters than any other metaheuristic approaches. Therefore parameter tuning is an easy task for this algorithm which is the main advantage of the Cuckoo Search algorithm. Experimental results show that this model gives better results than previous works. © Springer India 2016.
  • No Thumbnail Available
    Item
    Data privacy preservation using aes-gcm encryption in Heroku cloud
    (Blue Eyes Intelligence Engineering and Sciences Publication, 2019) Das, P.K.; Sinha, N.; Annappa, A.
    The increasing popularity of cloud data storage and its ever-rising versatility, shows that cloud computing is one of the most widely excepted phenomena. It not only helps with powerful computing facilities but also reduce a huge amount of computational cost. And with such high demand for storage has raised the growth of the cloud service industry that provides an affordable, easy-to-use and remotely-accessible services. But like every other emerging technology it carries some inherent security risks associated and cloud storage is no exception. The prime reason behind it is that users have to blindly trust the third parties while storing the useful information, which may not work in the best of interest. Hence, to ensure the privacy of sensitive information is primarily important for any public, third-party cloud. In this paper, we mainly focus on proposing a secure cloud framework with encrypting sensitive data’s using AES-GCM cryptographic techniques in HEROKU cloud platform. Here we tried to implement Heroku as a cloud computing platform, used the AES-GCM algorithm and evaluate the performance of the said algorithm. Moreover, analyses the performance of AES/GCM execution time with respect to given inputs of data. © BEIESP.