{"title":"Retinal vessel segmentation using Gabor filter and artificial neural network","authors":"M. Nandy, M. Banerjee","doi":"10.1109/EAIT.2012.6407885","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6407885","url":null,"abstract":"This paper demonstrates an automated segmentation scheme of retinal vasculature using Gabor filter bank, which is optimized on the basis of entropy. Different distributions of filter responses are encoded into features and the vasculature of normal and abnormal retina are segmented by artificial neural network(ANN). The training set of labeled pixels is obtained from the ground truth images of DRIVE database. The Receiver Operating Characteristics (ROC) in both abnormal and normal cases shows 96.16% accuracy.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114253305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Embedded DSP software optimization: Strategies and techniques","authors":"R. Dasgupta","doi":"10.1109/EAIT.2012.6407916","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6407916","url":null,"abstract":"DSP applications are characterized by the presence of a dedicated DSP and specific embedded software that runs on it. As the complexity of DSP applications grow rapidly, great demands are placed to perform more and more data intensive computations. The multi-dimensional requirements that are emerging in commercial DSP products such as cost, time-to-market, size, power consumption, latency, and throughput, further increase the challenge of DSP software implementation. Therefore to learn and apply best engineering practices on how to write and optimize DSP program is becoming very much essential.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114228694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Pattern Recognition for damage detection in aerospace vehicle structures","authors":"S. Goswami, P. Bhattacharya","doi":"10.1109/EAIT.2012.6407890","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6407890","url":null,"abstract":"A Pattern Recognition based damage detection scheme for aerospace vehicle structures is proposed. It involves capturing mechanical vibration signals from plate like structures using displacement sensors; removal of noise and extraction of features using Wavelet Transform based signal processing techniques, and training a Neural Network Ensemble to classify and identify the damages that appear in the structure. A few cases are studied. Encouraging results are found in classifying single damages in the structure. However success rates dropped in case of identifying multiple damages for the same structural form. A sensor placement strategy is then drawn out that improved the results significantly.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114543191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Manna, P. Khaitan, S. Chattopadhyay, I. Sengupta
{"title":"Particle Swarm Optimization based technique for Network-on-Chip testing","authors":"K. Manna, P. Khaitan, S. Chattopadhyay, I. Sengupta","doi":"10.1109/EAIT.2012.6407863","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6407863","url":null,"abstract":"Network-on-Chip (NoC) has emerged as a viable solution for the modern SoC design. It has guaranteed the reusability, scalability and parallelism in communication. Reuse of NoC as a test access mechanism reduces the testing cost. In this paper we present a Particle Swarm Optimization based technique to solve the test scheduling problem of NoC. In this method we have considered deterministic routing to establish the path for each core. Experimental results show that our approach requires less test time compared to other heuristics.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115748599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Network-on-chip routing using Structural Diametrical 2D mesh architecture","authors":"P. Ghosal, T. S. Das","doi":"10.1109/EAIT.2012.6408020","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6408020","url":null,"abstract":"Performance of a NoC (network-on-chip) strongly depends on its underlying architecture and related routing techniques. A structural scalable interconnection architecture may significantly increase the performance of a NoC in terms of scalability, modularity, transport latency and parallelism in communication. Well-constructed network architecture will also balance load of the network and try to reduce the chance of causing a hot spot on the network. In this work, our primary objective was to design an efficient NoC architecture to increase its performance in all these aspects with distribution of the load across the network and trying to reduce the diameter of the network in order to reduce the cost of routing. In this paper, we present a new architecture, called Structural Diametrical 2D (SD2D) mesh based on Structural Diametrical XY deterministic routing algorithm that tries to balance the load of the network, increase the level of parallelism, ensures that the packet will always reach the destination through the possible shortest path, and the path is deadlock free.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116400957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"DMODL — Distributed Multi-hop On-Demand Localization using virtual anchor nodes in Wireless Sensor Networks","authors":"C. M. Roopa, R. Sumathi","doi":"10.1109/EAIT.2012.6407987","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6407987","url":null,"abstract":"Localization system is not only for location identification, but also provides the base for routing, density control, tracking and a number of other communication network aspects. One of the main methods to improve localization accuracy is to increase the number of anchor nodes. However number of anchor nodes is always limited due to constraints such as hardware cost, energy consumption and so on. In this paper, we propose a novel Distributed Multi-hop On-Demand Localization(DMODL)algorithm, in which sensor nodes will localize as and when demand comes with the help of minimum GPS embedded nodes called actual anchor node(AAN). The localized nodes become virtual anchor node(VAN) and assist remaining sensor nodes to localize along with AAN. As a result, the DMODL achieves high localization ratio and energy efficiency by minimizing the hardware cost and communication overhead. Simulation results demonstrate that, the DMODL algorithm provides significant improvements in the number of VAN, localization ratio, energy efficiency.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128085312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Authentication technique for gray images using DCT (ATGIDCT)","authors":"A. Goswami, D. Pal, N. Ghoshal","doi":"10.1109/EAIT.2012.6407989","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6407989","url":null,"abstract":"This paper describes a novel steganographic technique based on Discrete Cosine Transform (DCT) for image authentication in frequency domain. The embedding algorithm applies DCT on a sub-image block called mask of size 2 × 2 of spatial components in row major order for the whole carrier image. Single bit of authenticating secret message/image is fabricated only in the real part of the frequency component of 2nd, 3rd and 4th carrier image bytes of each mask. The positions for embedding are pseudorandom in nature owing to a self derived hash function, which helps to improve the robustness of the technique. Also a minor re-adjustment is implemented only on the first component of each mask after embedding to keep the pixel values positive and non fractional in spatial domain. Experimental results prove statistically significantly enhanced performance of the proposed watermark technique.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128542850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel hyperstring based descriptor for an improved representation of motion trajectory and retrieval of similar video shots with static camera","authors":"C. Chattopadhyay, S. Das","doi":"10.1109/EAIT.2012.6407889","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6407889","url":null,"abstract":"A framework has been proposed for representing the trajectory of a moving object, using a novel hyperstring based approach for efficient retrieval of video shots. The hyperstring based model unifies both the structural and kinematic features for an improved representation of the trajectory. A Constraint-driven Adjacency Graph matching (CAGM) algorithm has been proposed to measure the similarity between a pair of query and model hyperstrings. Experiments have been performed on benchmark datasets of trajectories (one synthetic and three real-world video shots), to assess the performance (using Precision-Recall metric) of the proposed model. Results have been compared with two similar published works on video retrieval using trajectories, to demonstrate the superiority of our proposed framework.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125491555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"CSRP: A Centralized Secure Routing Protocol for mobile ad hoc network","authors":"Sourav Kumar Bhoi, I. Faruk, P. M. Khilar","doi":"10.1109/EAIT.2012.6407995","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6407995","url":null,"abstract":"Security in MANET is a grand challenge problem nowadays. The main security issues in MANET are identification and privacy. To combat with these problems, many secure routing protocols have been designed to reduce the security threats. In this paper, we have proposed a Centralized Secure Routing Protocol (CSRP) to enhance the security levels in the architecture to prevent the network against active and passive attacks. A Master Node (MN) is used in this architecture to control and manage the network security and data delivery. In the first step we have recognized the nodes and in the second step we have established session keys between the nodes for safe communication. The data delivery is done by encryption/decryption mechanism using session key. CSRP algorithm is mainly designed for secure and safe routing.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125521007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Barun Kumar Bairagi, Arpitam Chatterjee, Samir Chandra Das, B. Tudu
{"title":"Expressions invariant face recognition using SURF and Gabor features","authors":"Barun Kumar Bairagi, Arpitam Chatterjee, Samir Chandra Das, B. Tudu","doi":"10.1109/EAIT.2012.6407888","DOIUrl":"https://doi.org/10.1109/EAIT.2012.6407888","url":null,"abstract":"Face recognition is an active research area in the field of computer vision and pattern recognition. Despite of considerable research and developments a time and memory efficient method that is robust to different factors e.g. facial expressions, pose, illumination, age, etc. remains a major challenges. This paper presents expressions invariant face recognition by detecting the fiducial points and employing speeded up robust feature (SURF) along with Gabor filter. The presented method is tested with test images with different expressions and found to be a better performer over the conventional SURF algorithm.","PeriodicalId":194103,"journal":{"name":"2012 Third International Conference on Emerging Applications of Information Technology","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124669669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}