Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
Search Results
Item FIVDL: Fingerprint Image Verification using Dictionary Learning(Elsevier, 2015) Arunalatha, J.S.; Tejaswi, V.; Shaila, K.; Anvekar, D.; Venugopal, K.R.; Iyengar, S.S.; Patnaik, L.M.Fingerprints are used for identification in forensics and are classified into Manual and Automatic. Automatic fingerprint identification system is classified into Latent and Exemplar. A novel Exemplar technique of Fingerprint Image Verification using Dictionary Learning (FIVDL) is proposed to improve the performance of low quality fingerprints, where Dictionary learning method reduces the time complexity by using block processing instead of pixel processing. The dynamic range of an image is adjusted by using Successive Mean Quantization Transform (SMQT) technique and the frequency domain noise is reduced using spectral frequency Histogram Equalization. Then, an adaptive nonlinear dynamic range adjustment technique is utilized to determine the local spectral features on corresponding fingerprint ridge frequency and orientation. The dictionary is constructed using spatial fundamental frequency that is determined from the spectral features. These dictionaries help in removing the spurious noise present in fingerprints and reduce the time complexity by using block processing instead of pixel processing. Further, dictionaries are used to reconstruct the image for matching. The proposed FIVDL is verified on FVC database sets and Experimental result shows an improvement over the state-of-the-art techniques. © 2015 The Authors.Item Query click and text similarity graph for query suggestions(Springer Verlag service@springer.de, 2015) Sejal, D.; Shailesh, K.G.; Tejaswi, V.; Anvekar, D.; Venugopa, K.R.; Iyengar, S.S.; Patnaik, L.M.Query suggestion is an important feature of the search engine with the explosive and diverse growth of web contents. Different kind of suggestions like query, image, movies, music and book etc. are used every day. Various types of data sources are used for the suggestions. If we model the data into various kinds of graphs then we can build a general method for any suggestions. In this paper, we have proposed a general method for query suggestion by combining two graphs: (1) query click graph which captures the relationship between queries frequently clicked on common URLs and (2) query text similarity graph which finds the similarity between two queries using Jaccard similarity. The proposed method provides literally as well as semantically relevant queries for users’ need. Simulation results show that the proposed algorithm outperforms heat diffusion method by providing more number of relevant queries. It can be used for recommendation tasks like query, image, and product suggestion. © Springer International Publishing Switzerland 2015.Item SALR: Secure adaptive load-balancing routing in service oriented wireless sensor networks(Institute of Electrical and Electronics Engineers Inc., 2015) Lata, B.T.; Sumukha, T.V.; Suhas, H.; Tejaswi, V.; Shaila, K.; Venugopal, K.R.; Anvekar, D.; Patnaik, L.M.Congestion control and secure data transfer are the major factors that enhance the efficiency of Service Oriented Wireless Sensor Networks. It is desirable to modify the routing and security schemes adaptively in order to respond effectively to the rapidly changing Network State. Adding more complexities to the routing and security schemes increases the end-to-end delay which is not acceptable in Service Oriented WSNs which are mostly in real time. We propose an algorithm Secure Adaptive Load-Balancing Routing (SALR) protocol, in which the routing decision is taken at every hop considering the unforeseen changes in the network. Multipath selection based on Node Strength is done at every hop to decide the most secure and least congested route. The system predicts the best route rather than running the congestion detection and security schemes repeatedly. Simulation results show that security and latency performance is better than reported protocols. © 2015 IEEE.Item QRGQR: Query relevance graph for query recommendation(Institute of Electrical and Electronics Engineers Inc., 2015) Sejal, D.; Shailesh, K.G.; Tejaswi, V.; Anvekar, D.; Venugopal, K.R.; Iyengar, S.S.; Patnaik, L.M.Query recommendation is an important feature of the search engine with the explosive and diverse growth of web contents. Different kind of recommendation like query, image, movies, music and book etc. Are used every day. Various types of data sources are used for the recommendations. If we model the data into various kinds of graphs then we can build a general method for any recommendation. In this paper, we have proposed a general method for query recommendation by combining two graphs: 1) query click graph which captures the relationship between queries frequently clicked on common URLs and 2) query text similarity graph which finds the similarity between two queries using Jaccard similarity. The proposed method provides literally as well as semantically relevant queries for users' need. Simulation results show that the proposed algorithm outperforms heat diffusion method by providing more number of relevant queries. It can be used for recommendation tasks like query, image, and product recommendation. © 2015 IEEE.Item PCVOS: Principal component variances based off-line signature verification(Institute of Electrical and Electronics Engineers Inc., 2015) Arunalatha, J.S.; Prashanth, C.R.; Tejaswi, V.; Shaila, K.; Raja, K.B.; Anvekar, D.; Venugopal, K.R.; Iyengar, S.S.; Patnaik, L.M.Offline signature verification system is widely used as a behavioral biometric for identifying a person. This behavioral biometric trait is a challenge in designing the system that has to counter intrapersonal and interpersonal variations. In this paper, we propose a novel technique PCVOS: Principal Component Variances based Off-line Signature Verification on two critical parameters viz., the Pixel Density (PD) and the Centre of Gravity (CoG) distance. It consists of two parallel processes, namely Signature training which involves extraction of features from the samples of database and Test signature analysis which performs extraction of features from the test samples. The trained values from the database are compared with the features of the test signature using Principal Component Analysis (PCA). The PCVOS algorithm shows a notable improvement over the algorithms in [21], [22] and [23]. © 2015 IEEE.Item WNPWR: Web navigation prediction framework for webpage recommendation(Institute of Electrical and Electronics Engineers Inc., 2015) Sejal, D.; Kamalakant, T.; Tejaswi, V.; Anvekar, D.; Venugopal, K.R.; Iyengar, S.S.; Patnaik, L.M.Huge amount of user request data is generated in web-log. Predicting users' future requests based on previously visited pages is important for web page recommendation, reduction of latency, on-line advertising etc. These applications compromise with prediction accuracy and modelling complexity. we propose a Web Navigation Prediction Framework for webpage Recommendation(WNPWR) which creates and generates a classifier based on sessions as training examples. As sessions are used as training examples, they are created by calculating average time on visiting web pages rather than traditional method which uses 30 minutes as default timeout. This paper uses standard benchmark datasets to analyze and compare our framework with two-tier prediction framework. Simulation results shows that our generated classifier framework WNPWR outperforms two-tier prediction framework in prediction accuracy and time. © 2015 IEEE.