......

..

IJCTA-Volume 4 Issue 2/ March-April 2013
S.No
Title/Author Name
Page No
1
Lungs Cancer Detection from MRI Image Using Image Processing Technique
-Vipin Kumar Jain,Dr. Ritu Vijay
Abstract
This paper is designed to detect the lungs caner from a MRI image, taken from a particular angle. The image shows a big spot in left part of lung that may be suspicious object, from which some part is extracted that is our ROI. Another sample of normal image is also extracted. We compare the intensity of value of both image samples and observe that cancer infected flash image has very much variation in intensity values at many palaces while normal flash image don’t show any big variation in intensity values in image.
Keywords : Cancer detection, MRI ,ROI, Segmentation, Enhancement.
179-181


  PDF

2
Audio Segmentation for Speech Regonition using Segment Features
-Prof G.M.Bhandari,Dr. R.S.Kawitkar,Prof. M.C.Borawake
Abstract
We use Search Engines to search for information across the Internet. Internet being an ever-expanding ocean of data, their importance grew with every passing day. The diversity of the information itself made it necessary to have a tool to cut down on the time spent in searching. Page Rank is a probability distribution used to represent the likelihood that a person randomly clicking on links will arrive at any particular page. The main disadvantage is that it favors older pages, because a new page, even a very good one, will not have many links unless it is part of an existing site. Trust Rank is a major factor that now replaces PageRank as the flagship of parameter groups in the Google algorithm. It is of key importance for calculating ranking positions and the crawling frequency of web sites. Page Rank (Google PR) and Trust Rank are the two main issues which are discussed frequently on various SEO forums. In this paper, we will compare these algorithms.
Keywords: Ranking, Page, Trust, Hits
182-186

  PDF

3
Biometric Fingerprint Authentication by Minutiae Extraction Using USB Token System
-Prof. Archana C.Lomte,Dr.S.B.Nikam
Abstract
Biometrics is automated methods of identifying a person or verifying the identity of a person based on a physiological or behavioral characteristic. Many body parts, personal characteristics have been suggested and used for biometric security system. Which include fingerprint, hands, face, eyes, voice etc. so all physiological characteristics are the permanent identification of every person by birth and it never change throughout the life. There are number of Biometric techniques available to fulfill the different kinds demand in the market. Every method consists number of advantages compared to the others. But as if now there is no such method able to completely satisfy the current security system. so because of this research is continuously going on to find out the newer methods that willprovide a higher security.In this paper, the different methods of biometric authentication is presented.
Keywords: Minutiae Extraction, USB Token,Biometric Technique.
187-191


  PDF

4
Network Security: Authentication using Mixed Mode Approach
-Smita Jangale, Mr.Dashrath Mane
Abstract
Text passwords have been widely used for user authentication, e.g., by almost all websites on the Internet. However, it is well-known that text passwords are insecure for a variety of reasons. For example, users tend to choose simple passwords which can be remembered easily. in favour of memorability, making them subject to dictionary attacks; and text passwords can be stolen by malicious software (e.g., keystroke loggers) when being entered from keyboards. Phishing is another serious threat to text passwords, by which, a user could be persuaded to visit a forged website and enter their passwords.
In this paper we propose a two-step authentication method to strengthen text passwords by combining them with graphical passwords. Using this approach a hybrid user authentication approach combining text passwords, recognition-based graphical passwords, and a two-step process,to provide increased security
Keywords:Graphical passwords, authentication
192-195

  PDF

5
A Font and Size Independent Content Based Retrieval System for Kannada Document Images
-Nithya.E, Dr. Ramesh Babu, Chandrakala
Abstract
This paper presents a Content based image retrieval system for Kannada Document images. Given a query word, the system returns the documents in the database in which there is a similar word, with the word highlighted. The retrieval works for Kannada document images which have different font sizes and styles. First the scanned Kannada document images are preprocessed to reduce image noise. Then segmentation is performed on the Document images up to character level. Feature Extraction is performed on the characters. Features extracted will be used to find the matching words to the query word. This System is tested through trials. The results indicate that the system is quite accurate and efficient.
Keywords—Kannada Document Images, Content based image retrieval, median filter, word segmentation, character segmentation, feature extraction, correlation coefficient, horizontal dilation, vertical dilation.
196-201


  PDF

6
EDGE Detection using Fuzzy Logic
-Natinder Kaur,Deepak Sharma
Abstract
A rule based fuzzy-approach system based on the concept of fuzzy logic is applied to the curve partition point detection and segment classification processing. The concepts of curve partitioning and grouping as observed in the human visual perceptive process is used for edge classification. In this project, a set of fuzzy rules, membership functions, and algorithms for curve partition point detecting, curve classifying and grouping are developed and implemented. With these niles, the system is capable of detecting the curve partition point and accurate classifying of the edges into a predefined set of line and curve types.
Keywords- Fuzzy logic, Fuzzy interference system, Edge detection, SOBEL, CANNY OPERATOR
202-205

  PDF

7
Learn To Personalized Image Search from Photo Sharing Websites
-Rani Borkar,Mehjbeen Tamboli,Pooja Walunj
Abstract
Social sharing websites like facebook, twitter, YouTube they are allowing user to comment, tag, like and unlike the shared documents or images. Rapid Increase in the search services for social websites has been developed. We allow user to upload their images with the visibility whether it is private or public, so that images can be shared or commented. We exploit this social annotation and propose a framework by considering user interest and query relevance to learn to personalized image search. Web search experience will be improved by generating the return list according to user interest. User generated metadata can be used to personalize image search result. The proposed framework contains three components. 1. Keyword Based Search- keyword is submitted in search engine then images search based on the tag information entered by user .2.User Specific Search- In this component the searching is performed on the basis of the user interest. The user submitted query is mapped with the interest of the user which is specified in user profile. The result on retrieval experiment shows improvement in search performance.3.Collabrative filtering-Aggregate opinion of many users to recommend new items to likeminded users. In our system users are asked to rate item on universal scale. Keywords: Social Annotation, Personalized Search, Tagging, Collaborative Filtering Data
206-208

  PDF

8
Image Registration and Nose Detection Using Affine TransformationC
-C.Victoria Priscilla,B.Poorna
Abstract
Automated face recognition face the difficulties in the human pose, face expression, lighting conditions, orientation, etc. To overcome the problem to the some extent, the proposed method works with the simple mathematical concepts and the transformation concepts which are applied with morphological operations to achieve the invariant recognition. Automatic face recognition usually normalizes the face images as the preprocessing step and then proceeds with the recognition. In the proposed method image registration is implemented using affine transformation, morphological operations and mathematical theory (trigonometric) to normalize the face which is invariant to transformations.
Keywords: Registration point, transformations, Morphological processing, Mathematical concepts, feature Extraction, Normalization.
209-216

  PDF

9
Image Compression using Array Structure
-Chandni Sharma,Navneet Randhawa
Abstract
Digital image compression is playing an important role despite the rapid progress in digital communications and mass storage devices in the recent years. The efficient storage, manipulation and transmission of digitized pictures still remain a major challenge. In applications like video streaming, satellite imaging, medical imaging and high quality photography the size of data to be transferred is incredibly large when compared to the bandwidth available in the communication channel. Data compression is the technique to reduce the redundancies in data representation in order to decrease data storage requirements and hence communication costs. Image compression addresses the problem of reducing the amount of data required to represent a digital image. Digital images contain large amount of information that need evolving effective techniques for storing and transmitting the ever increasing volumes of data. Image compression addresses the problem by reducing the amount of data required to represent a digital image. The uncompressed image data requires a large storage capacity and transmission bandwidth. The purpose of the image compression algorithm is to reduce the amount of data required to represents the image with less degradation in the visual quality and without any information loss. In a monochrome image, the neighboring pixels are more correlated. The discrete cosine transform (DCT) and wavelet transform are commonly used to reduce the redundancy between the pixels and for energy compaction. The JPEG standard uses the DCT and the JPEG2000 standard uses the wavelet Inter Color Correlation Based Enhanced Color In a color image, correlation exists between the neighboring pixels of each color channel and as well as between the color channels But pixels beyond the neighbor matrix will not match so we will introduce a new method that is based on the image byte streaming and color correlation.
Keywords: - Discrete cosine transform (DCT), wavelet transform, JPEG2000
217-220

  PDF

10
Design and Implementation of Page Replacement Algorithm for Web Proxy Caching
-Yogesh Niranjan,Shailendra Tiwari
Abstract
With an ever- increasing emphasis of human activity on internet, www is growing extensively. Which result is heavy network traffic? To overcome network traffic and latency proxy caching is one of the remedy. Proxy caching has been used to enhance the performance of user access to popular web content. Web proxy caching is a well-known technique for reducing access latencies and bandwidth consumption. As in other caching systems, a replacement policy is necessary for determining when and what to evict from the cache, and many proxy caching algorithms have been earlier. This paper proposed a page replacement algorithm for proxy server. The simulation result shows that it performs better than other algorithms like LRU, LFU and FIFO.
Key words: Web cache, Latency, Access time, proxy server, page replacement algorithm.
221-225


  PDF

11
A Questionnaire on survey of Problems in Health Department using Data Mining
-Gaurav Singla, Amandeep Verma
Abstract
Today we all know that the problems in human health are increasing day by day. There are many reasons behind this like incompetence of experienced doctors and new diseases. We give some solutions after done survey on problems in heath department. If they follow these solutions they can provide best facilities to peoples and help them to cure from these diseases. It is very important for them to come to know about new human diseases like cancer, TB, HIV, swine flu etc. According to our survey we have shown using data mining that some new diseases like swine flu and HIV is increasing rapidly in these days. It also includes a survey questionnaire which takes all the factors in to count and before starting actual survey a pilot study for this questionnaire was done, which confirms its acceptance.
Keywords: Healthcare Services, Public Expenditure on Health, Technologies, Staff, Patients, Work Culture
226-231


  PDF

12
Quick Browsing Approach for Surveillance Videos
-Cheng-Chieh Chiang, Huei-Fang Yang
Abstract
Surveillance cameras have been widely installed in large cities to monitor and record human activities either in inside or outside environments. To efficiently utilize surveillance videos, how to extract valuable information from hundreds-of-hours videos becomes an important task. This paper proposes a quick browsing approach to help the user quickly look for targets of interest in surveillance videos. Our basic idea is to collect all of moving objects which carry the most significant information in a surveillance video to construct a corresponding compact video by tuning spatiotemporal positions of these moving objects. Our proposed compact video cannot only compress the video length but also preserve the essential activities involved in the original surveillance video. This paper presents the details of our browsing system and the approach to producing the compact video from a source surveillance video.
Keywords- surveillance video, compact video, moving object, background modelling
232-237

  PDF

13
TCM: Password Protection Using Text And Color Matrix
-Shruti Bhavsar,Tejasvini Waingankar,Rupali Thorat
Abstract
In today’s world,there are many techniques for protecting the passwords. These techniques are vulnerable to different attacks such as shoulder surfing, eves dropping, dictionary attack, spyware etc. Graphical passwords have their own disadvantages. Complicated passwords are difficult to remember. For this,we have come up with new technique which is coupled with two new techniques.We are using text password and color passsword for which session passwords are created for both. For every login user input is different password. The password is generated using text and color rating which are resistant to various attacks. It can be used where security is of main purpose such as net banking, trade transactions , server-side etc.
238-243

  PDF

14
A Questionnaire of student satisfaction from college using data Mining
-Hardeep kaur,Kiran bala,Preet inder kaur,Harjit Kaur
Abstract
Today a questionnaire of student satisfaction is adopted by Universities & very high level colleges but many medium level colleges are enable to decide upon proper implementation of student satisfaction. Although data mining has been successful implemented in the business world for some time now, its use in higher education is still relatively new, i.e. its use is intended for identification and extraction of new and potentially valuable knowledge from the data.Using data mining the aim was to develop a model which can derive the conclusion on students' academic success.Student Satisfaction Surveys are commonly used in higher education institutions internationally as feedback mechanisms to determine the level of delivery of education. More importantly, they provide data to management on student perceptions of education delivery. They are designed to encourage action for improvement, which forms part of appropriate accountability procedures at the institution. The analysis focused on those areas that students rated as important and were satisfied with, as well as those areas that were high in importance, but low on satisfaction.
Keywords:Educational data mining, online learning, online teaching, student-faculty interaction, student satisfaction, Student achievement, Motivation, higher education.
244-247

  PDF

15
A Survey on Manet Security Challenges and Routing Protocols
-B.Praveen Kumar,P.Chandra,Sekhar N.Papanna,B.Bharath Bhushan
Abstract
The advancement in the field of internet due to wireless networking technologies. It gives rise to many new applications. In the past of few decades, we have seen the advancement in wireless networks. The emerging capabilities of mobile devices have given a new direction to the internet, which decreases the cost and allow us to use infrastructure wireless networks and infrastructure less wireless networks (i.e. Mobile Ad Hoc Wireless Network).With so many applications that MANETs provides us, there are still some challenges that have to overcome..The infrastructureless and the dynamic nature of these networks demands new set of networking strategies to be implemented in order to provide efficient end-to-end communication. This along with the diverse application of these networks in many different scenarios such as battlefield and disaster recovery, have seen MANETs being researched by many different organisations and institutes. MANETs employ the traditional TCP/IP structure to provide end-to-end communication between nodes. One interesting research area in MANET is routing. Routing in the MANETs is a challenging task and has received a tremendous amount of attention from researches. Due to lack of a defined central authority, securitizing the routing process becomes a challenging task thereby leaving MANETs vulnerable to attacks, which results in deterioration in the performance characteristics as well as raises a serious question mark about the reliability of such networks.. In this paper, we provide the history of MANET, challenges (issues) involve in MANET and its some applications and an overview of a wide range of routing protocols proposed. We also provide a performance comparison of all routing protocols and suggest which protocols may perform best in large networks. And also the known routing attacks and the proposed counter measures to these attacks in various works.
Keywords-Manet,Routing,Routing protocols,Security,Attacks.
248-256

  PDF

16
Impact of Routing Overhead in A Real-Time MANET Environment
-P. Chandra Sekhar, M.R. Pavan Kumar, B.Praveen Kumar,Ch. Koteswararao
Abstract
Mobile Ad Hoc Network (MANETs) is collection of mobile/semi mobile nodes with no existing pre-established infrastructure, forming a temporary network. Mobile Ad hoc Networks are highly dynamic networks. Quality of Service (QoS) routing in such networks is usually limited by the network breakage due to either node mobility or energy depletion of the mobile nodes. Another issue that effects the QoS routing is routing overhead. Due to high mobility of nodes in mobile ad hoc networks (MANETs), there exist frequent link breakages which lead to frequent path failures and route discoveries. The overhead of a route discovery cannot be neglected. In this paper we described the impact of routing overhead in a real-time-time MANET environment with suitable scenarios. And also we suggested some methods to reduce the routing overhead over the network such that to improve the Quality of Service (QoS) routing in MANETS.
Index Terms - Mobile ad hoc networks, network connectivity, dynamic networks, routing overhead.
257-263

  PDF

17
A Questionnaire on Government Education System using Data Mining
-Preet Inder Kaur,Harjit Kaur,Hardeep Kaur
Abstract
Education has been given high priority by India’s central and state governments and continues to grow fast. Education access has been expanded by investment in education infrastructure and recruitment of teachers. In higher education too, the number of providers continues to rise rapidly. Private sector involvement is on the rise. While it helps expand education infrastructure, particularly in higher education, access has not always been assured and the availability of student loans for higher education needs to improve. In higher education the government has proposed reforms which have the potential to bring about much-needed improvements in regulatory effectiveness. Increasing the number of institutions subjected to quality assessments will be important for lifting standards across the higher education system, while reform of recruitment and promotion mechanisms could help attract and retain talent in academia.
Keywords: Government Education, educations, colleges, education policy, primary education, secondary education, education expenditures
264-267

  PDF

18
Identification of Person by fusion and using Scale Invariant Feature Transform
-V. L. Bagal,Prof. N. B. Sambre,Dr. P.Malathi
Abstract
Traditionally, passwords and ID cards have been used to restrict access to secure systems. However, security can be easily breached in these systems when a password is divulged to an unauthorized user or a card is stolen by an impostor. By using biometrics it is possible to establish an identity based on “who you are,”Current biometric systems make use of fingerprints, hand geometry, iris, retina, face, facial thermograms, signature, gait, palm print and voiceprint to establish a person’s identity.
We present multimodal face and fingerprint biometric verification system to improve the performance. We presented fusion of face and fingerprint to provide better accuracy. Simulation results shows that proposed multimodal recognition system is very efficient to reduce the false rejection rate. Here we can take two images, decomposition of images is carried out by using DWT i.e. Discrete Wavelet Transform, after decomposition , fusion of decomposition is carried out which produces a fused image. Then SIFT (Scale Invariant Feature Transform), features are extracted from the fused image that are stored in database. After extracting SIFT features matching are performed.
268-272


  PDF

19
Fuzzy sets in Data mining- A Review
-Muntaha Ahmad,Prof. Dr Ajay Rana
Abstract
Data mining, also called knowledge discovery in databases, is regarded as a non-trivial process of identifying valid, novel, potentially useful, and ultimately understandable knowledge in large-scale data. This paper briefly reviews some typical applications and highlights potential contributions that fuzzy set theory can make to data mining. In this connection, some advantages of fuzzy methods for representing and mining vague patterns in data are especially emphasized. The aim of this paper is to convey an impression of the current status and prospects of fuzzy set in data mining, especially highlighting potential features and advantages of fuzzy in comparison with non-fuzzy approaches.
Keywords: Fuzzy set; Data mining; Association rules; Fuzzy rule bases; Clustering; Decision trees; Gradual nature
273-278

  PDF

20
A UML/MARTE Detection of Starvation and Deadlocks at the Design Level in Concurrent System
-C.Revathi,Prof.M.Mythily
Abstract
Concurrency problem is when more than one job is executed in parallel. Concurrency problems such as deadlock and starvation should be identified in design process. The existing work is based on the analysis of design models expressed in the Unified Modelling Language (UML).It uses a genetic algorithm to detect concurrency problem. Concurrency information is extracted from system UML models that comply with the UML Modeling and Analysis of Real Time Embedded System (MARTE) profile. Genetic Algorithms (GA) is used for optimizing the search space to efficiently detect deadlock and starvation, Even though it handles large thread execution chromosomes, it failed to achieve accuracy and complexity. To overcome these issues, a Particle Swarm Optimization algorithm (PSO) is proposed which will reduce complexity and increase accuracy. The PSO can optimize thread execution interleaving that have a high probability of revealing deadlock and starvation faults. The concurrency problem such as deadlock and starvation approach can be implemented in JAVA. The result can be compared to the GA and PSO algorithm.
Keywords: Particle Swarm optimization (PSO), RAG, Deadlock and Starvation.
279-285


  PDF

 
 
IJCTA © Copyrights 2010| All Rights Reserved.

This work is licensed under a Creative Commons Attribution 2.5 India License.