{"title":"Improved recognition rate of language identification system in noisy environment","authors":"Randheer Bagi, Jainath Yadav, K. S. Rao","doi":"10.1109/IC3.2015.7346681","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346681","url":null,"abstract":"Spoken language identification is a technique to model and classify the language, spoken by an unknown person. Language identification task is more challenging in environmental condition due to addition of different types of noise. Presence of noise in speech signal causes several nuisances. This paper covers several aspect of language identification in noisy environment. Experiments have been carried out using speaker independent Multilingual Indian Language Speech Corpus of Indian Institute of Technology, Kharagpur (IITKGP-MLILSC). In the proposed method, acoustic features are extracted from the raw speech signal. Gaussian Mixture Models (GMMs) are used to train the language models. To analyze the behavior of the identification system in a noisy environment, white noise is added into the clean speech corpus at different noise levels. Recognition rate of noisy speech was near about 14.84%. Significant performance degradation was observed compared to the clean speech. To overcome this adverse identification condition, reduction of noise is necessary. Spectral Subtraction (SS) and Minimum Mean Square Error (MMSE) are used to suppress the noise. The overall average recognition rate of the proposed system using clean speech is 56.48%. In case of enhanced speech using SS and MMSE, recognition rate is 35.91% and 35.53% respectively, which is significant improvement over the recognition rate of noisy speech (14.84%).","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121235291","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":"DocTool - a tool for visualizing software projects using graph database","authors":"A. Sadar, J. VinithaPanicker","doi":"10.1109/IC3.2015.7346721","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346721","url":null,"abstract":"In an organization a software development life cycle consists of teams working in different structural hierarchies. Maintaining a complex software where continuous additions and updations are performed by different developers is a challenging task. Also there is a certain amount of latency in communication between two teams regarding an entity of interest in the software. Different software visualization tools have been proposed to address these issues. Many of them provide a view of the software structure by parsing through the source code and analyzing the depth and quality of code. In this paper we propose a DocTool which provide a simple and easy to use solution to two problems: (i) Visualizing the entities of a software and their properties and (ii) Visualizing the workflow in the software. The tool uses a set of json files and a graph database as the backbone. The solution proposed is very simple and provides the user total control over the data he wants to focus on. The tool can be implemented for softwares developed in any kind of platform. The design and implementation of the tool for a Java Web Application software are discussed in this paper.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131887020","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 Scientometric analysis of computer science research in India","authors":"Khushboo Singhal, S. Banshal, A. Uddin, V. Singh","doi":"10.1109/IC3.2015.7346675","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346675","url":null,"abstract":"This paper presents results of our Scientometrics and text-based analysis of computer science research output from India during the last 25 years. We have collected the data for research output indexed in Scopus and performed a detailed computational analysis to obtain important indicators, such as total research output, citation impact, collaboration patterns, top institutions/authors/publication sources. We also performed a text-based analysis on keywords of all papers indexed in Scopus to identify thematic trends during the period. The analytical results present a detailed and useful picture of status and competence of CS domain research in India.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134312091","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":"Removing occlusion using even odd interlacing for efficient class room teaching","authors":"V. Saxena, Ananya, Juhi Shukla","doi":"10.1109/IC3.2015.7346712","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346712","url":null,"abstract":"Occlusion is any unwanted object that hinders the view of the objects or scenes behind them. Many times the viewer cannot comprehend what is present in the background due to the continuous presence of the occlusion. In a similar setting of classroom /boardroom occlusion of the blackboard/whiteboard contents because of the presence of certain objects like teachers and other students walking in front of the board, leads to missing out on the valuable components of board contents. Capturing the board content in presence of the such occlusions is a difficult task. The work presented in this paper focuses particularly on the meeting and/or classroom that use whiteboard/blackboard heavily for lectures, project planning meetings etc. In these scenarios, boards are considered to be necessary. But the contents of the boards are lost most of the time without even being archived. Consequently, a tool to assist the students in the task of documenting the board content by removing the objects in front of the board is highly desirable. In this paper, we have developed the method to remove occlusion present in front of board by video inpainting and further we used even odd interlacing and contour formation to improve the results.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"238 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123037582","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}
Prafulla Kumar Choubey, A. K. Singh, Raghu B. Bankapur, SB VaisakhP.C., B. ManojPrabhu
{"title":"Content aware targeted image manipulation to reduce power consumption in OLED panels","authors":"Prafulla Kumar Choubey, A. K. Singh, Raghu B. Bankapur, SB VaisakhP.C., B. ManojPrabhu","doi":"10.1109/IC3.2015.7346727","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346727","url":null,"abstract":"FHD, QHD and UHD class of high pixel density panel enables precise rendering and smoothens the display quality of images. But driving such high resolution panel requires high power both on panel and rendering (GPU) side. In smartphones especially, where content is usually UI, it doesn't demand resolutions like 2k and 4k, unless it's graphics/multimedia. This paper proposes a display content and human visual acuity aware technique to reduce oled panel power consumption by turning off selective subpixels in specific regions of display. This technique uses the fact that power consumption in oled panels has direct relationship with color and intensity of each pixel and considerable power can be saved with intelligent control at pixel/subpixel level. Results obtained through first PoC implementation showed power saving up to 28% depending on aggressiveness of implementation.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122578281","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":"Gray scale image watermarking using fuzzy entropy and Lagrangian twin SVR in DCT domain","authors":"A. Yadav, R. Mehta, Raj Kumar","doi":"10.1109/IC3.2015.7346646","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346646","url":null,"abstract":"In this paper, the effect of low, middle and high frequency DCT coefficients are investigated onto gray scale image watermarking in terms of imperceptibility and robustness. The performance of Lagrangian twin support vector regression (LTSVR), which was successfully applied on synthetic datasets obtained from UCI repository for various kinds of regression problems by Balasundaram et al. [9], onto image watermarking problem, is validated by embedding and extracting the watermark on different standard and real world images. Also the good learning capability of image characteristics provides the good imperceptibility of the watermark and robustness against several kinds of image processing attacks verifies the high generalization performance of LTSVR. Through the experimental results, it is observed that significant amount of imperceptibility and robustness is achieved using low frequency (LF) DCT coefficients as compared to middle frequency (MF) and high frequency (HF) DCT coefficients as well as state-of-art technique.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123779486","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}
T. Kutzner, Fanyu Ye, Ingrid Bönninger, C. Travieso-González, M. Dutta, Anushikha Singh
{"title":"User verification using safe handwritten passwords on smartphones","authors":"T. Kutzner, Fanyu Ye, Ingrid Bönninger, C. Travieso-González, M. Dutta, Anushikha Singh","doi":"10.1109/IC3.2015.7346651","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346651","url":null,"abstract":"This article focuses on the writer verification using safe handwritten passwords on smartphones. We extract and select 25 static and dynamic biometric features from a handwritten character password sequence on an android touch-screen device. For the writer verification we use the classification algorithms of WEKA framework. Our 32 test persons wrote generated safe passwords with a length of 8 characters. Each person wrote their password 12 times. The approach works with 384 training samples on a supervised system. The best result of 98.72% success rate for a correct classification, the proposal reached with the KStar and k- Nearest Neighbor classifier after ranking with Fisher Score feature selection. The best result of 10.42% false accepted rate is reached with KStar classifier.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126849904","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}
Namrata Srivastava, Utkarsh Agrawal, S. Roy, U. Tiwary
{"title":"Human identification using Linear Multiclass SVM and Eye Movement biometrics","authors":"Namrata Srivastava, Utkarsh Agrawal, S. Roy, U. Tiwary","doi":"10.1109/IC3.2015.7346708","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346708","url":null,"abstract":"The paper presents a system to accurately differentiate between unique individuals by utilizing the various eye-movement biometric features. Eye Movements are highly resistant to forgery as the generation of eye movements occur due to the involvement of complex neurological interactions and extra ocular muscle properties. We have employed Linear Multiclass SVM model to classify the numerous eye movement features. These features were obtained by making a person fixate on a visual stimuli. The testing was performed using this model and a classification accuracy up to 91% to 100% is obtained on the dataset used. The results are a clear indication that eye-based biometric identification has the potential to become a leading behavioral technique in the future. Moreover, its fusion with different biometric processes such as EEG, Face Recognition etc., can also increase its classification accuracy.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126852677","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":"Secure data transmission using video","authors":"Nikita Lemos, Kavita Sonawane, Bidisha Roy","doi":"10.1109/IC3.2015.7346684","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346684","url":null,"abstract":"In today's world transmitting data in a safe and secure fashion is difficult, especially when highly sensitive data is involved. The data should be ideally robust to security threats. The paper aims at proposing a methodology which employs dual level of security using cryptography and steganography to hide the secret text data using video as a cover. A blend of existing and novel techniques is used for hiding the data. Cryptography aims at concealing the secret data and steganography hides the existence of the data. Since a video is addressed as a collection of frames, a frame selection logic is incorporated which inserts data into the frames in a random fashion so that the data cannot be retrieved easily by the attacker. Considering the goal of crypto and steganography the analysis of the methodology can be done on the basis of visual perceptibility, error ratios and histogram comparison of video frames before and after hiding data. Use of two techniques with distinct goals to hide the data increases the robustness as well as simple frame selection logic prevents the attacker to obtain the data easily, but at the same time simplifies the sender's job as a rule index of frames is maintained.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"189 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127640677","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":"ANPR Indian system using surveillance cameras","authors":"A. Singh, Souvik Roy","doi":"10.1109/IC3.2015.7346695","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346695","url":null,"abstract":"Number Plate Recognition technique is widely used in identifying vehicle identity across the world where a standard plate size and font are maintained which makes recognition easy. For implementing number plate recognition specifically in India a lot number of issue comes up like hundreds of different forms of fonts being used, size of plate not maintained, five different color number plate, double line number plate etc. All these problems are being taken care while developing a software for Indian number plate recognition and is tested in real Indian road conditions. Support Vector machines are trained & used for detection of number plate contours. ANN is used for character recognition from number plate and various algorithm for plate enhancement, noise reduction and ultimately neural networks are most efficient for result with erasing lot of camera constraints. The ANPR software is designed in C++ using Qt for GUI designing, OpenCV as image processing libraries and SQL as database management thereby making it a complete software implementation of idea.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129147445","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}