{"title":"Recognition strategies for general handwritten text documents","authors":"M. Shridhar, G. Houle, F. Kimura","doi":"10.3233/ICA-2009-0324","DOIUrl":"https://doi.org/10.3233/ICA-2009-0324","url":null,"abstract":"This paper presents document recognition strategies for an important application: Recognition of text document containing multiple lines of text data. A project to study the feasibility of recognizing essays written by middle school students is the focus of the second study. In this project, a scanned document is processed to extract individual lines of text from the essay, extract individual words from the line and then apply word recognition techniques to the extracted words. While individual lines of data are extracted accurately using gap information between lines, extraction of words is a much bigger challenge. Since the essays are written by middle school children, word boundaries are ambiguous, especially when words are written in a non-cursive discrete style. In these cases the gaps between words are sometimes smaller than the gaps between characters of the word causing errors in estimating the location of word boundaries. In this paper, we propose two classes of word boundaries: 1) strong boundaries due to large gaps between words, 2) weak boundaries due to small gaps between words. There are also cases when two words do not have a clear gap between them, but are rather joined to give the appearance of a single word. Results obtained from our phase 1 study will be presented in the paper.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125695620","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":"Artificial neural networks activation function HDL coder","authors":"M. Ahmadi, A. H. Namin, K. Leboeuf, Huapeng Wu","doi":"10.1109/EIT.2009.5189648","DOIUrl":"https://doi.org/10.1109/EIT.2009.5189648","url":null,"abstract":"The sigmoid and hyperbolic tangent functions are usually used as the activation functions in Artificial Neural Networks (ANNs). The exponential nature of these functions make them difficult for hardware implementation. Hence, several different methods for approximating them in hardware are proposed. In this work, we present a MATLAB toolbox called the “SigTan HDL Coder”, that generates synthesizable HDL Code which approximates these functions in hardware according to the specific user requirements. The HDL code is platform independent and can be used for FPGA as well as ASIC implementations. Input parameters to the system are the approximation error, input range, and the approximation method. Three different user-selectable methods for approximating the functions are programmed in the toolbox. All implemented approximation methods avoid the use of multipliers for their implementation, as multipliers are expensive hardware components in terms of area and speed.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117139130","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":"Using stereo geometry towards accurate 3D reconstruction","authors":"Zhuo Wang, B. Boufama","doi":"10.1109/EIT.2009.5189597","DOIUrl":"https://doi.org/10.1109/EIT.2009.5189597","url":null,"abstract":"This paper addresses the problem of threedimensional reconstruction and how the geometry of the stereo vision system affects the quality of such a reconstruction. We have considered the general case of non calibrated cameras with approximately known intrinsic parameters. The latter could be known either from previous experiments or from the manufacturer's specifications. In particular, the paper aims at finding the best geometric configuration of the stereo vision system(rotation and translation between the two cameras) that is the least sensitive to errors on the intrinsic parameters. Given that in most cases, in robotics for instance, we have the freedom to set-up the geometry of the stereo vision system, finding how cameras' geometry interacts with errors from different sources is a central issue. Furthermore, when the intrinsic parameters are completely unknown, we have used a single constraint from the scene that has allowed us to calculate the focal length and therefore, the Euclidean reconstruction. We have used extensive simulations where the stereo vision geometry has ranged from pure translation to general 3D motion. The obtained results have clearly shown that a pure translation is always better, as it is not significantly affected by errors on the intrinsic parameters. When assuming that the intrinsic parameters are not known, the use of the perpendicularity constraint from the scene has made it possible to avoid the classical and tedious calibration process.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127090411","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":"Graphical representation of DNA sequences","authors":"Swarna Bai Arniker, H. Kwan","doi":"10.1109/EIT.2009.5189633","DOIUrl":"https://doi.org/10.1109/EIT.2009.5189633","url":null,"abstract":"The sequencing of genomic data requires methods to allow this data to be visualized and analyzed. With the emergence of genomic signal processing, graphical representation techniques play a key role in applying digital signal processing techniques like Fourier transforms, and more recently, wavelet transform for visualizing DNA sequence. The choice of the graphical representation technique for a DNA sequence affects how well its biological properties can be reflected in the graphical domain for visualization and analysis of the characteristics of special regions of interest within the DNA sequence. This paper presents a summary of various DNA graphical representation methods and their applications in envisaging and analyzing long DNA sequences. A discussion on the comparative merits and demerits of the various methods and conclusions has also been included.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127130899","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 new image transform for a more crop-resilient NPT","authors":"Ayman M. T. Ahmed, D. Day","doi":"10.1109/EIT.2009.5189646","DOIUrl":"https://doi.org/10.1109/EIT.2009.5189646","url":null,"abstract":"In this paper, a new two-dimensional transform (crop-resilient image transform) is introduced. The transform is based on the Hartley transform, where the kernel matrix is modified to meet the requirements of the crop-resilient transform. This transform can be utilized in many applications; however, in this paper the main focus is on the data hiding and cropping applications only. Experimental results in this paper emphasize: the capability of the crop-resilient transform to invisibly hide a digital signature into a host data, and the robustness of the hidden data against the cropping attack.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125542267","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":"Design and implementation of MEMS based differential voltage controlled oscillator","authors":"B. S. Sreeja, S. Radha","doi":"10.1109/EIT.2009.5189611","DOIUrl":"https://doi.org/10.1109/EIT.2009.5189611","url":null,"abstract":"The main aim of the paper is to design a voltage controlled oscillator that can be later fabricated and used for high frequency applications such as the frequency synthesizer to generate the local oscillating signal for the modulation and demodulation of the RF signal. Among the building blocks of a wireless transceiver, the voltage-controlled oscillator (VCO) is an important block since it affects the system performances of the transceiver to a large extent .VCOs are also used as the core circuit of the clock recovery circuit, whose output signal is used for data decision and regeneration. In this project we design a VCO for high frequency purposes that has a high Q-factor using MEMS technology. MEMS devices dedicated to RF signal processing are very attractive for wireless communication because of their low power consumption, small size and potential for CMOS cointegration.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124070224","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":"Finite element simulation of SMFBAR based sensor","authors":"Chi-Jung Cheng, M. Atashbar","doi":"10.1109/EIT.2009.5189609","DOIUrl":"https://doi.org/10.1109/EIT.2009.5189609","url":null,"abstract":"In this work, a three dimensional finite element model for solidly mounted film bulk acoustic resonator (SMFBAR) devices is developed and simulated. The simulation is performed using the CoventorWareTM platform to analyze the performance of the device. The influence of the shape of the top electrode and its thickness on the sensitivity SMFBAR based sensors was investigated. Two different electrode shapes (square and circle) with surface areas of 0.04 mm2 and 0.09 mm2 and different thicknesses varying from 50 nm to 350 nm with increments of 100nm were investigated. The devices that were studied were ZnO based SMFBAR structures. The analysis revealed that both configurations have mass sensitivities with three orders of magnitude higher than that of quartz crystal microbalance sensing systems. These devices also exhibit high performance with maximum quality factor of 418 and effective electromechanical coupling coefficient of around 12.2%. Also, it was found out that the circular shaped top electrodes performance were slightly higher than that of square shaped one with respect to sensitivity, quality factor and effective electromechanical coupling.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131257998","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}
A. A. Mohammed, R. Minhas, Q. M. J. Wu, M. Sid-Ahmed
{"title":"Fingerprint image compression standard based on wave atoms decomposition and self organizing feature map","authors":"A. A. Mohammed, R. Minhas, Q. M. J. Wu, M. Sid-Ahmed","doi":"10.1109/EIT.2009.5189644","DOIUrl":"https://doi.org/10.1109/EIT.2009.5189644","url":null,"abstract":"Multiresolution analysis tools have been successfully applied to fingerprint image compression for more than a decade. Fingerprint image compression and reconstruction standards used by the US Federal Bureau of Investigation (FBI) are based upon the popular 9/7 discrete wavelet transform (DWT). A novel fingerprint image compression technique based on recently proposed multiresolution analysis tool i.e. wave atoms decomposition is proposed. Wave atoms decomposition has been specifically designed for enhanced representation of oscillatory patterns and to convey temporal and spatial information more precisely. Our proposed compression scheme is based upon vector quantization of decomposed wave atoms representation of fingerprint images using self organizing feature map (SOM). The quantized information is later encoded using arithmetic entropy scheme. The proposed compression scheme outperforms the FBI fingerprint image compression standard, the wavelet scalar quantization (WSQ). Data mining, law enforcement, border security, and forensic applications can potentially benefit from our proposed compression technique.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116390029","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}
Mahsa Tahermaram, M. Vadizadeh, A. Eslamzadeh, M. Fathipour
{"title":"Employing work function enginnering and asymmetric gate oxide in nano-scale source-heterojunction-MOS-transistor","authors":"Mahsa Tahermaram, M. Vadizadeh, A. Eslamzadeh, M. Fathipour","doi":"10.1109/EIT.2009.5189610","DOIUrl":"https://doi.org/10.1109/EIT.2009.5189610","url":null,"abstract":"The source-heterojunction-MOS-transistor provides high drain current. This is originated from the high velocity electron injection at the source edge due to band offset energy. However, these devices suffer from large off- state current. In this paper, we have analyzed the off-state current in this device and have proposed use of work function engineering as well as asymmetric gate oxide to minimize the magnitude of this off-state current. The analysis of the off-state current characteristics shows that provided 93% reduction in off-state current.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129442712","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 new probing scheme for fault detection and identification","authors":"A. Mohamed, O. Basir","doi":"10.1109/EIT.2009.5189590","DOIUrl":"https://doi.org/10.1109/EIT.2009.5189590","url":null,"abstract":"Probing technology has been used as a fault detection and identification method in computer networks and successful applications have been reported. One of the most appealing features of probing-based schemes is that it is an active approach. A set of probes can be sent on a periodic basis. If a network failure is detected, the outcomes of these probes are further analyzed to determine the root cause of the problem. However, the availability of a large set of such probes may in fact place a huge burden on management systems in terms of extra management traffic and storage space. Hence, the need of minimizing such a probing set has become highly desirable. In this work, we propose a preplanned probe selection scheme, in which a small set of probes are chosen such that it maintains the diagnostic power of the original set. The new approach is based on the constraint satisfaction problem paradigm and its powerful search techniques are exploited. The efficiency of the new algorithm has been demonstrated by the results reported.","PeriodicalId":393467,"journal":{"name":"2009 IEEE International Conference on Electro/Information Technology","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128934474","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}