Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350661
R. Vidhyapriya, P. Vanathi
Applications of sensor networks have become an emerging technology, which can monitor a specific area and collect environmental data around a place. In recent years, low power wireless communication and the availability of cheap and small micro sensor nodes lead to enhanced developments of wireless sensor network applications in real society. The energy constraint inherent in the small battery powered nodes presents a considerable problem, and much effort is being put into reducing the power consumption. We introduce a reactive routing protocol called energy aware routing that is intended to provide a reliable transmission environment with low energy consumption. This protocol efficiently utilizes both the energy available in the node and quality of the link to identify the best possible route to the destination. Simulation results show that the energy aware routing scheme outperforms the existing schemes even in the presence of high node density and overcomes simultaneous packet forwarding
{"title":"Energy Aware Routing for Wireless Sensor Networks","authors":"R. Vidhyapriya, P. Vanathi","doi":"10.1109/ICSCN.2007.350661","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350661","url":null,"abstract":"Applications of sensor networks have become an emerging technology, which can monitor a specific area and collect environmental data around a place. In recent years, low power wireless communication and the availability of cheap and small micro sensor nodes lead to enhanced developments of wireless sensor network applications in real society. The energy constraint inherent in the small battery powered nodes presents a considerable problem, and much effort is being put into reducing the power consumption. We introduce a reactive routing protocol called energy aware routing that is intended to provide a reliable transmission environment with low energy consumption. This protocol efficiently utilizes both the energy available in the node and quality of the link to identify the best possible route to the destination. Simulation results show that the energy aware routing scheme outperforms the existing schemes even in the presence of high node density and overcomes simultaneous packet forwarding","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128964756","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}
Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350787
A. Baskar, M. Prabukumar, S. Sathishkumar
Video shot boundary (VSB) detection plays an important role in modern video archiving and summarization applications. The classical linear approach towards VSB detection is basically a sequential search, however this approach is computationally very expensive for large databases. In this work we propose a non-linear approach for VSB detection, which is an improvement of existing adaptive skip. The proposed technique compares less than 10% of frames in an entire video. Our experimental result shows that the proposed technique outperforms the other existing non-linear algorithms with better accuracy and meaningful VSBs
{"title":"Improved Adaptive Skip Algorithm for Video Shot Boundary Detection","authors":"A. Baskar, M. Prabukumar, S. Sathishkumar","doi":"10.1109/ICSCN.2007.350787","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350787","url":null,"abstract":"Video shot boundary (VSB) detection plays an important role in modern video archiving and summarization applications. The classical linear approach towards VSB detection is basically a sequential search, however this approach is computationally very expensive for large databases. In this work we propose a non-linear approach for VSB detection, which is an improvement of existing adaptive skip. The proposed technique compares less than 10% of frames in an entire video. Our experimental result shows that the proposed technique outperforms the other existing non-linear algorithms with better accuracy and meaningful VSBs","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"57 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124321069","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}
Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350720
T. C. Sarmal, C. Srinivas
Remote sensing satellites orbit around the Earth around 600-900 kilometers in sun synchronous polar orbit. Each satellite transmits the image data in X-band and the data reception is carried out through a parabolic antenna along with the associated systems. The entire data acquisition system is complex and expensive as it has to meet the requirements of the fast orbiting remote sensing satellites. During the visibility of the satellite, the data is acquired at the acquisition systems, frame synchronized band separated and displayed in the monitor in real-time. The authors of this paper used the concept of archiving the RAW data directly to redundant array of inexpensive disks (RAID) in real-time and also to provide on the fly sub-sampled video image display using generic PC Based Linux Servers available in the industry. Handling of high speed image data from satellite involves de-randomization, decryption and decompression in real time. Innovative multiplexing techniques are used for digital correlation to increase the operating speed. Effective system design strategies rely on appropriate matching of systems hardware, software and environment. This needs the proper evaluation of the system environment. Schedulers for a realtime system are concerned with maximizing resource utilization subject to meeting system timing constraints. Priority-driven presumptive schedulers used in realtime systems require predictable cache performance. The design involved shared memory concepts, cache memory handling, image data handling and transfer to RAID while each system handles the data of around 500 GB per day. The paper deals with a generalized design of such system using a common platform as a part of Indian Remote Sensing Satellite Program and supplied to many users around the world. These systems are working error free all over
{"title":"Design and Implementation of High Bit Rate Satellite Image Data Ingest and Processing System","authors":"T. C. Sarmal, C. Srinivas","doi":"10.1109/ICSCN.2007.350720","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350720","url":null,"abstract":"Remote sensing satellites orbit around the Earth around 600-900 kilometers in sun synchronous polar orbit. Each satellite transmits the image data in X-band and the data reception is carried out through a parabolic antenna along with the associated systems. The entire data acquisition system is complex and expensive as it has to meet the requirements of the fast orbiting remote sensing satellites. During the visibility of the satellite, the data is acquired at the acquisition systems, frame synchronized band separated and displayed in the monitor in real-time. The authors of this paper used the concept of archiving the RAW data directly to redundant array of inexpensive disks (RAID) in real-time and also to provide on the fly sub-sampled video image display using generic PC Based Linux Servers available in the industry. Handling of high speed image data from satellite involves de-randomization, decryption and decompression in real time. Innovative multiplexing techniques are used for digital correlation to increase the operating speed. Effective system design strategies rely on appropriate matching of systems hardware, software and environment. This needs the proper evaluation of the system environment. Schedulers for a realtime system are concerned with maximizing resource utilization subject to meeting system timing constraints. Priority-driven presumptive schedulers used in realtime systems require predictable cache performance. The design involved shared memory concepts, cache memory handling, image data handling and transfer to RAID while each system handles the data of around 500 GB per day. The paper deals with a generalized design of such system using a common platform as a part of Indian Remote Sensing Satellite Program and supplied to many users around the world. These systems are working error free all over","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"61 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124323477","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}
Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350668
V. Murali Bhaskaran, A. Natarajan, S. Sivanandam
Internet protocol (IP) packet traceback system identifies the origin of the sequence of IP packets when the source addresses of these packets are spoofed. IP packet traceback is usually performed with the help of routers and gateways. Several approaches have been proposed to trace IP packets to their origin. The packet marking approach enables routers to probabilistically mark packets with partial path information and tries to reconstruct the complete path from the marked packets. In most of these approaches, routers and victims (affected systems) are considerably overloaded for marking the packet and reconstructing the trace path and requires more marked packets. This paper focuses on tracing the approximate source of attack instead of tracing the entire path in multi domain system without computation, by victim and also implementing security for authentication and confidentiality. It is assumed that Internet topology has been grouped as ISP domains
{"title":"Tracebacking the Spoofed IP Packets in Multi ISP Domains with Secured Communication","authors":"V. Murali Bhaskaran, A. Natarajan, S. Sivanandam","doi":"10.1109/ICSCN.2007.350668","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350668","url":null,"abstract":"Internet protocol (IP) packet traceback system identifies the origin of the sequence of IP packets when the source addresses of these packets are spoofed. IP packet traceback is usually performed with the help of routers and gateways. Several approaches have been proposed to trace IP packets to their origin. The packet marking approach enables routers to probabilistically mark packets with partial path information and tries to reconstruct the complete path from the marked packets. In most of these approaches, routers and victims (affected systems) are considerably overloaded for marking the packet and reconstructing the trace path and requires more marked packets. This paper focuses on tracing the approximate source of attack instead of tracing the entire path in multi domain system without computation, by victim and also implementing security for authentication and confidentiality. It is assumed that Internet topology has been grouped as ISP domains","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126278838","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}
Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350750
L. Suresh, S. Sundaravadivelu
The optical wireless communication is the only solution to the emerging next generation wireless communication. The photonic antennas play major role in the development of optical wireless communications. This photonic antenna transfers light energy from optical waveguide to free-space with high directionality and act as a matching device between optical source and channel (atmosphere). The analysis of light propagation through waveguide structures is indispensable in designing complex photonic devices. The optical waveguide grating structures with multiple longitudinal reflecting interfaces are analyzed to form photonic antennas. The multilayer triangular grating structure is analyzed using beam propagation method for its ability and suitability to optical wireless communication. The beam propagation method (BPM), extensively used tool for computer simulation of light propagation in optical waveguide structures, has been developed for analyzing optical waveguides with discontinuities in transmission, reflection and radiations. The discontinuities comprise changes in core thickness and effective refractive index. The optical powers radiated and transmitted at an abrupt discontinuity in waveguide gratings are calculated numerically by means of BPM for TE modes, and applied to the eigen mode and propagating beam analysis of that structure. The current method achieves soaring precision and converging time is significantly abridged and it is proportional to the log of the total number of periods in the waveguide than that in the conventional time-domain method. This paper intends a novel integrated photonic antenna with snooty directional efficiency and radiation which can be tattered for protracted distance optical wireless communication. The consequences confirm that it is promising to curtail radiation loss under sturdy mode coupling conditions. This method can be used for modeling of laser beam propagation in non-homogeneous atmosphere
{"title":"Radiation Characteristics of Photonic Antenna for Optical Wireless Communication using Beam Propagation Method","authors":"L. Suresh, S. Sundaravadivelu","doi":"10.1109/ICSCN.2007.350750","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350750","url":null,"abstract":"The optical wireless communication is the only solution to the emerging next generation wireless communication. The photonic antennas play major role in the development of optical wireless communications. This photonic antenna transfers light energy from optical waveguide to free-space with high directionality and act as a matching device between optical source and channel (atmosphere). The analysis of light propagation through waveguide structures is indispensable in designing complex photonic devices. The optical waveguide grating structures with multiple longitudinal reflecting interfaces are analyzed to form photonic antennas. The multilayer triangular grating structure is analyzed using beam propagation method for its ability and suitability to optical wireless communication. The beam propagation method (BPM), extensively used tool for computer simulation of light propagation in optical waveguide structures, has been developed for analyzing optical waveguides with discontinuities in transmission, reflection and radiations. The discontinuities comprise changes in core thickness and effective refractive index. The optical powers radiated and transmitted at an abrupt discontinuity in waveguide gratings are calculated numerically by means of BPM for TE modes, and applied to the eigen mode and propagating beam analysis of that structure. The current method achieves soaring precision and converging time is significantly abridged and it is proportional to the log of the total number of periods in the waveguide than that in the conventional time-domain method. This paper intends a novel integrated photonic antenna with snooty directional efficiency and radiation which can be tattered for protracted distance optical wireless communication. The consequences confirm that it is promising to curtail radiation loss under sturdy mode coupling conditions. This method can be used for modeling of laser beam propagation in non-homogeneous atmosphere","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134124349","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}
Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350762
K. Rajkumar, V. Vaidehi, S. Pradeep, N. Srinivasan, M. Vanishree
As network attacks have increased in number and severity over the past few years, intrusion detection systems have become a necessary addition to the security infrastructure of most organizations. From a security perspective, firewalls and SSL offer little protection. Web traffic often contains attacks such as cross-site scripting and SQL injection that enter through port 80 and are not blocked by the firewall. Among the Web applications HTTP holds the majority share of the traffic transported through Web. In this paper, implementation of an application level IDS has been presented which uses combination of pattern matching and protocol analysis approaches. The first method of detection relies on a multi pattern matching within the protocol fields, the second one provides an efficient decision tree adaptive to the application traffic characteristics to limit the number of patterns to be checked. The proposed IDS can be effectively implemented in a high performance semantic processor
{"title":"Application Level IDS using Protocol Analysis","authors":"K. Rajkumar, V. Vaidehi, S. Pradeep, N. Srinivasan, M. Vanishree","doi":"10.1109/ICSCN.2007.350762","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350762","url":null,"abstract":"As network attacks have increased in number and severity over the past few years, intrusion detection systems have become a necessary addition to the security infrastructure of most organizations. From a security perspective, firewalls and SSL offer little protection. Web traffic often contains attacks such as cross-site scripting and SQL injection that enter through port 80 and are not blocked by the firewall. Among the Web applications HTTP holds the majority share of the traffic transported through Web. In this paper, implementation of an application level IDS has been presented which uses combination of pattern matching and protocol analysis approaches. The first method of detection relies on a multi pattern matching within the protocol fields, the second one provides an efficient decision tree adaptive to the application traffic characteristics to limit the number of patterns to be checked. The proposed IDS can be effectively implemented in a high performance semantic processor","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123800858","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}
Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350696
V. Jagannathan, A. Mahadevan, R. Hariharan, S. Srinivasan
Image compression and image encryption are pivotal to proper storage and transmission of images. Simultaneous image compression and encryption aims at achieving enhanced bandwidth utilization and security at the same time. The proposed number theory based image compression encryption (NTICE) algorithm employs number theoretic paradigm-Chinese remainder theorem, to solve congruencies and hence realize the twin ideals of compression and encryption simultaneously. The NTICE algorithm has been implemented on color images. The image coding results, calculated from actual image size and encoded image file, are comparable to the results obtained through much more sophisticated and computationally complex methods. In addition, the algorithm has been applied to the scenario of image multiplexing in order to obtain enhanced level of security along with compression
{"title":"Number Theory Based Image Compression Encryption and Application to Image Multiplexing","authors":"V. Jagannathan, A. Mahadevan, R. Hariharan, S. Srinivasan","doi":"10.1109/ICSCN.2007.350696","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350696","url":null,"abstract":"Image compression and image encryption are pivotal to proper storage and transmission of images. Simultaneous image compression and encryption aims at achieving enhanced bandwidth utilization and security at the same time. The proposed number theory based image compression encryption (NTICE) algorithm employs number theoretic paradigm-Chinese remainder theorem, to solve congruencies and hence realize the twin ideals of compression and encryption simultaneously. The NTICE algorithm has been implemented on color images. The image coding results, calculated from actual image size and encoded image file, are comparable to the results obtained through much more sophisticated and computationally complex methods. In addition, the algorithm has been applied to the scenario of image multiplexing in order to obtain enhanced level of security along with compression","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123976198","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}
Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350766
K.M. Mukund, S. Seshadri, J. Devarajulu, M. Kannan
This paper proposes an architecture for a pipelined 1 GHz floating point arithmetic unit incorporated with the concept of modified dynamic scheduling which enables the unit to accept an input instruction every clock cycle until there is an output clash, in which case the outputs are sent out based on the first in first out concept. The architecture proposed has three independent functional units, which can be issued with instructions either one at a time using a small control word or in parallel using a large control word based on the dependency of input operations. The entire design has been simulated using Cadence NcSim. Synthesis and advanced flows such as low power, design for testability and multi Vt flows have been carried out with Cadence RTL compiler to ensure low power and maximum frequency of operation
{"title":"A 1 GHz Pipelined Low Power Floating Point Arithmetic Unit with Modified Scheduling for High Speed Applications","authors":"K.M. Mukund, S. Seshadri, J. Devarajulu, M. Kannan","doi":"10.1109/ICSCN.2007.350766","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350766","url":null,"abstract":"This paper proposes an architecture for a pipelined 1 GHz floating point arithmetic unit incorporated with the concept of modified dynamic scheduling which enables the unit to accept an input instruction every clock cycle until there is an output clash, in which case the outputs are sent out based on the first in first out concept. The architecture proposed has three independent functional units, which can be issued with instructions either one at a time using a small control word or in parallel using a large control word based on the dependency of input operations. The entire design has been simulated using Cadence NcSim. Synthesis and advanced flows such as low power, design for testability and multi Vt flows have been carried out with Cadence RTL compiler to ensure low power and maximum frequency of operation","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122735343","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}
Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350667
K. Yashwanth Reddy, N.V. Deepa Gandhi, K. Balachander
The present thrust is to develop a broadband intelligent network system which is able to sustain a large number of users and a varying amount of data while maintaining high availability of resources and acceptable performance. In such a scenario, scalability is an important aspect. In this paper we consider the impact of increasing the number of users supported by a network node and show that the network is scalable. Also congestion control is necessary to protect the broadband service control point during overload situations. Existing algorithms do not operate optimally with respect to important performance criteria such as responsiveness, efficiency and fairness. Here we try to identify their shortcomings and propose few enhancements. We also show that the proposed enhanced call-gapping algorithm performs consistently better than the existing automatic call-gapping algorithm in terms of above-mentioned criteria. The effectiveness of this analysis are shown using NS-2 simulator
{"title":"Simulation and Analysis of Performance Models of Broadband Intelligent Mobile Networks","authors":"K. Yashwanth Reddy, N.V. Deepa Gandhi, K. Balachander","doi":"10.1109/ICSCN.2007.350667","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350667","url":null,"abstract":"The present thrust is to develop a broadband intelligent network system which is able to sustain a large number of users and a varying amount of data while maintaining high availability of resources and acceptable performance. In such a scenario, scalability is an important aspect. In this paper we consider the impact of increasing the number of users supported by a network node and show that the network is scalable. Also congestion control is necessary to protect the broadband service control point during overload situations. Existing algorithms do not operate optimally with respect to important performance criteria such as responsiveness, efficiency and fairness. Here we try to identify their shortcomings and propose few enhancements. We also show that the proposed enhanced call-gapping algorithm performs consistently better than the existing automatic call-gapping algorithm in terms of above-mentioned criteria. The effectiveness of this analysis are shown using NS-2 simulator","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"359 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122760277","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}
Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350786
P. Nagabhushan, S. Angadi, B. Anami
Cursive word recognition requires tilt correction before extraction of features such as ascenders and descenders. Skew and slant are the two types of tilts found in cursive word images. This paper presents new algorithms for skew and slant correction using geometric model and image projections. A new algorithm for extraction of ascenders/descenders based on fitting top line and base line references using horizontal histogram projection of the image is also presented. The algorithms are tested on a large sample of 'area' name images drawn from postal addresses. The tilt correction algorithms have been tested on a large sample of images and the results are encouraging. The ascenders/descenders are correctly extracted from 87.86% of test images
{"title":"Geometric Model and Projection Based Algorithms for Tilt Correction and Extraction of Acsenders / Descenders for Cursive Word Recognition","authors":"P. Nagabhushan, S. Angadi, B. Anami","doi":"10.1109/ICSCN.2007.350786","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350786","url":null,"abstract":"Cursive word recognition requires tilt correction before extraction of features such as ascenders and descenders. Skew and slant are the two types of tilts found in cursive word images. This paper presents new algorithms for skew and slant correction using geometric model and image projections. A new algorithm for extraction of ascenders/descenders based on fitting top line and base line references using horizontal histogram projection of the image is also presented. The algorithms are tested on a large sample of 'area' name images drawn from postal addresses. The tilt correction algorithms have been tested on a large sample of images and the results are encouraging. The ascenders/descenders are correctly extracted from 87.86% of test images","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128909939","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：