Pub Date : 2012-12-13DOI: 10.1109/FIIW.2012.6378322
P. Zolnierczuk, B. Vacaliuc, M. Sundaram, A. Parizzi, C. Halbert, M. C. Hoffmann, J. Browning, J. Ankner
The Liquids Reflectometer (LR) Instrument installed at the Spallation Neutron Source (SNS) enables observations of chemical kinetics, solid-state reactions, phase-transitions and chemical reactions in general [1]. The ability of the instrument to complete measurements quickly and therefore process many samples is a key capability inherent in the system design [2]. Alignment and sample environment management are a time consuming and error prone process that has led to the development of automation in the control software operating the instrument. In fact, the original LR user interface, based on the Python scripting language, has been modularized and adapted to become the standard interface on many other instruments. A project to convert the original Python [3] implementation controlling the LR instrument into the modular version standardized at SNS was undertaken in the spring of 2012. The key features of automated sample alignment and robot-driven sample management system enable the instrument to reduce the manual labor required to prepare and execute observations, freeing up precious time for analysis and reporting activity. We present the modular PyDas control system [4], its implementation for the LR, and the lessons learned during the upgrade process.
{"title":"“Old wine in new wineskins:” Upgrading the liquids reflectometer instrument user control software at the Spallation Neutron Source","authors":"P. Zolnierczuk, B. Vacaliuc, M. Sundaram, A. Parizzi, C. Halbert, M. C. Hoffmann, J. Browning, J. Ankner","doi":"10.1109/FIIW.2012.6378322","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378322","url":null,"abstract":"The Liquids Reflectometer (LR) Instrument installed at the Spallation Neutron Source (SNS) enables observations of chemical kinetics, solid-state reactions, phase-transitions and chemical reactions in general [1]. The ability of the instrument to complete measurements quickly and therefore process many samples is a key capability inherent in the system design [2]. Alignment and sample environment management are a time consuming and error prone process that has led to the development of automation in the control software operating the instrument. In fact, the original LR user interface, based on the Python scripting language, has been modularized and adapted to become the standard interface on many other instruments. A project to convert the original Python [3] implementation controlling the LR instrument into the modular version standardized at SNS was undertaken in the spring of 2012. The key features of automated sample alignment and robot-driven sample management system enable the instrument to reduce the manual labor required to prepare and execute observations, freeing up precious time for analysis and reporting activity. We present the modular PyDas control system [4], its implementation for the LR, and the lessons learned during the upgrade process.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117193792","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 : 2012-12-13DOI: 10.1109/FIIW.2012.6378320
M. Karakaya, H. Qi
This paper addresses the communication and energy efficiency in collaborative visual sensor networks (VSNs) for people localization, a challenging computer vision problem of its own. We focus on the design of a light-weight and energy-efficient solution where people are localized based on distributed camera nodes integrating the so-called certainty map generated at each node, that records the target non-existence information within the camera's field of view. We first present a dynamic itinerary for certainty map integration where not only each sensor node transmits a very limited amount of data but that a limited number of camera nodes is involved. Then, we perform a comprehensive analytical study to evaluate communication and energy efficiency between different integration schemes, i.e., centralized and distributed integration. Based on results obtained from analytical study and real experiments, the distributed method shows effectiveness in detection accuracy as well as energy and bandwidth efficiency.
{"title":"Communication and energy efficiency in visual sensor networks for people localization","authors":"M. Karakaya, H. Qi","doi":"10.1109/FIIW.2012.6378320","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378320","url":null,"abstract":"This paper addresses the communication and energy efficiency in collaborative visual sensor networks (VSNs) for people localization, a challenging computer vision problem of its own. We focus on the design of a light-weight and energy-efficient solution where people are localized based on distributed camera nodes integrating the so-called certainty map generated at each node, that records the target non-existence information within the camera's field of view. We first present a dynamic itinerary for certainty map integration where not only each sensor node transmits a very limited amount of data but that a limited number of camera nodes is involved. Then, we perform a comprehensive analytical study to evaluate communication and energy efficiency between different integration schemes, i.e., centralized and distributed integration. Based on results obtained from analytical study and real experiments, the distributed method shows effectiveness in detection accuracy as well as energy and bandwidth efficiency.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122712656","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 : 2012-12-13DOI: 10.1109/FIIW.2012.6378353
P. Joshi, R. Dehoff, C. Duty, W. Peter, R. Ott, L. Love, C. Blue
In the past decade, additive manufacturing and printed electronics technologies have expanded rapidly on a global scale. As the additive manufacturing techniques have become more capable and affordable, and able to work with a broader range of materials, the machines are increasingly being used to make advanced products at significantly lower costs and risks. The additive manufacturing industry is populated by a broad family of technologies, and the present paper provides an overview of key additive manufacturing technologies and their impact on materials processing, device applications, and future markets. Our R&D efforts on the development of core technologies for the realization of flexible electronics, and 3D microscale structures are also highlighted.
{"title":"Direct digital additive manufacturing technologies: Path towards hybrid integration","authors":"P. Joshi, R. Dehoff, C. Duty, W. Peter, R. Ott, L. Love, C. Blue","doi":"10.1109/FIIW.2012.6378353","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378353","url":null,"abstract":"In the past decade, additive manufacturing and printed electronics technologies have expanded rapidly on a global scale. As the additive manufacturing techniques have become more capable and affordable, and able to work with a broader range of materials, the machines are increasingly being used to make advanced products at significantly lower costs and risks. The additive manufacturing industry is populated by a broad family of technologies, and the present paper provides an overview of key additive manufacturing technologies and their impact on materials processing, device applications, and future markets. Our R&D efforts on the development of core technologies for the realization of flexible electronics, and 3D microscale structures are also highlighted.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122074413","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 : 2012-12-13DOI: 10.1109/FIIW.2012.6378332
Ethan Coffey
Acoustic Resonance Testing (ART) is a nondestructive test that uses the vibrational characteristics of an object to find defects. It is a whole-part test, so measurements taken in one place can indicate defects anywhere. It can be done quickly and requires minimal equipment. ART can be completely automated and make objective, quantitative judgments, eliminating human error. ART uses the fact that a part's physical structure causes it to have a distinct and unique set of characteristic frequencies. Every part with the same physical properties will have the same vibration properties, and any flaw will cause this vibration “fingerprint” to change. After a hammer impact, the characteristic frequencies of the part will be excited and every other frequency will quickly attenuate. By measuring the location and amplitude of several peaks of the part's dynamic response and comparing these values to a database of acceptable values, parts with defects can be quickly separated. ART can be used to find parts with out-of-tolerance dimensions, voids, and cracks, among other things. While the test will not determine the cause of rejection, with appropriate transducer sensitivity and software it can reliably find faults anywhere in a part. Currently Gassco is researching ways to use ART for in-line inspection of gas pipelines. ART is also being used on some automotive production lines to ensure 100% compliance with specifications. It is well-suited for quality assurance on drive train parts, piping sections, shielding and containment hardware, and other applications where fast and dependable flaw detection is critical.
{"title":"Acoustic resonance testing","authors":"Ethan Coffey","doi":"10.1109/FIIW.2012.6378332","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378332","url":null,"abstract":"Acoustic Resonance Testing (ART) is a nondestructive test that uses the vibrational characteristics of an object to find defects. It is a whole-part test, so measurements taken in one place can indicate defects anywhere. It can be done quickly and requires minimal equipment. ART can be completely automated and make objective, quantitative judgments, eliminating human error. ART uses the fact that a part's physical structure causes it to have a distinct and unique set of characteristic frequencies. Every part with the same physical properties will have the same vibration properties, and any flaw will cause this vibration “fingerprint” to change. After a hammer impact, the characteristic frequencies of the part will be excited and every other frequency will quickly attenuate. By measuring the location and amplitude of several peaks of the part's dynamic response and comparing these values to a database of acceptable values, parts with defects can be quickly separated. ART can be used to find parts with out-of-tolerance dimensions, voids, and cracks, among other things. While the test will not determine the cause of rejection, with appropriate transducer sensitivity and software it can reliably find faults anywhere in a part. Currently Gassco is researching ways to use ART for in-line inspection of gas pipelines. ART is also being used on some automotive production lines to ensure 100% compliance with specifications. It is well-suited for quality assurance on drive train parts, piping sections, shielding and containment hardware, and other applications where fast and dependable flaw detection is critical.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132576637","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 : 2012-12-13DOI: 10.1109/FIIW.2012.6378326
C. Kiger, B. Shumaker, W. S. Johnson, H. Hashemian
Aging plants and reduced workforces are causing commercial nuclear power reactors to limit the extent of their predictive maintenance programs to only critical to safety and critical to operation systems. Some sites are even forced into living with a reactive maintenance strategy for all but the most critical systems. This typically leads to significant expense through costly downtime and component unavailability. Advancements in wireless technology have resulted in the implementation of measurement devices on some important systems that have alleviated the condition monitoring and testing burden on maintenance personnel. Through research and development (R&D) sponsored by the Department of Energy (DOE) Small Business Innovation Research (SBIR) program, a wireless condition monitoring application has been identified inside the containment of a pressurized water reactor (PWR) that can benefit from the introduction of wireless technology. The application that has been selected is the use of wireless vibration sensors to monitor the condition of containment cooling fans. The host utility for this project is the Arkansas Nuclear One (ANO) power generating station. Due to the location of the fans within the containment building, maintenance personnel are prevented from manually collecting vibration data frequently enough (e.g., monthly) to determine the health of the equipment. Through the use of wireless sensors, data can be collected once a day to provide a more complete picture of the fans' health with advanced warning of a failing component. This paper will document the efforts of this project to deploy a wireless vibration system at ANO.
{"title":"Expanding the capabilities of wireless condition monitoring sensors into the containment of pressurized water reactors","authors":"C. Kiger, B. Shumaker, W. S. Johnson, H. Hashemian","doi":"10.1109/FIIW.2012.6378326","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378326","url":null,"abstract":"Aging plants and reduced workforces are causing commercial nuclear power reactors to limit the extent of their predictive maintenance programs to only critical to safety and critical to operation systems. Some sites are even forced into living with a reactive maintenance strategy for all but the most critical systems. This typically leads to significant expense through costly downtime and component unavailability. Advancements in wireless technology have resulted in the implementation of measurement devices on some important systems that have alleviated the condition monitoring and testing burden on maintenance personnel. Through research and development (R&D) sponsored by the Department of Energy (DOE) Small Business Innovation Research (SBIR) program, a wireless condition monitoring application has been identified inside the containment of a pressurized water reactor (PWR) that can benefit from the introduction of wireless technology. The application that has been selected is the use of wireless vibration sensors to monitor the condition of containment cooling fans. The host utility for this project is the Arkansas Nuclear One (ANO) power generating station. Due to the location of the fans within the containment building, maintenance personnel are prevented from manually collecting vibration data frequently enough (e.g., monthly) to determine the health of the equipment. Through the use of wireless sensors, data can be collected once a day to provide a more complete picture of the fans' health with advanced warning of a failing component. This paper will document the efforts of this project to deploy a wireless vibration system at ANO.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117302634","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 : 2012-12-13DOI: 10.1109/FIIW.2012.6378354
P. Fuhr, J. Gutierrez
The ocean presents a sensing and communication system with a wide array of environmental and performance conditions not found anywhere else. Integrating sensors into a coherent measurement community in such a setting leads to an underwater observatory. An examination of the parameters of interest and operational conditions present at various ocean depths is presented.
{"title":"Sensing and communications in an underwater environment","authors":"P. Fuhr, J. Gutierrez","doi":"10.1109/FIIW.2012.6378354","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378354","url":null,"abstract":"The ocean presents a sensing and communication system with a wide array of environmental and performance conditions not found anywhere else. Integrating sensors into a coherent measurement community in such a setting leads to an underwater observatory. An examination of the parameters of interest and operational conditions present at various ocean depths is presented.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"469 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116188886","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 : 2012-12-13DOI: 10.1109/FIIW.2012.6378342
M. Colby, C. Parker, Kagan Tumer
As the complexity of power plants increase, so does the difficulty in accurately modeling the interactions among the subsystems. Distributed sensing and control offers a possible solution to this problem, but introduces a new one: how to ensure that each subsystem satisfying its control objective leads to the safe and reliable operation of the entire power plant. In this work we present a distributed coordination algorithm that offers safe, reliable, and scalable control of a distributed system. In this approach, each system component uses a reinforcement learning algorithms to achieve its own objectives, but those objectives are derived to coordinate implicitly and achieve the system level objective. We show that in a Time-Extended Defect Combination Problem where the agents need to determine when and whether or not they should be sensing in order to maintain QoS in a system, the proposed method outperforms traditional methods by up to two orders of magnitude.
{"title":"Coordination and control for large distributed sensor networks","authors":"M. Colby, C. Parker, Kagan Tumer","doi":"10.1109/FIIW.2012.6378342","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378342","url":null,"abstract":"As the complexity of power plants increase, so does the difficulty in accurately modeling the interactions among the subsystems. Distributed sensing and control offers a possible solution to this problem, but introduces a new one: how to ensure that each subsystem satisfying its control objective leads to the safe and reliable operation of the entire power plant. In this work we present a distributed coordination algorithm that offers safe, reliable, and scalable control of a distributed system. In this approach, each system component uses a reinforcement learning algorithms to achieve its own objectives, but those objectives are derived to coordinate implicitly and achieve the system level objective. We show that in a Time-Extended Defect Combination Problem where the agents need to determine when and whether or not they should be sensing in order to maintain QoS in a system, the proposed method outperforms traditional methods by up to two orders of magnitude.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117176423","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 : 2012-12-13DOI: 10.1109/FIIW.2012.6378334
David L. West, F. Montgomery
Sensing behavior of electrochemical transducers for the detection of sulfur dioxide (SO2) is described. These elements operate at temperatures in the range 800-900 °C, and are constructed from oxide and precious metal electrodes on oxygenion conducting substrates. The responses to SO2 at oxygen contents around 5% can be large, with 25 ppm SO2 causing a 30-40% change in the sensing signal. This SO2 response is shown to be little affected by oxides of nitrogen (NOx), carbon monoxide, and propylene, present at the 100s of ppm level. Element stability is demonstrated over about 50 days of operation at temperature.
{"title":"Stable and selective sulfur dioxide sensing elements operating at 800–900 centigrade","authors":"David L. West, F. Montgomery","doi":"10.1109/FIIW.2012.6378334","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378334","url":null,"abstract":"Sensing behavior of electrochemical transducers for the detection of sulfur dioxide (SO2) is described. These elements operate at temperatures in the range 800-900 °C, and are constructed from oxide and precious metal electrodes on oxygenion conducting substrates. The responses to SO2 at oxygen contents around 5% can be large, with 25 ppm SO2 causing a 30-40% change in the sensing signal. This SO2 response is shown to be little affected by oxides of nitrogen (NOx), carbon monoxide, and propylene, present at the 100s of ppm level. Element stability is demonstrated over about 50 days of operation at temperature.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126151082","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 : 2012-12-13DOI: 10.1109/FIIW.2012.6378333
C. Duarte, P. Delmar, K. Goossen, K. Barner, E. Gómez-Luna
Continuous Wavelet Transform (CWT) analysis to find feature vectors for switching voltage transients for Non-Intrusive Load Monitoring (NILM) is presented and discussed, and compared with the previously used short time Fourier transform (STFT). The feature vectors computed from both CWT and STFT were used to train Support Vector Machines (SVMs) that identify the connection or disconnection of appliances for a NILM system. Experimental results show that the CWT analysis based on the complex Morlet wavelet improves classification accuracy as compared to the analysis based on STFT. More importantly, a 20× reduction of the vector size requirement is shown, thus greatly lowering computational requirements. It can be expected that commercial transient-based NILM will be based upon the CWT methods shown here.
{"title":"Non-intrusive load monitoring based on switching voltage transients and wavelet transforms","authors":"C. Duarte, P. Delmar, K. Goossen, K. Barner, E. Gómez-Luna","doi":"10.1109/FIIW.2012.6378333","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378333","url":null,"abstract":"Continuous Wavelet Transform (CWT) analysis to find feature vectors for switching voltage transients for Non-Intrusive Load Monitoring (NILM) is presented and discussed, and compared with the previously used short time Fourier transform (STFT). The feature vectors computed from both CWT and STFT were used to train Support Vector Machines (SVMs) that identify the connection or disconnection of appliances for a NILM system. Experimental results show that the CWT analysis based on the complex Morlet wavelet improves classification accuracy as compared to the analysis based on STFT. More importantly, a 20× reduction of the vector size requirement is shown, thus greatly lowering computational requirements. It can be expected that commercial transient-based NILM will be based upon the CWT methods shown here.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131378375","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 : 2012-12-13DOI: 10.1109/FIIW.2012.6378323
D. Bolme, J. Beveridge
Accurately measuring the location of facial features is an important step in many face recognition algorithms. Every face is unique which means localization needs to be tolerant of differences between individual subjects. Additionally, changing illumination, poor focus, and deformation due to expression changes complicate the problem. This paper introduces a method for locating facial features that uses Minimum Output Sum of Squared Error (MOSSE) correlation filters to model object appearance and is combined with a Robust Active Shape Model (ASM) to model facial geometry. It is demonstrated that MOSSE correlation filters outperform Stasm (an open source ASM implementation), Gabor Jets and in some cases even matches human performance.
{"title":"Facial feature localization using MOSSE correlation filters","authors":"D. Bolme, J. Beveridge","doi":"10.1109/FIIW.2012.6378323","DOIUrl":"https://doi.org/10.1109/FIIW.2012.6378323","url":null,"abstract":"Accurately measuring the location of facial features is an important step in many face recognition algorithms. Every face is unique which means localization needs to be tolerant of differences between individual subjects. Additionally, changing illumination, poor focus, and deformation due to expression changes complicate the problem. This paper introduces a method for locating facial features that uses Minimum Output Sum of Squared Error (MOSSE) correlation filters to model object appearance and is combined with a Robust Active Shape Model (ASM) to model facial geometry. It is demonstrated that MOSSE correlation filters outperform Stasm (an open source ASM implementation), Gabor Jets and in some cases even matches human performance.","PeriodicalId":170653,"journal":{"name":"2012 Future of Instrumentation International Workshop (FIIW) Proceedings","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130354457","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：