Pub Date : 2003-10-14DOI: 10.1109/CCST.2003.1297565
Chih-Hsuan Tzeng, Wen-Hsiang Tsai
A new approach to hiding secret binary images behind noise images for covert communication with a capability of secret authentication is proposed. A secret image to be transmitted is transformed into a random noise image at a sender site with a given key, with the aim of both covering the secret and cheating illicit interceptors. Authentication bits are also embedded imperceptibly in the noise image. At the receiver site, the secret image is recovered from the noise image with the same key and verified by checking the existence of the authentication bits. Experimental results show the feasibility of the approach for real applications.
{"title":"Hiding binary images behind noise with authentication capability: a new approach to covert communication","authors":"Chih-Hsuan Tzeng, Wen-Hsiang Tsai","doi":"10.1109/CCST.2003.1297565","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297565","url":null,"abstract":"A new approach to hiding secret binary images behind noise images for covert communication with a capability of secret authentication is proposed. A secret image to be transmitted is transformed into a random noise image at a sender site with a given key, with the aim of both covering the secret and cheating illicit interceptors. Authentication bits are also embedded imperceptibly in the noise image. At the receiver site, the secret image is recovered from the noise image with the same key and verified by checking the existence of the authentication bits. Experimental results show the feasibility of the approach for real applications.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130626570","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 : 2003-10-14DOI: 10.1109/CCST.2003.1297532
Jin-ho Park, Jin-Wook Chung
This research presents the development of a certain highly efficient model for group security policy negotiation using mobile agents in the IPSec environment. The conventional IP security systems have some problems. A drawback to these systems is that the required policy between each security area is different. Another problem is not possible to guarantee whether a packet is transmitted through the same path by both directions and is protected by the same policy due to the topology of the network. Unlike conventional systems, the model developed herein can be resolved by using a mobile agent technology. If each domain needs a negotiation of security policy, a mobile agent manages the result of the negotiation in the form of a passport and guarantees the authentication and reliability each other by using the passport.
{"title":"Design of SPS model using mobile agent system","authors":"Jin-ho Park, Jin-Wook Chung","doi":"10.1109/CCST.2003.1297532","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297532","url":null,"abstract":"This research presents the development of a certain highly efficient model for group security policy negotiation using mobile agents in the IPSec environment. The conventional IP security systems have some problems. A drawback to these systems is that the required policy between each security area is different. Another problem is not possible to guarantee whether a packet is transmitted through the same path by both directions and is protected by the same policy due to the topology of the network. Unlike conventional systems, the model developed herein can be resolved by using a mobile agent technology. If each domain needs a negotiation of security policy, a mobile agent manages the result of the negotiation in the form of a passport and guarantees the authentication and reliability each other by using the passport.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133305252","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 : 2003-10-14DOI: 10.1109/CCST.2003.1297603
P. Páta, M. Klima
We devote to the further development of our tests in the field of image compression for security purposes. This phase has been oriented to the application of Karhunen-Loeve Transform (KLT) for efficient coding of car plate images. The car plate is a special class of images and the KLT is well matched to this purpose. A set of car plates was recorded and the suboptimal coding base was generated. Applying this base some examples of car plate images have been compressed and the compression results are presented including the dependence of compression rate vs MSE. The compressed standard image test LENA is also shown for comparison. The suggested efficient compression is design to be applied in various car identification systems such as entrance gates, highway entries etc. Finally the results are discussed.
{"title":"Efficient method for security image data compression","authors":"P. Páta, M. Klima","doi":"10.1109/CCST.2003.1297603","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297603","url":null,"abstract":"We devote to the further development of our tests in the field of image compression for security purposes. This phase has been oriented to the application of Karhunen-Loeve Transform (KLT) for efficient coding of car plate images. The car plate is a special class of images and the KLT is well matched to this purpose. A set of car plates was recorded and the suboptimal coding base was generated. Applying this base some examples of car plate images have been compressed and the compression results are presented including the dependence of compression rate vs MSE. The compressed standard image test LENA is also shown for comparison. The suggested efficient compression is design to be applied in various car identification systems such as entrance gates, highway entries etc. Finally the results are discussed.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114038529","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 : 2003-10-14DOI: 10.1109/CCST.2003.1297536
H.-C. Huang, J. Pan, C. Shieh, Feng-Hsing Wang
An innovative watermarking scheme based on progressive transmission with genetic algorithms (GA) is proposed. We implement the watermarking embedding and extraction system in the discrete cosine transform (DCT) domain, and apply the JPEG spectral selection mode for progressive transmission. By employing GA with a proper fitness function into the watermarking system, both the watermark imperceptibility and watermark robustness requirements are considered and optimized. In addition, the embedded watermark can be partly extracted in the receiver side even when the watermarked image is being transmitted. Simulation results show both the robustness and the effectiveness of progressive transmission under different attacking schemes and different bandwidth variations.
{"title":"Progressive watermarking techniques with genetic algorithms","authors":"H.-C. Huang, J. Pan, C. Shieh, Feng-Hsing Wang","doi":"10.1109/CCST.2003.1297536","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297536","url":null,"abstract":"An innovative watermarking scheme based on progressive transmission with genetic algorithms (GA) is proposed. We implement the watermarking embedding and extraction system in the discrete cosine transform (DCT) domain, and apply the JPEG spectral selection mode for progressive transmission. By employing GA with a proper fitness function into the watermarking system, both the watermark imperceptibility and watermark robustness requirements are considered and optimized. In addition, the embedded watermark can be partly extracted in the receiver side even when the watermarked image is being transmitted. Simulation results show both the robustness and the effectiveness of progressive transmission under different attacking schemes and different bandwidth variations.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"411 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116181438","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 : 2003-10-14DOI: 10.1109/CCST.2003.1297583
Y. Hung
Fraudulence cases have happened all the time in business environments. The responsibilities of auditors are to prevent the swindling cases and to ensure that every operation conforms to regulations. In recent years, IT is adopted in business environments. Traditional approaches with paper operation using papers to be audit trails should be changed to EDP auditing. Typically, since auditors come from nonIT backgrounds, it's difficult for them to involve the area of EDP auditing. Furthermore, enterprise resource planning (ERP) is adopted competing with other opponents around the world. ERP makes the enterprise systems more complicate. Hence, auditors face an even big problem about how to audit in ERP environment. We propose a mechanism to structure rules of auditing information by mapping from business processes to data flow and data model. With our mechanism, auditors can directly obtain auditing information based on business process and containing data changing process.
{"title":"Constructing auditing rules from ERP system: a business process flow approach","authors":"Y. Hung","doi":"10.1109/CCST.2003.1297583","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297583","url":null,"abstract":"Fraudulence cases have happened all the time in business environments. The responsibilities of auditors are to prevent the swindling cases and to ensure that every operation conforms to regulations. In recent years, IT is adopted in business environments. Traditional approaches with paper operation using papers to be audit trails should be changed to EDP auditing. Typically, since auditors come from nonIT backgrounds, it's difficult for them to involve the area of EDP auditing. Furthermore, enterprise resource planning (ERP) is adopted competing with other opponents around the world. ERP makes the enterprise systems more complicate. Hence, auditors face an even big problem about how to audit in ERP environment. We propose a mechanism to structure rules of auditing information by mapping from business processes to data flow and data model. With our mechanism, auditors can directly obtain auditing information based on business process and containing data changing process.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116336277","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 : 2003-10-14DOI: 10.1109/CCST.2003.1297546
Jonathan Jen-Rong Chen, R. Lin, An-Pin Chen
The development of digital signature provides a new field for cryptology. Chaum and van Heyet apply digital signature to group signature. The research of group digital signature is booming because group digital signature fits e-commerce very well. Although some literature has strong theoretical rationale, criticism cannot be waived because a good digital signature has to pass some rigid thresholds as follows: anonymity, unlinkability, protection, and trace-ability. Lately, Chen and Liu make use of zero knowledge and focus on faster computation time than does Camenisch. However, the development of Chen and Liu is on the basis of the Lucas cryptosystem suffering from the questioning by Bleichenbacher because the Lucas cryptosystem has the Laih's fold problem. We advance a new group digital signature scheme that can be free from the problem implicit in the Lucas cryptosystem by improving the Chen and Liu scheme. The new crypto scheme we provide is not only protected by dual complexities which can be safer while under a situation of being invaded but also possessed with the advantage of faster computation.
{"title":"A new convertible group signature scheme on the basis of dual complexities","authors":"Jonathan Jen-Rong Chen, R. Lin, An-Pin Chen","doi":"10.1109/CCST.2003.1297546","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297546","url":null,"abstract":"The development of digital signature provides a new field for cryptology. Chaum and van Heyet apply digital signature to group signature. The research of group digital signature is booming because group digital signature fits e-commerce very well. Although some literature has strong theoretical rationale, criticism cannot be waived because a good digital signature has to pass some rigid thresholds as follows: anonymity, unlinkability, protection, and trace-ability. Lately, Chen and Liu make use of zero knowledge and focus on faster computation time than does Camenisch. However, the development of Chen and Liu is on the basis of the Lucas cryptosystem suffering from the questioning by Bleichenbacher because the Lucas cryptosystem has the Laih's fold problem. We advance a new group digital signature scheme that can be free from the problem implicit in the Lucas cryptosystem by improving the Chen and Liu scheme. The new crypto scheme we provide is not only protected by dual complexities which can be safer while under a situation of being invaded but also possessed with the advantage of faster computation.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133612449","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 : 2003-10-14DOI: 10.1109/CCST.2003.1297570
G. Tai, Long-Wen Chang
Digital watermarking has been proposed to solve the ownership problem and prevent various malicious attacks in the recent years. However, most proposed watermarking algorithms are kept secret. If the watermarking algorithm can be open, it is more convincing for authentication when there is an argument. In this paper, a novel robust digital watermarking scheme for still images with public watermarking algorithm is proposed. We find the significant frequency coefficients to locate the position for embedding the watermark. The watermark is a binary image logo that can represent its ownership. Its bitmap is reordered by random permutation. Then we employ a data encryption algorithm such as DES (data encryption standard) to encrypt the bitmap permutation index of the logo. Each image is processed to generate a unique ID. The original image and ID is promulgated in the Internet Web site or trust third party as DVCS. An error correction coding scheme is also used to protect the watermark. Simulation shows that our watermarked images are robust against various attacks. Our watermarking algorithm can be open to the public, but only the owner, who uses the encryption algorithm to encrypt the random permutation order of the logo bitmap with the secret key, can retrieve the embedded watermark exactly in the cover image and recover the logo. If there is an argument between the owner and the attacker the secret key and ID can be provided to the arbitrator to resolve the copyright issue more convincingly.
{"title":"A novel public digital watermarking for still images based on encryption algorithm","authors":"G. Tai, Long-Wen Chang","doi":"10.1109/CCST.2003.1297570","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297570","url":null,"abstract":"Digital watermarking has been proposed to solve the ownership problem and prevent various malicious attacks in the recent years. However, most proposed watermarking algorithms are kept secret. If the watermarking algorithm can be open, it is more convincing for authentication when there is an argument. In this paper, a novel robust digital watermarking scheme for still images with public watermarking algorithm is proposed. We find the significant frequency coefficients to locate the position for embedding the watermark. The watermark is a binary image logo that can represent its ownership. Its bitmap is reordered by random permutation. Then we employ a data encryption algorithm such as DES (data encryption standard) to encrypt the bitmap permutation index of the logo. Each image is processed to generate a unique ID. The original image and ID is promulgated in the Internet Web site or trust third party as DVCS. An error correction coding scheme is also used to protect the watermark. Simulation shows that our watermarked images are robust against various attacks. Our watermarking algorithm can be open to the public, but only the owner, who uses the encryption algorithm to encrypt the random permutation order of the logo bitmap with the secret key, can retrieve the embedded watermark exactly in the cover image and recover the logo. If there is an argument between the owner and the attacker the secret key and ID can be provided to the arbitrator to resolve the copyright issue more convincingly.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133027655","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 : 2003-10-14DOI: 10.1109/CCST.2003.1297539
A. Gagnon
Tactical deployment of out-of-doors intrusion detection system sensors can be hazardous to law-enforcement personnel. There is a growing demand for deployment to be done secretly. Personnel are obliged to minimize their exposure to hazards and maximize mission effectiveness. Sensor hardware must be exceptionally low-cost in order to be "left behind", or considered disposable. Recent developments in noncoherent synergistic radar (NCSR) allow the RF transmitter (sensor) and RF receiver (processing engine) to be deployed wirelessly up to three kilometers away from each other. A 'leaky cable' sensor (ported coax) provides a two-meter wide contour of detection, typically fifty to two hundred meters in length. A miniature antenna provides a two-meter, spherical point-of-detection. For the purpose of this paper, "sensing elements" include; nonmetallic baseball-sized artificial stones and tree branches, RF miniature antenna, battery circuit and logic. All of which priced to be "left behind". The processing engine includes a portable receiver connected to a tripod-mounted directional antenna, located in a safe-zone far away from its related sensing elements. The receiver multiplexes, facilitating the processing of up to sixteen different frequency-coded transmitters (artificial stones). An alarm, resulting from an intrusion into any one of the sixteen spherical point zones is reported to wireless hand-held equipment. Results of a series of tactical field trials are published. Sensors (artificial stone) were secretly deposited by hand, dropped from aircraft or simply distributed using military artillery.
{"title":"New development in portable sensor allows low-cost components to be left behind (disposable)","authors":"A. Gagnon","doi":"10.1109/CCST.2003.1297539","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297539","url":null,"abstract":"Tactical deployment of out-of-doors intrusion detection system sensors can be hazardous to law-enforcement personnel. There is a growing demand for deployment to be done secretly. Personnel are obliged to minimize their exposure to hazards and maximize mission effectiveness. Sensor hardware must be exceptionally low-cost in order to be \"left behind\", or considered disposable. Recent developments in noncoherent synergistic radar (NCSR) allow the RF transmitter (sensor) and RF receiver (processing engine) to be deployed wirelessly up to three kilometers away from each other. A 'leaky cable' sensor (ported coax) provides a two-meter wide contour of detection, typically fifty to two hundred meters in length. A miniature antenna provides a two-meter, spherical point-of-detection. For the purpose of this paper, \"sensing elements\" include; nonmetallic baseball-sized artificial stones and tree branches, RF miniature antenna, battery circuit and logic. All of which priced to be \"left behind\". The processing engine includes a portable receiver connected to a tripod-mounted directional antenna, located in a safe-zone far away from its related sensing elements. The receiver multiplexes, facilitating the processing of up to sixteen different frequency-coded transmitters (artificial stones). An alarm, resulting from an intrusion into any one of the sixteen spherical point zones is reported to wireless hand-held equipment. Results of a series of tactical field trials are published. Sensors (artificial stone) were secretly deposited by hand, dropped from aircraft or simply distributed using military artillery.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125818769","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 : 2003-10-14DOI: 10.1109/CCST.2003.1297580
D. Lou, Jiang-Lung Liu, Ming-Chiang Hu
A novel image watermarking approach based on the human visual system (HVS) model and neural network technique is proposed. The human visual system model is utilized to generate the suitable strength of embedded watermark and can be described in terms of four properties of HVS model: entropy, frequency, luminance, and texture sensitivity. The neural network technique has been employed to obtain the local characteristics of image. In our experiments for each different image the watermark can be adjusted to provide a maximum and suitable strength subject to the imperceptibility constraint.
{"title":"Adaptive digital watermarking using neural network technique","authors":"D. Lou, Jiang-Lung Liu, Ming-Chiang Hu","doi":"10.1109/CCST.2003.1297580","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297580","url":null,"abstract":"A novel image watermarking approach based on the human visual system (HVS) model and neural network technique is proposed. The human visual system model is utilized to generate the suitable strength of embedded watermark and can be described in terms of four properties of HVS model: entropy, frequency, luminance, and texture sensitivity. The neural network technique has been employed to obtain the local characteristics of image. In our experiments for each different image the watermark can be adjusted to provide a maximum and suitable strength subject to the imperceptibility constraint.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125866942","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 : 2003-10-14DOI: 10.1109/CCST.2003.1297588
C. Wen, Shih-hsuan Chiu, Jiun-Jian Liaw, Chuan-Pin Lu
The automatic teller machine (ATM) plays an important role in the modern economical activity. It provides a fast and convenient way to process economical transactions between banks and their customers. Unfortunately, it also provides a convenient way for criminals to get illegal money. For the safety reason, each ATM is with the surveillance system to record customer's face information. However, when criminals use the ATM to withdraw illegal money, they usually hide their faces with something (e.g. safety helmets) to avoid that the surveillance system records their face information. That will make the surveillance system decrease their efficiency. We propose a circle/circular arc detection method based upon the modified Hough transform, and apply it to the detection of safety helmet for the surveillance system of the ATM. Since the safety helmet location will be in the set of the obtained possible circles/circular arcs (if any exists). We use geometric features to verify if any safety helmet exists in the set. The proposed method can be applied to the surveillance systems of ATMs and banks, and it can provide the early warning to save-guards when any "customer" tries to avoid his/her face information from surveillance, such as withdrawing money with the safety helmet. That will make the surveillance system more useful. A real ATM image is used to see the performance of proposed method.
{"title":"The safety helmet detection for ATM's surveillance system via the modified Hough transform","authors":"C. Wen, Shih-hsuan Chiu, Jiun-Jian Liaw, Chuan-Pin Lu","doi":"10.1109/CCST.2003.1297588","DOIUrl":"https://doi.org/10.1109/CCST.2003.1297588","url":null,"abstract":"The automatic teller machine (ATM) plays an important role in the modern economical activity. It provides a fast and convenient way to process economical transactions between banks and their customers. Unfortunately, it also provides a convenient way for criminals to get illegal money. For the safety reason, each ATM is with the surveillance system to record customer's face information. However, when criminals use the ATM to withdraw illegal money, they usually hide their faces with something (e.g. safety helmets) to avoid that the surveillance system records their face information. That will make the surveillance system decrease their efficiency. We propose a circle/circular arc detection method based upon the modified Hough transform, and apply it to the detection of safety helmet for the surveillance system of the ATM. Since the safety helmet location will be in the set of the obtained possible circles/circular arcs (if any exists). We use geometric features to verify if any safety helmet exists in the set. The proposed method can be applied to the surveillance systems of ATMs and banks, and it can provide the early warning to save-guards when any \"customer\" tries to avoid his/her face information from surveillance, such as withdrawing money with the safety helmet. That will make the surveillance system more useful. A real ATM image is used to see the performance of proposed method.","PeriodicalId":344868,"journal":{"name":"IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129249552","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：