Che-Yen Wen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Che-Yen Wen has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
C-C Yu
Central Police University 1 Department of Forensic Science 56 Shu-Ren Road, Kuei-Shan, Taoyuan, Taiwan33334
1 shared publication- Cui Yu
Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou, China
1 shared publication J.K. Chen
1 shared publicationJing-Yue Yao
Department of Forensic Science, Central Police University, 56 Shu-Ren Road, Kuei-Shan, Taoyuan 33334, Taiwan
1 shared publicationZ-D Hun
Central Police University 1 Department of Forensic Science 56 Shu-Ren Road, Kuei-Shan, Taoyuan, Taiwan33334
1 shared publication
Latest Publications
- 1 December 2005
- Published by Elsevier in Forensic Science International
- Vol. 155 (1) , 35-50
Pistol image retrieval by shape representation
- 1 December 2005
- Published by Elsevier in Forensic Science International
- Vol. 155 (1) , 35-50
Pistol image retrieval by shape representation
- 1 July 2004
- Published by ASTM International in Journal of Forensic Sciences
- Vol. 49 (4) , 1-11
The Safety Helmet Detection Technology and Its Application to the Surveillance System
The Automatic Teller Machine (ATM) plays an important role in the modern economy. It provides a fast and convenient way to process transactions between banks and their customers. Unfortunately, it also provides a convenient way for criminals to get illegal money or use stolen ATM cards to extract money from their victim's accounts. For safety reasons, each ATM has a surveillance system to record customer's face information. However, when criminals use an ATM to withdraw money illegally, they usually hide their faces with something (in Taiwan, criminals usually use safety helmets to block their faces) to avoid the surveillance system recording their face information, which decreases the efficiency of the surveillance system. In this paper, we propose a circle/circular arc detection method based upon the modified Hough transform, and apply it to the detection of safety helmets for the surveillance system of ATMs. Since the safety helmet location will be within the set of the obtainable circles/circular arcs (if any exist), we use geometric features to verify if any safety helmet exists in the set. The proposed method can be used to help the surveillance systems record a customer's face information more precisely. If customers wear safety helmets to block their faces, the system can send a message to remind them to take off their helmets. Besides this, the method can be applied to the surveillance systems of banks by providing an early warning safeguard when any “customer” or “intruder” uses a safety helmet to avoid his/her face information from being recorded by the surveillance system. This will make the surveillance system more useful. Real images are used to analyze the performance of the proposed method.
- 1 July 2004
- Published by ASTM International in Journal of Forensic Sciences
- Vol. 49 (4) , 1-11
The Safety Helmet Detection Technology and Its Application to the Surveillance System
The Automatic Teller Machine (ATM) plays an important role in the modern economy. It provides a fast and convenient way to process transactions between banks and their customers. Unfortunately, it also provides a convenient way for criminals to get illegal money or use stolen ATM cards to extract money from their victim's accounts. For safety reasons, each ATM has a surveillance system to record customer's face information. However, when criminals use an ATM to withdraw money illegally, they usually hide their faces with something (in Taiwan, criminals usually use safety helmets to block their faces) to avoid the surveillance system recording their face information, which decreases the efficiency of the surveillance system. In this paper, we propose a circle/circular arc detection method based upon the modified Hough transform, and apply it to the detection of safety helmets for the surveillance system of ATMs. Since the safety helmet location will be within the set of the obtainable circles/circular arcs (if any exist), we use geometric features to verify if any safety helmet exists in the set. The proposed method can be used to help the surveillance systems record a customer's face information more precisely. If customers wear safety helmets to block their faces, the system can send a message to remind them to take off their helmets. Besides this, the method can be applied to the surveillance systems of banks by providing an early warning safeguard when any “customer” or “intruder” uses a safety helmet to avoid his/her face information from being recorded by the surveillance system. This will make the surveillance system more useful. Real images are used to analyze the performance of the proposed method.
- 1 March 2004
- Published by Elsevier in Forensic Science International
- Vol. 140 (2-3) , 217-232
Multi-resolution image fusion technique and its application to forensic science
- 1 March 2004
- Published by Elsevier in Forensic Science International
- Vol. 140 (2-3) , 217-232
Multi-resolution image fusion technique and its application to forensic science
- 1 September 2003
- Published by ASTM International in Journal of Forensic Sciences
- Vol. 48 (5) , 1-12
Fingerprint Pattern Restoration by Digital Image Processing Techniques
Fingerprint evidence plays an important role in solving criminal problems. However, defective (lacking information needed for completeness) or contaminated (undesirable information included) fingerprint patterns make identifying and recognizing processes difficult. Unfortunately, this is the usual case. In the recognizing process (enhancement of patterns, or elimination of "false alarms" so that a fingerprint pattern can be searched in the Automated Fingerprint Identification System (AFIS)), chemical and physical techniques have been proposed to improve pattern legibility. In the identifying process, a fingerprint examiner can enhance contaminated (but not defective) fingerprint patterns under guidelines provided by the Scientific Working Group on Friction Ridge Analysis, Study and Technology (SWGFAST), the Scientific Working Group on Imaging Technology (SWGIT), and an AFIS working group within the National Institute of Justice. Recently, the image processing techniques have been successfully applied in forensic science. For example, we have applied image enhancement methods to improve the legibility of digital images such as fingerprints and vehicle plate numbers. In this paper, we propose a novel digital image restoration technique based on the AM (amplitude modulation)-FM (frequency modulation) reaction-diffusion method to restore defective or contaminated fingerprint patterns. This method shows its potential application to fingerprint pattern enhancement in the recognizing process (but not for the identifying process). Synthetic and real images are used to show the capability of the proposed method. The results of enhancing fingerprint patterns by the manual process and our method are evaluated and compared.
- 1 September 2003
- Published by ASTM International in Journal of Forensic Sciences
- Vol. 48 (5) , 1-12
Fingerprint Pattern Restoration by Digital Image Processing Techniques
Fingerprint evidence plays an important role in solving criminal problems. However, defective (lacking information needed for completeness) or contaminated (undesirable information included) fingerprint patterns make identifying and recognizing processes difficult. Unfortunately, this is the usual case. In the recognizing process (enhancement of patterns, or elimination of "false alarms" so that a fingerprint pattern can be searched in the Automated Fingerprint Identification System (AFIS)), chemical and physical techniques have been proposed to improve pattern legibility. In the identifying process, a fingerprint examiner can enhance contaminated (but not defective) fingerprint patterns under guidelines provided by the Scientific Working Group on Friction Ridge Analysis, Study and Technology (SWGFAST), the Scientific Working Group on Imaging Technology (SWGIT), and an AFIS working group within the National Institute of Justice. Recently, the image processing techniques have been successfully applied in forensic science. For example, we have applied image enhancement methods to improve the legibility of digital images such as fingerprints and vehicle plate numbers. In this paper, we propose a novel digital image restoration technique based on the AM (amplitude modulation)-FM (frequency modulation) reaction-diffusion method to restore defective or contaminated fingerprint patterns. This method shows its potential application to fingerprint pattern enhancement in the recognizing process (but not for the identifying process). Synthetic and real images are used to show the capability of the proposed method. The results of enhancing fingerprint patterns by the manual process and our method are evaluated and compared.
- 1 May 2002
- Published by ASTM International in Journal of Forensic Sciences
- Vol. 47 (3) , 578-585
A 3-D Transformation to Improve the Legibility of License Plate Numbers
In this paper, a novel three-dimensional transformation method for vehicle license plate number recognition is proposed. This method provides an efficient solution to normalize skew distorted vehicle license plate images. The Hough transform is used to estimate the license plate position and the normalization angle. After the three-dimensional transformation and normalization processes, the vehicle license plate numbers are recognized easily. Real vehicle license plate images are used to show the capability of the proposed method. The provided method is also useful for other skewed writings, such as the text printed on a suspect's shirt.
- 1 May 2002
- Published by ASTM International in Journal of Forensic Sciences
- Vol. 47 (3) , 578-585
A 3-D Transformation to Improve the Legibility of License Plate Numbers
In this paper, a novel three-dimensional transformation method for vehicle license plate number recognition is proposed. This method provides an efficient solution to normalize skew distorted vehicle license plate images. The Hough transform is used to estimate the license plate position and the normalization angle. After the three-dimensional transformation and normalization processes, the vehicle license plate numbers are recognized easily. Real vehicle license plate images are used to show the capability of the proposed method. The provided method is also useful for other skewed writings, such as the text printed on a suspect's shirt.