A5042838823- Music and Audio Processing
- Digital Media Forensic Detection
- Speech and Audio Processing
- Manufacturing Process and Optimization
- Cardiac and Coronary Surgery Techniques
- Advanced Algorithms and Applications
- Advanced Measurement and Detection Methods
- Healthcare and Venom Research
- Oral and Maxillofacial Pathology
- Orthopedic Surgery and Rehabilitation
- Industrial Vision Systems and Defect Detection
- Ear Surgery and Otitis Media
- Advanced Image and Video Retrieval Techniques
- Lung Cancer Diagnosis and Treatment
- Renal and Vascular Pathologies
- Diagnosis and treatment of tuberculosis
- Congenital Diaphragmatic Hernia Studies
- Image Processing Techniques and Applications
- Sinusitis and nasal conditions
- Ear and Head Tumors
- Radiomics and Machine Learning in Medical Imaging
- Tendon Structure and Treatment
- Congenital Heart Disease Studies
- Lymphadenopathy Diagnosis and Analysis
- Advanced Control Systems Optimization
South China University of Technology
2014-2016
Changzhou University
2012
Nanchong Central Hospital
2010
Jiangsu University of Technology
2010
Source recording device recognition is an important emerging research field of digital media forensic. Most the prior literature focus on identification problem. In this study we propose a source cell phone verification scheme based sparse representation. We employed Gaussian supervectors (GSVs) Mel-frequency cepstral coefficients (MFCCs) extracted from speech recordings to characterize intrinsic fingerprint phone. For representation, both exemplar dictionary and learned by K-SVD algorithm...
Recording device recognition is an important research field of digital audio forensic. In this paper, we utilize Gaussian mixture model-universal background model (GMM-UBM) as the classifier to form a recording system. We examine performance Mel-frequency cepstral coefficients (MFCCs) and Power-normalized (PNCCs) problem. Experiments conducted on recordings come from 14 cell phones show that MFCCs are more effective than PNCCs in phone recognition. find identification can be improved by...
Source recording device matching from two speech recordings is a new and important problem of digital media forensics. It aims to answer the question that whether or not are recorded by same device. In this study we propose source cell phone scheme. The Gaussian supervector (GSV) based on Mel-frequency cepstral coefficients (MFCCs) extracted sparse represented with respect dictionary learned K-SVD algorithm. reduced-dimensional representation coefficient utilized characterize intrinsic...
Aiming at fabric defects detection in textile industry, a Gabor filtering strategy based on scale transformation was presented, which the extension of filter function shown. Firstly banks are convolved with normal image to extract texture features. Secondly convolution and defected is carried out obtain deviation images, then they fused. Lastly detected by threshold processing. The results show that method effective for detecting.
Objective To measure the frequency of visualization pancreatic feeding arteries with thin-slice maximum intensity projection(TSMIP),maximum projection(MIP) and volume rendering(VR) computed tomography angiography(CTA) techniques using multidetector-row CT(MDCT).To compare advantages different techniques.Methods Dual-phase CTA a Siemens Sensation 16 scanner was performed in 40 cases meeting including excluding criteria.CTA artery were made TSMIP,MIP VR techniques.Two radiologists evaluated...