A5101966949- Biometric Identification and Security
- User Authentication and Security Systems
- Advanced Vision and Imaging
- Hand Gesture Recognition Systems
- Anomaly Detection Techniques and Applications
- Remote Sensing and Land Use
- Infrared Target Detection Methodologies
- Image and Object Detection Techniques
- Video Surveillance and Tracking Methods
- Industrial Vision Systems and Defect Detection
- Advanced Authentication Protocols Security
- Image Processing Techniques and Applications
- Advanced Measurement and Detection Methods
- Advanced Malware Detection Techniques
Beijing Jiaotong University
2019
Suzhou Nonferrous Metals Research Institute
2015-2016
Implicit authentication is a new research direction to enhance the privacy protection of smartphones. However, implicit has low robustness due its vulnerability environment. Motivated by this, this paper proposes context-aware authentication, which scheme improve introducing context awareness module. In scheme, multi-sensor data (including accelerometer, gyroscope, magnetometer, timestamp, pressure, touch size) first captured in fine-grained manner characterize one's action. Then, based on...
A single defect image segmentation algorithm cannot obtain the desired results for all images because of diversity. parallel combination method is proposed to integrate multiple different algorithms map high-speed aluminum surface detection. Two types are designed in this framework, namely, automatic threshold based on statistical model and adaptive entropy-based segmentation. The detects defects rapidly using parameters obtained by modeling effectively, effectively ID information entropy....
Touch dynamic is a new biological recognition method based on one's touch pattern. However, less works have been done to explore the use of motion sensors embedded in smart phone for enhance password authentication. In this paper, we propose touch-based authentication system protection level traditional mechanism by adding pattern into mechanism. The proposed leverages only three (accelerometer, magnetometer and gyroscope) monitor users' behavior. After performing pre-processing series...
With the popularity of smartphones, more and users are accustomed to storing sensitive information related personal privacy, which puts forward higher requirements for current authentication system. In this paper, an implicit solution based on user's keystroke behavior smartphone usage is proposed. Firstly, a data collected by three types built-in sensors in smartphone. After performing smoothing normalization processing, we extract temporal features time domain using statistical methods....
Extracting the motion patterns from videos is a basic task in video surveillance and has become an active research area. In this paper, we propose novel approach for discovering scene observed by one or two cameras. The chaos theory employed to compute chaotic invariant features (CIFs) after obtaining all trajectories. CIFs other are combined feature vector trajectory represented vector. Based on CIFs, grouped via mean shift clustering algorithm. Five challenging datasets used validation....