(1 - 2 of 2)
- REAL-TIME FACEDETECTION ANDRECOGNITION SYSTEM INCOMPLEX BACKGROUNDS
- Zhang, Xin
- 2015, 2015-07
This report provides a fast and reliable system for real-time face detection and recognition in complex backgrounds. Most current face...
Show moreThis report provides a fast and reliable system for real-time face detection and recognition in complex backgrounds. Most current face recognition systems identify faces under constrained conditions, such as constant lighting condition, the same background. In the real world, people need to be recognized in complex backgrounds under different conditions, such as tilted head poses, various facial expressions, dark or strong lighting conditions. Meanwhile, because of large amounts of real-time applications for face recognition, such as intelligent robot, unmanned vehicle, security monitor, the fast face recognition rate needs to be satisfied for the real-time requirement. In this project, a fast and reliable system is designed to real-time detect and recognize faces under various conditions. Frames are obtained directly from VGA camera. Image preprocessing and face detection, collection, recognition are sequentially implemented on the frames. Local binary patterns and Haar features are used for face detection and eye detection. Local binary pattern encodes every pixel of the image for texture extraction, which is several times faster than Haar feature detection. Adaptive boosting algorithm is used for selecting the best weak classifiers and cascading method divides the extracted best classifiers into several stages to enhance detection rate. Affine transformation is implemented to unify the size of detected facial images and align two eyes to the desired position for improving recognition accuracy. 33 Gaussian filter is designed to remove noises of the pre-processed facial images. Principal component analysis (PCA) is used for face recognition, which is fast to identify high-dimensional faces with few principal components.
M.S. in Electrical Engineering, July 2015
- Machine Learning for NDE Imaging Applications
- Zhang, Xin
Infrared Thermography and Ultrasonic Imaging of materials are promising non-destructive evaluation (NDE) methods but signals face challenges...
Show moreInfrared Thermography and Ultrasonic Imaging of materials are promising non-destructive evaluation (NDE) methods but signals face challenges to be analyzed and characterized due to the nature of complex signal patterns and poor signal-to-noise ratios (SNR). Industries such as nuclear energy, are constructed with components produced using high-strength superalloys. These metallic components face challenges for wide deployment because material defects and mechanical conditions need to be non-destructively evaluated to identify potential danger before they enter service. Low NDE performance and lack of automation, particularly considering the complex environment in the in-situation NDE and nuclear power plant, present a major challenge to implement conventional NDE. This study solves the problems of using the advantages of machine learning as signal processing methods for Infrared Thermography and Ultrasonic NDE imaging applications. In Pulsed Infrared Thermography (PIT), for quality control of metal additive manufacturing, we proposed an intelligent PIT NDE system and developed innovative unsupervised learning models and thermal tomography 3D imaging algorithms to detect calibrated internal defects (pores) of various sizes and depths for different nuclear-grade metallic structures. Unsupervised learning aims to learn the latent principal patterns (dictionaries) in PIT data to detect defects with minimal human supervision. Difficulties to detect defects by using PIT are thermal imaging noise patterns; uneven heating of the specimen; defects of micron-level size with overly weak temperature signals and so on. The unsupervised learning methods overcome these barriers and achieve the high defect detection accuracies (F-score) of 0.96 to detect large defects and 0.89 to detect microscopic defects, and can successfully detect defects with diameter of only 0.101-mm. In addition, we researched and developed innovative unsupervised learning models to compress high-resolution PIT imaging data and achieve the average high compression ratio >30 and a highest compression of 46 with reconstruction accuracy peak signal-to-noise ratio (PSNR) >73dB while preserving weak thermal features corresponding to microscopic defects. In ultrasonic NDE imaging, for structural health monitoring of materials, we built a high-performance ultrasonic computational system to inspect the integrity of high-strength metallic materials which are used in high-temperature corrosive environments of nuclear reactors. For system automation, we have been developing neural networks with various architectures for grain size estimation by characterizing the ultrasonic backscattered signals with high accuracy and data-efficiency. In addition, we introduce a response-based teacher-student knowledge distillation training framework to train neural networks and achieve 99.27% characterization accuracy with a high image processed throughput of 192 images/second on testing. Furthermore, we introduce a reinforcement learning based neural architecture search framework to automatically model the optimal neural networks design for ultrasonic flaws detection. At last, we comprehensively researched the performance of using unsupervised learning methods to compress 3D ultrasonic data and achieve high compression performance using only 4.25% of the acquired experimental data.