A5101586377- Industrial Vision Systems and Defect Detection
- Surface Roughness and Optical Measurements
- Image Processing Techniques and Applications
- Remote-Sensing Image Classification
- Metaheuristic Optimization Algorithms Research
- Seismic Waves and Analysis
- Image Processing and 3D Reconstruction
- Metallurgy and Material Science
- Color Science and Applications
- Earthquake Detection and Analysis
- Metallurgical Processes and Thermodynamics
- Optical Systems and Laser Technology
- Seismology and Earthquake Studies
- Advanced machining processes and optimization
- Manufacturing Process and Optimization
- Advanced Chemical Sensor Technologies
- Spectroscopy and Chemometric Analyses
- Image and Object Detection Techniques
- Advanced Algorithms and Applications
- Anomaly Detection Techniques and Applications
Hebei University of Technology
2016-2019
Hyperspectral Images (HSIs) contain enriched information due to the presence of various bands, which have gained attention for past few decades. However, explosive growth in HSIs’ scale and dimensions causes “Curse dimensionality” “Hughes phenomenon”. Dimensionality reduction has become an important means overcome dimensionality”. In hyperspectral images, labeled samples are more difficult collect because they require many labor material resources. Semi-supervised dimensionality is very...
Semisupervised support vector machine (S3VM) algorithm mainly depends on the predicted accuracy of unlabeled samples, if lots misclassified samples are added to training will make model performance degrade. Thus, cuckoo search (CS) is used optimize S3VM which also enhances S3VM. Considering that limited local optimum problem, a new based chaotic catfish effect optimization proposed. First, use mechanism with high randomness initialize nest for range expansion. Second, introduced into...
Strip steel surface defect recognition is a pattern problem with wide applications. Previous works on strip mainly focus feature selection and dimension reduction. There are also approaches real-time systems that exploit the autocorrection within some given picture. However, instances cannot be used in practical applications because of bad rate low efficiency. In this paper, we study intelligent algorithm recognition, where goal to improve accuracy save running time. This very important...
De-noising for the strip steel surface defect image is conductive to accurate detection of defects. In order filter Gaussian noise and salt pepper images, an improved compressive sensing algorithm was applied de-noising in this paper. First, Regularized Orthogonal Matching Pursuit described. Then, three typical defects (scratch, scar, upwarping) images were selected as experimental samples. Last, detailed tests carried out de-noising. Through comparison analysis test results, Peak Signal...
The kernel function optimization is the key issues to address when using support vector machine (SVM) algorithm. To solve parameter selection for SVM, a semi-definite programming optimized SVM (SDP-SVM) algorithm proposed in this paper. steps of are described, and shown an SDP method. method used find best SVM. heart_scale data University California Irvine database then simulated SDP-SVM model. experimental results shows that generalization capability classification accuracy have been...