Face Recognition and Video Processing Lab

Publications (by category) (by year) (citation in SCOPUS) (citation in Google Scholar)

Teaching

• Artificial Intelligence (undergraduate)
• Artificial Intelligence (graduate)
• Pattern Recognition and Applications
• Computer Vision
• Face Recognition and Video Processing
• Image Processing
• Computer Programming and Problem Solving
  

Recent Research

1. Machine Learning and AI for Optimizing and Safeguarding Energy Transmission in Storms by Automatic Inspection of Electrical Wires
2. Preventing Wildfires in Energy Transmission by Automatic Power Line Defects Detection Using Machine Learning and AI
3. Twin Wire Crawlers for Power Line and Infrastructure Inspection and Critical Data Collection
4. Advanced Image and Video Analytics for Detecting Power Line Defects and Infrastructure Failures
5. Smart Energy using Innovative Computer Vision, Video Analytics, Smart UAS/Drones, Edge Computing, and 5G technologies

1. AI Doctor & Digital Assistant by Capitalizing on a Mixture of AI Medical Systems for Providing the Best Care for Anyone, Anywhere, and Anytime
2. Innovative AI Model for Accurately Predicting Margin Positivity from Intraoperative Digital Specimen Mammograms to Guide Surgical Decision-making and Reduce Re-excision Rates
3. Innovative AI for Rosacea Detection and Innovating Interpretability of AI Models for Enhancing Trust and Adoptability
4. Robust Parkinson’s Disease Early Detection Using Advanced Open and Scalable AI with the Optimal Feature Extraction and the Bayes Classifier
5. Deep Learning Based Prediction of Alzheimer’s Disease Conversion From Mild Cognitive Impairment Using Structural MRI: Toward an Early-Detection AI Doctor
6. ASHVINI: AI Surgical Histopathology Visualization & Interpretable Network Intelligence for Glioma Detection
7. Innovative Artificial Intelligence Framework for Medical Data Security in Large Language Models.
8. Electronic Health Records Prediction, Laparoscopic Image Desmoking and Enhancement for Improving Surgical Visualization, Brain Trauma Detection, Automatic Liver Tumor Detection, Automatic Prostate Tumor Detection, Automatic Skin Tumor Detection, Automatic Gastric Tumor Detection
   

1. By fusing our new kernel methods (kernel Fisher analysis, kernel PCA with fractional power polynomial models), new color models, new similarity measures, we achieve the best face verification performance for the government organized FRGC competition.
2. By fusing new color models with popular image descriptors, such as the scale-invariant feature transform (SIFT) and the local binary patterns (LBP), we are able to develop new image descriptors with improved image search and image category classification performance.

1. One example is an efficient support vector machine (eSVM).  The eSVM, which introduces a single value for all the slack variables corresponding to the training samples on the wrong side of their margin, defines a much smaller set of support vectors and hence improves computational efficiency without sacrificing generalization performance. 
2. Another example is feature local binary patterns (FLBP).  The FLBP method, which encodes both local and feature information, improves upon the popular LBP approach for texture description and pattern recognition.
3. Yet another example is the Bayesian discriminating features (BDF) method.  The BDF method, when trained on images from only one database yet works on test images from diverse sources, displays robust generalization performance for face detection.
4. The eSVM, FLBP, and BDF methods have been successfully applied to automatic target detection on large-scale and challenging databases, such as eye detection and face detection.