AI Deep Learning in Image Processing

Frank Y. Shih received his B.S. from National Cheng Kung University, Tainan, Taiwan, in 1980; M.S. from State University of New York, Stony Brook, U.S.A., in 1984; and Ph.D. from Purdue University, West Lafayette, Indiana, U.S.A., in 1987. He is a professor jointly appointed in the Department of Computer Science, the Department of Electrical and Computer Engineering, and the Department of Biomedical Engineering at New Jersey Institute of Technology, Newark, New Jersey. He currently serves as director of Artificial Intelligence and Computer Vision Laboratory.Dr. Shih held a visiting professor position at Princeton University, Columbia University, National Taiwan University, National Institute of Informatics (Tokyo, Japan), Conservatoire National Des Arts Et Metiers (Paris, France), and Nanjing University of Information Science and Technology (China). He is an internationally renowned scholar and currently serves as editor-in-chief for the International Journal of Pattern Recognition and Artificial Intelligence. He was editor-in-chief for the International Journal of Multimedia Intelligence and Security. In addition, he is on the editorial board of 12 international journals. He has served as a steering member, session chair, and committee member for numerous professional conferences and workshops. He has received numerous grants from the National Science Foundation, the NIH, NASA, the Navy and Air Force, and industry companies Industry. He has won the Research Initiation Award from NSF, the Outstanding Teaching Award and the Board of Overseers Excellence in Research Award from NJIT, and the Best Paper Awards from journals and conferences.Dr. Shih is internationally recognized as an expert in artificial intelligence and pattern recognition, deep learning, watermarking, steganography, and forensics. He has authored seven books, including Digital Watermarking and Steganography, Image Processing and Mathematical Morphology, Image Processing and Pattern Recognition, and Multimedia Security: Watermarking, Steganography, and Forensics. He has published over 160 journal papers, 110 conference papers, and 23 book chapters. His current research interests include artificial intelligence, deep learning, image processing, watermarking and steganography, digital forensics, pattern recognition, bioinformatics, biomedical engineering, fuzzy logic, and neural networks.

• PART I Fundamentals of Image Processing 1. Introduction 2. Image Enhancement 3. Mathematical Morphology 4. Image Segmentation 5. Image Representation and Description 6. Feature Extractiion PART II Fundamentals of AI Deep Learning 7. Pattern Recognition 8. Deep Learning 9. Image Processing by Deep Learning 10. Development of Deep-Learning Framework for Mathematical Morphology 11. Deep Morphological Neural Networks PART III Practical Applications 12. A Robust and Blind Image Watermarking System Based on Deep Neural Networks 13. Deep Learning Classification on Optical Coherence Tomography Retina Images 14. Classification of Ecological Data by Deep Learning 15. Joint Learning for Pneumonia Classification and Segmentation on Medical Images 16. Classification of Chest X-Ray Images Using Novel Adaptive Morphological Neural 17. Land-Cover Image Segmentation Based on Individual Class Binary Masks 18. FPA-Net: Frequency-Guided Position-Based Attention Network for Land-Cover Image Segmentation 19. Defense against Adversarial Attacks Based on Stochastic Descent Sign Activation 20. Adaptive Image Reconstruction for Defense against Adversarial Attacks 21. A Novel Multi-Data-Augmentation and Multi-Deep-Learning Framework for Counting Small Vehicles and Crowds 22. Drug Toxicity Prediction by Machine-Learning Approaches 23. An Efficient Detection and Recognition System for Multiple Motorcycle License Plates Based on Decision Tree 24. The Deep Hybrid Neural Network and an Application on Polyp Detection 25. BFC-Cap: Background and Frequency-Guided Contextual Image 26. A Novel Adaptive Data Transformation for Contrastive Learning