Deep Learning for Image Recognition
- 1st Edition - November 1, 2025
- Imprint: Elsevier
- Authors: Peng Long, Yu Song
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 4 3 9 5 0 - 6
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 4 3 9 5 1 - 3
Deep Learning for Image Recognition provides a detailed explanation of the fundamental theories underpinning image recognition and code for recognition tasks in specific applic… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteDeep Learning for Image Recognition provides a detailed explanation of the fundamental theories underpinning image recognition and code for recognition tasks in specific application scenarios. Readers can manipulate the existing code, thereby deepening their understanding. Chapters include project work enabling readers to apply the skills and knowledge gained from that section of the book. Projects are based on the accessible Pytorch framework, which is straightforward to learn and can be replicated and modified. Readers are presented with current research findings and up to date techniques in image recognition and deep learning.
- A comprehensive introduction to the technology and applications of image recognition based on deep learning
- Delves into the core concepts of image recognition, from pre-processing to modelling and algorithm implementation. This is supported by clear descriptions of neural networks, including convolutional neural network principles, model visualization, model compression and model deployment
- Highlights current research outcomes of multiple new technologies in the field of computer vision
- Examples and case studies are included
Researchers and scholars in the field of artificial intelligence, especially those specializing in image processing and pattern recognition
1. Fundamentals of Neural Networks and Convolutional Neural Networks
1.1 Biological foundations and mathematical models of neural networks
1.2 Fundamentals of Neural Networks and Convolutional Neural Networks
1.3 Summary
2. Fundamentals of Deep Learning Optimization
2.1 Activation Function
2.2 Parameter initialization
2.3 Standardization methods
2.4 Learning rate and optimization
2.5 Regularization Methods and Generalization
2.6 Mainstream Open Source Framework for Deep Learning
3. Data Process Methods in Deep Learning
3.1 Development of General Datasets for Deep Learning
3.2 Common Computer Vision Task Datasets
3.3 Data collection, cleaning, and organization
3.4 Data annotation
3.5 Data augmentation
3.6 Data Visualization
3.7 Summary
4. Image Classification
4.1 Fundamentals of Image Classification
4.2 Multi label image classification
4.3 Fine grained image classification
4.4 Semi supervised and unsupervised image classification
4.5 Typical challenges in other image classification problems
4.6 Facial expression image classification project practice
4.7 Fine-grained image classification for birds project practice
5. Object Detection
5.1 Fundamentals of Object Detection
5.2 Two-stage object detection method for deep learning
5.3 One stage object detection method for deep learning
5.4 Yolo v3 Cat Face Detection project practice
5.5 Summary
6. Image Segmentation
6.1 Fundamentals of Image Segmentation
6.2 Semantic segmentation
6.3 Image Matting model
6.4 Instance segmentation model
6.5 Lip image semantic segmentation project practice
6.6 Portrait matting project practice
7. Model Visualization
7.1 Fundamentals of Model Visualization
7.2 Visualization of Model Structure
7.3 Model Visualization Analysis
7.4 Practice of Model Visualization Analysis
7.5 Summary
8. Model Compression
8.1 Lightweight Model Design
8.2 Model pruning
8.3 Model quantification
8.4 Knowledge distillation
8.5 Structured Model Pruning project practice
8.6 Model quantification project practice
8.7 Classic Model Distillation project practice
9. Model Deployment and Launch
9.1 WeChat Mini Program Front End Development
9.2 Development of WeChat Mini Program Server
9.3 Summary
1.1 Biological foundations and mathematical models of neural networks
1.2 Fundamentals of Neural Networks and Convolutional Neural Networks
1.3 Summary
2. Fundamentals of Deep Learning Optimization
2.1 Activation Function
2.2 Parameter initialization
2.3 Standardization methods
2.4 Learning rate and optimization
2.5 Regularization Methods and Generalization
2.6 Mainstream Open Source Framework for Deep Learning
3. Data Process Methods in Deep Learning
3.1 Development of General Datasets for Deep Learning
3.2 Common Computer Vision Task Datasets
3.3 Data collection, cleaning, and organization
3.4 Data annotation
3.5 Data augmentation
3.6 Data Visualization
3.7 Summary
4. Image Classification
4.1 Fundamentals of Image Classification
4.2 Multi label image classification
4.3 Fine grained image classification
4.4 Semi supervised and unsupervised image classification
4.5 Typical challenges in other image classification problems
4.6 Facial expression image classification project practice
4.7 Fine-grained image classification for birds project practice
5. Object Detection
5.1 Fundamentals of Object Detection
5.2 Two-stage object detection method for deep learning
5.3 One stage object detection method for deep learning
5.4 Yolo v3 Cat Face Detection project practice
5.5 Summary
6. Image Segmentation
6.1 Fundamentals of Image Segmentation
6.2 Semantic segmentation
6.3 Image Matting model
6.4 Instance segmentation model
6.5 Lip image semantic segmentation project practice
6.6 Portrait matting project practice
7. Model Visualization
7.1 Fundamentals of Model Visualization
7.2 Visualization of Model Structure
7.3 Model Visualization Analysis
7.4 Practice of Model Visualization Analysis
7.5 Summary
8. Model Compression
8.1 Lightweight Model Design
8.2 Model pruning
8.3 Model quantification
8.4 Knowledge distillation
8.5 Structured Model Pruning project practice
8.6 Model quantification project practice
8.7 Classic Model Distillation project practice
9. Model Deployment and Launch
9.1 WeChat Mini Program Front End Development
9.2 Development of WeChat Mini Program Server
9.3 Summary
- Edition: 1
- Published: November 1, 2025
- Imprint: Elsevier
- Language: English
- Paperback ISBN: 9780443439506
- eBook ISBN: 9780443439513
PL
Peng Long
Peng Long received the B.S. degree in Electronic science and technology in 2012 from Huazhong University of Science and Technology, and the M.S. degree in electronic circuit and system from university of Chinese Academy of Sciences, in 2015. He is currently CEO of YouSan Educational Technology Co., Ltd., and Most Valuable Professional of Alibaba Cloud and HUAWEI Cloud. He has published five books in China. His current research interests include pattern recognition, computer vision, and image processing
Affiliations and expertise
YouSan Educational Technology Co., Ltd, ChinaYS
Yu Song
Dr Yu Song obtained her PhD degree from the National Laboratory of Pattern Recognition at the Institute of Automation, Chinese Academy of Sciences, and a master's degree in automation from Tianjin University; she currently works in the Department of Industrial Design at the College of Mechanical Engineering, University of Science and Technology Beijing. Her research interests include artificial intelligence content generation, aesthetic computation, image collage, image scaling, and machine learning
Affiliations and expertise
University of Science and Technology Beijing, China