Advances in Computer Vision

1. Front Matter

   Pages i-xii

   PDF

2. Deep Learning for Detection of Railway Signs and Signals

   • Georgios Karagiannis, Søren Olsen, Kim Pedersen

   Pages 1-15

3. 3D Conceptual Design Using Deep Learning

   • Zhangsihao Yang, Haoliang Jiang, Lan Zou

   Pages 16-26

4. The Effect of Color Channel Representations on the Transferability of Convolutional Neural Networks

   • Javier Diaz-Cely, Carlos Arce-Lopera, Juan Cardona Mena, Lina Quintero

   Pages 27-38

5. Weakly Supervised Deep Metric Learning for Template Matching

   • Davit Buniatyan, Sergiy Popovych, Dodam Ih, Thomas Macrina, Jonathan Zung, H. Sebastian Seung

   Pages 39-58

6. Nature Inspired Meta-heuristic Algorithms for Deep Learning: Recent Progress and Novel Perspective

   • Haruna Chiroma, Abdulsalam Ya’u Gital, Nadim Rana, Shafi’i M. Abdulhamid, Amina N. Muhammad, Aishatu Yahaya Umar et al.

   Pages 59-70

7. Transfer Probability Prediction for Traffic Flow with Bike Sharing Data: A Deep Learning Approach

   • Wenwen Tu, Hengyi Liu

   Pages 71-85

8. CanvasGAN: A Simple Baseline for Text to Image Generation by Incrementally Patching a Canvas

   • Amanpreet Singh, Sharan Agrawal

   Pages 86-98

9. Unsupervised Dimension Reduction for Image Classification Using Regularized Convolutional Auto-Encoder

   • Chaoyang Xu, Ling Wu, Shiping Wang

   Pages 99-108

10. ISRGAN: Improved Super-Resolution Using Generative Adversarial Networks

    • Vishal Chudasama, Kishor Upla

    Pages 109-127

11. Deep Learning vs. Traditional Computer Vision

    • Niall O’Mahony, Sean Campbell, Anderson Carvalho, Suman Harapanahalli, Gustavo Velasco Hernandez, Lenka Krpalkova et al.

    Pages 128-144

12. Self-localization from a 360-Degree Camera Based on the Deep Neural Network

    • Shintaro Hashimoto, Kosuke Namihira

    Pages 145-158

13. Deep Cross-Modal Age Estimation

    • Ali Aminian, Guevara Noubir

    Pages 159-177

14. Multi-stage Reinforcement Learning for Object Detection

    • Jonas König, Simon Malberg, Martin Martens, Sebastian Niehaus, Artus Krohn-Grimberghe, Arunselvan Ramaswamy

    Pages 178-191

15. Road Weather Condition Estimation Using Fixed and Mobile Based Cameras

    • Koray Ozcan, Anuj Sharma, Skylar Knickerbocker, Jennifer Merickel, Neal Hawkins, Matthew Rizzo

    Pages 192-204

16. Robust Pedestrian Detection Based on Parallel Channel Cascade Network

    • Jiaojiao He, Yongping Zhang, Tuozhong Yao

    Pages 205-221

17. Novel Scheme for Image Encryption and Decryption Based on a Hermite-Gaussian Matrix

    • Mohammed Alsaedi

    Pages 222-236

18. MAP Interpolation of an Ising Image Block

    • Matthew G. Reyes, David L. Neuhoff, Thrasyvoulos N. Pappas

    Pages 237-256

19. Volumetric Data Exploration with Machine Learning-Aided Visualization in Neutron Science

    • Yawei Hui, Yaohua Liu

    Pages 257-271

20. License Plate Character Recognition Using Binarization and Convolutional Neural Networks

    • Sandeep Angara, Melvin Robinson

    Pages 272-283

This book presents a remarkable collection of chapters covering a wide range of topics in the areas of Computer Vision, both from theoretical and application perspectives. It gathers the proceedings of the Computer Vision Conference (CVC 2019), held in Las Vegas, USA from May 2 to 3, 2019. The conference attracted a total of 371 submissions from pioneering researchers, scientists, industrial engineers, and students all around the world. These submissions underwent a double-blind peer review process, after which 120 (including 7 poster papers) were selected for inclusion in these proceedings.

The book’s goal is to reflect the intellectual breadth and depth of current research on computer vision, from classical to intelligent scope. Accordingly, its respective chapters address state-of-the-art intelligent methods and techniques for solving real-world problems, while also outlining future research directions. Topic areas covered include Machine Vision and Learning, Data Science,Image Processing, Deep Learning, and Computer Vision Applications.

• Computer Vision Algorithms
• 3D Computer Vision
• Deep Learning for Vision
• Soft Computing
• Artificial Intelligence
• Pattern Recognition
• Optimization Methods
• Support Vector Machines
• Neural Networks
• Affective Computing
• SAI
• CVC2018
• CVC

• Saga University, Saga, Japan

  Kohei Arai

• The Science and Information (SAI) Organization, Bradford, UK

  Supriya Kapoor

Policies and ethics