Preface

Visual object tracking (VOT) and face recognition (FR) are both essential tasks in computer vision with various real-world applications, including human-computer interaction, autonomous vehicles, robotics, motion-based recognition, video indexing, surveillance and security. VOT and FT have remained active research topics due to both their opportunities and challenges. Significant efforts have been made by the research community in the past few decades, but VOT and FR have amazing potential still to be explored.

Major difficulties lie in different challenges, such as occlusions, clutter, illumination change, scale variations, low-resolution targets, target deformation, target re-identification, fast motion, motion blur, in-plane and out-of-plane rotations, and target tracking in presence of noise.

Traditional object tracking algorithms employed hand-crafted features like pixel intensity, color, and Histogram of Oriented Gradients (HOG) to represent the target in the object appearance model. Although hand-crafted features achieve satisfactory performance in constrained environments, they are not robust to severe appearance changes.

Recently, deep learning using a Convolutional Neural Network (CNN) has achieved a significant performance boost to various computer vision applications. VOT and FR have been affected by this popular trend in order to overcome tracking challenges and obtain better performance in respect to hand-crafted features.

This book presents the state-of-the-art and new algorithms, methods, and systems of these research fields by using deep learning. It is organized into nine chapters across three sections. Section I discusses object detection and tracking ideas and algorithms. Section II examines applications based on re-identification challenges. Section III presents applications based on FR research.

The editors thank the authors for their high-level contributions and their proactive collaboration in the realization of this book.

**II**

**Chapter 7 137** Extended Binary Gradient Pattern (eBGP): A Micro- and Macrostructure-Based

**Chapter 8 159**

**Chapter 9 175**

Granular Approach for Recognizing Surgically Altered Face Images Using

Binary Gradient Pattern for Face Recognition in Video Surveillance Area

*by Nuzrul Fahmi Nordin, Samsul Setumin, Abduljalil Radman* 

Matrix Factorization on Complex Domain for Face Recognition *by Viet-Hang Duong, Manh-Quan Bui and Jia-Ching Wang*

Keypoint Descriptors and Artificial Neural Network *by Archana Harsing Sable and Haricharan A. Dhirbasi*

*and Shahrel Azmin Suandi*

**Pier Luigi Mazzeo and Paolo Spagnolo** National Research Council of Italy (CNR), Institute of Applied Sciences and Intelligent Systems (ISASI), Lecce

**Srinivasan Ramakrishnan** Department of Information Technology at Dr. Mahalingam College of Engineering and Technology, Pollachi, India

**1**

Section 1

Detection and Tracking

Section 1
