《智能视感学（英文版）》作者张秀彬、曼苏乐根据自己和博士、硕士生们的研究成果，结合多年从事本科生及研究生的教学经验与体会整理出这本教材，将其定名为《智能视感学》。考虑到目前在该学科方向上尚缺乏较为浅显易懂、又能形成体系的简明教程，作者想做一次尝试，希望能用一种较为通俗和深入浅出的方法来阐述智能视感的一些深奥知识，对初学者能够起到入门和建立继续深造的起点之作用。

这是一本基于图像信息的非接触式传感理论的技术书。教材中所阐述的内容涉及到图像识别、视差原理、计算几何原理、计算机图像图形学，乃至人类对自然界认识的诸多先验知识如何与视感检测相结合的方法和技术问题。因此，本书是一本多学科交叉的较为前沿的大学研究型教材。

张秀彬、曼苏乐编著的《智能视感学（英文版）》从计算机视感及其信号处理的基本概念与基础理论出发，阐述了基于图像信息的识别、理解与检测技术原理与方法。

本书根据作者多年来从事智能视感理论与技术研究的成果，结合研究性本科与研究生教学特点编撰而成。全书分为基础篇与应用篇两大部分，其中，基础篇系统地介绍了智能视感的基本原理、方法、关键技术及其算法；应用篇则由配合主要基础理论和方法的应用技术实例所组成。全书遵循理论知识与实用技术的紧密结合、数学方法与实用效果的相互映证等编写原则。本书涉及的教学内容主要包括：图像处理基础、摄像机数学模型、视感识别与检测原理、智能视感实用技术等。

《智能视感学（英文版）》可以作为检测与控制、自动化、计算机、机器人及人工智能等专业的高年级本科生和研究生的教材，也可作为专业技术人员的参考工具书。

Foreword

Preface

Base article

Chapter 1 Introduction

 1.1 Overview

1.1.1 Concept about the Visual Perception

1.1.2 The Development of Visual Perception Technology

1.1.3 Classification of Visual Perception System

 1.2 A Visual Perception Hardware-base

1.2.1 iImage Sensing

1.2.2 Image Acquisition

1.2.3 PC Hardware Requirements for VPS

 Exercises

Chapter 2 Foundations of Image Processing

 2.1 Basic Processing Methods for Gray Image

2.1.1 Spatial Domain Enhancement Algorithm

2.1.2 Frequency Domain Enhancement Algorithm

 2.2 Edge Detection of Gray Image

2.2.1 Threshold Edge Detection

2.2.2 Gradient-based Edge Detection

2.Z.3 Laplacian Operator

2.2.4 Canny Edge Operator

2.2.5 Mathematical Morphological Method

2.2.6 Brief Description of Other Algorithms

 2.3 Binarization Processing and Segmentation of Image

2.3.1 General Description

2.3.2 Histogram-based Valley-point Threshold Image Binarization

2.3.3 OTSU Algorithm

2.3.4 Minimum Error Method of Image Segmentation

 2.4 Color Image Enhancement

2.4.1 Color Space and Its Transformation

2.4.2 Histogram Equalization of Color Levels in Color Image

 2.5 Color Image Edge Detection

2.5.1  Color Image Edge Detection Based on Gradient Extreme Value

2.5.2 Practical Method for Color Image Edge Detection

 Exercises

Chapter 3 Mathematical Model of the Camera

 3.1 Geometric Transformations of Image Space

3.1.1  Homogeneous Coordinates

3.1.2 Orthogonal Transformation and Rigid Body Transformation

3.1.3 Similarity Transformation and Affine Transformation

3.1.4 Perspective Transformation

 3.2 Image Coordinate System and Its Transformation

3.2.1 Image Coordinate System

3.2.2 Image Coordinate Transformation

 3.3 Common Method of Calibration Camera Parameters

3.3.1 Step Calibration Method

3.3.2 Calibration Algorithm Based on More than One Free Plane

3.3.3 Non-linear Distortion Parameter Calibration Method

 Exercises

Chapter 4 Visual Perception Identification Algorithms

 4.1 Image Feature Extraction and Identification Algorithm

4.1.1 Decision Theory Approach

4.1.2 Statistical Classification Method

4.1.3 Feature Classification Discretion Similarity about the Image Recognition Process

 4.2 Principal Component Analysis

4.2.1 Principal Component Analysis Principle

4.2.2 Kernel Principal Component Analysis

4.2.3 PCA-based Image Recognition

 4.3 Support Vector Machines

4.3.1  Main Contents of Statistical Learning Theory

4.3.2 Classification-Support Vector Machine ~

4.3.3 Solution to the Nonlinear Regression Problem

4.3.4 Algorithm of Support Vector Machine

4.3.5 Image Characteristics Identification Based on SVM

 4.4 Moment Invariants and Normalized Moments of Inertia

4.4.1 Moment Theory

4.4.2 Normalized Moment of Inertia

 4.5 Template Matching and Similarity

4.5.1 Spatial Domain Description of Template Matching

4.5.2 Frequency Domain Description of Template Matching

 4.6 Object Recognition Based on Color Feature

4.6.1 Image Colorimetric Processing

4.6.2 Construction of Color-Pool

4.6.3 Object Recognition Based on Color

 4.7 Image Fuzzy Recognition Method

4.7.1 Fuzzy Content Feature and Fuzzy Similarity Degree

4.7.2 Extraction of Fuzzy Structure

4.7.3 Fuzzy Synthesis Decision-making of Image Matching

 Exercises

Chapter 5 Detection Principle of Visual Perception

 5.1 Single View Geometry and Detection Principle of Monocular Visual Perception

5.1.1 Single Vision Coordinate System

5.1.2 Basic Algorithm for Single Vision Detection

5.1.3 Engineering Technology Based on Single View Geometry

 5.2 Detection Principle of Binocular Visual Perception

5.2.1 Two-view Geometry and Detection of Binocular Perception

5.2.2 Epipolar Geometry Principle

5.2.3 Determination Method of Spatial Coordinates

5.2.4 Camera Calibration in Binocular Visual Perception System

 5.3 Theoretical Basis for Multiple Visual Perception Detection

5.3.1 Tensor Geometry Principle

5.3.2 Geometric Properties of Three Visual Tensor

5.3.3 Operation of Three-visual Tensor

5.3.4 Constraint Matching Feature Points of Three-visual Tensor

5.3.5 Three-visual Tensor Restrict the Three Visual Restraint Feature Line' s Matching

 Exercises

 Application article

Chapter 6 Practical Technology of Intelligent Visual Perception

 6.1 Automatic Monitoring System and Method of Load Limitation of The Bridge

6.1.1 The Basic Composition of The System

6.1.2 System Algorithm

 6.2 Intelligent Identification System for Billet Number

6.2.1 System Control Program

6.2.2 Recognition Algorithm

 6.3 Verification of Banknotes-Sorting Based on Image Information

6.3.1 Preprocessing of the Banknotes Image

6.3.2 Distinction Between Old and New Banknotes

6.3.3 Distinction of the Denomination and Direction of the Banknotes

6.3.4 Banknotes Fineness Detection

 6.4 Intelligent Collision Avoidance Technology of Vehicle

6.4.1 Basic Hardware Configuration

6.4.2 Road Obstacle Recognition Algorithm

6.4.3 Smart Algorithm of Anti-collision to Pedestrians

 6.5 Intelligent Visual Perception Control of Traffic Lights

6.5.1 Overview

6.5.2 The Core Algorithm of Intelligent Visual Perception Control of Traffic Lights

 Exercises

Appendix

 Least Square and Common Algorithms in Visual Perception Detection

 I.1 Basic Idea of the Algorithm

 I.2 Common Least Square Algorithms in Visual Perception Detection

I.2.1  Least Square of Linear System of Equations

I.2.2 Least Square Solution of Nonlinear Homogeneous System of Equations Theory and Method of BAYES Decision

  II.1 Introduction

  II.2 BAYES Classification Decision Mode

II.2.1 BAYES Classification of Minimum Error Rate

II.2.2 BAYES Classification Decision of Minimum Risk

III Statistical Learning and VC-dimension Theorem

 III.1 Bounding Theory and VC-dimension Principle

 III.2 Generalized Capability Bounding

 III.3 Structural Risk Minimization Principle of Induction

IV Optimality Conditions on Constrained Nonlinear Programming Problem

 IV.1 Kuhn-Tucker Condition

IV.1.1 Gordon Lemma

IV.1.2 Fritz John Theorem

IV.1.3 Proof of the Kuhn-Tucker Condition

 IV.2 Karush-Kuhn-Tucker Condition

Subject Index

References