Download link: https://pan.baidu.com/s/1h7dVls7r9kzl4o-9J9-fw Password: xv5e
- Publisher: Electronics Industry Press; 1st edition (May 1, 2014)
- Paperback: 287 pages
- Language: Simplified Chinese
- Format: 16
- ISBN: 9787121229664, 7121229668
- Barcode: 9787121229664
- Product size: 25.8 x 18.4 x 1.4 cm
- Item weight: 381 g
- Brand: Electronic Industry Press
- ASIN: B00KIWESY4
Editor's Choice
The teaching materials of digital image processing and pattern recognition are mainly purely academic, focusing on theoretical derivation and analysis, and are out of touch with actual programming implementation and specific projects. This book integrates the author's many years of research achievements in the field of digital image processing and pattern recognition, combined with practical application projects, expounds the relevant knowledge of image recognition, and introduces the realization method of development examples. Each example provides the technical principle of project development, the implementation process, and the implementation steps of the algorithm, implements the implementation technology into programming, and provides the programming code of VC++ or MATLAB.
About the Author
Yang Shuying, professor of the Department of Computer Science, Tianjin University of Technology, Ph.D., School of Electronic Information, Tianjin University, has published nearly 20 related papers, four of which have been indexed by EI. Many of his published books have been selected as teaching materials for graduate or undergraduate students by Tsinghua University and other universities. Publication direction: computer vision, pattern recognition, image processing and applications, computer control and robot vision control.
content
Chapter 1 Overview of Image Recognition (1)
1.1 Image Recognition Meaning (1)
1.2 Image Recognition Technology (3)
1.3 Handwritten Digit Recognition (6)
1.4 Postal Code Recognition (8)
1.5 Introduction to License Plate Recognition (10)
1.6 Printed Chinese Character Recognition ( 13)
1.7 Barcode Recognition (16)
1.8 Face Recognition (18)
1.9 Iris Recognition (20)
1.10 Fingerprint Recognition (22)
1.11 Image Recognition System Performance Evaluation (24)
Chapter 2 Image Recognition Key Technologies (27)
2.1 Image Recognition Development Basic process (27)
2.2 Image preprocessing (28)
2.2.1 Grayscale (29)
2.2.2 Grayscale transformation (30)
2.2.3 Grayscale distribution equalization (32)
2.2.4 Geometric transformation (33)
2.2 .5 Denoising (34)
2.2.6 Sharpening (36)
2.2.7 Morphological processing (38)
2.2.8 Thinning (43)
2.2.9 Contour extraction of target objects (45)
2.2.10 Segmentation (48)
2.2.11 Projection-based localization (51)
2.2.12 Measurement (51)
2.3 Transform domain processing (53)
2.3.1 Fourier transform (54)
2.3.2 Gabor transform (55)
2.3.3 Wavelet transform (56)
2.4 Feature extraction (59)
2.4.1 Color-based feature extraction (60)
2.4.2 Texture-based feature extraction (60)
2.4.3 Shape-based feature extraction (62)
2.4.4 Feature Extraction Based on Spatial Relationship (63)
2.5 Pattern Recognition (63)
2.5.1 Introduction to Pattern Recognition (63)
2.5.2 Pattern Recognition Method (65)
2.5.3 Template Matching Method (67)
Chapter 3 Handwritten Digit Recognition (70 ) )
3.1 Characteristic Analysis of Handwritten Digit Image Data (70)
3.2 Design of Handwritten Digit Recognition System (72)
3.3 Feature Extraction (73)
3.4 Handwritten Digit Recognition (77)
Chapter 4 Postcode Recognition (81)
4.1 Postcode Image Data Feature Analysis ( 81)
4.2 Postcode Recognition System Design (82)
4.3 Postcode Preprocessing (83)
4.3.1 Red Frame Removal (84)
4.3.2 Grayscale and Binarization (87)
4.3.3 Coding Location Based on Projection (89)
4.3.4 Digit cutting (90)
4.4 Postal code sample feature extraction and feature library (96)
4.4.1 Postal code sample feature extraction (96)
4.4.2 Construction of postal code sample feature library (97)
4.5 Postal code identification (99)
Chapter 5 Recognition of Vehicle License Plate Numbers (104)
5.1 Characteristic Analysis of Vehicle License Plate Image Data (104)
5.2 Design of Vehicle License Plate Number Recognition System (105)
5.3 Image Preprocessing (106)
5.3.1 Binarization (106)
5.3.2 Remove Noise (111)
5.3.3 License Plate Location (113)
5.3.4 License Plate Image Normalization (118)
5.3.5 Character Segmentation (120)
5.3.6 Character Refinement (124)
5.4 License Plate Number Recognition (128)
Chapter 6 Printing Chinese character recognition (141)
6.1 Characteristic analysis of printed Chinese characters image data (141)
6.2 Chinese character recognition system design (142)
6.3 Image preprocessing (142)
6.3.1 Binarization (142)
6.3.2 Noise elimination (146)
6.3. 3 Chinese character line segmentation and character segmentation (148)
6.4 Feature extraction (155)
6.5 Chinese character recognition (161)
Chapter 7 1D barcode recognition (167)
7.1 1D barcode image data feature analysis (167)
7.2 1D barcode recognition System Design (170)
7.3 One-dimensional Barcode Image Preprocessing (171)
7.3.1 Grayscale (171)
7.3.2 Binarization (173)
7.3.3 Image Correction (175)
7.3.4 Noise Processing (178)
7.4 One-dimensional Barcode Recognition (180)
Chapter 8 Face Recognition (189)
8.1 Feature Analysis of Face Image Data (189)
8.2 Design of Face Recognition System (190)
8.3 Preprocessing of Face Image (192)
8.3.1 Background Removal (192)
8.3.2 Binarization (194)
8.3.3 Noise removal (195)
8.4 Face localization based on composite multi-projection detection (197)
8.4.1 Composite multi-projection detection method (197)
8.4.2 Face region Location (198)
8.4.3 Eye Region Location (202)
8.4.4 Mouth Region Location (208)
8.5 Feature Extraction (211)
8.6 Face Recognition (226)
Chapter 9 Iris Recognition (229)
9.1 Iris Image Data Features Analysis (229)
9.2 Design of Iris Recognition System (230)
9.3 Iris Localization (231)
9.3.1 Rapid Iris Localization Based on Region of Interest (232)
9.3.2 Iris Outer Circle Location (232)
9.3.3 Iris Inner Circle Location ( 234)
9.4 Iris region processing (238)
9.4.1 Iris region extraction (238)
9.4.2 Iris region polar transformation (240)
9.4.3 Iris image normalization (243)
9.5 Iris feature extraction (244)
9.5.1 Two-dimensional Gabor filter (244)
9.5.2 Iris feature extraction (247)
9.6 Iris feature dimensionality reduction (250)
9.7 Iris recognition (254)
Chapter 10 Fingerprint recognition (262)
10.1 Fingerprint recognition image data feature analysis ( 262)
10.2 Fingerprint Identification System Design (263)
10.3 Fingerprint Image Preprocessing (264)
10.4 Fingerprint Image Gabor Filtering (272)
10.4.1 Gabor Filtering (272)
10.4.2 Fingerprint Image Gabor Filtering Method (274)
10.5 Fingerprint Feature Dimensionality Reduction (276)
10.6 Fingerprinting (279)
References (284)
abstract
版权页： 
频率域法则只在图像的某种变换域里对图像的变换值进行运算，如我们对图像进行傅里叶变换，然后在变换域里对图像的频谱进行某种计算，最后把计算后的图像逆变换到空间域。频率域法通常分为高、低通滤波、频率带通和带阻滤波等。图像复原技术就是利用图像的先验知识来改变一副被退化的图像的过程。图像复原技术需要我们先建立图像模型，然后逆向反解这个退化过程，最后获得退化前的最优图像。这里我们主要介绍图像增强的一些关键技术，有关编程代码请参考作者主编的国家级“十一五”规划教材《VC++图像处理程序设计》（第二版）。
2.2.1灰度化
将彩色的图像转换为灰度图像的过程叫作图像灰度化。由于彩色图像每个像素的颜色由R、G、B三个分量组成，即红、绿、蓝三种颜色。每种颜色都有255种灰度值可以取，而灰度图像则是R、G、B三个分量灰度值相同的一种特殊的图像。灰度化处理是把含有亮度和色彩的彩色图像变换成灰度图像的过程。所以在数字图像处理过程中将彩色图像转换成灰度图像后就会使后续的图像处理时的计算量变得相对很少，这也就是图像灰度化的原因。而且灰度图像对图像特征的描述与彩色图像没有什么区别，仍能反映整个图像整体和局部的亮度和色度特征。现在大部分的彩色图像都是采用RGB颜色模式，处理图像的时候，要分别对R、G、B三种分量进行处理实际上，R、G、B并不能反映图像的形态特征，只是从光学的原理上进行颜色的调配。所以，人们在进行图像处理和预处理时都会先进行图像的灰度化处理，方便对图像的后续化处理，减少图像的复杂度和信息处理量。
彩色图像RGB模型中，如果R=G=B，则彩色表示一种灰度颜色，其中这个值叫灰度值。一般情况下，彩色图像的每个像素用3个字节表示，每个字节对应着R、G、B分量的亮度（红、绿、蓝），转换后的黑白图像的一个像素用一个字节表示该点的灰度值，它的值在0～255之间，数值越大，该点越白，即越亮。越小则越黑。