图像处理分析与机器视觉（第二版）（英文版）
分类: 图书,计算机/网络,计算机理论,
作者： [美]桑肯 等编著
出 版 社： 人民邮电出版社
出版时间： 2002-1-1字数： 1117000版次： 1页数： 770印刷时间： 2002-6-1开本：印次：纸张： 胶版纸I S B N ： 9787115097712包装： 平装编辑推荐
内容简介
本书是为计算机专业图像处理、图像分析和机器视觉课程编写的教材，被美国卡耐基梅隆等大学选用。
本书针对图像处理和机器视觉领域的技术话题展开了广泛深入的讨论，包括多种格式的图像压缩、模糊逻辑识别、3D视觉等等，还附有实例的学习和讨论，力图将复杂的概念用易于理解的算法描述出来。
本书可作为各高等院校计算机专业研究生相应课程的教材，可以结合实际教学情况选用相应的章节。本书对从事此科学领域研究的专业人士也有较高的参考价值。
作者简介
目录
1Introduction1
1.1Summary8
1.2Exercises8
1.3References9
2The digitized image and its properties10
2.1Basic concepts10
2.1.1Image functions10
2.1.2The Dirac distribution and convolution13
2.1.3The Fourier transform13
2.1.4Images as a stochastic process15
2.1.5Images as linear systems17
2.2Image digitization18
2.2.1Sampling18
2.2.2Quantization22
2.2.3Color images23
2.3Digital image properties27
2.3.1Metric and topological properties of digital images27
2.3.2Histograms32
2.3.3Visual perception of the image33
2.3.4Image quality35
2.3.5Noise in images35
2.4Summary37
2.5Exercises38
2.6References40
3Data Structures for image analysis42
3.1Levels of image data representation42
3.2Traditional image data structures43
3.2.1Matrices43
3.2.2Chains45
3.2.3Topological data structures47
3.2.4Relational structures48
3.3Hierarchical data structures49
3.3.1Pyramids49
3.3.2Quadtrees51
3.3.3Other pyramidical structures52
3.4Summary53
3.5Exercises54
3.6References55
4Image pre-processing57
4.1Pixel brightness transformations58
4.1.1Position-dependent brightness correction58
4.1.2Gray-scale transformation59
4.2Geometric transformations62
4.2.1Pixel co-ordinate transformations63
4.2.2Brightness interpolation65
4.3Local pre-processing68
4.3.1Image smoothing69
4.3.2Edge detectors77
4.3.3Zero-crossings of the second derivative83
4.3.4Scale in image processing88
4.3.5Canny edge detection90
4.3.6Parametric edge models93
4.3.7Edges in multi-spectral images94
4.3.8Other local pre-processing operators94
4.3.9Adaptive neighborhood pre-processing98
4.4Image restoration102
4.4.1Degradations that are easy to restore105
4.4.2Inverse filtration106
4.4.3Wiener filtration106
4.5Summary108
4.6Exercises111
4.7References118
5Segmentation123
5.1Thresholding124
5.1.1Threshold detection methods127
5.1.2Optimal thresholding128
5.1.3Multi-spectral thresholding131
5.1.4Thresholding in hierarchical data structures133
5.2Edge-based segmentation134
5.2.1Edge image thresholding135
5.2.2Edge relaxation137
5.2.3Border tracing142
5.2.4Border detection as graph searching148
5.2.5Border detection as dynamic programming158
5.2.6Hough transforms163
5.2.7Border detection using border location information173
5.2.8Region construction from borders174
5.3Region-based segmentation176
5.3.1Region merging177
5.3.2Region splitting181
5.3.3Splitting and merging181
5.3.4Watershed segmentation186
5.3.5Region growing post-processing188
5.4Matching190
5.4.1Matching criteria191
5.4.2Control strategies of matching193
5.5Advanced optimal border and surface detection approaches194
5.5.1Simultaneous detection of border pairs194
5.5.2Surface detection199
5.6Summary205
5.7Exercises210
5.8References216
6Shape representation and description228
6.1Region identification232
6.2Contour-based shape representation and description235
6.2.1Chain codes236
6.2.2Simple geometric border representation237
6.2.3Fourier transforms of boundaries240
6.2.4Boundary description using segment sequences242
6.2.5B-spline representation245
6.2.6Other contour-based shape description approaches248
6.2.7Shape invariants249
6.3Region-baed shape representation and description254
6.3.1Simple scalar region descriptors254
6.3.2Moments259
6.3.3Convex hull262
6.3.4Graph representation based on region skeleton267
6.3.5Region decomposition271
6.3.6Region neighborhood graphs272
6.4Shape classes273
6.5Summary274
6.6Exercises276
6.7References279
7Object recognition290
7.1Knowledge representation291
7.2Statistical pattern recognition297
7.2.1Classification principles 298
7.2.2Classifier setting300
7.2.3Classifier learning303
7.2.4Cluster analysis307
7.3Neural nets308
7.3.1Feed-forward networks310
7.3.2Unsupervised learning312
7.3.3Hopfield neural nets313
7.4Syntactic pattern recognition315
7.4.1Grammars and languages317
7.4.2Syntactic analysis，syntactic classifier319
7.4.3Syntactic classifier learning，grammar inference321
7.5Recognition as graph matching323
7.5.1Isomorphism of graphs and sub-graphs324
7.5.2Similarity of graphs328
7.6Optimization techniques in recognition328
7.6.1Genetic algorithms330
7.6.2Simulated annealing333
7.7Fuzzy systems336
7.7.1Fuzzy sets and fuzzy membership functions336
7.7.2Fuzzy set operators338
7.7.3Fuzzy reasoning339
7.7.4Fuzzy system design and training343
7.8Summary344
7.9Exercises347
7.10References354
8Image understanding362
8.1Image understanding control strategies364
8.1.1Parallel and serial processing control364
8.1.2Hierarchical control364
8.1.3Bottom-up control strategies365
8.1.4Model-based controlstrategies366
8.1.5Combined control strategies367
8.1.6Non-hierarchical control371
8.2Active contour models-snakes374
8.3Point distribution models380
8.4Pattern recognition methods in image understanding390
8.4.1Contextual image classification392
8.5Scene labeling and constraint propagation397
8.5.1Discrete relaxation398
8.5.2Probabilistic relaxation400
8.5.3Searching interpretation trees404
8.6Semantic image segmentation and understanding404
8.6.1Semantic region growing406
8.6.2Genetic image interpretation408
8.7Hidden Markov models417
8.8Summary423
8.9Exercises426
8.10References428
93D Vision，geometry，and radiometry441
9.13D vision tasks442
9.1.1Marr's theory444
9.1.2Other vision paradigms：Active and purposive vision446
9.2Geometry for 3D Vision448
9.2.1Basics of projective geometry448
9.2.2The single perspective camera449
9.2.3An overview of single camera calibration453
9.2.4Calibration of one camera from a known scene455
9.2.5Two cameras，stereopsis457
9.2.6The geometry of two cameras；the fundamental matrix460
9.2.7Relative motion of the camera；the essential matrix462
9.2.8Fundamental matrix estimation from image point correspondences464
9.2.9Applications of epipolar geometry in vision466
9.2.10Three and more cameras471
9.2.11Stereo correspondence algorithms476
9.2.12Active acquisition of range images483
9.3Radiometry and 3D vision486
9.3.1Radiometric considerations in determining gray-level486
9.3.2Surface reflectance490
9.3.3Shape from shading494
9.3.4Photometric stereo498
9.4Summary499
9.5Exercises501
9.6References502
10Use of 3D vision508
10.1Shape from X508
10.1.1Shape from motion508
10.1.2Shape from texture515
10.1.3Other shape from X techniques517
10.2Full 3D objects519
10.2.13D objects，models，and related issues519
10.2.2Line labeling521
10.2.3Volumetric representation，direct measurements523
10.2.4Volumetric modeling strategies525
10.2.5Surface modeling strategies527
10.2.6Registering surface patches and their fusion to get a full 3D model529
10.33D model-based vision535
10.3.1General considerations535
10.3.2Goad's algorithm537
10.3.3Model-based recognition of curved objects from intensity images541
10.3.4Model-based recognition based on range images543
10.42D view-based representations of a 3D scene544
10.4.1Viewing space544
10.4.2Multi-view representations and aspect graphs544
10.4.3Geons as a 2D view-based structural representation545
10.4.4Visualizing 3D real-world scenes using stored collections of 2D views546
10.5Summary551
10.6Exercises552
10.7References553
11Mathematical morphology559
11.1Basic morphological concepts559
11.2Four morphological principles561
11.3Binary dilation and erosion563
11.3.1Dilation563
11.3.2Erosion565
11.3.3Hit-or-miss transformation568
11.3.4Opening and closing568
11.4Gray-scale dilation and erosion568
11.4.1Top surface，umbra，and gray-scale dilation and erosion570
11.4.2Umbra homeomorphism theorem，properties of erosion and dilation，opening and closing573
11.4.3Top hat transformation574
11.5Skeletons and object marking576
11.5.1Homotopic transformations576
11.5.2Skeleton，maximal ball576
11.5.3Thinning，thickening，and homotopic skeleton578
11.5.4Quench function，ultimate erosion581
11.5.5Ultimate erosion and distance functions584
11.5.6Geodesic transformations585
11.5.7Morphological reconstruction586
11.6Granulometry589
11.7Morphological segmentation and watersheds590
11.7.1Particles segmentation，marking，and watersheds590
11.7.2Binary morphological segmentation592
11.7.3Gray-scale segmentation，watersheds594
11.8Summary595
11.9Exercises597
11.10References598
12Linear discrete image transforms600
12.1Basic theory600
12.2Fourier transform602
12.3Hadamard transform604
12.4Discrete cosine transform605
12.5Wavelets606
12.6Other orthogonal image transforms608
12.7Applications of discrete image transforms609
12.8Summary613
12.9Exercises617
12.10References619
13Image data compression621
13.1Image data properties622
13.2Discrete image transforms in image data compression623
13.3Predictive compression methods624
13.4Vector quantization629
13.5Hierarchical and progressive compression methods630
13.6Comparison of compression methods631
13.7Other techniques632
13.8Coding633
13.9JPEG and MPEG image compression634
13.9.1JPEG—still image compression634
13.9.2MPEG-full-motion video compression636
13.10Summary637
13.11Exercises640
13.12References641
14Texture646
14.1Statistical texture description649
14.1.1Methods based on spatial frequencies649
14.1.2Co-occurrence matrices651
14.1.3Edge frequency653
14.1.4Primitive length(run length)655
14.1.5Laws' texture energy measures565
14.1.6Fractal texture description657
14.1.7Other statistical methods of texture description659
14.2Syntactic texture description methods660
14.2.1Shape chain grammars661
14.2.2Graph grammars663
14.2.3Primitive grouping in hierarchical textures664
14.3Hybrid texture description methods666
14.4Texture recognition method applications667
14.5Summary668
14.6Exercises670
14.7References672
15Motion analysis679
15.1Differential motion analysis methods682
15.2Optical flow685
15.2.1Optical flow computation686
15.2.2Global and local optical flow estimation689
15.2.3Optical flow computation approaches690
15.2.4Optical flow in motion analysis693
15.3Analysis based on correspondence of interest points696
15.3.1Detection of interest points696
15.3.2Correspondence of interest points697
15.3.3Object tracking700
15.4Kalman filters708
15.4.1Example709
15.5Summary710
15.6Exercises712
15.7References714
16Case studies722
16.1An optical music recognition system722
16.2Automated image analysis in cardiology727
16.2.1Robust analysis of coronary angiograms730
16.2.2Knowledge-based analysis of intra-vascular ultrasound733
16.3Automated identification of airway trees738
16.4Passive surveillance744
16.5References750
Index755
媒体评论
