图像处理、分析与机器视觉(第2版) (平装)

书籍目录

1　Introduction　11.1　Summary　81.2　Exercises　81.3　References　92　The digitized image and its properties　102.1　Basic concepts　102.1.1　Image functions　102.1.2　The Dirac distribution and convolution　132.1.3　The Fourier transform　132.1.4　Images as a stochastic process　152.1.5　Images as linear systems　172.2　Image digitization　182.2.1　Sampling　182.2.2　Quantization　222.2.3　Color images　232.3　Digital image properties　272.3.1　Metric and topological properties of digital images　272.3.2　Histograms　322.3.3　Visual perception of the image　332.3.4　Image quality　352.3.5　Noise in images　352.4　Summary　372.5　Exercises　382.6　References　403　Data Structures for image analysis　423.1　Levels of image data representation　423.2　Traditional image data structures　433.2.1　Matrices　433.2.2　Chains　453.2.3　Topological data structures　473.2.4　Relational structures　483.3　Hierarchical data structures　493.3.1　Pyramids　493.3.2　Quadtrees　513.3.3　Other pyramidical structures　523.4　Summary　533.5　Exercises　543.6　References　554　Image pre-processing　574.1　Pixel brightness transformations　584.1.1　Position-dependent brightness correction　584.1.2　Gray-scale transformation　594.2　Geometric transformations　624.2.1　Pixel co-ordinate transformations　634.2.2　Brightness interpolation　654.3　Local pre-processing　684.3.1　Image smoothing　694.3.2　Edge detectors　774.3.3　Zero-crossings of the second derivative　834.3.4　Scale in image processing　884.3.5　Canny edge detection　904.3.6　Parametric edge models　934.3.7　Edges in multi-spectral images　944.3.8　Other local pre-processing operators　944.3.9　Adaptive neighborhood pre-processing　984.4　Image restoration　1024.4.1　Degradations that are easy to restore　1054.4.2　Inverse filtration　1064.4.3　Wiener filtration　1064.5　Summary　1084.6　Exercises　1114.7　References　1185　Segmentation　1235.1　Thresholding　1245.1.1　Threshold detection methods　1275.1.2　Optimal thresholding　1285.1.3　Multi-spectral thresholding　1315.1.4　Thresholding in hierarchical data structures　1335.2　Edge-based segmentation　1345.2.1　Edge image thresholding　1355.2.2　Edge relaxation　1375.2.3　Border tracing　1425.2.4　Border detection as graph searching　1485.2.5　Border detection as dynamic programming　1585.2.6　Hough transforms　1635.2.7　Border detection using border location information　1735.2.8　Region construction from borders　1745.3　Region-based segmentation　1765.3.1　Region merging　1775.3.2　Region splitting　1815.3.3　Splitting and merging　1815.3.4　Watershed segmentation　1865.3.5　Region growing post-processing　1885.4　Matching　1905.4.1　Matching criteria　1915.4.2　Control strategies of matching　1935.5　Advanced optimal border and surface detection approaches　1945.5.1　Simultaneous detection of border pairs　1945.5.2　Surface detection　1995.6　Summary　2055.7　Exercises　2105.8　References　2166　Shape representation and description　2286.1　Region identification　2326.2　Contour-based shape representation and description　2356.2.1　Chain codes　2366.2.2　Simple geometric border representation　2376.2.3　Fourier transforms of boundaries　2406.2.4　Boundary description using segment sequences　2426.2.5　B-spline representation　2456.2.6　Other contour-based shape description approaches　2486.2.7　Shape invariants　2496.3　Region-baed shape representation and description　2546.3.1　Simple scalar region descriptors　2546.3.2　Moments　2596.3.3　Convex hull　2626.3.4　Graph representation based on region skeleton　2676.3.5　Region decomposition　2716.3.6　Region neighborhood graphs　2726.4　Shape classes　2736.5　Summary　2746.6　Exercises　2766.7　References　2797　Object recognition　2907.1　Knowledge representation　2917.2　Statistical pattern recognition　2977.2.1　Classification principles 2987.2.2　Classifier setting　3007.2.3　Classifier learning　3037.2.4　Cluster analysis　3077.3　Neural nets　3087.3.1　Feed-forward networks　3107.3.2　Unsupervised learning　3127.3.3　Hopfield neural nets　3137.4　Syntactic pattern recognition　3157.4.1　Grammars and languages　3177.4.2　Syntactic analysis，syntactic classifier　3197.4.3　Syntactic classifier learning，grammar inference　3217.5　Recognition as graph matching　3237.5.1　Isomorphism of graphs and sub-graphs　3247.5.2　Similarity of graphs　3287.6　Optimization techniques in recognition　3287.6.1　Genetic algorithms　3307.6.2　Simulated annealing　3337.7　Fuzzy systems　3367.7.1　Fuzzy sets and fuzzy membership functions　3367.7.2　Fuzzy set operators　3387.7.3　Fuzzy reasoning　3397.7.4　Fuzzy system design and training　3437.8　Summary　3447.9　Exercises　3477.10　References　3548　Image understanding　3628.1　Image understanding control strategies　3648.1.1　Parallel and serial processing control　3648.1.2　Hierarchical control　3648.1.3　Bottom-up control strategies　3658.1.4　Model-based control　strategies　3668.1.5　Combined control strategies　3678.1.6　Non-hierarchical control　3718.2　Active contour models-snakes　3748.3　Point distribution models　3808.4　Pattern recognition methods in image understanding　3908.4.1　Contextual image classification　3928.5　Scene labeling and constraint propagation　3978.5.1　Discrete relaxation　3988.5.2　Probabilistic relaxation　4008.5.3　Searching interpretation trees　4048.6　Semantic image segmentation and understanding　4048.6.1　Semantic region growing　4068.6.2　Genetic image interpretation　4088.7　Hidden Markov models　4178.8　Summary　4238.9　Exercises　4268.10　References　4289　3D Vision，geometry，and radiometry　4419.1　3D vision tasks　4429.1.1　Marrs theory　4449.1.2　Other vision paradigms：Active and purposive vision　4469.2　Geometry for 3D Vision　4489.2.1　Basics of projective geometry　4489.2.2　The single perspective camera　4499.2.3　An overview of single camera calibration　4539.2.4　Calibration of one camera from a known scene　4559.2.5　Two cameras，stereopsis　4579.2.6　The geometry of two cameras；the fundamental matrix　4609.2.7　Relative motion of the camera；the essential matrix　4629.2.8　Fundamental matrix estimation from image point correspondences　4649.2.9　Applications of epipolar geometry in vision　4669.2.10　Three and more cameras　4719.2.11　Stereo correspondence algorithms　4769.2.12　Active acquisition of range images　4839.3　Radiometry and 3D vision　4869.3.1　Radiometric considerations in determining gray-level　4869.3.2　Surface reflectance　4909.3.3　Shape from shading　4949.3.4　Photometric stereo　4989.4　Summary　4999.5　Exercises　5019.6　References　50210　Use of 3D vision　50810.1　Shape from X　50810.1.1　Shape from motion　50810.1.2　Shape from texture　51510.1.3　Other shape from X techniques　51710.2　Full 3D objects　51910.2.1　3D objects，models，and related issues　51910.2.2　Line labeling　52110.2.3　Volumetric representation，direct measurements　52310.2.4　Volumetric modeling strategies　52510.2.5　Surface modeling strategies　52710.2.6　Registering surface patches and their fusion to get a full 3D model　52910.3　3D model-based vision　53510.3.1　General considerations　53510.3.2　Goads algorithm　53710.3.3　Model-based recognition of curved objects from intensity images　54110.3.4　Model-based recognition based on range images　54310.4　2D view-based representations of a 3D scene　54410.4.1　Viewing space　54410.4.2　Multi-view representations and aspect graphs　54410.4.3　Geons as a 2D view-based structural representation　54510.4.4　Visualizing 3D real-world scenes using stored collections of 2D views　54610.5　Summary　55110.6　Exercises　55210.7　References　55311　Mathematical morphology　55911.1　Basic morphological concepts　55911.2　Four morphological principles　56111.3　Binary dilation and erosion　56311.3.1　Dilation　56311.3.2　Erosion　56511.3.3　Hit-or-miss transformation　56811.3.4　Opening and closing　56811.4　Gray-scale dilation and erosion　56811.4.1　Top surface，umbra，and gray-scale dilation and erosion　57011.4.2　Umbra homeomorphism theorem，properties of erosion and dilation，opening and closing　57311.4.3　Top hat transformation　57411.5　Skeletons and object marking　57611.5.1　Homotopic transformations　57611.5.2　Skeleton，maximal ball　57611.5.3　Thinning，thickening，and homotopic skeleton　57811.5.4　Quench function，ultimate erosion　58111.5.5　Ultimate erosion and distance functions　58411.5.6　Geodesic transformations　58511.5.7　Morphological reconstruction　58611.6　Granulometry　58911.7　Morphological segmentation and watersheds　59011.7.1　Particles segmentation，marking，and watersheds　59011.7.2　Binary morphological segmentation　59211.7.3　Gray-scale segmentation，watersheds　59411.8　Summary　59511.9　Exercises　59711.10　References　59812　Linear discrete image transforms　60012.1　Basic theory　60012.2　Fourier transform　60212.3　Hadamard transform　60412.4　Discrete cosine transform　60512.5　Wavelets　60612.6　Other orthogonal image transforms　60812.7　Applications of discrete image transforms　60912.8　Summary　61312.9　Exercises　61712.10　References　61913　Image data compression　62113.1　Image data properties　62213.2　Discrete image transforms in image data compression　62313.3　Predictive compression methods　62413.4　Vector quantization　62913.5　Hierarchical and progressive compression methods　63013.6　Comparison of compression methods　63113.7　Other techniques　63213.8　Coding　63313.9　JPEG and MPEG image compression　63413.9.1　JPEG—still image compression　63413.9.2　MPEG-full-motion video compression　63613.10　Summary　63713.11　Exercises　64013.12　References　64114　Texture　64614.1　Statistical texture description　64914.1.1　Methods based on spatial frequencies　64914.1.2　Co-occurrence matrices　65114.1.3　Edge frequency　65314.1.4　Primitive length(run length)　65514.1.5　Laws texture energy measures　56514.1.6　Fractal texture description　65714.1.7　Other statistical methods of texture description　65914.2　Syntactic texture description methods　66014.2.1　Shape chain grammars　66114.2.2　Graph grammars　66314.2.3　Primitive grouping in hierarchical textures　66414.3　Hybrid texture description methods　66614.4　Texture recognition method applications　66714.5　Summary　66814.6　Exercises　67014.7　References　67215　Motion analysis　67915.1　Differential motion analysis methods　68215.2　Optical flow　68515.2.1　Optical flow computation　68615.2.2　Global and local optical flow estimation　68915.2.3　Optical flow computation approaches　69015.2.4　Optical flow in motion analysis　69315.3　Analysis based on correspondence of interest points　69615.3.1　Detection of interest points　69615.3.2　Correspondence of interest points　69715.3.3　Object tracking　70015.4　Kalman filters　70815.4.1　Example　70915.5　Summary　71015.6　Exercises　71215.7　References　71416　Case studies　72216.1　An optical music recognition system　72216.2　Automated image analysis in cardiology　72716.2.1　Robust analysis of coronary angiograms　73016.2.2　Knowledge-based analysis of intra-vascular ultrasound　73316.3　Automated identification of airway trees　73816.4　Passive surveillance　74416.5　References　750Index　755

作者简介

　　《图像处理、分析与机械视觉(第2版)》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。《图像处理、分析与机械视觉(第2版)》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。　　《图像处理、分析与机械视觉(第2版)》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。《图像处理、分析与机械视觉(第2版)》对从事此科学领域研究的专业人士也有较高的参考价值。

图书封面

 图像处理、分析与机器视觉(第2版) (平装)下载