Segmentation

  • Heinrich Niemann
Part of the Springer Series in Information Sciences book series (SSINF, volume 4)

Abstract

In this chapter it is assumed that a pattern is available which was preprocessed in the best possible way. Referring back to Sect. 1.2, where “analysis” and “description” were defined, it is necessary to decompose or to segment a pattern into simpler constituents or segmentation objects. Since the most important examples of complex patterns are images and connected speech, these will be treated in the following with emphasis on images.

Keywords

Entropy Nickel Coherence Autocorrelation Convolution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 3.1
    H. Niemann: Methoden der Mustererkennung (Akademische Verlagsgesellschaft, Frankfurt 1974)MATHGoogle Scholar
  2. 3.2
    W.K. Pratt: Digital Image Processing (Wiley, New York 1978)Google Scholar
  3. 3.3
    J.W. Strohbehn, C.H. Yates, B.H. Curran, E.S. Sternick: Image enhancement of conventional transverse-axis tomograms, IEEE Trans. BME-26, 253–262 (1979)Google Scholar
  4. 3.4
    J.W. Modestino, R.W. Fries: Edge detection in noisy images using recursive digital filtering. Comput. Graph. Image Proc. 6, 409 (1977)CrossRefGoogle Scholar
  5. 3.5
    J. Canny: A computational approach to edge detection. IEEE Trans. PAMI 8, 679 (1986)Google Scholar
  6. 3.6
    Y. Liu: Detektion von Konturpunkten in Bildern. Diplomarbeit, Lehrstuhl für Informatik 5 (Mustererkennung) Universität Erlangen-Nürnberg, Erlangen (1987)Google Scholar
  7. 3.7
    N. Blasius: Extraktion elementarer Bestandteile des Herzens für ein nuklearmedizinisches Bildanalysesystem. Studienarbeit, Lehrstuhl für Informatik 5 (Mustererkennung) Universität Erlangen-Nürnberg (1988)Google Scholar
  8. 3.8
    P. Brodatz: Textures (Dover, New York 1966)Google Scholar
  9. 3.9
    W.I. Smirnov: Lehrgang der höheren Mathematik, Teil IV (VEB, Berlin 1966)Google Scholar
  10. 3.10
    G. Schmid: Glattheitsbeschränkungen bei der Berechnung des optischen Flusses aus einem Stereobildpaar. Studienarbeit, Lehrstuhl für Informatik 5 (Mustererkennung), Universität Erlangen-Nürnberg (1988)Google Scholar
  11. 3.11
    R.T. Frankot, R. Chellapa: A method for enforcing integrability in shape from shading algorithms. Proc. 1. Int’l Conf. on Computer Vision, London 1987, p. 118–127Google Scholar
  12. 3.12
    R. Prechtel: Extraktion dreidimensionaler Information aus Grauwertbildern durch “Local Shading Analysis”. Diplomarbeit, Lehrstuhl für Informatik 5 (Mustererkennung), Universität Erlangen-Nürnberg (1988)Google Scholar
  13. 3.13
    T.B. Martin: Acoustic recognition of a limited vocabulary in continuous speech. Ph.D. Thesis, Dept. Electr. Eng, Univ. of Pennsylvania (1970)Google Scholar
  14. 3.14
    I. Biederman: Human image understanding: Recent research and theory. Computer Vision, Graphics, and Image Processing 32, 29 (1985)CrossRefGoogle Scholar
  15. 3.15
    P. Regel: Akustisch-Phonetische Transkription für die automatische Spracherkennung. Fortschrittberichte VDI Reihe 10 83 (VDI, Düsseldorf 1988)Google Scholar
  16. 3.16
    D. Sahoa: A survey of thresholding techniques. Comp. Vision, Graphics and Image Processing 41, 233–260 (1988)CrossRefGoogle Scholar
  17. 3.17
    H. Bley: Segmentation and preprocessing of electrical schematics using picture graphs. Comp. Vision, Graphics, and Image Processing 28, 271 (1984)CrossRefGoogle Scholar
  18. 3.18
    H. Bunke, H. Feistei, H. Nieman, G. Sagerer, F. Wolf, G.X. Zhou: Smoothing, thresholding, and contour extraction in images from gated blood pool studies. Proc. First IEEE Comp. Soc. Int’l Symp. on Medical Imaging and Image Interpretation, Berlin (1982) pp. 146–151Google Scholar
  19. 3.19
    C.K. Chow, T. Kaneko: Boundary detection of radiographic images by a threshold method. In Frontiers of Pattern Recognition, ed. by S. Watanabe (Academic, New York 1972) pp.61–82Google Scholar
  20. 3.20
    M. Ingram, K. Preston: Automatic analysis of blood cells. Sei. Am. 223, 72 (1970)ADSGoogle Scholar
  21. 3.21
    R.S. Ledley: High-speed automatic analysis of biomedical pictures. Science 146, 216 (1964)ADSCrossRefGoogle Scholar
  22. 3.22
    J. Schürmann: Bildvorverarbeitung für die automatische Zeichenerkennung. Wiss. Ber. AEG Telefunken 47 Heft 3/4, 90 (1974)Google Scholar
  23. 3.23
    J.R. Ullmen: Binarization using associative addressing. Pattern Recognition 6, 127–135 (1974)CrossRefGoogle Scholar
  24. 3.24
    J.S. Weszka, R.N. Nagel, A. Rosenfeld: A threshold selection technique. IEEE Trans. C-23, 1322 (1974)Google Scholar
  25. 3.25
    N. Otsu: Discriminant and least-squares threshold selection. Proc. 4th Int’l Joint Conf. on Pattern Recognition, Kyoto (1978) pp.592–596Google Scholar
  26. 3.26
    W.A. Barrett: An iterative algorithm for multiple threshold detection. Proc. IEEE Comp. Soc. Conf. on Pattern Recognition and Image Processing, Dallas TX (1981) p.273Google Scholar
  27. 3.27
    E.C. Greanias: The recognition of handwritten numerals by contour analysis. IBM J. Res. Dev. 7, 14 (1963)MATHCrossRefGoogle Scholar
  28. 3.28
    S.J. Mason, J.K. Clemens: Character recognition in an experimental reading machine for the blind. In Recognizing Patterns, ed. by P.A. Kolers, M. Eden (MIT Press, Cambridge 1968) pp. 155–167Google Scholar
  29. 3.29
    C. Arcelli, S. Levialdi: Parallel shrinking in three dimensions. Comput. Graph. Image Proc. 1, 21 (1972)CrossRefGoogle Scholar
  30. 3.30
    Z. Kulpa: Area and perimeter measurements of blobs in discrete binary pictures. Comput. Graph. Imag. Proc. 6, 434 (1977)MathSciNetCrossRefGoogle Scholar
  31. 3.31
    B. Moayer, K.S. Fu: A syntactic approach to fingerprint pattern recognition. Pattern Recognition 7, 23 (1975)CrossRefGoogle Scholar
  32. 3.32
    I.S.N. Murthy, K.J. Udupa: A search algorithm for skeletonization of thick patterns. Comput. Graph. Image Proc. 3, 247 (1974)CrossRefGoogle Scholar
  33. 3.33
    R. Pavlidis: Structural Pattern Recognition, Springer Ser. Electrophysics, Vol. 1 (Springer, Berlin, Heidelberg 1977)MATHGoogle Scholar
  34. 3.34
    J. Sobel: Neighboorhood coding of binary images for fast contour following and general binary array processing. Comput. Graph. Image Proc. 8, 127 (1978)CrossRefGoogle Scholar
  35. 3.35
    A. Perez, R.C. Gonzalez: An iterative thresholding algorithm for image segmentation. IEEE Trans. PAMI-9, 742 (1987)Google Scholar
  36. 3.36
    L.S. Davis: A survey of edge detection techniques. Comput. Graph. Image Proc. 4, 248 (1975)ADSCrossRefGoogle Scholar
  37. 3.37
    E.M. Riseman, M.A. Arbib: Computational techniques in the visual segmentation of static scenes. Comput. Graph. Image Proc. 6, 221 (1977)CrossRefGoogle Scholar
  38. 3.38
    C.H. Chen: Note on a modified gradient method for image analysis. Pattern Recognition 10, 261 (1978)ADSCrossRefGoogle Scholar
  39. 3.39
    K.K. Pingle: Visual perception by a computer. In Automatic Interpretation and Classification of Images, ed. by A. Grasselli (Academic, New York 1969) pp.277–284Google Scholar
  40. 3.40
    L.G. Roberts: Machine perception of three-dimensional solids, in Optical and Electro-Optical Information Processing, ed. by J.T. Tippelt, D.A. Berkowitz, L.C. Clapp, C.J. Koester, A.V.D. Burgh (MIT Press, Cambridge 1965) pp. 159–194Google Scholar
  41. 3.41
    A. Rosenfeld: A nonlinear edge detection technique. Proc. IEEE 58, 814 (1970)CrossRefGoogle Scholar
  42. 3.42
    A. Rosenfeld, M. Thurston: Edge and curve detection for visual scene analysis. IEEE Trans. C-20, 562 (1971)Google Scholar
  43. 3.43
    A. Rosenfeld, M. Thurston, Y.H. Lee: Edge and curve detection, further experiments. IEEE Trans. C 21, 677 (1972)Google Scholar
  44. 3.44
    H. Wechsler, J. Sklansky: Finding the rib cage in chest radiographs. Pattern Recognition 9, 21 (1977)CrossRefGoogle Scholar
  45. 3.45
    D. Middleton: An Introduction to Statistical Communication Theory (McGraw Hill, New York 1960)Google Scholar
  46. 3.46
    G. Winkler: Stochastische Systeme, Analyse and Synthese (Akademische Verlagsgesellschaft, Wiesbaden 1977)Google Scholar
  47. 3.47
    B. Kruse, K. Rao: A matched filtering technique for corner detection. Proc. 4th Int’l Joint Conf. on Pattern Recognition, Kyoto (1978) pp.642–644Google Scholar
  48. 3.48
    A.W. Lohmann, D.P. Paris: Computer generated spatial filters for coherent optical data processing. App. Opt. 7, 651 (1968)ADSCrossRefGoogle Scholar
  49. 3.49
    B.J. Schachter, A. Rosenfeld: Some new methods of detecting step edges in digital pictures. Commun. ACM 21, 172 (1978)Google Scholar
  50. 3.50
    K.S. Shanmugam, F.M. Dickey, J.A. Green: An optimal frequency domain filter for edge detection in digital pictures. IEEE Trans. PAMI-1, 37 (1979)Google Scholar
  51. 3.51
    D. Marr: Computer Vision (Freeman, San Francisco 1982)Google Scholar
  52. 3.52
    D. Marr, E.C. Hildreth: Theory of edge detection. MIT AI Memo 518, MIT, Cambridge, MA (1979)Google Scholar
  53. 3.53
    M. Hueckel: An opertor which locates edges in digitized pictures. J. Assoc. Comput. Mach. 18, 113 (1971)MATHCrossRefGoogle Scholar
  54. 3.54
    M. Hueckel: A local visual operator which recognizes edges and lines. J. Assoc. Comput. Mach. 20, 634 (1973)MathSciNetMATHCrossRefGoogle Scholar
  55. 3.55
    F. Holdermann, H. Kazmierczak: Preprocessing of gray-scale pictures. Comput. Graph. Image Proc. 1, 66 (1972)CrossRefGoogle Scholar
  56. 3.56
    Y. Yakimovski: Boundary and object detection in real world images. J. Assoc. Comput. Mach. 23, 599 (1976)MathSciNetCrossRefGoogle Scholar
  57. 3.57
    A.K. Griffith: Mathematical models for automatic line detection. J. Assoc. Comput. Mach. 20, 62 (1973)MATHCrossRefGoogle Scholar
  58. 3.58
    N.E. Nahi, S. Lopez-Mora: Estimation-detection of object boundaries in noisy images. IEEE Trans. AC-23, 834 (1978)Google Scholar
  59. 3.59
    A. Kundu, S.K. Mitra: A new algorithm for image edge extraction using a statistical classifier approach. IEEE Trans. PAMI-9, 569–577 (1987)Google Scholar
  60. 3.60
    H.P. Kramer, J.B. Bruckner: Iterations of a nonlinear transformation for enhancement of digital images. Pattern Recogn. 7, 53 (1975)MathSciNetMATHCrossRefGoogle Scholar
  61. 3.61
    A. Rosenfeld: Iterative methods in image analysis. Pattern Recognition 10, 181 (1978)CrossRefGoogle Scholar
  62. 3.62
    S. Yokoi, T. Naruse, J. Toriwaki, T. Fukumura: A theoretical analysis of grey weighted distance transformations. Proc. 4th Int’l Joint Conf. on Pattern Recognition, Kyoto (1978) pp.573–575Google Scholar
  63. 3.63
    S.W. Zucker, R.A. Hummel, A. Rosenfeld: An application of relaxation labeling to line and curve enhancement. IEEE Trans. C-26, 394 (1977)Google Scholar
  64. 3.64
    G.J. Vander Brug: Experiments in iterative enhancement of linear features. Comput. Graph. Image Proc. 6, 25 (1977)CrossRefGoogle Scholar
  65. 3.65
    R. Nevada: A color edge detector. Proc. 3rd Int’l Joint Conf. on Pattern Recognition, Coronado, CA (1976) pp.826–832Google Scholar
  66. 3.66
    J.B. Burns, A.R. Hanson, E.M. Riseman: Extracting straight lines. IEEE Trans. PAMI-8, 425 (1986)Google Scholar
  67. 3.67
    S.A. Dudani, A.L. Luk: Locating straight-line edge segments on outdoor scenes. Pattern Recognition 10, 145 (1978)CrossRefGoogle Scholar
  68. 3.68
    P. Gallinari, M. Milgram: A parallel edge following algorithm. Proc. 8th Int’l Conf. Pattern Recognition, Paris (1986) pp.907–909Google Scholar
  69. 3.69
    T. Pavlidis, S.L. Horowitz: Segmentation of plane curves. IEEE Trans. C-23, 860 (1974)MathSciNetGoogle Scholar
  70. 3.70
    M. Suk, O. Song: Curvilinear feature extraction using minimum spanning trees. Computer Vision, Graphics, and Image Processing 26, 400 (1984)CrossRefGoogle Scholar
  71. 3.71
    C.M. Williams: An efficient algorithm for the piecewise linear approximation of planar curves. Comput. Graph. Image Proc. 8, 286 (1978)CrossRefGoogle Scholar
  72. 3.72
    R.O. Duda, P.E. Hart: Use of the Hough transformation to detect lines and curves in pictures. Commun. ACM 15, 11 (1972)Google Scholar
  73. 3.73
    S.D. Shapiro: Properties of transforms for the detection of curves in noisy pictures. Comput. Graph. Image Proc. 8, 219 (1978)CrossRefGoogle Scholar
  74. 3.74
    D.H. Ballard: Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognition 13, 111 (1981)MATHCrossRefGoogle Scholar
  75. 3.75
    H. Bunke: Modellgesteuerte Bildanalyse (Teubner, Stuttgart 1985)MATHCrossRefGoogle Scholar
  76. 3.76
    H. Elliot, L. Srinivasan: An application of dynamic programming to sequential boundary estimation. Comp. Graphics and Image Processing 17, 291 (1981)CrossRefGoogle Scholar
  77. 3.77
    J.J. Gerbrands, E. Backer, W.A.G. v.d. Hoeven: Edge detection by dynamic programming. Proc. 6 Symp. on Information Theory in the Benelux, Mierlo (1985) pp.35–42Google Scholar
  78. 3.78
    U. Montanari: On the optimal detection of curves in noisy pictures. CACM 14, 335 (1971)MATHCrossRefGoogle Scholar
  79. 3.79
    H. Niemann, H. Bunke, I. Hofmann, G. Sagerer, F. Wolf, H. Feistel: A knowledge based system for analysis of gated blood pool studies. IEEE Trans. PAMI-7, 246 (1985)Google Scholar
  80. 3.80
    G.H. Granlund: In search of a general picture processing operator. Comput. Graph. Image Proc. 8, 155 (1978)CrossRefGoogle Scholar
  81. 3.81
    M.K. Hu: Visual pattern recognition by moment invariants. IEEE Trans. IT-18, 179 (1962)Google Scholar
  82. 3.82
    G. Nagy: Feature extraction on binary patterns. IEEE Trans. SSC-5, 273 (1969)Google Scholar
  83. 3.83
    T. Pavlidis: A review of algorithms for shape analysis. Comput. Graph. Image Proc. 7, 243 (1978)CrossRefGoogle Scholar
  84. 3.84
    E. Persoon, K.S. Fu: Shape discrimination using Fourier descriptors. IEEE Trans. SMC-7, 170 (1977)MathSciNetGoogle Scholar
  85. 3.85
    R.Y. Wong, E.L. Hall: Scene matching with invariant moments. Comput. Graph. Image Proc. 8, 16 (1978)CrossRefGoogle Scholar
  86. 3.86
    C.T. Zahn, R.Z. Roskies: Fourier descriptors for plane closed curves. IEEE Trans. C-21, 269 (1972)MathSciNetGoogle Scholar
  87. 3.87
    H. Blum, R.N. Nagel: Shape description using weighted symmetric axis features. Pattern Recognition 10, 167 (1978)MATHCrossRefGoogle Scholar
  88. 3.88
    H.Y. Feng. T. Pavlidis: Decomposition of polygons into simpler components: feature extraction for syntactic pattern recognition. IEEE Trans. C-24, 636 (1975)MathSciNetGoogle Scholar
  89. 3.89
    H. Freeman: Shape description via the use of critical points. Pattern Recognition 10, 159 (1978)MATHCrossRefGoogle Scholar
  90. 3.90
    Y. Nakimoto, Y. Nakano, K. Nakata, Y. Uchikara, A. Nakajima: Improvement of Chinese character recognition using projection profiles. Proc. 1st Int’l Joint Conf. on Pattern Recognition, Washington, DC (1973) pp. 172–178Google Scholar
  91. 3.91
    L.G. Shapiro, R.M. Haralick: Decomposition of two-dimensional shapes by graph-theoretical clustering. IEEE Trans. PAMI-1, 10 (1979)Google Scholar
  92. 3.92
    E. Wong, J.A. Steppe: Invariant recognition of geometric shapes. In Methodologies of Pattern Recognition, ed. by S. Watanabe (Academic, New York 1969) pp.535–546Google Scholar
  93. 3.93
    S.W. Zucker: Region growing: childhood and adolescence. Comput. Graph. Image Proc. 5, 382 (1976)CrossRefGoogle Scholar
  94. 3.94
    C.R. Brice, C.L. Fennema: Scene analysis using regions. Artif. Intell. 1, 205 (1970)CrossRefGoogle Scholar
  95. 3.95
    E.C. Freuder: Affinity, a relative approach to region finding. Comput. Graph. Image Proc. 5, 254 (1976)CrossRefGoogle Scholar
  96. 3.96
    J.L. Muerle, D.C. Allen: Experimental evaluation of techniques for automatic segmentation of objects in a complex scene. In Pictorial Pattern Recognition, ed. by G.C. Cheng, R.S. Ledley, D.K. Pollock, A. Rosenfeld (Tompson, Washington 1968) pp.3–13Google Scholar
  97. 3.97
    R. Ohlander, K. Price, D.R. Reddy: Picture segmentation using a recursive region splitting method. Comput. Graph. Image Proc. 8, 313 (1978)CrossRefGoogle Scholar
  98. 3.98
    T.V. Robertson, P.H. Swain, K.S. Fu: Multispectral image partitioning. TR-WW 73-26, LARS Inf. Note 071373, School of Electr. Eng., Purdue Univ. (1973)Google Scholar
  99. 3.99
    S.L. Horowitz, T. Pavlidis: Picture segmentation by a tree traversal algorithm. J. Assoc. Comput. Mach. 23, 368 (1976)MATHCrossRefGoogle Scholar
  100. 3.100
    F. Cheevasuvit, H. Maitre, D. Vidal-Madjar: A robust method for picture segmentation based on a split-and-merge procedure. Computer Vision, Graphics, and Image Processing 34, 268 (1986)ADSCrossRefGoogle Scholar
  101. 3.101
    C.H. Lee: Recursive region splitting at hierarchical scope views. Computer Vision, Graphics, and Image Processing 33, 237 (1986)CrossRefGoogle Scholar
  102. 3.102
    A.M. Nazif, M.D. Levine: Low level image segmentation: an expert system. IEEE Trans. PAMI-6, 555 (1984)Google Scholar
  103. 3.103
    P.A. Devijver: Probabilistic labeling in a hidden second order Markov mesh. In Pattern Recognition in Practice II, ed. by E.S. Gelsema, L.N. Kanal (North-Holland, Amsterdam 1986) p. 113–123CrossRefGoogle Scholar
  104. 3.104
    P.A. Devijver, M.M. Dekessel: Real-time restoration and segmentation algorithms for hidden Markov mesh random field models. In Real-Time Object Measurement and Classification, ed. by A.K. Jain, NATO ASI Ser. F42 (Springer, Berlin, Heidelberg 1988) pp.293–307CrossRefGoogle Scholar
  105. 3.105
    B. Julesz: Experiments in the visual perception of texture. Sei. Am. 232, 34 (April 1975)Google Scholar
  106. 3.106
    B. Julesz: The role of terminators in preattentive preception of line textures. In Recognition of Pattern and Form, ed. by D.G. Albrecht (Springer, Berlin, Heidelberg 1982) pp.33–55CrossRefGoogle Scholar
  107. 3.107
    R.M. Haralick: Statistical and structural approaches to texture. Proc. 4th Int’l Joint Conf. on Pattern Recognition, Kyoto (1978) pp.45–69Google Scholar
  108. 3.108
    J.K. Hawkins: Textural properties for pattern recognition. In Picture Processing and Psychopictorics, ed. by B.S. Lipkin, A. Rosenfeld (Academic, New York 1970) pp.347–370Google Scholar
  109. 3.109
    G.R. Cross, A.K. Jain: Markov random field texture models. IEEE Trans. PAMI-5, 25 (1983)Google Scholar
  110. 3.110
    A. Gagalowicz: Analysis of texture using a stochastic model, Proc. 4th Int’l Joint Conf. on Pattern Recognition, Kyoto (1978) pp.541–544Google Scholar
  111. 3.111
    M. Hassner, J. Sklansky: Markov random field models of digitized image texture. Proc. 4th Int’l Joint Conf. on Pattern Recognition, Kyoto (1978) pp.538–540Google Scholar
  112. 3.112
    O.D. Faugeras: Texture analysis and classification using a human visual model. Proc. 4th Int’l Joint Conf. on Pattern Recognition, Kyoto (1978) pp.549–552Google Scholar
  113. 3.113
    M.M. Galloway: Texture analysis using gray level run lengths. Comput. Graph. Image Proc. 4, 172 (1975)CrossRefGoogle Scholar
  114. 3.114
    R. Haralick, K. Shanmugan, I. Dinstein: Textural features for image classification. IEEE Trans. SMC-3, 610 (1973)Google Scholar
  115. 3.115
    S.L. Tanimoto: An optimal algorithm for computing Fourier texture descriptors, IEEE Trans. C-27, 81 (1978)MathSciNetGoogle Scholar
  116. 3.116
    S.W. Zucker, A. Rosenfeld, L.S. Davis: Picture segmentation by texture discrimination. IEEE Trans. C 24, 1228 (1975)Google Scholar
  117. 3.117
    S.Y. Lu, K.S. Fu: A syntactic approach to texture analysis. Comput. Graph. Image Proc. 7, 303 (1977)MathSciNetCrossRefGoogle Scholar
  118. 3.118
    H.G. Musmann, P. Pirsch, H.-J. Gallert: Advances in picture coding. Proc. IEEE 73, 523 (1985)CrossRefGoogle Scholar
  119. 3.119
    H.H. Nagel: Analyse und Interpretation von Bildfolgen. Informatik Spektrum 8, 178, 312 (1985)Google Scholar
  120. 3.120
    B.K.P. Horn, B.G. Schunk: Determining optical flow. Artif. Intelligence 17, 185 (1981)CrossRefGoogle Scholar
  121. 3.121
    H.H. Nagel, W. Enkelmann: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans. PAMI-8, 565 (1986)Google Scholar
  122. 3.122
    J. Hutchinson, C. Koch, J. Luo, C. Mead: Computing motion using analog and binary resistive networks. IEEE Computer 21 3, 52 (1988)CrossRefGoogle Scholar
  123. 3.123
    R.Y. Tsai, T.S. Huang: Uniquenses and estimation of 3-D motion parameters of rigid bodies with curved surfaces. IEEE Trans. PAMI-6, 13 (1984)Google Scholar
  124. 3.124
    J. Weng, T.S. Huang, N. Ahuja: 3-D motion estimation, understanding, and prediction from noisy images. IEEE Trans. PAMI-9, 370 (1987)Google Scholar
  125. 3.125
    A. v. Brandt, W. Tengler: Obtaining smoothed optical flow fields by modified block matching. Proc. 5th Scandinavian Conf. on Image Analysis, Stockholm (1987) pp.523–529Google Scholar
  126. 3.126
    A. v. Brandt: Motion estimation and subband coding using quadrature mirror filters. Proc. EUSIPCO-86 2, 829 (1986)Google Scholar
  127. 3.127
    D. Terzopoulos: Image analysis using multigrid relaxation methods. IEEE Trans. PAMI-8, 129 (1986)Google Scholar
  128. 3.128
    S.T. Barnard, M.A. Fischer: Computational Stereo. Comp. Surveys 14, 553 (1982)CrossRefGoogle Scholar
  129. 3.129
    E.L. Hall, C.A. McPherson: Three-dimensional perception for robot vision. Proc. SPIE Conf. on Robotics and Robot Sensing Systems, San Diego 442, 117–143 (1983)CrossRefGoogle Scholar
  130. 3.130
    R.A. Jarvis: A perspective of range finding techniques for computer vision. IEEE Trans. PAMI 5, 122 (1983)Google Scholar
  131. 3.131
    E.L. Hall, J.B.K. Tio, C.A. McPherson, C.S. Draper F.A. Sadjadi: Measuring curved surfaces for robot vision. Computer 15 12, 42 (1982)CrossRefGoogle Scholar
  132. 3.132
    A. Scheuing, H. Niemann: Computing depth from stereo images by using optical flow. Pattern Recognition Lett. 4, 205 (1986)CrossRefGoogle Scholar
  133. 3.133
    Y. Yakimovski, R. Cunningham: A system for extracting three-dimensional measurements from a pair of TV cameras. Comp. Graphics and Image Proc. 7, 195 (1978)ADSCrossRefGoogle Scholar
  134. 3.134
    S. Barnard, W. Thompson: Disparity analysis of images: IEEE Trans. PAMI-2, 333 (1980)Google Scholar
  135. 3.135
    G. Medioni, R. Nevatia: Segment based stereo matching. Comp. Vision, Graphics, and Image Processing 31, 2 (1985)CrossRefGoogle Scholar
  136. 3.136
    H. Baker, T. Binford: A system for automated stereo mapping. Proc. Image Understanding Workshop, Palo Alto CA, (1982) p.215Google Scholar
  137. 3.137
    W. Grimson, D. Marr: A computer implementation of a theory of human stereo vision. Proc. Image Understanding Workshop, Palo Alto, CA (1979) pp.41–47Google Scholar
  138. 3.138
    W. Hoff, N. Ahuja: Extracting surfaces from stereo images: An integrated approach. Proc. 1th Int’l Conf. on Computer Vision, London (1987) pp.284–294Google Scholar
  139. 3.139
    S.A. Lloyd, E.R. Haddow, J.F. Boyce: A parallel binocular stereo algorithm utilizing dynamic programming and relaxation labeling. Comp. Vision, Graphics, and Image Processing 39, 202 (1987)CrossRefGoogle Scholar
  140. 3.140
    Y. Ohta, T. Kanade: Stero by intra- and inter-scanline search using dynamic programming. IEEE Trans. PAMI-7, 139–154 (1985)Google Scholar
  141. 3.141
    S. Posch: Hierarchische linienbasierte Tiefenbestimmung in einem Stereobild, in Künstliche Intelligenz, Informatik-Fachberichte Vol.181 ed. by W. Hoeppner (Springer, Berlin, Heidelberg 1988) pp.275–285CrossRefGoogle Scholar
  142. 3.142
    B.K.P. Horn: Understanding image intensities: Artif. Intelligence 8, 201 (1977)MATHGoogle Scholar
  143. 3.143
    B.K.P. Horn, M.J. Brooks: The variational approach to shape from shading. Computer Vision, Graphics, and Image Processing 33, 174 (1986)MATHCrossRefGoogle Scholar
  144. 3.144
    A.P. Pentland: Local shading analysis. IEEE Trans. PAMI-6, 170 (1984)Google Scholar
  145. 3.145
    C.H. Lee, A. Rosenfeld: Improved methods of estimating shape from shading using the light source coordinate system. Artificial Intelligence 26, 125 (1985)MathSciNetMATHCrossRefGoogle Scholar
  146. 3.146
    G. Healey, T.O. Binford: Local shape from specularity. Proc. 1. Int’l Conf. on Computer Vision, London (1987) pp.151–160Google Scholar
  147. 3.147
    B.T. Phong: Illumination for computer generated pictures. CACM 18, 311 (1975)CrossRefGoogle Scholar
  148. 3.148
    J.E. Shoup: Phonological aspects of speech recognition. In [Ref. 1.8, pp. 125–138]Google Scholar
  149. 3.149
    J.L. Flanagan: Speech Analysis, Synthesis, and Perception, Kommunikation und Kybernetik in Einzeldarstellungen, Vol. 3, 2nd edn. (Springer, Berlin, Heidelberg, New York 1972)CrossRefGoogle Scholar
  150. 3.150
    F. Itakura: Minimum prediction residual principle applied to speech recognition. IEEE Trans. ASSP 23, 67 (1975)Google Scholar
  151. 3.151
    J.D. Markel, A.H. Gray, Jr.: Linear Prediction of Speech, Communications and Cybernetics, Vol. 12 (Springer, Berlin, Heidelberg, 1976)CrossRefGoogle Scholar
  152. 3.152
    R.J. Niederjohn, P.F. Castelaz: Zero-crossing analysis methods for speech recognition. Proc. IEEE Conf. Pattern Recognition and Image Proc., Chicago (1978) pp.507–513Google Scholar
  153. 3.153
    H.F. Silverman, N.R. Dixon: The 1976 modular acoustic processor (MAP). IEEE Trans. ASSP 25, 367 (1977)Google Scholar
  154. 3.154
    G.M. White, R.B. Neeley: Speech recognition experiments with linear prediction, bandpass filtering, and dynamic programming. IEEE Trans. ASSP-24, 183 (1976)Google Scholar
  155. 3.155
    S.S. McCandless: An algorithm for automatic formant extraction using linear prediction spectra. IEEE Trans. ASSP 22, 135 (1974)Google Scholar
  156. 3.156
    J.D. Markel: Digital inverse filtering - a new tool for formant trajectory estimation. IEEE Trans. AU-20, 129 (1972)Google Scholar
  157. 3.157
    W. Hess: Algorithms and Devices for Pitch Determination of Speech Signals, Springer Ser. Inf. Sei., Vol.3 (Springer, Berlin, Heidelberg 1983)CrossRefGoogle Scholar
  158. 3.158
    J.D. Markel: The SIFT algorithm for fundamental frequency estimation. IEEE Trans. AU-20, 367 (1972)Google Scholar
  159. 3.159
    S. Sennef: Real-time harmonic pitch detector: IEEE Trans ASSP-26, 358 (1978)Google Scholar
  160. 3.160
    E. Nöth, H. Niemann, S. Schmölz: Prosodic features in German speech: stress assignment by man and machine. In Recent Advances in Speech Understanding and Dialog Systems, ed. by H. Niemann, M. Lang, G. Sagerer, NATO ASI Series F46 (Springer, Berlin, Heidelberg 1988) pp.101–106CrossRefGoogle Scholar
  161. 3.161
    A.M. Noll: Cepstrum pitch determination. J. Acoust. Soc. Am. 41, 293 (1967)ADSCrossRefGoogle Scholar
  162. 3.162
    R.J. Niederjohn, I.B. Thomas: Computer recognition of the continuant phonemes in connected English speech. IEEE Trans. AU-21, 526 (1973)Google Scholar
  163. 3.163
    W.A. Lea, M.F. Medress, T.E. Skinner: A prosodically guided speech understanding strategy. IEEE Trans. ASSP-23, 30 (1975)Google Scholar
  164. 3.164
    A. Waibel: Prosody and Speech Recognition. PhD Thesis, Carnegie-Mellon Univ., Pittsburgh (1986)Google Scholar
  165. 3.165
    J.Y. Cheung, A.D.C. Holden, F.D. Minifie: Computer recognition of linguistic stress patterns in connected speech. IEEE Trans. ASSP-25, 252–256 (1977)Google Scholar
  166. 3.166
    J. Vaissiére: The use of prosodic parameters in automatic speech recognition: in Recent Advances in Spech Understanding and Dialog Systems, ed. by H. Niemann, M. Lang, G. Sagerer, NATO ASI Series F46 (Springer, Berlin, Heidelberg 1988) pp.71–100CrossRefGoogle Scholar
  167. 3.167
    M. Jalanko, S. Haltsonen, K.J. Bry, T. Kohonen: Application of orthogonal projection principles to simultaneous phonemic segmentation and labeling of continuous speech. Proc. 4th Int’l Joint Conf. on Pattern Recognition, Kyoto (1978) pp. 1006–1008Google Scholar
  168. 3.168
    R. Andre-Obrecht: Automatic segmentation of continuous speech signals. Proc. ICASSP Tokyo (1986) p.2275Google Scholar
  169. 3.169
    M. Cravers, R. Pieraccini, F. Raineri: Definition and evaluation of phonetic units for speech recognition by hidden Markov models. Proc. ICASSP Tokyo (1986) pp.2235–2238Google Scholar
  170. 3.170
    P. Demichelis, R. DeMori, P. Laface, M. O’Kane: Computer recognition of plosive sounds using contextual information. IEEE Trans. ASSP-31, 359 (1983)Google Scholar
  171. 3.171
    F. Jelinek, L.R. Bahl, R.L. Mercer: Design of a linguistic statistical decoder for the recognition of continuous speech. IEEE Trans. IT-21, 250 (1975)Google Scholar
  172. 3.172
    K. Mano, S. Ishige, K. Shirai: Phoneme recognition in connected speech using both static and dynamic properties of spectrum described by vector quantization. Proc. ICASSP Tokyo (1986) pp.2243–2246Google Scholar
  173. 3.173
    G. Ruske, T. Schotola: The efficiency of demisyllable segmentation in the recognition of spoken words. Proc. ICASSP Atlanta (1981) pp.971–974Google Scholar
  174. 3.174
    A. Tanaka, S. Kamiya: A speech processing based on syllable identification by using phonological patterns. Proc. ICASSP Tokyo (1986) pp.2231–2234Google Scholar
  175. 3.175
    T. Watanabe: Syllable recognition for continuous Japanese speech recognition. Proc. ICASSP Tokyo 1986, p.2295–2298Google Scholar
  176. 3.176
    W. Woods, M. Bates, G. Brown, B. Bruce, C. Cook, J. Klovstad, J. Makhoul, B. Nash-Webber, R. Schwartz, J. Wolf, V. Zue: Speech understanding systems, Vol.2, Acoustic Front End, Final Report (Bolt, Beranek and Newman Inc., Cambridge, MA 1976)Google Scholar
  177. 3.177
    V. Zue, L.F. Lamel: An expert spectrogram reader: A knowledge-based approach to speech recognition. Proc. ICASSP Tokyo (1986) pp. 1197–1200Google Scholar
  178. 3.178
    H. Niemann, M. Lang, G. Sagerer (eds.): Recent Advances in Speech Understanding and Dialog Systems. NATO ASI Ser. F46 (Springer, Berlin, Heidelberg 1988)MATHGoogle Scholar
  179. 3.179
    A. Abut, R.M. Gray, G.R. Robelledo: Vector quantization of speech and speech-like waveforms. IEEE Trans. ASSP-30, 423 (1982)Google Scholar
  180. 3.180
    D. Wolf; H. Reininger: Recent advances in speech coding. In Recent Advances in Speech Understanding and Dialog Systems, ed. by H. Niemann, M. Lang, G. Sagerer, NATO ASI Ser. F46 (Springer, Berlin, Heidelberg 1988) pp. 1–24CrossRefGoogle Scholar
  181. 3.181
    Y. Linde, A. Buzo, R.M. Gray: An algorithm for vector quantizer design. IEEE Trans. COM-28, 84 (1980)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • Heinrich Niemann
    • 1
    • 2
  1. 1.Lehrstuhl für Informatik 5 (Mustererkennung)Friedrich-Alexander-Universität Erlangen-NürnbergErlangenFed. Rep. of Germany
  2. 2.Forschungsgruppe WissensverarbeitungBayerisches Forschungszentrum für Wissensbasierte SystemeErlangenFed. Rep. of Germany

Personalised recommendations