Identification of Address Blocks Through Multiple Illuminations, Multiple Images and Multicolor Images

We propose a methodology to identify the address labels on flat mail pieces, for the cases where the surface characteristics of the address label are different from the remaining surface. Two methods are used: movement of highlights with differing illumination, and identification of highlights using color information. Reasoning about changes in hue, saturation and intensity, using a new representation of color, allows us to discriminate between matte and glossy surfaces. On grayscale images, we separate diffuse reflectance areas from glossy reflectance areas, using highlights which change with illumination angle. If that does not disambiguate the label, we use color, reasoning that highlights decrease the saturation value and increase the intensity. Comments University of Pennsylvania Department of Computer and Information Science Technical Report No. MSCIS-90-66. This technical report is available at ScholarlyCommons: http://repository.upenn.edu/cis_reports/583 Identification of Address Blocks Through Multiple Illuminations, Multiple Images and Multicolor Images MS-CIS-90-66 GRASP LAB 233 Ruzena Bajcsy Helen Anderson Sang Wook Lee Department of Computer and Information Science School of Engineering and Applied Science University of Pennsylvania Philadelphia, PA 19104

[1]  J. Parkkinen,et al.  Characteristic spectra of Munsell colors , 1989 .

[2]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[3]  R. Bajcsy,et al.  Color image segmentation with detection of highlights and local illumination induced by inter-reflections , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[4]  L. Maloney,et al.  Color constancy: a method for recovering surface spectral reflectance. , 1986, Journal of the Optical Society of America. A, Optics and image science.

[5]  G. Buchsbaum,et al.  Chromaticity coordinates of frequency-limited functions. , 1984, Journal of the Optical Society of America. A, Optics and image science.

[6]  Ruzena Bajcsy,et al.  Second Interim Technical Report for Advanced Research in Range Image Interpretation for Automated Mail Handling , 1988 .

[7]  L. Maloney.  Evaluation of linear models of surface spectral reflectance with small numbers of parameters. , 1986, Journal of the Optical Society of America. A, Optics and image science.

[8]  R. Nevatia.  A Color Edge Detector and Its Use in Scene Segmentation , 1977 .

[9]  J. Cohen.  Dependency of the spectral reflectance curves of the Munsell color chips , 1964 .

[10]  David A. Forsyth,et al.  A Novel Approach To Colour Constancy , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[11]  Helen Anderson.  GRASP Lab Camera Systems and Their Effects on Algorithms , 1988 .

[12]  Takeo Kanade,et al.  Image Segmentation And Reflection Analysis Through Color , 1988, Defense, Security, and Sensing.

[13]  Steven A. Shafer,et al.  Using color to separate reflection components , 1985 .

[14]  D. B. Judd,et al.  Spectral Distribution of Typical Daylight as a Function of Correlated Color Temperature , 1964 .

[15]  R. Gershon.  The use of color in computational vision , 1987 .

[16]  T. Kanade,et al.  Extracting shape reflectance of Lambertian, specular, and hybrid surfaces , 1988 .

[17]  Brian A. Wandell,et al.  The Synthesis and Analysis of Color Images , 1992, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  James D. Foley,et al.  Fundamentals of interactive computer graphics , 1982 .

[19]  Keith Price,et al.  Picture Segmentation Using a Recursive Region Splitting Method , 1998 .

[20]  P. Beckmann,et al.  The scattering of electromagnetic waves from rough surfaces , 1963 .

[21]  Sang Wook Lee,et al.  Computational Aspects of Color Constancy , 1989 .

[22]  J. M. Rubin,et al.  Color Vision: Representing Material Categories , 1984 .

[23]  M D'Zmura,et al.  Mechanisms of color constancy. , 1986, Journal of the Optical Society of America. A, Optics and image science.