System automatycznych pomiarów rynometrycznych (4)

pol Artykuł w języku polskim DOI:

wyślij Tomasz Kuśmierczyk Studenckie Koło Naukowe Cybernetyki, Politechnika Warszawska

Pobierz Artykuł

Streszczenie

Celem projektowanego systemu jest analiza i rozpoznawanie obrazów trójwymiarowych twarzy. Wykorzystując dostępne metody analizy i narzędzia algorytmiczne dąży się do pozyskania, z danych pochodzących ze skanerów 3D, informacji dotyczących wymiarów nosa. Artykuł przybliża aspekty stosowania jednego z głównych podejść do zagadnienia analizy obrazów 3D, tj. deskryptorów punktów. Przybliżono istniejące rozwiązania. Rozważono różne podejścia do wyboru punktów sąsiednich. Omówiono dobór skali i skwantowania. Wprowadzono odległość między deskryptorami. Pokazano też, jak zastosować deskryptory w rozpoznawaniu obrazów.

Słowa kluczowe

hacking, analiza twarzy, antropometria, deskryptor, rozpoznawanie kształtu, rynometria

Automatic nose measurement system, part 4

Abstract

The purpose of designed system is to analyze and recognice three-dimensional face images. Using known techniques, algorithms and tools I am aiming to retrieve nose parameters directly from 3D scans. Current part is devoted to describe different aspects of point descriptors usage. Wide range of known approaches is explained. Several methods of neighborhood analysis are considered. Distance measure of two descriptors is introduced. Possible methods of quantization are described. At the end, application of Hungarian algorithm for descriptors matching is shown.

Keywords

3D scans, anthropometry, descriptor, face analysis, nose measurements, shape recognition, spin images

Bibliografia

  1. Cristina Conde, Angel Serrano, Licesio J. Rodriguez-Aragón, Enrique Cabello (ed.): 3D Facial Normalization with Spin Images and Influence of Range Data Calculation over Face Verification. Universidad Rey Juan Carlos (URJC), Escuela Superior de Ciencias Experimentales y Tecnologia (ESCET), Face Recognition and Artificial Vision Group (FRAY), IEEE, 2005. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05).
  2. Chin-Seng Chua, Feng Han, Yeong-Khing Ho (ed.): 3D Human Face Recognition Using Point Signature. School of Electrical and Electronic Engineering, Nanyang Technological University, IEEE, 2000. 4th IEEE International Conference on Automatic Face and Gesture Recognition (FG’00).
  3. Serge Belongie, Jitendra Malik, Jan Puzicha: Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(24), April 2002.
  4. Serge Belongie, Jitendra Malik (ed.): Matching with Shape Contexts. IEEE, 2000. IEEE Workshop on Contentbased Access of Image and Video Libraries (CBAIVL-2000).
  5. Marian Yusuf, Tarique Haider (ed.): Recognition of Handwritten Urdu Digits using Shape Context. Department of Computer Science, KASBIT, Karachi, IEEE, 2004. Multitopic Conference, 2004. Proceedings of INMIC 2004. 8th International.
  6. Yang Li, William A.P. Smith, Edwin R. Hancock (ed.): Face Recognition using Patch-based Spin Images. Department of Computer Science, University of York, IEEE, 2006. 18th International Conference on Pattern Recognition (ICPR’06).
  7. Andrew E. Johnson, Martial Hebert: Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(5), May 1999.
  8. Salvadro Ruiz-Correa, Linda G. Shapiro, Marina Melia (ed.): A New Signature-Based Method for Efficient 3-D Object Recognition. Department of Electrical Engineering, Department of Statistics, University of Washington, IEEE, 2001.
  9. Hui Chen, Bir Bhanu: 3D free-form object recognition in range images using local surface patches. Pattern Recognition Letters, 28:1252-1262, 2007.
  10. Zhnohui Wu, Yueming Wang, Gnng Pan (ed.): 3D Face Recognition Using Local Shape Map. Department of Computer Science and Engineering Zhejiang University, Hangzhou, IEEE, 2004. 2004 International Conference on Image Processing (ICIP).
  11. Chin Seng Chua, Ray Jarvis. Point signatures: A new representation for 3D object recognition. International Journal of Computer Vision, 25(1):63-85, 1997.
  12. Hui Chen, Bir Bhanu: Human ear recognition in 3D. IEEE Transactions On Pattern Analysis And Machine Intelligence, 29(4), April 2007.