Abstract
In this paper, we describe the human ear creation in a system for 3-D photorealistic face modeling from frontal and profile images taken by an un-calibrated handheld digital camera. The ear part is segmented in profile facial image with a boundary detection algorithm, and then mapped to the created face model. Our ear modeling procedure has several advantages. (1) A highly automatic detection algorithm is proposed to locate profile ear boundary accurately and robustly despite of a variety of illumination, hair shape, gender and race. (2) Deliberately designed shape deformation algorithm is proposed to stitch the ear and head smoothly. (3) Synthesized texture is utilized and merged with input images to compensate occluded ear-nearby areas and create realistic results. Experimental results show that the created ear is smooth and convincing, improving the face appearance dramatically.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Yang, M.H., Kriegman, D., Ahuja, N.: Detecting faces in images: a survey. IEEE Trans. On Pattern Analysis and Machine Intelligence 24, 34–58 (2002)
Hjelmas, E., Low, B.: Face detection: A survey. ComputerVision and Image Understanding 83, 236–274 (2001)
Brunelli, R., Poggio, T.: Face recognition: Features versus templates. IEEE Trans. on Pattern Analysis and Machine Intelligence 15, 1042–1052 (2003)
Goto, T., Lee, W., Thalmann, N.: Facial feature extraction for quick 3d face modeling. Signal Processing: Image Communication 17, 243–259 (2002)
Lee, W., Kalra, P., Thalmann, N.: Model based face reconstruction for animation. In: Proc. Of Multimedia Modeling, pp. 323–338 (1997)
Pighin, F., Hecker, J., Lischinski, D., Szeliski, R., Salesin, D.: Perceptual 3d shape descriptor: Result of core experiment. In: Proc. of SIGGRAPH, pp. 75–84 (1998)
Blanz, V., Vetter, T.: A morphable model for the synthesis of 3-d faces. In: Proc. of SIGGRAPH, pp. 187–191 (1999)
Shan, Y., Liu, Z., Zhang, Z.: Model-based bundle adjustment with application to face modeling. In: Proc. of IEEE International Conference on Computer Vision (2001)
Fua, P.: Regularized bundle-adjustment to model heads from image sequences without calibration data. International Journal of Computer Vision 38, 153–171 (2000)
Sarris, N., Grammalidis, N., Strintzis, M.: Building three dimensional head models. Graphical Models 63, 333–368 (2001)
Park, I.K., Zhang, H., Vezhnevets, V., Choh, H.K.: Image-based photorealistic 3-d face modeling. In: Proc. of Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 49–54 (2004)
Carr, J., Beaton, R., Cherrie, J., Mitchell, T., Fright, W., McCallum, B., Evans. T.: Reconstruction and representation of 3-d objects with radial basis functions. Proc. of SIGGRAPH (2001)
Akimoto, T., Suenaga, Y., Wallace, R.: Automatic creation of 3d facial models. IEEE Computer Graphics and Applications 13, 16–22 (1993)
Mortensen, E., Barrett, W.: Intelligent scissors for image composition. In: Prof. of SIGGRAPH, pp. 191–198 (1995)
Burt, P., Adelson, E.: The earth mover’s distance as a metric for image retrieval. ACM Trans. on Graphic 2, 217–236 (1983)
Reinhard, E., Ashikhmin, M., Gooch, B., Shirley, P.: Color transfer between images. IEEE Computer Graphics and Applications 21, 34–41 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, H., Park, I.K. (2004). Easy and Convincing Ear Modeling for Virtual Human. In: Aizawa, K., Nakamura, Y., Satoh, S. (eds) Advances in Multimedia Information Processing - PCM 2004. PCM 2004. Lecture Notes in Computer Science, vol 3331. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30541-5_49
Download citation
DOI: https://doi.org/10.1007/978-3-540-30541-5_49
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23974-1
Online ISBN: 978-3-540-30541-5
eBook Packages: Computer ScienceComputer Science (R0)