CORRESPONDENCE: Image SegmentationNo Access

STILL IMAGE SEGMENTATION TOOLS FOR OBJECT-BASED MULTIMEDIA APPLICATIONS

Informatics and Telematics Institute, Centre for Research and Technology Hellas, 1st Km Thermi-Panorama Road, Thessaloniki 57001, Greece

Information Processing Laboratory, Electrical and Computer Engineering Department, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece

Search for more papers by this author

IOANNIS KOMPATSIARIS

Informatics and Telematics Institute, Centre for Research and Technology Hellas, 1st Km Thermi-Panorama Road, Thessaloniki 57001, Greece

Search for more papers by this author

, and

MICHAEL G. STRINTZIS

Informatics and Telematics Institute, Centre for Research and Technology Hellas, 1st Km Thermi-Panorama Road, Thessaloniki 57001, Greece

Information Processing Laboratory, Electrical and Computer Engineering Department, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece

Author for correspondence.

Search for more papers by this author

https://doi.org/10.1142/S0218001404003393Cited by:53 (Source: Crossref)

Abstract

In this paper, a color image segmentation algorithm and an approach to large-format image segmentation are presented, both focused on breaking down images to semantic objects for object-based multimedia applications. The proposed color image segmentation algorithm performs the segmentation in the combined intensity–texture–position feature space in order to produce connected regions that correspond to the real-life objects shown in the image. A preprocessing stage of conditional image filtering and a modified K-Means-with-connectivity-constraint pixel classification algorithm are used to allow for seamless integration of the different pixel features. Unsupervised operation of the segmentation algorithm is enabled by means of an initial clustering procedure. The large-format image segmentation scheme employs the aforementioned segmentation algorithm, providing an elegant framework for the fast segmentation of relatively large images. In this framework, the segmentation algorithm is applied to reduced versions of the original images, in order to speed-up the completion of the segmentation, resulting in a coarse-grained segmentation mask. The final fine-grained segmentation mask is produced with partial reclassification of the pixels of the original image to the already formed regions, using a Bayes classifier. As shown by experimental evaluation, this novel scheme provides fast segmentation with high perceptual segmentation quality.

This work was supported by the EU projects aceMedia "Integrating Knowledge Semantics and Content for User Centred Intelligent Media Services" (FP6-001765) and SCHEMA "Network of Excellence in Content-Based Semantic Scene Analysis and Information Retrieval" (IST-2001-32795). The assistance of COST211 quat is also gratefully acknowledged.

Keywords:

References

S. T. Acton , A. C. Bovik and M. M. Crawford , Anisotropic diffusion pyramids for image segmentation , Proc. IEEE Int. Conf. Image Processing . Google Scholar
S. Belongie et al. , Color- and texture-based image segmentation using EM and its application to content-based image retrieval , Proc. Sixth Int. Conf. Computer Vision . Google Scholar
N. V. Boulgouris et al. , Content-based watermarking for indexing using robust segmentation , Proc. Workshop on Image Analysis For Multimedia Interactive Services . Google Scholar
C. Carsonet al., IEEE Trans. Patt. Anal. Mach. Intell. 24, 1026 (2002), DOI: 10.1109/TPAMI.2002.1023800. Crossref, Web of Science, Google Scholar
S. Cooray et al. N. O'Connor et al. , Semi-automatic video object segmentation using recursive shortest spanning tree and binary partition tree , Proc. Workshop on Image Analysis for Multimedia Interactive Services . Google Scholar
Corel Stock Photo Library (Corel Corp., Ontario, Canada) . Google Scholar
Y. Deng and B. S. Manjunath, An efficient low-dimensional color indexing scheme for region-based image retrieval, Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP) (1999) pp. 3017–3020. Google Scholar
R. O. Duda , P. E. Hart and D. G. Stork , Pattern Classification ( Wiley-Interscience , 2001 ) . Google Scholar
J. Fanet al., IEEE Trans. Imag. Process. 10, 1454 (2001). Web of Science, Google Scholar
K. S. Fu and J. K. Mui, Patt. Recogn. 13, 3 (1981), DOI: 10.1016/0031-3203(81)90028-5. Crossref, Web of Science, Google Scholar
K. Fukunaga , Introduction to Statistical Pattern Recognition , 2nd edn. ( Academic Press , 1990 ) . Google Scholar
H. Gao, W.-C. Siu and C.-H. Hou, IEEE Trans. Circuits Syst. Vid. Technol. 11, 1273 (2001). Crossref, Web of Science, Google Scholar
D. Geiger and A. Yuille, Int. J. Comput. Vis. 6, 227 (1991), DOI: 10.1007/BF00115697. Crossref, Web of Science, Google Scholar
N. Grammalidiset al., Sign. Process.: Imag. Commun. 7, 129 (1995), DOI: 10.1016/0923-5965(95)00002-E. Crossref, Web of Science, Google Scholar
R. M. Haralick and L. G. Sapiro, Comput. Vis. Graph. Imag. Process. 29, 100 (1985), DOI: 10.1016/S0734-189X(85)90153-7. Crossref, Google Scholar
R. Jain , R. Kasturi and B. G. Schunck , Machine Vision ( McGraw-Hill International Editions , 1995 ) . Google Scholar
M. Kass, A. Witkin and D. Terzopoulos, Int. J. Comput. Vis. 1, 312 (1988). Web of Science, Google Scholar
M. D. Kelly, Mach. Intell. VI, 397 (1971). Google Scholar
I. Kompatsiaris , E. Triantafillou and M. G. Strintzis , Region-based color image indexing and retrieval , Proc. IEEE Int. Conf. Image Processing . Google Scholar
I. Kompatsiaris and M. G. Strintzis , 3D representation of videoconference image sequences using VRML 2.0 , Eur. Conf. Multimedia Applications Services and Tech niques (ECMAST'98) ( 1998 ) . Google Scholar
I. Kompatsiaris and M. G. Strintzis , Content-based representation of colour image sequences , IEEE Int. Conf. Acoustics, Speech, and Signal Processing 2001 (ICASSP 2001) ( 2001 ) . Google Scholar
I. Kompatsiaris and M. G. Strintzis, IEEE Trans. Circuits Syst. Vid. Technol. 10, 1388 (2000), DOI: 10.1109/76.889030. Crossref, Web of Science, Google Scholar
I. Kompatsiaris and M. G. Strintzis , Visualisation of videoconference image sequences using VRML 2.0 , IX Eur. Sign. Process. Conf. . Google Scholar
S. Liapis, E. Sifakis and G. Tziritas, Color and/or texture segmentation using deter ministic relaxation and fast marching algorithms, Proc. Int. Conf. Pattern Recognition3 pp. 621–624. Google Scholar
M. Matheron , Random Sets and Integral Geometry ( Wiley , NY , 1975 ) . Google Scholar
J. McQueen, Some methods for classification and analyis of multivariate observations, Proc. 5th Berkely Symp. Mathematics Statistics and Probability1 (1967) pp. 281–296. Google Scholar
MIT Vision Texture (VisTex) Database, http://www-white.media.mit.edu/vismod/imagery/VisionTexture/vistex.html . Google Scholar
O. J. Morris, M. J. Lee and A. G. Constantinides, IEE Proc. 133, 146 (1986). Google Scholar
MPEG Requirements Group, MPEG-7 context and objectives, Doc. ISO/MPEC 2460, MPEG Atlantic City Meeting, October 1998 . Google Scholar
N. O'Connor et al. T. Adamek et al. , QIMERA: a software platform for video object segmentation and tracking , Proc. Workshop on Image Analysis For Multimedia Interactive Services . Google Scholar
P. Perona and J. Malik, IEEE Trans. Patt. Anal. Mach. Intell. 12, 629 (1990), DOI: 10.1109/34.56205. Crossref, Web of Science, Google Scholar
M. R. Rezaeeet al., IEEE Trans. Imag. Process. 9, 1238 (2000), DOI: 10.1109/83.847836. Crossref, Web of Science, Google Scholar
S. Sakaidaet al., Image segmentation by integration approach using initial dependence of k-means algorithm, Proc. Picture Coding Symp. 97 (1997) pp. 265–269. Google Scholar
P. Salembieret al., Proc. IEEE 83, 843 (1995), DOI: 10.1109/5.387088. Crossref, Web of Science, Google Scholar
D. Santa-Cruz and T. Ebrahimi, An analytical study of JPEG 2000 functionalities, Proc. IEEE Int. Conf. Imag. Process.2 (2000) pp. 49–52. Google Scholar
S. Z. Selim and M. A. Ismail, IEEE Trans. Patt. Anal. Mach. Intell. 6, 81 (1984). Web of Science, Google Scholar
J. Serra , Image Analysis and Mathematical Morphology ( Academic , London , 1982 ) . Google Scholar
T. Sikora, IEEE Trans. Circuits Syst. Vid. Technol. 7, 19 (1997), DOI: 10.1109/76.554415. Crossref, Web of Science, Google Scholar
IEEE Trans. Circuits Syst. Vid. Tech nol. 8, 19 (1998). Google Scholar
Signal Processing 66, (1998). Google Scholar
L. H. Staib and J. S. Duncan, IEEE Trans. Patt. Anal. Mach. Intell. 14, 161 (1992). Google Scholar
M. M. Trivedi and J. C. Bezdek, IEEE Trans. Syst. Man Cybern. SMC 16, 589 (1986), DOI: 10.1109/TSMC.1986.289264. Crossref, Web of Science, Google Scholar
E. Tuncel and L. Onural, IEEE Trans. Circuits Syst. Vid. Technol. 10, 776 (2000), DOI: 10.1109/76.856454. Crossref, Web of Science, Google Scholar
D. Tzovaras, N. Grammalidis and M. G. Strintzis, IEEE Trans. Circuits Syst. Vid. Technol. 7, 801 (1997). Web of Science, Google Scholar
M. Unser, IEEE Trans. Imag. Process. 4, 1549 (1995), DOI: 10.1109/83.469936. Crossref, Web of Science, Google Scholar
P. Villegas, X. Marichal and A. Salcedo, Objective evaluation of segmentation masks in video sequences, Proc. Workshop on Image Analysis For Multimedia Interactive Services pp. 85–88. Google Scholar
L. Vincent and P. Soille, IEEE Trans. Patt. Anal. Mach. Intell. 13, 583 (1991), DOI: 10.1109/34.87344. Crossref, Web of Science, Google Scholar
D. Wang, Patt. Recogn. 30, 2043 (1997), DOI: 10.1016/S0031-3203(97)00015-0. Crossref, Web of Science, Google Scholar