An New Modified Automatic Panoramic Image Stitching Model in Fabric Defect Inspecting Area

Abstract:

This paper presents some techniques for constructing panoramic image stitching from sequences of images captured by cameras from different angle in garment defects detecting area. The image stitching representation associates a transformation matrix with each input image. In this paper, we formulate stitching as a multi-image matching problem, and use invariant local features to find matches between all of the images. Our method is insensitive to the ordering, orientation, scale and illumination of the input images. It is also insensitive to noise images that are not part of a panorama, and can recognise multiple panoramas in an unordered image dataset. An improved SIFT(Scale Invariant Feature Transform) algorithm was used to locate the feature points in the scanned images targeting at the problem of automatically stitching of textile images which were scanned in divided pieces. RANSAC (random sample consensus) method is proposed to to estimate image transformation parameters and to find a solution that has the best consensus with the data. Techniques for estimating and rening camera focal lengths are also presented. In order to reduce accumulated registration errors, we apply global alignment (block adjustment) to the whole sequence of images, which results in an optimally registered image stitching. A local alignment technique is also developed which warps each image based on the results of pairwise local image registrations to compensate for small amounts of motion parallax introduced by translations of the camera and other unmodeled distortions.

• Periodical: Applied Mechanics and Materials (Volume 389)
• Pages: 781-788
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.389.781
• Online since: August 2013
• Authors: Y.H. Zhang, C.W.M. Yuen, W.K. Wong, Chi Wai Kan
• Keywords: Block Adjustment, Global Alignment, Invariant Features, Local Alignment, Panoramic Image Stitching, Random Sample Consensus (RANSAC), Scale Invariant Feature Transform (SIFT)

References

[1] R. Szliski, : Image Aliment and Stitching : A Tutorial, Technical Report MSR-TR-2004-92, Microsoft Research. (2004).

[2] Szeliski, R. and Kang, S. : Direct methods for visual scene reconstruction. In IEEE Workshop on Representations of Visual Scenes. Cambridge, MA, (1995)p.26–33.

DOI: 10.1109/wvrs.1995.476849

[3] Irani, M. and Anandan, P.: About direct methods. In Triggs, B., Zisserman, A., and Szeliski, R. (eds. ), Vision Algorithms: Theory and Practice, number 1883 in LNCS. Springer-Verlag, Corfu, Greece, (1999)p.267–277.

DOI: 10.1007/3-540-44480-7_18

[4] Sawhney, H. and Kumar, R. : True multi-image alignment and its application to mosaicing and lens distortion correction. IEEE Transactios on Pattern Analysis and Machine Intelligence, 21(1999)P. 235–243.

DOI: 10.1109/34.754589

[5] Shum, H. and Szeliski, R. 2000. Construction of panoramic mosaics with global and local alignment. International Journal of Computer Vision, 36. (2000) p.101–130.

DOI: 10.1109/iccv.1998.710831

[6] Zoghlami, I., Faugeras, O., and Deriche, R. : Using geometric corners to build a 2D mosaic from a set of images. In Proceedings of the International Conference on Computer Vision and Pattern Recognition, Puerto Rico. IEEE. (1997).

DOI: 10.1109/cvpr.1997.609359

[7] Capel, D. and Zisserman, A.: Automated mosaicing with superresolution zoom. In Proceedings of the Interational Conference on Computer Vision and Pattern Recognition (CVPR98), (1998)p.885–891.

DOI: 10.1109/cvpr.1998.698709

[8] McLauchlan, P. and Jaenicke, A. : Image mosaicing using sequential bundle adjustment. Image and Vision Computing . (2002) p.751–759.

DOI: 10.1016/s0262-8856(02)00064-1

[9] Harris, C.: Geometry from visual motion. In Blake, A. and Yuille, A., (eds. ), Active Vision. MIT Press. (1992) p.263–284.

[10] Shi, J. and Tomasi, C. : Good features to track. In Proceedings of the Interational Conference on Computer Vision and Pattern Recognition (1994).

[11] P.J. Burt and E.H. Adelson, : A Multiresolution Spline with Applications to Image Mosaics, ACM Trans. Graphics, vol. 2, no. 4. (1983) pp.217-236.

DOI: 10.1145/245.247

[12] A. Levin, A. Zomet, S. Peleg, and Y. Weiss, Seamless Image Stitching in the Gradient Domain, Proc. European Conf. Computer Vision. (2004).

DOI: 10.1007/978-3-540-24673-2_31

[13] M. Uyttendaele, A. Eden, and R. Szeliski: Eliminating Ghosting and Exposure Artifacts in Image Mosaics, Proc. IEEE Conf. Computer Vision and Pattern Recognition. (2001).

DOI: 10.1109/cvpr.2001.991005

[14] H. Fang and J.C. Hart, : Textureshop: Texture Synthesis as a Photograph Editing Tool, " Proc. ACM SIGGRAPH , 04. ( 2004).

DOI: 10.1145/1186562.1015728

[15] J. Jia and C. -K. Tang : Image Registration with Global and Local Luminance Alignment, " Proc. Int, l Conf. Computer Vision, vol. I, (2003) pp.156-163.

[16] Brown, M. and Lowe, D.: Recognising panoramas. In Proceedings of the 9th International Conference on Computer Vision (ICCV03). Nice, vol. 2, (2003) p.1218–1225.

[17] Lowe, D. : Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2)(2004).P. 91–110.

DOI: 10.1023/b:visi.0000029664.99615.94

[18] Brown, M., Szeliski, R., and Winder, S.: Multi-image matching using multi-scale oriented patches. In Proceedings of the Interational Conference on Computer Vision and Pattern Recognition (CVPR05). San Diego. (2005).

DOI: 10.1109/cvpr.2005.235

[19] Hartley, R. and Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, ISBN: 0521540518. (2004).

[20] Fischler, M. and Bolles, R. : Random sample consensus: A paradigm for model fitting with application to image analysis and automated cartography. Communications of the ACM, 24(1981). P. 381–395.

DOI: 10.1145/358669.358692

[21] S. B. Kang and R Weiss.: Characterization of errors in compositing panoramic images. Technical Report 96/2, Digital Equipment Corporation, Cambridge Research Lab. (1996).