Quantitative Quality Assessment of Microscopic Image Mosaicing
The mosaicing technique has been employed in more and more application fields, from entertainment to scientific ones. In the latter case, often the final evaluation is still left to human beings, that assess visually the quality of the mosaic. Many times, a lack of objective measurements in microscopic mosaicing may prevent the mosaic from being used as a starting image for further analysis. In this work we analyze three different metrics and indexes, in the domain of signal analysis, image analysis and visual quality, to measure the quality of different aspects of the mosaicing procedure, such as registration errors and visual quality. As the case study we consider the mosaicing algorithm we developed. The experiments have been carried out by considering mosaics with very different features: histological samples, that are made of detailed and contrasted images, and live stem cells, that show a very low contrast and low detail levels.
[1] C. Sun, R. Beare, V. Hilsenstein, and P. Jackway, "Mosaicing of
microscope images with global geometric and radiometric corrections,"
Journal of Microscopy, vol. 224, no. 2, pp. 158-165, Nov. 2006.
[2] D. Gareau, Y. Patel, Y. Li, I. Aranda, A. Halpern, K. Nehal, and
M. Rajadhyaksha, "Confocal mosaicing microscopy in skin excisions: a
demonstration of rapid surgical pathology," Journal of Microscopy, vol.
233, no. 1, pp. 149-159, Jan. 2009.
[3] E. Zagrouba, W. Barhoumi, and S. Amri, "An efficient image-mosaicing
method based on multifeature matching," Machine Vision and Applications,
vol. 20, pp. 139-162, 2009.
[4] D. Steckhan, T. Bergen, T. Wittenberg, and S. Rupp, "Efficient large
scale image stitching for virtual microscopy," in 30th Annual International
IEEE EMBS Conference Vancouver, British Columbia, Canada,
August 20-24, Aug. 2008, pp. 4019-4023.
[5] A. Bevilacqua, A. Gherardi, and M. Ferri, "Predicting biological age
from a skin surface capacitive analysis," Int. J. Mod. Phys. C, vol. 15,
no. 9, pp. 1309-1320, 2004.
[6] B. D. Lucas and T. Kanade, "An iterative image registration technique
with an application to stereo vision," in International Joint Conference
on Artificial Intelligence, 1981, pp. 674-679.
[7] J. Y. Bouguet, "Pyramidal implementation of the Lukas Kanade feature
tracker: Description of the algorithm," In Intel Research Laboratory,
Technical Report, pp. 1-9, 1999.
[8] H. Foroosh, J. B. Zerubia, and M. Berthod, "Extension of phase correlation
to subpixel registration," IEEE Transactions on Image Processing,
vol. 14, no. 1, pp. 12-22, 2002.
[9] M. A. Fischler and R. C. Bolles, "Random sample and consensus:
A paradigm for model fitting with application to image analysis and
automated cartography," Comm. of the ACM, vol. 24, no. 6, pp. 381-
395, 1981.
[10] A. Bevilacqua, A. Gherardi, L. Carozza, and F. Piccinini, "Semiautomatic
background detection in microscopic images," in International
Conference on Biological Science and Engineering (ICBSE), Venice,
Italy, November 24-26, 2010.
[11] P. Azzari and A. Bevilacqua, "Joint spatial and tonal mosaic alignment
for motion detection with ptz camera," Lecture Notes in Computer
Science, vol. 4142, pp. 764-775, 2006.
[12] Z. Wang and A. C. Bovik, "A universal image quality index," IEEE
Signal Processing Letters, vol. 9, no. 3, pp. 81-84, Mar. 2002.
[1] C. Sun, R. Beare, V. Hilsenstein, and P. Jackway, "Mosaicing of
microscope images with global geometric and radiometric corrections,"
Journal of Microscopy, vol. 224, no. 2, pp. 158-165, Nov. 2006.
[2] D. Gareau, Y. Patel, Y. Li, I. Aranda, A. Halpern, K. Nehal, and
M. Rajadhyaksha, "Confocal mosaicing microscopy in skin excisions: a
demonstration of rapid surgical pathology," Journal of Microscopy, vol.
233, no. 1, pp. 149-159, Jan. 2009.
[3] E. Zagrouba, W. Barhoumi, and S. Amri, "An efficient image-mosaicing
method based on multifeature matching," Machine Vision and Applications,
vol. 20, pp. 139-162, 2009.
[4] D. Steckhan, T. Bergen, T. Wittenberg, and S. Rupp, "Efficient large
scale image stitching for virtual microscopy," in 30th Annual International
IEEE EMBS Conference Vancouver, British Columbia, Canada,
August 20-24, Aug. 2008, pp. 4019-4023.
[5] A. Bevilacqua, A. Gherardi, and M. Ferri, "Predicting biological age
from a skin surface capacitive analysis," Int. J. Mod. Phys. C, vol. 15,
no. 9, pp. 1309-1320, 2004.
[6] B. D. Lucas and T. Kanade, "An iterative image registration technique
with an application to stereo vision," in International Joint Conference
on Artificial Intelligence, 1981, pp. 674-679.
[7] J. Y. Bouguet, "Pyramidal implementation of the Lukas Kanade feature
tracker: Description of the algorithm," In Intel Research Laboratory,
Technical Report, pp. 1-9, 1999.
[8] H. Foroosh, J. B. Zerubia, and M. Berthod, "Extension of phase correlation
to subpixel registration," IEEE Transactions on Image Processing,
vol. 14, no. 1, pp. 12-22, 2002.
[9] M. A. Fischler and R. C. Bolles, "Random sample and consensus:
A paradigm for model fitting with application to image analysis and
automated cartography," Comm. of the ACM, vol. 24, no. 6, pp. 381-
395, 1981.
[10] A. Bevilacqua, A. Gherardi, L. Carozza, and F. Piccinini, "Semiautomatic
background detection in microscopic images," in International
Conference on Biological Science and Engineering (ICBSE), Venice,
Italy, November 24-26, 2010.
[11] P. Azzari and A. Bevilacqua, "Joint spatial and tonal mosaic alignment
for motion detection with ptz camera," Lecture Notes in Computer
Science, vol. 4142, pp. 764-775, 2006.
[12] Z. Wang and A. C. Bovik, "A universal image quality index," IEEE
Signal Processing Letters, vol. 9, no. 3, pp. 81-84, Mar. 2002.
@article{"International Journal of Electrical, Electronic and Communication Sciences:49499", author = "Alessandro Bevilacqua and Alessandro Gherardi and Filippo Piccinini", title = "Quantitative Quality Assessment of Microscopic Image Mosaicing", abstract = "The mosaicing technique has been employed in more and more application fields, from entertainment to scientific ones. In the latter case, often the final evaluation is still left to human beings, that assess visually the quality of the mosaic. Many times, a lack of objective measurements in microscopic mosaicing may prevent the mosaic from being used as a starting image for further analysis. In this work we analyze three different metrics and indexes, in the domain of signal analysis, image analysis and visual quality, to measure the quality of different aspects of the mosaicing procedure, such as registration errors and visual quality. As the case study we consider the mosaicing algorithm we developed. The experiments have been carried out by considering mosaics with very different features: histological samples, that are made of detailed and contrasted images, and live stem cells, that show a very low contrast and low detail levels.
", keywords = "Mosaicing, quality assessment, microscopy, stem cells.", volume = "4", number = "11", pages = "1582-4", }
