Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

RootsGLOH2: embedding RootSIFT ‘square rooting’ in sGLOH2

RootsGLOH2: embedding RootSIFT ‘square rooting’ in sGLOH2

For access to this article, please select a purchase option:

Buy article PDF
$19.95
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

This study introduces an extension of the sGLOH2 local image descriptor inspired by RootSIFT ‘square rooting’ as a way to indirectly alter the matching distance used to compare the descriptor vectors. The extended descriptor, named RootsGLOH2, achieved the best results in terms of matching accuracy and robustness among the latest state-of-the-art non-deep descriptors in recent evaluation contests dealing with both planar and non-planar scenes. RootsGLOH2 also achieves a matching accuracy very close to that obtained by the best deep descriptors to date. Beside confirming that ‘square rooting’ has beneficial effects on sGLOH2 as it happens on SIFT, experimental evidence shows that classical norm-based distances, such as the Euclidean and Manhattan distances, only provide suboptimal solutions to the problem of local image descriptor matching. This suggests matching distance design as a topic to investigate further in the near future.

References

    1. 1)
      • 26. Pultar, M., Mishkin, D., Matas, J.: ‘Leveraging outdoor webcams for local descriptor learning’, 24th Computer Vision Winter Workshop (CVWW2019), Stift Vorau, Austria, 2019, pp. 5160.
    2. 2)
      • 29. Mukundan, A., Tolias, G., Bursuc, A., et al: ‘Understanding and improving kernel local descriptors’, Int. J. Comput. Vis., 2019, 127, pp. 17231737, https://link.springer.com/article/10.1007/s11263-018-1137-8.
    3. 3)
      • 33. Mikolajczyk, K., Schmid, C.: ‘A performance evaluation of local descriptors’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (10), pp. 16151630.
    4. 4)
      • 31. Morel, J.M., Yu, G.: ‘ASIFT: a new framework for fully affine invariant image comparison’, SIAM J. Imaging Sci., 2009, 2, (2), pp. 438469.
    5. 5)
      • 61. Alcantarilla, P.F., Nuevo, J., Bartoli, A.: ‘Fast explicit diffusion for accelerated features in nonlinear scale space’. Proc. British Machine Vision Conf. (BMVC), Bristol, UK, 2013.
    6. 6)
      • 36. Lazebnik, S., Schmid, C., Ponce, J.: ‘A sparse texture representation using local affine regions’, IEEE Trans. Pattern. Anal. Mach. Intell, 2005, 27, (8), pp. 12651278.
    7. 7)
      • 22. Tian, Y., Fan, B., Wu, F.: ‘L2-net: deep learning of discriminative patch descriptor in Euclidean space’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA, 2017, pp. 61286136.
    8. 8)
      • 12. Fan, B., Wu, F., Hu, Z.: ‘Rotationally invariant descriptors using intensity order pooling’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (10), pp. 20312045.
    9. 9)
      • 54. ‘On the art of establishing correspondence’, 2019. Available from https://image-matching-workshop.github.io/slides/slides-matas.pdf.
    10. 10)
      • 41. Simo.Serra, E., Trulls, E., Ferraz, L., et al: ‘Discriminative learning of deep convolutional feature point descriptors’. Proc. IEEE Int. Conf. on Computer Vision (ICCV), Santiago, Chile, 2015.
    11. 11)
      • 52. Schönberger, J.L., Hardmeier, H., Sattler, T., et al: ‘Comparative evaluation of hand-crafted and learned local features’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA, 2017.
    12. 12)
      • 42. He, K., Lu, Y., Sclaroff, S.: ‘Local descriptors optimized for average precision’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, 2018.
    13. 13)
      • 48. Balntas, V., Lenc, K., Vedaldi, A., et al: ‘HPatches: a benchmark and evaluation of handcrafted and learned local descriptors’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA, 2017, pp. 38523861.
    14. 14)
      • 47. Bellavia, F., Tegolo, D., Valenti, C.: ‘Keypoint descriptor matching with context-based orientation estimation’, Image Vis. Comput., 2014, 32, (9), pp. 559567.
    15. 15)
      • 53. Schönberger, J.L., Frahm, J.M.: ‘Structure-from-motion revisited’. Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, USA, 2016.
    16. 16)
      • 21. Rublee, E., Rabaud, V., Konolige, K., et al: ‘ORB: an efficient alternative to SIFT or SURF’. Proc. IEEE Int. Conf. on Computer Vision (ICCV), Barcelona, Spain, 2011, pp. 25642571.
    17. 17)
      • 59. Ebel, P., Mishchuk, A., Yi, K.M., et al: ‘Beyond Cartesian representations for local descriptors’. IEEE Int. Conf. on Computer Vision (ICCV), Venice, Italy, 2019.
    18. 18)
      • 38. Yang, T., Lin, Y., Chuang, Y.: ‘Accumulated stability voting: a robust descriptor from descriptors of multiple scales’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, USA, 2016, pp. 327335.
    19. 19)
      • 9. Mukundan, A., Tolias, G., Chum, O.: ‘Multiple-kernel local-patch descriptor’. British Machine Vision Conf. (BMVC), London, UK, 2017.
    20. 20)
      • 57. Bian, J., Lin, W.Y., Matsushita, Y., et al: ‘GMS: grid-based motion statistics for fast, ultra-robust feature correspondence’. 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA, 2017, pp. 28282837.
    21. 21)
      • 30. Noh, H., Araujo, A., Sim, J., et al: ‘Large-scale image retrieval with attentive deep local features’. IEEE Int. Conf. on Computer Vision (ICCV), Venice, Italy, 2017.
    22. 22)
      • 27. Bellavia, F., Colombo, C.: ‘‘Which is which?’ evaluation of local descriptors for image matching in real-world scenarios’. Int. Conf. on Computer Analysis of Images and Patterns (CAIP), Salerno, Italy, 2019. Available from http://cvg.dsi.unifi.it/wisw.caip2019.
    23. 23)
      • 24. Tian, Y., Yu, X., Fan, B., et al: ‘SOSNet: second order similarity regularization for local descriptor learning’. 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, California, USA, 2019.
    24. 24)
      • 2. Snavely, N., Seitz, S.M., Szeliski, R.: ‘Modeling the world from internet photo collections’, Int. J. Comput. Vis., 2008, 80, (2), pp. 189210.
    25. 25)
      • 45. Luo, Z., Shen, T., Zhou, L., et al: ‘Geodesc: learning local descriptors by integrating geometry constraints’. Proc. European Conf. on Computer Vision (ECCV), Munich, Germany, 2018.
    26. 26)
      • 32. Bursuc, A., Tolias, G., Jégou, H.: ‘Kernel local descriptors with implicit rotation matching’. ACM Int. Conf. on Multimedia Retrieval (ICMR), Shangai, China, 2015.
    27. 27)
      • 14. Ke, Y., Sukthankar, R.: ‘PCA-SIFT: a more distinctive representation for local image descriptors’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA, vol. 2, 2004, pp. 506513.
    28. 28)
      • 16. Dong, J., Soatto, S.: ‘Domain-size pooling in local descriptors: DSP-SIFT’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA, 2015.
    29. 29)
      • 46. ‘Image Matching Workshop (IMW) challenge at (CVPR2019)’, 2019, Available from https://image-matching-workshop.github.io.
    30. 30)
      • 25. Li, Z., Snavely, N.: ‘Megadepth: learning single-view depth prediction from internet photos’. Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, 2018.
    31. 31)
      • 49. Yi, K.M., Verdie, Y., Fua, P., et al: ‘Learning to assign orientations to feature points’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 18.
    32. 32)
      • 13. Bellavia, F., Colombo, C.: ‘Rethinking the sGLOH descriptor’, IEEE Trans. Pattern Anal. Mach. Intell., 2018, 40, (4), pp. 931944.
    33. 33)
      • 58. Ma, J., Zhao, J., Jiang, J., et al: ‘Locality preserving matching’, Int. J. Comput. Vis., 2019, 127, (5), pp. 512531.
    34. 34)
      • 60. Balntas, V., Riba, E., Ponsa, D., et al: ‘Learning local feature descriptors with triplets and shallow convolutional neural networks’. Proc. British Machine Vision Conf. (BMVC), 2016, pp. 119.1119.11.
    35. 35)
      • 44. Ono, Y., Trulls, E., Fua, P., et al: ‘LF-Net: learning local features from images’. NIPS'18: Proc. 32nd Int. Conf. on Neural Information Processing Systems, Montreal, Canada, 2018.
    36. 36)
      • 34. Cui, Y., Hasler, N., Thormählen, T., et al: ‘Scale invariant feature transform with irregular orientation histogram binning’. Proc. Int. Conf. on Image Analysis and Recognition (ICIAR), Halifax, Canada, 2009, pp. 258267.
    37. 37)
      • 50. Bellavia, F., Valenti, C., Lupascu, C.A., et al: ‘Approximated overlap error for the evaluation of feature descriptors on 3D scenes’. Proc. Int. Conf. on Image Analysis and Processing (ICIAP), Naples, Italy, 2013, pp. 270279.
    38. 38)
      • 55. Bellavia, F., Tegolo, D., Valenti, C.: ‘Improving Harris corner selection strategy’, IET Comput. Vis., 2011, 5, (2), pp. 8696.
    39. 39)
      • 39. Treen, G., Whitehead, A.: ‘Efficient SIFT matching from keypoint descriptor properties’. Proc. Workshop on Applications of Computer Vision (WACV), Snowbird, Utah, USA, 2009, pp. 17.
    40. 40)
      • 37. Baber, J., Dailey, M.N., Satoh, S., et al: ‘BIG-OH: binarization of gradient orientation histograms’, Image Vis. Comput., 2014, 32, (11), pp. 940953.
    41. 41)
      • 35. Hassner, T., Mayzels, V., Zelnik.Manor, L.: ‘On SIFTs and their scales’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, USA, 2012, pp. 15221528.
    42. 42)
      • 20. Balntas, V., Tang, L., Mikolajczyk, K.: ‘BOLD – binary online learned descriptor for efficient image matching’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA, 2015, pp. 23672375.
    43. 43)
      • 10. Leutenegger, S., Chli, M., Siegwart, R.: ‘BRISK: binary robust invariant scalable keypoints’. Proc. IEEE Int. Conf. on Computer Vision (ICCV), Barcelona, Spain, 2011.
    44. 44)
      • 11. Alahi, A., Ortiz, R., Vandergheynst, P.: ‘Freak: fast retina keypoint’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, USA, 2012, pp. 510517.
    45. 45)
      • 40. Tsai, C.Y., Tsao, A.H., Wang, C.W.: ‘Real-time feature descriptor matching via a multi-resolution exhaustive search method’, J. Softw., 2013, 8, (9), pp. 21972201.
    46. 46)
      • 51. Fan, B., Kong, Q., Wang, X., et al: ‘A performance evaluation of local features for image based 3d reconstruction’. IEEE Transactions on Image Processing, 2019, 28, (10), pp. 47744789.
    47. 47)
      • 17. Trzcinski, T., Christoudias, M., Lepetit, V., et al: ‘Learning image descriptors with the boosting-trick’. Advances in Neural Information Processing Systems, Lake Tahoe, Nevada, USA, 2012, pp. 269277.
    48. 48)
      • 3. Fanfani, M., Bellavia, F., Colombo, C.: ‘Accurate keyframe selection and keypoint tracking for robust visual odometry’, Mach. Vis. Appl., 2016, 27, (6), pp. 833844.
    49. 49)
      • 63. Rodriguez, M., Facciolo, G., von Gioi, R.G., et al: ‘SIFT-AID: boosting SIFT with and affine invariant descriptor based on convolutional neural networks’. Proc. Int. Conf. of Image Processing (ICIP), Taipei, Taiwan, 2019.
    50. 50)
      • 7. Wang, Z., Fan, B., Wang, G., et al: ‘Exploring local and overall ordinal information for robust feature description’, IEEE Trans. Pattern Anal. Mach. Intell., 2016, 38, (11), pp. 21982211.
    51. 51)
      • 56. Mishkin, D., Radenovic, F., Matas, J.: ‘Repeatability is not enough: learning affine regions via discriminability’. Proc. European Conf. on Computer Vision (ECCV), Munich, Germany, 2018.
    52. 52)
      • 1. Brown, M., Lowe, D.G.: ‘Automatic panoramic image stitching using invariant features’, Int. J. Comput. Vis., 2007, 74, (1), pp. 5973.
    53. 53)
      • 8. Bay, H., Ess, A., Tuytelaars, T., et al: ‘Speeded-up robust features (SURF)’, Comput. Vis. Image Underst., 2008, 110, (3), pp. 346359.
    54. 54)
      • 28. Luo, Z., Shen, T., Zhou, L., et al: ‘Contextdesc: local descriptor augmentation with cross-modality context’, Computer Vision and Pattern Recognition (CVPR), 2019.
    55. 55)
      • 43. Dusmanu, M., Rocco, I., Pajdla, T., et al: ‘D2-Net: a trainable CNN for joint detection and description of local features’. Proc. 2019 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, California, USA, 2019.
    56. 56)
      • 18. Strecha, C., Bronstein, A.M., Bronstein, M.M., et al: ‘LDAHash: improved matching with smaller descriptors’, IEEE Trans Pattern Anal Mach Intell, 2012, 34, (1), pp. 6678.
    57. 57)
      • 19. Brown, M.A., Hua, G., Winder, S.A.J.: ‘Discriminative learning of local image descriptors’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (1), pp. 4357.
    58. 58)
      • 6. Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’, Int. J. Comput. Vis., 2004, 60, (2), pp. 91110.
    59. 59)
      • 23. Mishchuk, A., Mishkin, D., Radenovic, F., et al: ‘Working hard to know your neighbor's margins: local descriptor learning loss’. Advances in Neural Information Processing Systems 30: Annual Conf. on Neural Information Processing Systems (NIPS), 2017, pp. 48294840.
    60. 60)
      • 5. Bertini, M., Colombo, C., Bimbo, A.D.: ‘Automatic caption localization in videos using salient points’. IEEE Int. Conf. on Multimedia and Expo (ICME 2001), Tokyo, Japan, 2001, pp. 6871.
    61. 61)
      • 62. DeTone, D., Malisiewicz, T., Rabinovich, A.: ‘Superpoint: self-supervised interest point detection and description’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) Workshops, Salt Lake City, Utah, USA, 2018.
    62. 62)
      • 4. Fan, B., Kong, Q., Trzcinski, T., et al: ‘Receptive fields selection for binary feature description’, IEEE Trans. Image Process., 2014, 26, (6), pp. 25832595.
    63. 63)
      • 15. Arandjelovíc, R., Zisserman, A.: ‘Three things everyone should know to improve object retrieval’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, USA, 2012, pp. 29112918.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2019.0716
Loading

Related content

content/journals/10.1049/iet-cvi.2019.0716
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address