EL: local image descriptor based on extreme responses to partial derivatives of 2D Gaussian function. (English) Zbl 1435.94137
Summary: We propose a two-part local image descriptor EL (Edges and Lines), based on the strongest image responses to the first- and second-order partial derivatives of the two-dimensional Gaussian function. Using the steering theorems, the proposed method finds the filter orientations giving the strongest image responses. The orientations are quantized, and the magnitudes of the image responses are histogrammed. Iterative adaptive thresholding of histogram values is then applied to normalize the histogram, thereby making the descriptor robust to nonlinear illumination changes. The two-part descriptor is empirically evaluated on the HPatches benchmark for three different tasks, namely, patch verification, image matching, and patch retrieval. The proposed EL descriptor outperforms the traditional descriptors such as SIFT and RootSIFT on all three evaluation tasks and the deep-learning-based descriptors DeepCompare, DeepDesc, and TFeat on the tasks of image matching and patch retrieval.
MSC:
| 94A60 | Cryptography |
References:
| [1] | Bianco, S.; Mazzini, D.; Pau, D. P.; Schettini, R., Local detectors and compact descriptors for visual search: a quantitative comparison, Digital Signal Processing, 44, 1-13 (2015) · doi:10.1016/j.dsp.2015.06.001 |
| [2] | Brawn, M.; Lowe, D. G., Automatic panoramic image stitching using invariant features, International Journal of Computer Vision, 74, 1, 59-73 (2007) |
| [3] | Ghosh, D.; Kaabouch, N., A survey on image mosaicing techniques, Journal of Visual Communication and Image Representation, 34, 1-11 (2016) · doi:10.1016/j.jvcir.2015.10.014 |
| [4] | Yu, X.; Zhang, Y.; Wang, H., A novel local human visual perceptual texture description with key feature selection for texture classification, Mathematical Problems in Engineering, 2019, 20 (2019) · Zbl 1435.94009 |
| [5] | Zhou, W.; Lu, Y.; Li, H.; Song, Y.; Tian, Q., Spatial coding for large scale partial duplicate web image search, Proceedings of the 18th ACM International Conference on Multimedia |
| [6] | Dou, Y.; Hao, K.; Ding, Y.; Mao, M., A mean-shift-based feature descriptor for wide baseline stereo matching, Mathematical Problems in Engineering, 2015, 14 (2015) |
| [7] | Mele, K.; Šuc, D.; Maver, J., Local probabilistic descriptors for image categorisation, IET Computer Vision, 3, 1, 8-23 (2009) · doi:10.1049/iet-cvi:20070001 |
| [8] | Xie, L.; Wang, J.; Lin, W.; Zhang, B.; Tian, Q., Towards reversal-invariant image representation, International Journal of Computer Vision, 123, 2, 226-250 (2017) · doi:10.1007/s11263-016-0970-x |
| [9] | Lowe, D. G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60, 2, 91-110 (2004) · doi:10.1023/b:visi.0000029664.99615.94 |
| [10] | Mikolajczyk, K.; Schmid, C., A performance evaluation of local descriptors, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 10, 1615-1630 (2005) · doi:10.1109/tpami.2005.188 |
| [11] | Bay, H.; Ess, A.; Tuytelaars, T.; van Gool, L., Speeded-up robust features (SURF), Computer Vision and Image Understanding, 110, 3, 346-359 (2008) · doi:10.1016/j.cviu.2007.09.014 |
| [12] | Calonder, M.; Lepetit, V.; Ozuysal, M.; Trzcinski, T.; Strecha, C.; Fua, P., BRIEF: computing a local binary descriptor very fast, IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 7, 1281-1298 (2012) · doi:10.1109/tpami.2011.222 |
| [13] | Alcantarilla, P.; Bartoli, A. F.; Davison, A. J., KAZE features, Proceedings of the 12th ECCV |
| [14] | Mandeljc, R.; Maver, J., AGs: local descriptors derived from the dependent effects model, Journal of Visual Communication and Image Representation, 58, 503-514 (2019) · doi:10.1016/j.jvcir.2018.12.008 |
| [15] | Xie, L.; Tian, Q.; Zhang, B., Max-sift: flipping invariant descriptors for web logo search, Proceedings of the 18th ACM International Conference on Multimedia |
| [16] | Yang, L.; Lu, Z., A new scheme for keypoint detection and description, Mathematical Problems in Engineering, 2015, 10 (2015) · Zbl 1395.94317 |
| [17] | Winder, S.; Brown, M., Learning local image descriptors, Proceedings of the IEEE Conference CVPR |
| [18] | Zagoruyko, S.; Komodakis, N., Learning to compare image patches via convolutional neural networks, Proceedings of the IEEE Conference CVPR |
| [19] | Simo-Serra, E.; Trulls, E.; Ferraz, L.; Kokkinos, I.; Fua, P.; Moreno-Noguer, F., Discriminative learning of deep convolutional feature point descriptors, Proceedings of the IEEE ICCV |
| [20] | Balntas, V.; Riba, E.; Ponsa, D.; Mikolajczyk, K., Learning local feature descriptors with triplets and shallow convolutional neural networks, Proceedings of the British Machine Vision Conference |
| [21] | Aanæs, H.; Dahl, A. L.; Pedersen, K. S., Interesting interest points, International Journal of Computer Vision, 97, 18-35 (2012) |
| [22] | Heinly, J.; Dunn, E.; Frahm, J.-M.; Fitzgibbon, A.; Lazebnik, S.; Perona, P.; Sato, Y.; Schmid, C., Comparative evaluation of binary features, Computer Vision -ECCV 2012 (2012), Springer, Florence, Italy: vol. 7573 of Lecture Notes in Computer Science, Springer, Florence, Italy · doi:10.1007/978-3-642-33709-3_54 |
| [23] | Madeo, S.; Bober, M., Fast, compact, and discriminative: evaluation of binary descriptors for mobile applications, IEEE Transactions on Multimedia, 19, 2, 221-235 (2017) · doi:10.1109/tmm.2016.2615521 |
| [24] | Moreels, P.; Perona, P., Evaluation of features detectors and descriptors based on 3D objects, International Journal of Computer Vision, 73, 3, 263-284 (2007) · doi:10.1007/s11263-006-9967-1 |
| [25] | Schoenberger, J. L.; Hardmeier, H.; Sattler, T.; Pollefeys, M., Comparative evaluation of hand-crafted and learned local features, Proceedings of the Conference Computer Vision and Pattern Recognition |
| [26] | Balntas, V.; Lenc, K.; Vedaldi, A.; Mikolajczyk, K., HPatches: A benchmark and evaluation of handcrafted and learned local descriptors, Proceedings of the IEEE Conference CVPR |
| [27] | Arandjelović, R.; Zisserman, A., Three things everyone should know to improve object retrieval, Proceedings of the IEEE Conference CVPR |
| [28] | Koenderink, J.; van Doorn, A., Representation of local geometry in the visual system, Biological Cybernetics, 55, 376-375 (1987) · Zbl 0617.92024 · doi:10.1007/bf00318371 |
| [29] | Florack, L. M. J.; Ter Haar Romeny, B. M.; Koenderink, J. J.; Viergever, M. A., General intensity transformations and differential invariants, Journal of Mathematical Imaging and Vision, 4, 2, 171-187 (1994) · Zbl 1433.68514 · doi:10.1007/bf01249895 |
| [30] | Freeman, W. T.; Adelson, E. H., The design and use of steerable filters, IEEE Transactions on Pattern Analysis and Machine Intelligence, 13, 9, 891-906 (1991) · doi:10.1109/34.93808 |
| [31] | Griffin, L. D.; Lillholm, M., Symmetry sensitivities of derivative-of-Gaussian filters, IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 6, 1072-1083 (2010) · doi:10.1109/tpami.2009.91 |
| [32] | Jaccard, N.; Szita, N.; Griffin, L. D., Segmentation of phase contrast microscopy images based on multi-scale local basic image features histograms, Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 5, 5, 359-367 (2017) · doi:10.1080/21681163.2015.1016243 |
| [33] | Lillholm, M.; Griffin, L., Novel image feature alphabets for object recognition, Proceedings of the 19th IEEE Conference ICPR |
| [34] | Winder, S.; Hua, G.; Brown, M., Picking the best daisy, Proceedings of the IEEE Conference CVPR |
| [35] | Dong, J.; Soatto, S., Domain-size pooling in local descriptors: Dsp-sift, Proceedings of the IEEE Conference CVPR |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
