Skip to main content

2017 | OriginalPaper | Buchkapitel

A Multi-modal SPM Model for Image Classification

verfasst von : Peng Zheng, Zhong-Qiu Zhao, Jun Gao

Erschienen in: Intelligent Computing Methodologies

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

The BoF (bag-of-features) model is one of the most famous models applied to many fields in computer vision and has achieved impressive results. However, the SIFT/HOG visual words have a limit discriminative power which is partly due to the fact that it only describes the local gradient distribution. In the meanwhile, there is still redundancy and hidden information existed in the formed histogram. Considering these respects, we propose a multi-modal SPM model which fuses global features to complement traditional local ones and conducts dimensionality reduction in local spaces for mining possible feature dependencies. Experimental results show the efficiency of the proposed method in comparison with the existing counterparts.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Bosch, A., Zisserman, A., Muoz, X.: Scene classification using a hybrid generative/discriminative approach. IEEE Trans. Pattern Anal. Mach. Intell. 30(4), 712–727 (2008)CrossRef Bosch, A., Zisserman, A., Muoz, X.: Scene classification using a hybrid generative/discriminative approach. IEEE Trans. Pattern Anal. Mach. Intell. 30(4), 712–727 (2008)CrossRef
2.
Zurück zum Zitat Cao, L., Ji, R., Gao, Y., Yang, Y., Tian, Q.: Weakly supervised sparse coding with geometric consistency pooling. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012, pp. 3578–3585. IEEE (2012) Cao, L., Ji, R., Gao, Y., Yang, Y., Tian, Q.: Weakly supervised sparse coding with geometric consistency pooling. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012, pp. 3578–3585. IEEE (2012)
3.
Zurück zum Zitat Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: automaticquery expansion with a generative feature model for object retrieval. In: ICCV, pp. 1–8 (2007) Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: automaticquery expansion with a generative feature model for object retrieval. In: ICCV, pp. 1–8 (2007)
4.
Zurück zum Zitat Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Computer Vision and Pattern Recognition. vol. 1, pp. 886–893. IEEE (2005) Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Computer Vision and Pattern Recognition. vol. 1, pp. 886–893. IEEE (2005)
5.
Zurück zum Zitat Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. Image Proc. 15(12), 3736–3745 (2006)MathSciNetCrossRef Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. Image Proc. 15(12), 3736–3745 (2006)MathSciNetCrossRef
6.
Zurück zum Zitat Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: CVPR, vol. 2, pp. 524–531. IEEE (2005) Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: CVPR, vol. 2, pp. 524–531. IEEE (2005)
7.
Zurück zum Zitat Gao, S., Tsang, I.W., Chia, L.T., Zhao, P.: Local features are not lonely–laplacian sparse coding for image classification. In: CVPR, pp. 3555–3561. IEEE (2010) Gao, S., Tsang, I.W., Chia, L.T., Zhao, P.: Local features are not lonely–laplacian sparse coding for image classification. In: CVPR, pp. 3555–3561. IEEE (2010)
8.
Zurück zum Zitat Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset (2007) Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset (2007)
9.
Zurück zum Zitat Jurie, F., Triggs, B.: Creating efficient codebooks for visual recognition. In: ICCV, vol. 1, pp. 604–610. IEEE (2005) Jurie, F., Triggs, B.: Creating efficient codebooks for visual recognition. In: ICCV, vol. 1, pp. 604–610. IEEE (2005)
10.
Zurück zum Zitat Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: CVPR, pp. 2169–2178 (2006) Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: CVPR, pp. 2169–2178 (2006)
11.
Zurück zum Zitat Li, F.F., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106(1), 59–70 (2007)CrossRef Li, F.F., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106(1), 59–70 (2007)CrossRef
12.
Zurück zum Zitat Long, M., Ding, G., Wang, J., Sun, J., Guo, Y., Yu, P.S.: Transfer sparse coding for robust image representation. In: CVPR, pp. 407–414. IEEE (2013) Long, M., Ding, G., Wang, J., Sun, J., Guo, Y., Yu, P.S.: Transfer sparse coding for robust image representation. In: CVPR, pp. 407–414. IEEE (2013)
13.
Zurück zum Zitat Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRef Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRef
14.
Zurück zum Zitat Manjunath, B., Ma, W.: Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Mach. Intell. 18(8), 837–842 (1996)CrossRef Manjunath, B., Ma, W.: Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Mach. Intell. 18(8), 837–842 (1996)CrossRef
15.
Zurück zum Zitat Oliva, A., Torralba, A.: Building the gist of a scene: the role of global image features in recognition. Prog. Brain Res. 155, 23–36 (2006)CrossRef Oliva, A., Torralba, A.: Building the gist of a scene: the role of global image features in recognition. Prog. Brain Res. 155, 23–36 (2006)CrossRef
16.
Zurück zum Zitat Quelhas, P., Monay, F., Odobez, J.M., Gatica-Perez, D., Tuytelaars, T., Van Gool, L.: Modeling scenes with local descriptors and latent aspects. In: ICCV, vol. 1, pp. 883–890. IEEE (2005) Quelhas, P., Monay, F., Odobez, J.M., Gatica-Perez, D., Tuytelaars, T., Van Gool, L.: Modeling scenes with local descriptors and latent aspects. In: ICCV, vol. 1, pp. 883–890. IEEE (2005)
17.
Zurück zum Zitat Stricker, M., Orengo, M.: Similarity of color images. In: SPIE Conference on Storage and Retrieval for Image and Video Databases, vol. 2420, pp. 381–392, San Jose, USA (1995) Stricker, M., Orengo, M.: Similarity of color images. In: SPIE Conference on Storage and Retrieval for Image and Video Databases, vol. 2420, pp. 381–392, San Jose, USA (1995)
18.
Zurück zum Zitat Wang, D., Lu, H., Chen, Y.W.: Object tracking by multi-cues spatial pyramid matching. In: ICIP, pp. 3957–3960. IEEE (2010) Wang, D., Lu, H., Chen, Y.W.: Object tracking by multi-cues spatial pyramid matching. In: ICIP, pp. 3957–3960. IEEE (2010)
19.
Zurück zum Zitat Wang, M., Gao, Y., Lu, K., Rui, Y.: View-based discriminative probabilistic modeling for 3d object retrieval and recognition. IEEE Trans. Image Proc. 22(4), 1395–1407 (2013)MathSciNetCrossRef Wang, M., Gao, Y., Lu, K., Rui, Y.: View-based discriminative probabilistic modeling for 3d object retrieval and recognition. IEEE Trans. Image Proc. 22(4), 1395–1407 (2013)MathSciNetCrossRef
20.
Zurück zum Zitat Wang, M., Li, W., Liu, D., Ni, B., Shen, J., Yan, S.: Facilitating image search with a scalable and compact semantic mapping. IEEE Trans. Cybern. 45(8), 1561–1574 (2015)CrossRef Wang, M., Li, W., Liu, D., Ni, B., Shen, J., Yan, S.: Facilitating image search with a scalable and compact semantic mapping. IEEE Trans. Cybern. 45(8), 1561–1574 (2015)CrossRef
21.
Zurück zum Zitat Wang, M., Liu, X., Wu, X.: Visual classification by l1-hypergraph modeling. IEEE Trans. Knowl. Data Eng. 27(9), 2564–2574 (2015)CrossRef Wang, M., Liu, X., Wu, X.: Visual classification by l1-hypergraph modeling. IEEE Trans. Knowl. Data Eng. 27(9), 2564–2574 (2015)CrossRef
22.
Zurück zum Zitat Wu, J.X., Rehg, J.M.: Where am i: place instance and category recognition using spatial pact. In: CVPR, pp. 1–8. IEEE (2008) Wu, J.X., Rehg, J.M.: Where am i: place instance and category recognition using spatial pact. In: CVPR, pp. 1–8. IEEE (2008)
23.
Zurück zum Zitat Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: CVPR, pp. 1794–1801. IEEE (2009) Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: CVPR, pp. 1794–1801. IEEE (2009)
24.
Zurück zum Zitat Yin, H., Cao, Y., Sun, H.: Combining pyramid representation and adaboost for urban scene classification using high-resolution synthetic aperture radar images. Radar Sonar Navig. IET 5(1), 58–64 (2011)CrossRef Yin, H., Cao, Y., Sun, H.: Combining pyramid representation and adaboost for urban scene classification using high-resolution synthetic aperture radar images. Radar Sonar Navig. IET 5(1), 58–64 (2011)CrossRef
25.
Zurück zum Zitat Yuan, X.T., Liu, X., Yan, S.: Visual classification with multitask joint sparse representation. IEEE Trans. Image Proc. 21(10), 4349–4360 (2012)MathSciNetCrossRef Yuan, X.T., Liu, X., Yan, S.: Visual classification with multitask joint sparse representation. IEEE Trans. Image Proc. 21(10), 4349–4360 (2012)MathSciNetCrossRef
26.
Zurück zum Zitat Zhao, Z.Q., Glotin, H., Xie, Z., Gao, J., Wu, X.D.: Cooperative sparse representation in two opposite directions for semi-supervised image annotation. IEEE Trans. Image Proc. 21(9), 4218–4231 (2012)MathSciNetCrossRef Zhao, Z.Q., Glotin, H., Xie, Z., Gao, J., Wu, X.D.: Cooperative sparse representation in two opposite directions for semi-supervised image annotation. IEEE Trans. Image Proc. 21(9), 4218–4231 (2012)MathSciNetCrossRef
27.
Zurück zum Zitat Zheng, L., Wang, S., Liu, Z., Tian, Q.: Packing and padding: coupled multi-index for accurate image retrieval. In: CVPR (2014) Zheng, L., Wang, S., Liu, Z., Tian, Q.: Packing and padding: coupled multi-index for accurate image retrieval. In: CVPR (2014)
Metadaten
Titel
A Multi-modal SPM Model for Image Classification
verfasst von
Peng Zheng
Zhong-Qiu Zhao
Jun Gao
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-63315-2_46

Premium Partner