Abstract
With the rapid growth of digital documents, big data puts higher demands on document image retrieval. Document image retrieval is the domain between classical information retrieval and content-based retrieval. The traditional document image retrieval method relies on complex OCR-based text recognition and text similarity detection. This paper proposes a new content-based retrieval method for document graphics objects. This method focuses on feature extraction, feature fusion, and indexing. This paper uses the pretrained convolutional neural network model to learn the image representation of the retrieval task, extracts various features of the document image, and then performs the PCA reduction on the extracted high-dimensional features, and then uses the improved Rank fusion method based on Rank_avg to form new features matrix. Transfer learning is used to fine-tune the trained CNN model and apply it to the retrieval algorithm, which can effectively deal with the deficiency of training data. Finally, the similarity of the features is used to sort, and the query index is established based on the inverted indexing technique of visual vocabulary. Experiments with document image datasets containing charts and texts show that this method has better ability to retrieve document images with similar text contents. The fusion of dimension-reduced CNN features can effectively improve MAP of the retrieval system. The MAP of model fusion with good performance can reach 0.85. The reverse indexing technology based on visual vocabulary can effectively reduce the retrieval time by 27%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wu, S., Oerlemans, A., Bakker, E.M., Lew, M.S.: Deep binary codes for large scale image retrieval. Neurocomputing (2017)
Kuo, C.-M., Yang, N.-C., Tseng, S.-C., Chenm, M.-T.: A novel texture descriptor for texture image retrieving. J. Netw. Intell. 3(4), 278–290 (2018)
En, S., Petitjean, C., Nicolas, S., Heutte, L.: A scalable pattern spotting system for historical documents. Pattern Recognit. 54, 149–161 (2016)
Chen, X., Peng, X., Li, J.-B., Peng, Y.: Overview of deep kernel learning based techniques and applications. J. Netw. Intell. 1(3), 83–98 (2016)
Lee, C.-F., Wang, Y.-J., Chu, S.-C., Roddick, J.F.: An adaptive content-based image retrieval method exploiting an affine invariant region based on a VQ-applied quadtree robust to geometric distortions. J. Netw. Intell. 3(3), 214–234 (2018)
Hong, R., Zhang, L., Tao, D.: Unified photo-enhancement by discovering aesthetic communities from flickr. IEEE Trans. Image Process. 25(3), 1124–1135 (2016)
Hong, S., Wang, A., Zhang, X., Gui, Z.: Low-dose CT image processing using artifact suppressed total generalized variation. J. Netw. Intell. 3(1), 26–49 (2018)
Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real time object detection. Comput. Sci. 779–788 (2015)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Gatys, L.A., Ecker, A.S.: A neural algorithm of artistic style. Comput. Sci. (2015)
Babenko, A., Lempitsky, V.: Aggregating local deep features for image retrieval. ICCV (2015)
Mohedano, E., McGuinness, K., O’Connor, N.E., et al.: Bags of local convolutional features for scalable instance search. ICMR (2016)
Thuy, Q.D.T., Huu, Q.N., Van, C.P., Quoc, T.N.: An efficient semantic—related image retrieval method. Expert Syst. Appl. 72, 30–41 (2017)
Chatfield, K., Simonyan, K., Vedaldi, A., et al.: Return of the devil in the details: delving deep into convolutional nets. Comput. Sci. (2014)
Babenko, A., Slesarev, A., Chigorin, A., et al.: Neural Codes for Image Retrieval, vol. 8689, pp. 584–599. (2014)
Kaggle ensembling guide. https://mlwave.com/kaggle-ensembling-guide/. Last accessed 11 June 2015
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhou, J., Guo, B., Zheng, Y. (2020). Document Image Retrieval Based on Convolutional Neural Network. In: Pan, JS., Li, J., Tsai, PW., Jain, L. (eds) Advances in Intelligent Information Hiding and Multimedia Signal Processing. Smart Innovation, Systems and Technologies, vol 156. Springer, Singapore. https://doi.org/10.1007/978-981-13-9714-1_24
Download citation
DOI: https://doi.org/10.1007/978-981-13-9714-1_24
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9713-4
Online ISBN: 978-981-13-9714-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)