Abstract
In the interpretation of images, contextual comprehension serves a key task in a natural scene. The text present in scene images often bestows qualitative details which can be analyzed in many aspects of image processing. The text and non-text natural image classification help in pruning out unnecessary processing to get the key textual information. In this work, we designed a convolutional neural network (CNN), named TNTNet, and also a transfer learning-based method was considered for this purpose. We proposed an ensemble network by combining the TNTNet and the pre-trained VGG-19 model. The accuracies were computed for different train-test ratios. The highest accuracy of 99.45% was obtained in our ensemble network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ghosh, M., Roy, S.S., Mukherjee, H., Obaidullah, S.M., Santosh, K.C., Roy, K.: Automatic text localization in scene images: a transfer learning based approach. In: National Conference on Computer Vision. Pattern Recognition, Image Processing, and Graphics, pp. 470–479. Springer, Singapore (2019)
Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. Int. J. Comput. Vis., 1-24 (2020)
Ghosh, M., Mukherjee, H., Obaidullah, S.M., Santosh, K.C., Das, N., Roy, K.: Artistic multi-script identification at character level with extreme learning machine. Procedia Comput. Sci. 167, 496–505 (2020)
Lyu, P., Shi, B., Zhang, C., Bai, X.: Distinguishing text/non-text natural images with multi-dimensional recurrent neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 3981–3986. IEEE (2016)
Ghosh, M., Mukherjee, H., Obaidullah, S. M., Santosh, K. C., Das, N., Roy, K.: Identifying the presence of graphical texts in scene images using CNN. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), Vol. 1, pp. 86–91. IEEE (2019)
Alessi, N.G., Battiato, S., Gallo, G., Mancuso, M., Stanco, F.: Automatic discrimination of text images. In: Sensors and Camera Systems for Scientific, Industrial, and Digital Photography Applications IV, Vol. 5017, pp. 351–359. International Society for Optics and Photonics (2003)
Le, V.P., Nayef, N., Visani, M., Ogier, J.M., De Tran, C.: Text and non-text segmentation based on connected component features. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1096–1100. IEEE (2015)
Zhang, C., Yao, C., Shi, B., Bai, X.: Automatic discrimination of text and non-text natural images. In: 2015 13th International Conference on Document Analysis and Recognition (icdar), pp. 886–890. IEEE (2015)
Sriman, B., Schomaker, L.: Multi-script text versus non-text classification of regions in scene images. J. Vis. Commun. Image Represent. 62, 23–42 (2019)
Gupta, N., Jalal, A.S.: Text or non-text image classification using fully convolution network (FCN). In: 2020 International Conference on Contemporary Computing and Applications (IC3A), pp. 150–153. IEEE (2020)
Karmakar, P., MdMizan, C., Astya, R., Chakraborty, S.: Discrimination of text and non-text images. In: Advances in Electromechanical Technologies, pp. 323–331. Springer, Singapore (2020)
Xie, J., Xu, B., Chuang, Z.: Horizontal and vertical ensemble with deep representation for classification (2013). arXiv preprint arXiv:1306.2759,2013
Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almazan, J.A., De Las Heras, L.P.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484–1493. IEEE (2013)
Yao, C., Wu, J., Zhou, X., Zhang, C., Zhou, S., Cao, Z., Yin, Q.: Incidental scene text understanding: recent progresses on icdar 2015 robust reading competition challenge 4 (2015). arXiv preprint arXiv:1511.09207
Farahzadeh, E., Cham, T. J., Li, W.: Semantic and spatial content fusion for scene recognition. In: New Development in Robot Vision, pp. 33–53. Springer, Berlin, Heidelberg (2015)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ghosh, M., Chatterjee, S., Mukherjee, H., Sen, S., Obaidullah, S.M. (2022). Text/Non-text Scene Image Classification Using Deep Ensemble Network. In: Mandal, J.K., Buyya, R., De, D. (eds) Proceedings of International Conference on Advanced Computing Applications. Advances in Intelligent Systems and Computing, vol 1406. Springer, Singapore. https://doi.org/10.1007/978-981-16-5207-3_47
Download citation
DOI: https://doi.org/10.1007/978-981-16-5207-3_47
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5206-6
Online ISBN: 978-981-16-5207-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)