Abstract
Document image analysis and processing has drawn the attention of many researchers due to its real-time applications in day-to-day life. Document database comprising of logo provides a good opportunity for an easier way of indexing, searching and retrieval of the documents. Logo detection is an essential need for the implementation of any logo-based document indexing or retrieval techniques. This paper aims to develop an efficient logo detection method for document images. The major steps employed in the developed system include preprocessing of the input document, finding the connected components and classification of these components into the logo and non-logo candidates. The preprocessing step employs a median filter and a unique procedure for the removal of clutter noise to reduce the false detection rate. Histogram of Oriented Gradient (HOG) features and an SVM classifier are used to identify the logo and non-logo candidates of the document. The presented system is evaluated using Tobacco 800 dataset and the results are compared with existing techniques. The results show an improvement of 5% in average logo detection rate with the proposed work.
Similar content being viewed by others
References
Bay H, Ess A, Tuytelaars T, Gool LV (2008) SURF: Speeded up robust features. Comp Vision Image Underst (CVIU) 110(3):346–359
Bultheel A (1995) Learning to swim in a sea of wavelets. Bull Belg Math Soc Simon Stevin 2(1):1–45
Chang SG, Yu B, Vetterli M (2000) Adaptive wavelet thresholding for image denoising and compression. IEEE Trans Image Process 9(9):1532–1546
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. Proc. of Int’l Conf. on Computer Vision Pattern Recognition, 886–893
Dixit UD, Shirdhonkar MS (2016) Automatic logo detection and extraction using singular value decomposition. Proc. of IEEE Int’l Conf. on Communication and Signal Processing (ICCSP), 787–790
Dixit UD, Shirdhonkar MS (2016) Logo-based document image retrieval using singular value decomposition features. Proc. of IEEE Int’l Conf. on Signal and Information Processing (IConSIP), 1–4
Dixit UD, Shirdhonkar MS (2017) Face-biometric based document image retrieval using SVD features, Computational Intelligence in Data Mining, Advances in Intelligent Systems and Computing Series 556:481–488
Dixit UD, Shirdhonkar MS (2019) Language-Based Classification of Document Images Using Hybrid Texture Features. In: Sinha G (ed) Advances in Biometrics. Springer, Cham
Dixit UD, Shirdhonkar MS (2019) Fingerprint-based document image retrieval. Int J Image Graph 19(2):1–17
Dixit UD, Shirdhonkar MS (2020) Language-based document image retrieval for Trilingual System. Int J Inform Technol 12:1217–1226
Dixit UD, Shirdhonkar MS (2021) Document image retrieval: Issues and future directions. Proc. of 2021 International Conference on Computational Intelligence and Computing Applications (ICCIA) :1–4
Guan B, Ye H, Liu H, Sethares WA (2020) Video logo retrieval based on local features. Proc. of IEEE International Conference on Image Processing (ICIP), 1396–1400
Hassanzadeh S, Pourghassem H (2011) A novel logo detection and recognition framework for separated part logos in document images. Aust J Basic Appl Sci 5:936–946
Hoang TV, Smith EHB, Tabbone S (2014) Sparsity-based edge noise removal from bilevel graphical document images. Int J Doc Anal Recognit (IJDAR) 17(2):161–179
Jain R, Doermann D (2012) Logo Retrieval in Document Images, Document Analysis Systems. Proc. of IAPR International Workshop on, Document Analysis Systems, 135–139
Justusson BI (1981) Median filtering: statistical properties. In: Proc. of Two-Dimensional Digital Signal Processing II, 161–196
Kumar G, Keserwani P, Roy PP, Dogra DP (2021) Logo detection using weakly supervised saliency map. Multimed Tools Appl 80(3):4341–4365
Le VP, Nayef N, Visani M, Ogier JM, Tran CD (2014) Document retrieval based on logo spotting using key-point matching. Proc. of Int’l Conf. on Pattern Recognition (ICPR-2014), 3056–3061
Meethongjan K, Surinwarangkoon T, Hoang VT (2020) Vehicle logo recognition using histograms of oriented gradient descriptor and sparsity score. Telkomnika, pp 3019–3025
Nejad AA, Faez K (2012) A novel method for extracting and recognizing logos. Int J Electr Comput Eng 2(5):577–588
Pan J, Zhuang Y, Fong S (2016) The impact of data normalization on stock market prediction: using SVM and technical indicators. Proc. of International Conference on Soft Computing in Data Science, 72–88
Patil PB, Ijeri DM (2021) Classification of text documents. In: Chiplunkar N and Fukao T (ed) Advances in Artificial Intelligence and Data Engineering, Advances in Intelligent Systems and Computing, 1133:675–685
Pham T (2003) Unconstrained logo detection in document images. Pattern Recogn 36:3023–3025
Seiden S, Dillencourt M, Irani S, Borrey R, Murphy T (1997) Logo detection in document images. Proc of Int’l Conf. on Imaging Science, Systems, and Technology, pp 446–449
Shirdhonkar MS, Kokare M (2010) Automatic logo detection in document images. Proc. of IEEE Int’l Conf. on Computational Intelligence and Computer Research, 905–907
Vapnik V (2013) The nature of statistical learning theory. Springer Science & Business Media, Berlin
Wang H, Chen Y (2009) Logo detection in document images based on boundary extension of feature rectangles. Proc of 10th Int’l Conf. on Document Analysis and Recognition, 1335–1337
Zhao J, Wang X (2019) Vehicle-logo recognition based on modified HU invariant moments and SVM. Multimed Tools Appl 78:75–97
Zhu G, Doermann D (2007) Automatic document logo detection. Proc. of Conf. on Document Analysis and Recognition, 864–868
Zhu D, Doermann D (2008) Tobacco-800 complex document image database and ground truth. online. http://lampsrv01.umiacs.umd.edu/projdb/edit/project.php?id=52
Zhu G, Doermann D (2009) Logo matching for document image retrieval. Proc. of 10th Int’l Conf. on Document Analysis and Recognition, 606–610
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dixit, U.D., Shirdhonkar, M.S. & Sinha, G.R. Automatic logo detection from document image using HOG features. Multimed Tools Appl 82, 863–878 (2023). https://doi.org/10.1007/s11042-022-13300-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13300-5