An efficient method for stamps isolation from background combined K-mean/ISODATA with region growing

Maha A. Rajab, Dr. Loay E. George


     Often image stamp surrounding with an unwanted data such as, noise, object, text, patches etc., thus, it becomes necessary to extract stamp and removing the unwanted background. In this paper, an efficient and robust method for extracting stamp is proposed. The proposed stamp extraction method comprises of four main phases (i.e., data points clustering, background isolation, image segmentation, and finally stamp extracted). Data points clustering is done by applying k-mean clustering algorithm to cluster RGB band and ISODATA clustering algorithm to merge clusters and compute mean and standard deviation for each cluster to isolated background cluster from stamp cluster in background isolation stage. For stamp extraction, a region growing algorithm is applied to segment the image and then choosing the connected region to produce a binary mask for the stamp area. Finally, the binary mask is combined with the original image to extract the stamp disconnected regions. The proposed method is implemented on one dataset available publicly named Stamps Dataset. The test results indicate that the number of clusters can be determined dynamically and the largest cluster that has minimum standard deviation (i.e., always the largest cluster is the background cluster). The test results show that the binary mask can be established from more than one segment to cover are all stamp’s disconnected pieces and it can be useful to remove the noise patches way appear with stamp region.      


K-Mean clustering; ISODATA clustering; Image segmentation ; Region growing; Stamps extraction


B. Micenkova and J. Beusekom, " Stamp Detection in Color Document Images, " International Conference on Document Analysis and Recognition, pp. 1125- 1129, 2011. doi 10.1109/ICDAR.2011.227.

P. Forczman´ski and D. Frejlichowski, " Robust Stamps Detection and Classification by Means of General Shape Analysis, " Springer International Conference on Computer Vision and Graphics, pp. 1-8, 2010. DOI: 10.1007/978-3-642-15910-7-41· Source: OI.

S. Dey, et al., " Removal of Gray Rubber Stamps, " IAPR Workshop on Document Analysis Systems, pp. 210- 214, 2016. doi 10.1109/DAS.2016.26.

A. V. Nandedkar, et al., " A Spectral Filtering Based Deep Learning for Detection of Logo and Stamp, " IEEE Conference: Fifth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), 2015. doi: 10.1109/NCVPRIPG.2015.7490053.

A. V. Nandedkar, et al., " SPODS: A Dataset of Color-Official Documents and Detection of Logo, Stamp, and Signature, " Springer International Publishing, pp. 219–230, 2017.

A. Farahmand, et al. " Document Image Noises and Removal Methods, " International MultiConference of Engineers and Computer Scientists (IMECS), vol. 1, 2013.

G. K. Seerha and R. Kaur, " Review on Recent Image Segmentation Techniques, " International Journal on Computer Science and Engineering (IJCSE), vol. 5 (02), pp. 109- 112, 2013.

S. Panda, " Color Image Segmentation Using K-means Clustering and Thresholding Technique, " IJESC, pp.1132 –1136, 2015. doi 10.4010/2015.310.

P. Panwar, et al., " Image Segmentation using K-means clustering and Thresholding, " International Research Journal of Engineering and Technology (IRJET), vol. 03 (05), pp. 1787- 1793, 2016.

W. Liu, et al., " An Adaptive Clustering Algorithm Based on The Possibility Clustering and ISODATA for Multispectral Image Classification, " The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, pp. 565- 568, 2008.

A. W. Abbas, et al., " K-Means and ISODATA Clustering Algorithms for Landcover Classification Using Remote Sensing, " Sindh University Research Journal (Science Series), vol. 48 (2), pp. 315-318, 2016.

Q. Lu, et al., " A Novel Clustering-Based Feature Representation for the Classification of Hyperspectral Imagery,” Remote Sensing, vol. 6, pp. 5732-5753, 2014. doi: 10.3390/rs6065732.

P. Gantuya, et al., " Mongolian Traditional Stamp Recognition using Scalable kNN, " International Journal of Advanced Smart Convergence, vol. 4 (2), pp. 170-176, 2015.

D. Frejlichowski and P. Forczma " General Shape Analysis Applied to Stamps Retrieval from Scanned Documents, " Springer-Verlag Berlin Heidelberg, vol. 6304, pp. 251–260, 2010.

N. Dhanachandra, et al., " Image Segmentation using K-means Clustering Algorithm and Subtractive Clustering Algorithm, " Elsevier Eleventh International Multi-Conference on Information Processing (IMCIP), vol. 54, pp. 764 – 771, 2015.

B. Mahaseni and N. D. Salih, " Asian Stamps Identification and Classification System, " arXiv: 1709.05065v1, pp. 1-9, 2017.

P. Forczmański, " Stamp Detection in Scanned Documents, " Annales UMCS Informatica Lublin-Polonia Sectio AI, vol.1, pp. 61-68, 2010. doi: 10.2478/v10065-010-0036-6.

P. Forczma and D. Frejlichowski, " Classification of Elementary Stamp Shapes by Means of Reduced Point Distance Histogram Representation, " Springer-Verlag Berlin Heidelberg, pp. 603–616, 2012.

M. N. Qureshia and M. V. Ahamadb, " An Improved Method for Image Segmentation Using K-Means Clustering with Neutrosophic Logic, " Elsevier. International Conference on Computational Intelligence and Data Science (ICCIDS), vol. 132, pp. 534–540, 2018.

Total views : 34 times


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

shopify stats IJEECS visitor statistics