Implementation of Maximally Stable Extremal Region for Text Segmentation on Food Package

Authors

  • Marlindia Ike Sari
  • Rini Handayani
  • Sidiq Maulana

How to Cite

Ike Sari, M., Handayani, R., & Maulana, S. (2019). Implementation of Maximally Stable Extremal Region for Text Segmentation on Food Package. International Journal of Engineering and Technology, 8(1.9), 157-160. https://doi.org/10.14419/ijet.v8i1.9.26391

Received date: January 22, 2019

Accepted date: January 22, 2019

Published date: January 26, 2019

DOI:

https://doi.org/10.14419/ijet.v8i1.9.26391

Keywords:

Text Segmentation, MSER, image processing, food package

Abstract

Many technologies help people with vision disabilities. It helps these people to walk, read, and other activities. However, when these people have to shop and there is no one to help, they can’t determine what product in their hand is. In this research, we applied image processing to recognize the name of the product based on text in the food package. We applied Maximally Stable Extremal Region (MSER) for text segmentation in the food package. The model is applied to predict the result of implementation MSER for text segmentation in the food package. We implement MSER with input from camera board in Raspberry Pi. Light intensity and type of food package give a different result. The result of this research has average 85%. It shows that MSER works for text segmentation in the food package.

 

References

  1. [1] Chucai Yi, a. Y. (2012). Localizing Text in Scene Images by Boundary Clustering, Stroke Segmentation, and String Fragment Classification. IEEE TRANSACTIONS ON IMAGE PROCESSING, 4256-4268.

    [2] J. Matas, O. C. (2002). Robust Wide Baseline Stereo from Maximally Stable Extremal Regions. Proc. Of British Machine Vision Conference (BMVC), (pp. 384–396).

    [3] Kethineni Venkateswarlu, S. M. (2015). Text Detection on Scene Image Using MSER. International Journal of Research in Computer and Communication Technology, 452-456.

    [4] Matas, ˇ. S. (2006). Object Recognition using Local Affine Frames on Maximally Stable Extremal Regions. In Toward Category-Level Object Recognition, (pp. 83-104).

    [5] Pedro Martins a, P. C. (2016). On the completeness of feature-driven maximally stable extremal regions. Pattern Recognition Letter, 9-16.

    [6] Petra Bosilj, E. K. (n.d.). Beyond MSER: Maximally Stable Regions using Tree of Shapes.

Downloads

How to Cite

Ike Sari, M., Handayani, R., & Maulana, S. (2019). Implementation of Maximally Stable Extremal Region for Text Segmentation on Food Package. International Journal of Engineering and Technology, 8(1.9), 157-160. https://doi.org/10.14419/ijet.v8i1.9.26391

Received date: January 22, 2019

Accepted date: January 22, 2019

Published date: January 26, 2019