An Applied Local Binary Pattern by Hyperbolic Secant for Edge Detection of Images and applied to Images Retrieval

Main Article Content

ทรงพล นคเรศเรืองศักดิ์
สุทธิลักษณ์ ชุนประวัติ


The objective of this research is proposed Applying local binary pattern method to edge detection of images. We added Hyperbolic Secant function Similarity function and parameters for increasing detail and sharper of edge into the original equation. The experimental results show that this proposed method can obtain the border has more detailed and high contrast. And it can be explaining the internal differences between two distinct areas, but get the same result, which is the result of original Local Binary Pattern. In this paper, the researcher used the proposed method for edge detection of common images and edge results applied to content based images retrieval by calculated edge histogram, then we obtained edge histogram five directions of edge, which is created to index for images retrieval. The researchers found that the index of edges from the proposed method gave an overall performance value of 80%, which was high.


Download data is not yet available.

Article Details

How to Cite
นคเรศเรืองศักดิ์ ท., & ชุนประวัติ ส. (2018). An Applied Local Binary Pattern by Hyperbolic Secant for Edge Detection of Images and applied to Images Retrieval. Journal of Energy and Environment Technology of Graduate School Siam Technology College, 5(1), 1–11. Retrieved from
Research Article


[1] C. R. Gonzales and E. R. Woods, “Digital Images Processing,” Second ed. India: Pearson Education.

[2] L. Zeng, K. Shen and H. Jiang. “An effective edge extraction method using improved local binary pattern for blurry digital radiography images,” NDT&E International 53, 2013, pp. 26-30.

[3] S. Nakharacruangsak, M. Sodanil and S. Nitsuwat, “An improved local binary pattern for edge detection of images,” Proceedings of IEEE Region 10 Conference: TENCON, 2014, pp. 1-4.

[4] H. Jin, Q. Liiu, H. Lu, and X. Tong, “Face Detection Using Improved LBP Under Bayesian Framework,” Proceeding of the Third International Conference on Image and Graphics, (2004), pp.306-309.
[5] Y. Ding, H. Pang, X. Wu and J. Lan, “Recongnition of Hand-Gestures Using Improved Local Binary Pattern,” Multimedia Technology (ICMT), 2011 International Conference on July 2011, pp. 3171-3174.

[6] J. Liu, X. Liu, J. Chen and J. Tang, “Improved Local Binary Pattern for Classification of Masses Using Mammography,” Systems, Man, and Cybernetics (SMC), IEEE International Conference on Oct 2011, pp.2692-2695.

[7] G. Schaefer and N P. Doshi, “Multi-dimensional Local Binary Pattern Descriptors for Improved Texture Analysis,” Pattern Recognition (ICPR), 2012 21st International Conference on Nov 2012, pp.2500-2503.

[8] X. Xianchuan and Z. Qi, “Medical Image Retrieval Using Local Binary Patterns with Image Euclidean Distance,” Information Engineering and Computer Science, International Conference on Dec 2009, pp.1-4.

[9] XY. Tan and B. Triggs, “Enhanced local texture feature sets for face recognition under difficult lighting conditions,” IEEE trans Image Process 2010, pp.1635-50.

[10] L. Nanni, A. Lummini and S. Brahnam, “Local binary patterns variants as texture descriptors for medical image analysis,” Artif Intell Med 2010, pp.117-25.

[11] CR. Zhu and RS. Wang, “Local multiple patterns based multiresolution gray-scale and rotation invariant texture classification,” InfoSci, 2012, pp.93-108.