Effective Compression of Center Symmetric Local Binary Pattern

Abstract

In this paper, we propose simple and effective compression of CSLBP (Center Symmetric Local Binary Pattern) descriptors, which is a textured based operator and mostly used as key point descriptor. With default parameters for computation, it is 256-length descriptor for each keypoint or affine patch. CSLBP is an extended form of LBP (Local Binary Patterns). The calculation of CSLBP descriptor is effective, robust, and straightforward for different image transformations for instance; image blurring and illumination alteration. However, an improvement in time and space consumption of CSLBP can be attained by means of simple compression. For this reason, CSLBP is a smart choice for smart phones as well as large databases. We reduce the descriptor length (dimensions) upto 50% without applying any techniques of dimensionality reduction like PCA (Principle Component Analysis) or LDA (Linear Discriminant Analysis). The compressed CSLBP descriptor is denoted as C-CSLBP. The performance of C-CSLBP is evaluated on state-of-the-art datasets using standard metrics. It is quantitatively shown by experiments that C-CSLBP is equivalently effective compared to CSLBP despite of reduced dimensions.

Authors and Affiliations

Junaid Baber, Maheen Bakhtyar, Ihsanullah Kaker, Mariam Rehman, Muhammad Khalid

Keywords

Related Articles

Selective Leaching of Steel Pollutant Element from Dilband Iron Ore, Pakistan

Dilband Iron ore of Pakistan is lean grade ore which contains sufficient amount of phosphorous bearing mineral called fluorapatite. Since phosphorous is widely acknowledged as steel pollutant and disturbs the blast furna...

Planning Failure of Satellite Town: A Case Study of Korangi, Karachi-Pakistan

The Satellite town of Korangiis part of the ‘Greater Karachi Resettlement Plan’ along with other satellite towns of Landhi and New Karachi proposed by the Greek Architect Constantinos Apostolou Doxiadis in 1958. It is lo...

Change Detection Algorithms for Surveillance in Visual IoT: A Comparative Study

The VIoT (Visual Internet of Things) connects virtual information world with real world objects using sensors and pervasive computing. For video surveillance in VIoT, ChD (Change Detection) is a critical component. ChD a...

Modified NEH Algorithm for Multi-Objective Sequencing in Mixed-Model Assembly Lines

Assembly lines are usually used for the mass production. The dawn of mass customization has forced the industries to shift to MMAL (Mixed-Model Assembly Lines). ALBP (Assembly Line Balancing Problem) and MSP (Model Seque...

Implementing a Business Intelligence Environment in Local Market of Pakistan

The BI (Business Intelligence) has gained great success during the last decade throughout the world to aid in decision support with the availability of necessary knowledge to reduce costs, increase revenues and minimize...

Download PDF file
  • EP ID EP182955
  • DOI 10.22581/muet1982.1702.01
  • Views 147
  • Downloads 0

How To Cite

Junaid Baber, Maheen Bakhtyar, Ihsanullah Kaker, Mariam Rehman, Muhammad Khalid (2017). Effective Compression of Center Symmetric Local Binary Pattern. Mehran University Research Journal of Engineering and Technology, 36(2), 209-224. https://europub.co.uk/articles/-A-182955