A Study on Edge Preserving Filter in Image Matching

Rostam Affendi Hamzah, A.F. Kadmin, S. F. A. Gani, K. A. Aziz, T. M. F. T. Wook, N. Mohamood, M. G. Y. Wei

Abstract


This article presents a study on edge preserving filter in image matching. This study comprises a novel development of stereo matching algorithm using edge preserving filter in the algorithm framework. Fundamentally, the matching process consist of several stages which will produce the disparity or depth map. The clear problem and the most challenging problem for matching process is to get an accurate corresponding point between two images. Hence, this article proposes an algorithm for stereo matching using Sum of Squared Differences (SSD) and dual edge preserving filters. It is Median Filter (MF) and Bilateral Filter (BF) to surge up the accuracy. The SSD will be implemented at the first stage to get the preliminary corresponding result, then the BF works as an edge-preserving filter to remove the noise from the first stage. The MF is used at the last stage to improve final disparity map. A standard benchmarking dataset from the Middlebury has been used for the experimental analysis and validation. The proposed work in this article achieves good accuracy about 6.65% and 9.32% of nonocc and all errors respectively. The comparison is also conducted with some established methods where the proposed framework performs much better.

Keywords


bilateral filter, edge preserving filter, image matching, median filter, stereo vision


Refbacks

  • There are currently no refbacks.


Bulletin of EEI Stats