Contributions to Proceedings:

C. Ossimitz, N. TaheriNejad:
"A Fast Line Segment Detector Using Approximate Computing";
in: "2021 IEEE International Symposium on Circuits and Systems (ISCAS)", issued by: IEEE; IEEE International Symposium on Circuits and Systems (ISCAS), 2021, ISBN: 978-1-7281-9201-7, 5 pages.

English abstract:
The Line Segment Detector (LSD) algorithm is an underlying step of many image processing systems. Hence, its performance has a significant on the upper layers using the detected line segment for various purposed. In this paper, we propose a fast LSD algorithm. This method approximates several floating point operations, including the logarithmic Gamma function, by a series of lookup table searches. Due to the simplicity of such approximation (lookup table search) compared to the naïve implementation (calculation-based), this method is considerably faster. The proposed method has implications on reduction of the necessary efforts to implement and enhancement of the performance of the LSD hardware accelerators. Our experiments show that the proposed method reduces the run-time of the algorithm by 13% on average, with no considerable quality loss in the detection results. This improvement further propagates through other image processing algorithms using LSD.

"Official" electronic version of the publication (accessed through its Digital Object Identifier - DOI)

Electronic version of the publication:

Created from the Publication Database of the Vienna University of Technology.