English

Memory Efficient Multi-Scale Line Detector Architecture for Retinal Blood Vessel Segmentation

Computer Vision and Pattern Recognition 2017-01-02 v1 Hardware Architecture

Abstract

This paper presents a memory efficient architecture that implements the Multi-Scale Line Detector (MSLD) algorithm for real-time retinal blood vessel detection in fundus images on a Zynq FPGA. This implementation benefits from the FPGA parallelism to drastically reduce the memory requirements of the MSLD from two images to a few values. The architecture is optimized in terms of resource utilization by reusing the computations and optimizing the bit-width. The throughput is increased by designing fully pipelined functional units. The architecture is capable of achieving a comparable accuracy to its software implementation but 70x faster for low resolution images. For high resolution images, it achieves an acceleration by a factor of 323x.

Keywords

Cite

@article{arxiv.1612.09524,
  title  = {Memory Efficient Multi-Scale Line Detector Architecture for Retinal Blood Vessel Segmentation},
  author = {Hamza Bendaoudi and Farida Cheriet and J. M. Pierre Langlois},
  journal= {arXiv preprint arXiv:1612.09524},
  year   = {2017}
}

Comments

This paper was accepted and presented at Conference on Design and Architectures for Signal and Image Processing - DASIP 2016

R2 v1 2026-06-22T17:37:51.323Z