Recognizing white blood cells with local image descriptors

作者：

Highlights：

• We address the problem of recognizing 6 types of white blood cells from images.

• The methodology of local image descriptors and the bag-of-words is explored.

• Three keypoint detectors and five sampling strategies are studied and compared.

• Results are competitive with a simple, general and segmentation-free approach.

摘要

•We address the problem of recognizing 6 types of white blood cells from images.•The methodology of local image descriptors and the bag-of-words is explored.•Three keypoint detectors and five sampling strategies are studied and compared.•Results are competitive with a simple, general and segmentation-free approach.

论文关键词：White blood cells recognition,Local image descriptors,SIFT,Interest point detectors,Visual vocabulary

论文评审过程：Received 13 January 2018, Revised 27 July 2018, Accepted 15 August 2018, Available online 21 August 2018, Version of Record 9 September 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.08.029