Object Detection in a Cluttered Scene Using SURF for Computer Assisted Histopathology

DOI

10.2991/icemie-16.2016.56How to use a DOI?

Keywords

computer vision; surf; ransac; computer assisted diagnostics; histopathology

Abstract

Computer vision imitates human vision ability to perceive real world. Computer vision has proven its part from autonomous navigation on martin surface to histopathology images recognition. In practice, histopathologists examine microscopic imagery of diseased tissue and diagnose on the bases of malignancy, likewise a computer assisted diagnosis (CAD) system is devised for histopathology images recognition on the basis of visual features. This paper describes the design methodology, workflow and test results of locating an object in a cluttered scene. In this paper speeded up robust features are used for feature extraction and matching. After object detection, Random sample consensus is used for removing outliers to refine results. This CAD system provides a heuristic approach to assist histopathologists in diagnostics.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Aqeel Abbas
AU  - Talat Zehra
AU  - Fu Li
PY  - 2016/04
DA  - 2016/04
TI  - Object Detection in a Cluttered Scene Using SURF for Computer Assisted Histopathology
BT  - Proceedings of the 2016 International Conference on Electrical, Mechanical and Industrial Engineering
PB  - Atlantis Press
SP  - 224
EP  - 227
SN  - 2352-5401
UR  - https://doi.org/10.2991/icemie-16.2016.56
DO  - 10.2991/icemie-16.2016.56
ID  - Abbas2016/04
ER  -