"

Cookies ussage consent

Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.

A new method for segmentation of microscopic blood cell images by using histogram based automatic thresholding

RESUL COTELI1,* , TURKER TUNCER2, ENGIN AVCI3, MEHMET USTUNDAG4, ESIN DOGANTEKIN5, AKIF DOGANTEKIN6

Affiliation

  1. Firat University, Faculty, Energy Systems Engineering, 23119, Elazig, Turkey
  2. Firat University, Technology Faculty, Software Engineering, 23119, Elazig, Turkey
  3. Firat University, Technology Faculty, Digital Forensic Engineering, 23119, Elazig, Turkey
  4. Bıngol University, architecture-Engineering Faculty, Electrıcal-electronics Engineering, 12000, Bıngol, Turkey
  5. Ministry of Health, 27100, Gaziantep, Turkey
  6. Emek Hospital, 27100, Gaziantep, Turkey

Abstract

In this study, a novel thresholding algorithm based on histogram shape (TAHS) is proposed for determining the multiple thresholding. In the proposed thresholding method, histogram is divided into smaller windows with same size. In the proposed method, the biggest difference between pixel intensities is found. The proposed method is applied to blood cell images and is compared with Otsu method for a better validation. Advantage of the proposed method is that one or more thresholding points can be obtained. Therefore, objects with different spatial feature can be detected successfully. The experimental studies show that TAHS method gives satisfactory thresholding results..

Keywords

Image segmentation, Automatic image thresholding method, Microscopic blood cell images, Multiple thresholding method, Histogram shape.

Citation

RESUL COTELI, TURKER TUNCER, ENGIN AVCI, MEHMET USTUNDAG, ESIN DOGANTEKIN, AKIF DOGANTEKIN, A new method for segmentation of microscopic blood cell images by using histogram based automatic thresholding, Optoelectronics and Advanced Materials - Rapid Communications, 11, 7-8, July-August 2017, pp.430-435 (2017).

Submitted at: Feb. 4, 2017

Accepted at: Aug. 9, 2017