ABSTRACT:
The human blood is a health indicator; it delivers necessary substances such as oxygen and substance that provides nourishment is necessary. Hence, segmentation of blood cells and identification of blood type is very important. The human blood consists of the RBCs, WBCs, Platelets and Plasma. Presently, lab technicians tests blood groups manually and they use a device called Hemocytometer and microscope to count blood cells. But this method is extremely time consuming, monotonous and leads to the inaccurate results due to human errors. To overcome the problems regarding time, accuracy and cost, a method is proposed based on processing of images acquired from laboratory The image processing techniques such as Segmentation, Morphological operations. Disease detection based on machine learning we have applied Accuracy of the system is high with very low execution time.
INTRODUCTION:
Blood cell segmentation and identification is a vital task in the study of blood as a health indicator. A complete blood count is used to determine the state of a person’s health based on the contents of the blood in particular white blood cells and the red blood cells. The main problem arises when massive amounts of blood samples are required to be processed by the hematologist or Medical Laboratory Technicians. The time and skill required for the task, limits the speed and accuracy with which the blood sample can be processed. This will aim to provide user-friendly software that allows quick user interaction with a simple tool for counting red and white blood cells from a provided image.
Conducting blood tests using the old conventional method of counting blood cells under microscope is time-consuming and may lead to inaccurate results. For this reason, hardware solutions such as Automated Hematology Counter was developed and used in most hospitals. Unfortunately, this device is way too expensive for a developing country or rural areas. On the other hand, the existing systems that use image processing in analysing microscopic images of blood lack other blood parameters and is limited to only one cell.Since rural areas often have fewer doctors or specialists might not be available at all, and providing equipment such as Automated Hematology Counter for blood analysis is quite unfeasible, the researchers came up with the study of developing an image processing software-based cost effective android application that will recognize and count the blood cells, and that enables the doctors from rural areas to easily send the result to other specialist for further diagnosis.
Blood cell counting is nothing but the complete blood count (CBC) which refers to compilation test for all type of cells including red blood cells (RBC), white blood cells (WBC), platelet, hemoglobin and hematocrit. Each of them has their role in body system and the counting result is used to determine the capability or deficiency of the body system. Any abnormal reading of any of these cells can give the sign of disease or infection.
OBJECTIVE:
The main objective of out proposed method is to detect number of WBC and RBC present in microscopic image of Blood, and to find that person is diseased or not.
PROBLEM STATEMENT:
Conducting blood tests using the old conventional method of counting blood cells under microscope is time-consuming and may lead to inaccurate results.