Scribd
Upload
42 views16 pages

Blood Detection Using Image

The document outlines a mini project on blood group detection using image processing techniques, highlighting the advantages of automation in medical diagnostics. It discusses the methodology, including the use of digital images and algorithms to classify blood types based on visual features. The project aims to provide a faster, more accurate, and cost-effective solution for blood group identification.

Uploaded by

4MU22CS071
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
42 views16 pages

Blood Detection Using Image

The document outlines a mini project on blood group detection using image processing techniques, highlighting the advantages of automation in medical diagnostics. It discusses the methodology, including the use of digital images and algorithms to classify blood types based on visual features. The project aims to provide a faster, more accurate, and cost-effective solution for blood group identification.

Uploaded by

4MU22CS071
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

MYSURU ROYAL INTITUTE OF TECHNOLOGY

Department of Computer Science and Engineering


Mini Project
On
“Blood Group Detection Using Image Processing”

Presented By, Under the guidance of


NISHCHITHA R [4MU22CS056] SUSHMA S
NITHYASHREE L [4MU22CS057] Assistant Professor
RASHMI M [4MU22CS071] Dept.of.CSE
SAVITA RAMESH NAIK[4MU22CS076]
CONTENTS

 Abstract
 Introduction
 Literature Survey
 System Requirements
 System Design
 Implementation
 Result
 Conclusion
 Reference
ABSTRACT

 Traditional blood group detection is time-consuming and error-prone.

 Image processing techniques are used to analyze blood sample images.

 Relevant features (color, texture, shape) are extracted from the images.

 Image processing algorithms classify images into different blood groups.

 Image processing offers a potential solution for faster and more accurate blood

group detection.
INTRODUCTION
 Blood group identification is an essential part of medical diagnostics and
transfusion treatment procedures.

 It's a technique that uses computer vision and image processing to detect a
person's blood group from a digital image of their blood sample.

 Blood group detection using image analysis leverages modern technology to


automate and enhance traditional blood typing methods.

 This approach uses digital images of blood samples processed through advanced
algorithms to determine blood types based on visual patterns and reactions.
LITERATURE SURVEY
 Kaur et al. (2018): Used a digital camera to capture images of blood
samples.
 Singh et al. (2019): Used a smartphone camera to capture images of blood
samples.
 Kumar et al. (2020): Used Gaussian filtering to remove noise from images.
 Sharma et al. (2020): Used thresholding and edge detection to segment
blood cells from the background.
 Kaur et al. (2018): Applied watershed transform to segment overlapping
blood cells.
SYSTEM REQUIREMENTS
Hardware Requirements
 Front End: HTML,CSS
 Back End: Python
 Language: Python 3.8

Software requirements
 Hard Disk: Minimum 20 GB
 RAM: Greater than 4 GB
 Processor: 13 and Above
 Editor: Visual Studio Code
SYSTEM DESIGN
IMPLEMENTATION
 Techniques: Tkinter ,OpenCV ,NumPy ,Matplotlib, Pillow.

 A blood sample is mixed with a reagent that reacts with the blood cells to produce

a visible pattern.

 A digital image of the blood sample is captured using a camera or smartphone.

 The image is then processed using computer algorithms to enhance the quality
and extract features from the image.

 The extracted features are then compared to a database of known blood group

patterns to determine the person's blood group.


RESULTS

Fig : Terminal Output


RESULTS

 Fig : Experimental Setup


RESULTS

 Fig : Experimental Outcome


RESULTS

 Fig : Experimental Observation


RESULTS

 Fig : Final Output


CONCLUSION
 Blood group detection using image processing is fast and cost-
effective.

 It uses techniques like color detection to ensure accurate results.

 The method is adaptable to low-resource and emergency settings.

 Image quality challenges can be resolved with advanced algorithms.

 AI integration makes it scalable and accessible for healthcare.


REFERENCE

 Hafeez, S., & Awais, M. (2015). Image processing based blood group detection
 Bansal, A., Jain, R., & Vyas, V. (2013). Automated system for ABO-RH blood
group detection using neural network.
 Nayak, V., Kamath, S., & Pai, M. (2016). Automated blood group detection using
image processing techniques.
 Anwar, N., & Islam, M. Z. (2017). ABO and Rh blood group detection using
image processing and machine learning
Thank You

You might also like