krishna111809/fingerprint-based-blood-group-detection
This repository presents an innovative approach to classifying blood groups using fingerprint images through deep learning techniques. The project explores state-of-the-art convolutional neural network (CNN) architectures, such as ResNet, VGG16, AlexNet, and LeNet, to analyze and predict blood groups accurately.
The project implements transfer learning with PyTorch across four CNN architectures, training on ~6,000–7,000 fingerprint images categorized into eight blood group types (A+, A−, B+, B−, AB+, AB−, O+, O−). Each model includes dedicated Jupyter notebooks for end-to-end training and evaluation, with systematic storage of training metrics (accuracy, validation loss curves) and comparative performance bar graphs to assess architecture effectiveness.
No commits in the last 6 months.
Stars
43
Forks
25
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/krishna111809/fingerprint-based-blood-group-detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
iArunava/Malaria-Detection-using-Keras
Malaria Detection using Deep Learning from Images made available publicly from NIH
sauravmishra1710/Malaria-Detection-Using-Deep-Learning-Techniques
Malaria Parasite Detection using Efficient Neural Ensembles. Malaria, a life threatening disease...
wObbLee00/Non-Invasive-Blood-Group-Prediction-Using-Fingerprint-Analysis
End-to-end system for non-invasive blood group prediction using fingerprint images, built with...
aniketpatilanalyst/Disease-Prediction-Model
Prediction Model on Cell Images for Detecting Malaria
mdhabibi/CNN-Predictor-for-Malaria_Cells-LIME-CAM
Enhanced CNN model for malaria cell classification, featuring Class Activation Mapping (CAM) as...