Performance Analysis of Multimodal Biometric Security System using Palm and Face Recognition
Scenario -1 Using Resnet Model:
————————————–
Implementation Plan:
—————————
Step 1: Initially, we collect the Dataset based Palm and Face Images individually and Organize the Labels based Dataset Sub-folder.
Step 2: Next, we train the Face Recognition model based on the Face Images using Convolutional Neural Networks (CNNs).
Step 3: Next, we train the Palm Recognition model based on the Palm Images using Convolutional Neural Networks (CNNs).
Step 4: We collect biometric data (face, palm, or both (face and palm)) via webcam, preprocess it using augmentation and ROI extraction, and register the user by storing their details along with extracted embeddings in organized folders based on the selected mode.
Step 5: Next, we apply the trained model for face, palm or multimodal fusion for the user verification process based on selected biometric mode.
Step 6: Next, we implement User Management Functionality such as Listing Registered User and Removing Existing User.
Step 7: Finally, we plot performance for the following metrics:
7.1: RMSE
7.2: Dice Score
7.3: System Overhead
7.4: Feature Count
7.5: Recall Rate
7.6: Sensitivity
7.7: Accuracy
7.8: Decision Time
Scenario -2 Using EfficientNet:
————————————-
Implementation Plan:
—————————
Step 1: Initially, we collect the Dataset based Palm and Face Images individually and Organize the Labels based Dataset Sub-folder.
Step 2: Next, we train the Palm Recognition model based on the Palm Images using EfficientNet Model.
Step 3: Next, we train the Face Recognition model based on the Face Images using EfficientNet Model.
Step 4: We collect biometric data (face, palm, or both (face and palm)) via webcam, preprocess it using augmentation and ROI extraction, and register the user by storing their details along with extracted embeddings in organized folders based on the selected mode.
Step 5: Next, we apply the trained model for face, palm or multimodal fusion for the user verification process based on selected biometric mode.
Step 6: Next, we implement User Management Functionality such as Listing Registered User and Removing Existing User.
Step 7: Finally, we plot performance for the following metrics:
7.1: RMSE
7.2: Dice Score
7.3: System Overhead
7.4: Feature Count
7.5: Recall Rate
7.6: Sensitivity
7.7: Accuracy
7.8: Decision Time
Scenario -3 Using MobileNet V2:
————————————–
Implementation Plan:
—————————
Step 1: Initially, we collect the Dataset based Palm and Face Images individually and Organize the Labels based Dataset Sub-folder.
Step 2: Next, we train the Palm Recognition model based on the Palm Images using MobileNet V2 Model.
Step 3: Next, we train the Face Recognition model based on the Face Images using MobileNet V2 Model.
Step 4: We collect biometric data (face, palm, or both (face and palm)) via webcam, preprocess it using augmentation and ROI extraction, and register the user by storing their details along with extracted embeddings in organized folders based on the selected mode.
Step 5: Next, we apply the trained model for face, palm or multimodal fusion for the user verification process based on selected biometric mode.
Step 6: Next, we implement User Management Functionality such as Listing Registered User and Removing Existing User.
Step 7: Finally, we plot performance for the following metrics:
7.1: RMSE
7.2: Dice Score
7.3: System Overhead
7.4: Feature Count
7.5: Recall Rate
7.6: Sensitivity
7.7: Accuracy
7.8: Decision Time
Software Requirements:
—————————–
1. Development Tool: Python 3.11.4 or above
2. Operating System: Windows-10(64-bit) or above
Note :-
——–
1) If the plan does not meet your requirements, provide detailed steps, parameters, models, or expected results in advance. Once implemented, changes won’t be possible without prior input; otherwise, we’ll proceed as per our implementation plan.
2) If the plan satisfies your requirement, Please confirm with us.
3) If you have any changes in the Dataset , kindly provide before implementation. Our work is completely based on dataset values.
4) Please understand that any modifications made to the confirmed implementation plan will not be made after the project development.
