Practical no:-2

ABSTRACT

Abstract of the Project: Vehicle Ignition System with Face Detection and Aadhaar-Based Age
Verification

This project is designed to make vehicles safer by adding a face recognition system and Aadhaar-
based age verification to the ignition process. When someone tries to start the vehicle, the system
checks their face and matches it with the Aadhaar database to verify their age. If they meet the legal
driving age, the vehicle starts; otherwise, it stays locked. This technology helps prevent underage
driving, reducing the chances of accidents and improving road safety.
 Practical no:-3

Literature Survey

1. Introduction to Vehicle Safety and Access Control

Vehicle safety has become increasingly important with the rise in road accidents, many of
which involve unauthorized or underage drivers. Traditional vehicle access control methods
rely on keys or key fobs, which can easily be misused or handed over to others. To counter
this, advanced technologies such as biometrics and identity verification systems have been
explored. A key focus in recent research is the use of face detection and Aadhaar-based age
verification to prevent unauthorized vehicle access, ensuring only legally eligible individuals
can operate the vehicle.

2. Biometric Verification for Access Control

Biometric verification has been widely adopted across various fields due to its accuracy and
reliability. Face recognition, in particular, is gaining popularity in security and access control
systems because it uses unique facial features to verify identity. Studies have shown that face
recognition systems provide a high level of security compared to other biometric systems,
such as fingerprint or iris scanning, due to their non-intrusive nature and convenience for
users. The integration of face recognition in vehicle ignition systems provides a secure and
efficient way to control vehicle access.

3. Aadhaar-Based Age Verification

In India, Aadhaar is a unique identification system that contains personal details, including
age. Using Aadhaar for age verification adds an additional layer of security to the vehicle
access system. By cross-referencing the driver's age with their Aadhaar data, this project
ensures that only individuals of legal driving age can start the vehicle. Research on Aadhaar-
based verification has shown its effectiveness in secure authentication and eligibility checks
across multiple applications, making it an ideal choice for enforcing age restrictions in this
vehicle ignition system.

4. Integration of Face Detection and Aadhaar Verification

Combining face detection with Aadhaar-based age verification is a novel approach to vehicle
safety. This integrated system works by first identifying the individual through face
recognition, then confirming their eligibility to drive using Aadhaar-based age verification.
This dual-verification system prevents underage drivers from accessing the vehicle, thus
reducing the risk of accidents. Studies show that multi-layered authentication systems
improve security, as they require multiple verifications before granting access, reducing the
chances of unauthorized usage.
5. Benefits and Challenges

The primary benefit of this system is the enhanced security it offers, which goes beyond
traditional vehicle keys. By enforcing age-based access control, it helps reduce accidents
involving underage drivers. However, implementing such a system poses challenges,
including ensuring accurate face recognition in different lighting conditions and maintaining
data security for Aadhaar information. Additionally, users need to be educated about the new
technology to ensure smooth adoption.

6. Conclusion

In conclusion, the literature supports the effectiveness of biometric and Aadhaar-based

systems in enhancing security and preventing unauthorized vehicle access. The integration of
face recognition and Aadhaar verification provides a strong foundation for this project, which
aims to restrict vehicle use to eligible drivers, ensuring safer roads. Further research could
explore additional biometric features or integrate more comprehensive data for even greater
security and user convenience.
 Practical no:-4

Problem Definition (Identification)

The key problem addressed by this project is the issue of unauthorized and underage driving, which
contributes to road accidents and safety concerns. Traditional vehicle ignition systems do not restrict
access based on age, allowing underage individuals to operate vehicles if they have access to the
keys. This lack of age-based restriction poses significant risks, especially in countries like India
where driving laws require drivers to be of a certain age. The project aims to solve this by
integrating face detection and Aadhaar-based age verification, ensuring that only authorized and age-
eligible users can start the vehicle. This innovative approach combines biometric technology and
Aadhaar verification to improve vehicle safety and reduce accident risks associated with underage
drivers.

Proposed System

The proposed system aims to enhance vehicle security and prevent underage driving by combining
face detection and Aadhaar-based age verification. When a user attempts to start the vehicle, the
system captures their facial image and compares it with stored biometric data to verify their identity.
Simultaneously, it retrieves age information from the Aadhaar database to ensure the user meets the
legal driving age. Only if both identity and age are verified successfully will the ignition system allow
the vehicle to start. This approach ensures that only authorized, age-eligible users can operate the
vehicle, reducing accidents associated with underage driving.
Conclusion
The proposed Vehicle Control System aims to enhance safety, efficiency, and driving comfort by
integrating automated features such as collision detection, adaptive speed control, and intelligent
suspension adjustments.
 Practical no:5
Proposed Methodology of Solving identified problem
Problem 1: Lesion Classification
- Problem Statement: Accurately classify skin lesions into different disease categories (e.g.,
melanoma, basal cell carcinoma, psoriasis).

- Challenges:

- Variability in lesion appearance

- Overlapping features between diseases

- Limited training data

- Goals:

- Develop a robust lesion classification model

- Improve diagnostic accuracy

- Reduce false positives/negatives

Problem 2: Skin Disease Severity Assessment

- Problem Statement: Automatically assess the severity of skin diseases (e.g., psoriasis,
eczema, acne).

- Challenges:

- Subjective nature of severity assessment

- Variability in disease manifestation

- Limited annotated training data

- Goals:

- Develop a reliable severity assessment model

- Monitor disease progression

- Optimize treatment plans

Problem 3: Skin Disease Diagnosis from Medical History

- Problem Statement: Diagnose skin diseases based on patient medical history, symptoms, and
demographic information.

- Challenges:
- Incomplete or inaccurate medical history

- Complexity of disease-symptom relationships

- Limited data on rare diseases

- Goals:

- Develop a predictive model for skin disease diagnosis

- Improve diagnostic accuracy

- Reduce unnecessary testing and referrals

Some potential solutions to these problems include:

1. Deep learning-based image analysis

2. Natural language processing (NLP) for medical history analysis

3. Transfer learning from related medical domains

4. Ensemble methods combining multiple models

5. Active learning for selective data annotation

Would you like me to elaborate on any of these problems or solutions?

Conclusion
Hence we list here which problems are occur and also solve then and give their details
 Practical no:-6
Description of Modules
Skin disorders are illnesses that affect the surface of your skin. Rashes, inflammation, itching,
and other skin abnormalities may be caused by several disorders. Some skin disorders are
caused by genetics, while others are caused by lifestyle factors

MODULES
• Input Image
• Pre-Processing
• Segmentation
• Classification
• Performance metrics

1. Input Image: A Collection of data is called datasets. Let us consider, Skin disease
databases namely, normal and abnormal prediction of the patient. Here, an input data
can be obtained in the image format to predict the disease based on the Skin Disease
Detection.

2. Preprocessing: Data cleaning, smoothing, grouping or filtering the image. Data

can require preprocessing techniques to ensure accurate, efficient, or meaningful
analysis. Data cleaning refers to methods for finding, removing, and replacing bad or

missing data. Here, the Gaussian method is used in the Preprocessing techniques.

3. Segmentation: Image segmentation is the process of partitioning a image into

multiple segments (sets of pixels, also known as image objects). The goal of
segmentation is to simplify or change the representation of an image into something
that is more meaningful and easier to analyze. Image segmentation is typically used to
locate objects and boundaries (lines, curves, etc.) in images. More precisely, image
segmentation is the process of assigning a label to every pixel in an image such that
pixels with the same label share certain characteristics. Here, segmentation can be
 used in the FCM of the systemA FCM is a one type of technique is used to segment
the image from the input data.

4. Classification: Classification is a term used both about the process to classify

disease based on the normal and abnormal of the patient. A classification process can
be obtained to training the network of the system. Here, a classification techniques
can be obtained from using SVM model to classify the result of the model. Finally, the

performance of the system can be analysed.

Conclusion

Hence in this practical we can explain the overall project and give the list of all modules and
also explain each module step by step in detail also explain the Data flow Diagram, Use case
Diagram, Sequence Diagram, Activity Diagram of the Project (Skin Diseases Detection).
Data Flow Diagram
Activity Diagram

Use Case Diagram

Sequence Diagram