Scribd
Upload
3 views3 pages

Signature Identification Report

Uploaded by

C28Jain Sanjita Sanjay
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
3 views3 pages

Signature Identification Report

Uploaded by

C28Jain Sanjita Sanjay
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

K. K.

Wagh Institute of Engineering


Education & Research, Nashik
DEPARTMENT OF COMPUTER ENGINEERING

A Project Report
On
“Signature Identification Using Convectional Neural Networks”

Submitted by
Rupprashik Anand Khare (BE_A_54)

In partial fulfillment of
BACHELOR OF ENGINEERING

In

Computer Engineering

Savitribai Phule Pune University, Pune

INTRODUCTION
Signature identification is a crucial application of pattern recognition in security systems.
The goal is to create a system that can identify or verify the authenticity of a signature. In
this project, we develop a machine learning-based approach using Convolutional Neural
Networks (CNNs) to identify signatures from a data-set of student signatures collected from
our college.

OBJECTIVE
To develop an application for signature identification using CNNs by creating a custom data-
set of signatures from college students.
H/W AND S/W REQUIREMENTS

Hardware Requirements:
- Processor: Core i5 or higher

- RAM: 8GB or higher

- Storage: 500 GB HDD

Software Requirements:
- Python 3.7+

- Libraries: TensorFlow, Keras, OpenCV, scikit-learn

THEORY CONCEPTS
Convolutional Neural Networks (CNNs) are deep learning models that are particularly
effective for image classification tasks. They use convolution layers to extract features from
input images, followed by dense layers that classify the image based on the extracted
features. In this project, each student's signature is treated as a class, and the CNN model is
trained to classify images of signatures into their respective classes.

ALGORITHM

1. Data Collection:
Collect signature images from students, label them, and organize them into folders for each
student.

2. Prepossessing:
Convert images to grayscale.
Resize images to 128x128 pixels.
Normalize pixel values.

3. CNN Model:
Two convolution layers with ReLU activation.
Max-pooling layers to reduce dimensionality.
Dense layers for classification.

4. Training:
Train the model on the preprocessed dataset.
Use a portion of the data-set for testing and validation.

5. Evaluation:
Evaluate the model's performance using accuracy as a metric.
CONCLUSION
The project successfully implemented a Convolutional Neural Network (CNN) to identify
student signatures from a custom data-set. The model demonstrated high accuracy,
showcasing the effectiveness of CNNs for signature identification.

You might also like