Code and documentation of Shapes Classification using SVM Project

Code and documentation of Shapes Classification using SVM Project

Project Domain/Category

Image Processing

Abstract / Introduction

Image processing is a method of performing operations on an image in order to improve it or obtain useful information from it. Image processing has various applications in fields such as medical, defense, industry, remote sensing, pattern recognition, and video processing, among many others.

In this project, we will create an application that should identify different objects like rectangles, squares and circle,s etc., based on their features from the input image.

Functional Requirements:

1. For this application, you should use 4 shapes i.e., square, circle, rectangle, and star.
2. Use 10 different sizes for each of the shapes.
3. Create 10 images of each of the shapes and sizes using jpeg format in MS paint or any other software.
4. All the images should have an equal height and width of 128 X 128 pixels.
5. All the images should have black and white. Black shape with white background.
6. The complete dataset should consist of 400 images.
7. Divide the dataset into 70% training set to train a model and 30% testing set to test the trained model. The division should not be biased.
8. You should use a Support Vector Machine (SVM) for the classification.
9. Extract features from the images using different built-in functions of MATLAB like regionprops() etc.
10. Train the SVM model using the training dataset.
11. Test the SVM model using the test dataset.
12. The system should have the capability to test the complete testing set and then generate the accuracy report for all the shapes.
13. The system should also have the capability to test a single image.
14. You should create a proper interface for all these activities.
15. You should use different built-in functions of MATLAB where applicable.

Tools & Technologies:

Preferred tool and technology: MATLAB (Any latest version of MATLAB)

Class diagram, activity diagram, data flow diagram, sequence diagram, use case diagram, Use case description, scope, hard requirements, non-functional requirements, testing test cases, SRS document, design manual, and other diagrams are needed to draw for this project.