Car Make and Model Recognition, otherwise known as Make and Model Recognition (MMR) system is our project. This project incorporates image processing method sand machine learning techniques to recognize and classify vehicles according to their make and model. The aim of this project is to develop a software system that takes an image or video feed as input; process it using image processing techniques, and then use machine learning to recognize and classify the make and model of the vehicle.
when an image of a Honda Civic is loaded as an input to the system, it should classify the make as “Honda” and model as “Civic”, with a satisfactory accuracy. This project illustrates the methods and implementation of Car Make and Model Recognition CMMR system. Development platform was MATLAB, project included built-in MATLAB functions, and the User Interface(GUI) is implemented using MATLAB GUI developer.
A number of image processing techniques are used for feature extraction, such as SURF (speeded up robust features), SIFT (scalar invariant feature transform), HOG(histogram of oriented gradients), cross correlation, peak correlation and edge detection. Various filters are also used to extract special information such as edges, intensities, colour information and a lot more, for training a neural network. The machine learning algorithms used in this project include Convolutional Neural Networks, Deep Neural Networks, Transfer Learning, Support Vector Machines(SVM) classifier, and a Bag-Of-Features model
Keywords:
vehicle classification; target detection; compressed sensing; convolutional neural network; machine learning algorithms.
Install the packages /Libraries
Import the dependencies / libraries import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.tree import DecisionTreeClassifier