What is image classification?

Image classification, also known as image recognition, is used to classify an image based on its features. It has several practical applications, such as object detection, object recognition in self-driving cars, anomaly detection in medical images, image classification in social media posts, and more. The following block diagram illustrates how images are classified:

Support vector machines

A support vector machine (SVM) is a supervised ML approach that can be used to develop classification and regression applications. However, it’s mostly used for classification. A SVM constructs a decision boundary that can divide high-dimensional space to classify new data points. The decision boundary is created by selecting the extreme points, known as support vectors.

For example, a dataset containing images of cats and dogs can construct a model that differentiates cats and dogs using a SVM. First, the model is trained with images to learn the respective features of cats and dogs. As a result, the SVM generates a decision boundary between cats and dogs and chooses extreme cases (support vectors). The SVM then categorizes the new image as a cat or dog based on the decision boundary and support vectors, as shown below:

Introduction to the Course

Getting Started

Understanding Noisy Data, Label Noise, and Its Types

Introduction to Convolutional Neural Network (CNN)

Cats vs Dogs Classification with Convolutional Neural Networks

Performance Comparison of Mislabeled and Clean Dataset

Dealing with Imbalance Dataset

Gauge the Impact of Imbalanced and Mislabeled Datasets

Comprehensive Quiz

Wrap Up

Appendix

Dealing With Small Datasets In ML

Image Classification

What is image classification?

Support vector machines