tanziyaya/svmhogclass

Pedestrian classification from photos using the Linear SVM and HOG features in INRIA dataset

Pedestrian classification from photos using the Linear SVM and HOG features

Introduction to HOG

HOG is an acronym for Histogram of Oriented Gradients. It's an algorithm called a feature descriptor which helps with object detection in computer vision and image processing models. HOG is a kind of feature descriptor that counts occurrences of gradient orientation in localized portions of an image.

The INRIA Person dataset

Summary

After working through this tutorial you learned:

• What is HOG and how to use it
• What is Computer Vision
• How to use ready dataset
• What is classification
• The basics of OpenCV, Scikit-learn and Scikit-image

If you have any questions about the project or this post, please ask your question in the comments.

You can run the project in your browser or download it from GitHub.

Resources

1. INRIA Person dataset