Využití "random forestů" pro rozpoznávání objektů v obrazech

Abstract

The aim of this master's thesis is to describe use of Random Forest and its ability to recognize objects in images. The theoretical part deals with terminology and process of assembling decision tree and Random forest. The practical part compares success rate and duration of image classification using Random forest and SVM methods. Thereafter a program for detecting vehicles at the junction is created.

Description

Import 23/08/2017

Subject(s)

Image processing, Decission tree, Random forrest, SVM, HOG, OpenCV, C++

Citation