From the course: Computer Vision on the Raspberry Pi 4
Join today to access over 22,700 courses taught by industry experts or purchase this course individually.
Understanding Support Vector Machines (SVMs)
From the course: Computer Vision on the Raspberry Pi 4
Understanding Support Vector Machines (SVMs)
- Once you've obtained a set of feature descriptors, the next step is to send them to a classifier, such as a support vector machine or SVM. This video explains what SVMs are and how they work. To use open CV's SVM class, you only need three lines of code. The first creates the SVM and the second calls it to train method. Train, accepts a set of vectors and their labels, and it teaches the SVM how to classify vectors into categories. The last step calls predict to classify an unknown vector. If a vector has 'n' element, you can think of it as a point 'n' dimensional space. This slide illustrates points in two sets, A and B, which are separated by lines L1 and L2. L1 and L2 are called boundaries because they separate the points into two sets. L2 is a better boundary because it's points are further away from this point in set A and set B. The goal of an SVM is to find the best boundary that separates sets of points.…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.