Login Register



Auto-login on future visits

Forgot your password?

All videos


Deep Learning step-by-step in perClass 5

In this tutorial, we discuss basics of convolutional neural networks and show an example how you can build your own network in perClass 5 with one command.

Deep Learning coming to perClass

Convolutional neural networks show strong performance in many image classification tasks. We've been hard at work bringing the power of deep learning into perClass. In this 3 min video, we show you the first example of running a deep network in perClass.

Avoiding specific errors with cost-sensitive optimization

This tutorial shows how to minimize some specific errors, important in our application, using ROC cost-sensitive optimization

Interactive tools to choose a good classifier trade-off

New tool helps us to interactively select the best error classifier trade-off helpful especially in multi-class situations.

Flower classification by perceptual similarity measure

Flower classification is difficult due to high image variability. This video shows live demo of Alstroemeria classification using perceptual similarity meaure.

Building outlier removal in a classifier

Outlier removal is an important initial step for almost any machine learning project. In this real-world example, we show how to clean our data set and how to include outlier removal into the final classifier.

How to run a classifier in a C++ application?

In this example of wood defect detection, we illustrate how to run a classifier out-of-Matlab, directly in your application. First we design a good classifier. Then we use perClass SDK to export the classifier and load it into the C++ application.

VISION14 talk: Machine learning for next generation vision applications

How can machine learning help us to develop next generation applications? Recording of our presentation at Industrial Vision Days conference accompanying VISION14 Trade Fair in Stuttgart, Germany.

Object detection

This video shows how to detect objects in an image using machine learning tools. First we use a classifier to detect candidate regions, and then a powerful segmentation tool to identify each object.

Labeling image by clustering

This video shows step by step process of labeling hyperspectral image using cluster analysis, renaming and merging of the clusters and training a classifier.

Page 1 of 4 pages  1 2 3 >  Last » | Next Page