Login Register



Auto-login on future visits

Forgot your password?

Newsletter November-December 2011

Interactive thresholding

Tutorial part 2: Building a classifier by thresholding

In the previous tutorial we have seen how to build a hyperspectral classifier for French fries sorting. Today we will discuss how to quickly build an object detector. Do we always need a complex classifier? Not really, sometimes we can do the job, or part of it, with a simple threshold. In this tutorial we will see how to build a classifier interactively by thresholding one feature.
Check out this short video! (4 min).

Cancer detection

Histoscanning by AMD logo

Customer story

Advanced Medical Diagnostics has brought to market a new generation of cancer-detection ultrasound technology, providing physicians with clinically-meaningful visualization of prostate cancer. Dror Nir, CEO of Advanced Medical Diagnostics, says: We use perClass to train our tissue characterization algorithm, that is- to train a classifier to detect abnormalities in ultrasound data taken in clinical setting. We work with huge data sets and dozens of features, and perClass is able to handle them without performance issues or glitches... read more

impressions from Vision trade fair

Decisions trees and random forest

Feature Highlight

perClass 3.1 has introduced the decision tree and the random forest classifiers, that are fast and scalable to large data sets. In this knowledge base article perClass sdtree is compared with the state-of-the-art implementations of C4.5 and PRTools.

Impressions from Vision 2011 trade fair

our booth at Vision

Last November we have presented the perClass software suite at the Vision 2011 trade fair in Stuttgart. It is the largest European fair in machine vision, with exhibitors ranging from machine vision components to complete system solutions, from software to services.
Companies and visitors came from across the globe. We really enjoyed meeting many people interested in adding more intelligence to their machine vision systems or improving performances. The general feeling is that people expect automation to deliver more. For example, dealing with natural objects greatly increases the challenges imposed on automatic classification systems. People are looking for new or better solutions. Our visitors were intrigued by the possibilities of statistical machine learning in perClass. With perClass they can quickly develop their own solutions in-house, saving a lot of time both in the design phase and when embedding the classifiers in their application. See our new brochure.
And, by the way, thanks to all of you that came by to our stand. It was very nice to see you all in person!

impressions from Vision trade fair