Welcome to SPLab

The SPLab research group is a part of Brno University of Technology and is involved in fundamental and applied research in the fields of voice, image, video and text processing. We can offer advanced technologies and also customized solutions in variety of industry fields and we have long-term experience in cooperation with many national and international subjects all over the world.

IMMI - Rapidminer 5 Image Mining Extension

RELEASE 1.4.0 (May 2012)

IMMI has moved to http://splab.cz/immi...

Read more...

IMMI3D - RapidMiner 5 3D image mining extension

Tool for mining data form 3D images based on IMMI extension.

AUMI - Rapidminer 5 Audio Mining Extension

Tool for mining data from audio.

SPLab International Workshop 2011

On the 27th and 28th October 2011, our lab will be hosting the international workshop. About 15 scientists from abroad as well as several members of SPLab will present their work. For details see this page.

Emotion Recognition from Czech Texts

Rapidminer 5 OpenCV Extension

We have started support of Rapidminer OpenCV Extension. The Rapidminer OpenCV Extension is an extension of RapidMiner 5.0 platform for OpenCV library function. The OpenCV librar supports more than 500 different functions for image processing and image mining.

JEF - Grammar Guided Genetic Programming

Description:

Evolution Framework is a software library for working effectively with evolutionary computation techniques based on techniques of genetic algorithms and grammar guided genetic programming. The library is designed universally and it is possible to program own modules that extend and complement existing functionality. Library helps to achieve, with appropriate combination of input parameters, a satisfactory solution of problems classified as NP-complete. The library is implemented in Java.

Ultrasound image database

The image database contains 84 B-mode ultrasound images of common carotid artery (CCA) in longitudinal section. The database contains images of CCA of ten young healthy volunteers (mean age 27.5  +/- 3.5 years) with different weight (mean weight 76.5 +/- 9.7kg). Images were acquired with Sonix OP ultrasound scanner with different set-up of depth, gain, time gain compensation (TGC) curve and different linear array transducers. The resolution of images is approximately 390x330px. The exact resolution depends on the set-up of the ultrasound scanner.

The database can be downloaded here.

Towards an Automatic Construction of Machine Vision Systems on Ultrasound Images

In this section you will find data sets, which can be freely downloaded and used in your research work. Also you will find grammar used in our research in paper "Towards an Automatic Construction of Machine Vision Systems on Ultrasound Images".

This dataset contain 72 different video-sequences. Common carotid artery (CCA) in its transversal section is depicted in this video-sequence. The position and radius of the CCA in the first image of vide-sequence is noted as separate text file.

Download:

• IMT database
• Grammar used in paper "Towards an Automatic Construction of Machine Vision Systems on Ultrasound Images".

Original paper:

This article describes a novel method for the localization of CCA in the transverse section of a B-mode ultrasound image. The method is tested on a validation database of CCA images that was specially created for this purpose and released for use by other scientists. The resulting success of the proposed solution was 82.7%, which exceeded the current state of the art by 4% while the computation time requirements were acceptable.The paper also describes an automatic method that was used in designing the proposed solution. This automatic method provides a universal approach to designing complex solutions with the support of evolutionary algorithms.