Scribd
Upload
44 views2 pages

Eyesweb User'S Tutorial #1 Reading From A Movie File and Extracting Edges

This document provides a tutorial on using EyesWeb software to read movie files, extract edges, and display the results. It describes several processing blocks: a multimedia file reader to extract frames from a video; a color to gray converter; a converter to change image properties; a Canny corner detection algorithm; and a display block. It explains that the multimedia reader and Canny detector require certain image formats, so the color and property conversion blocks are used to prepare the input images.

Uploaded by

apoddar_26
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
44 views2 pages

Eyesweb User'S Tutorial #1 Reading From A Movie File and Extracting Edges

This document provides a tutorial on using EyesWeb software to read movie files, extract edges, and display the results. It describes several processing blocks: a multimedia file reader to extract frames from a video; a color to gray converter; a converter to change image properties; a Canny corner detection algorithm; and a display block. It explains that the multimedia reader and Canny detector require certain image formats, so the color and property conversion blocks are used to prepare the input images.

Uploaded by

apoddar_26
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

DIST - University of Genova

Laboratorio di Informatica Musicale (InfoMus)


http://www.infomus.dist.unige.it

EyesWeb User’s Tutorial #1


Reading from a Movie File and Extracting Edges
By Riccardo Trocca ([email protected])

This brief tutorial introduces some important concepts of the EyesWeb Software
Environment.
The first block is a ‘Multimedia file read’ block (Imaging->Input->Multimedia file read):
it can read an AVI or mpeg file and extract its frames.
It is important to notice the ‘Start’ button. This button sends a signal to the block
whenever the patch is locked and run. It is necessary to use it, or the ‘Multimedia file
read’ block will never start reading anything!

The second block is called ‘Color To Gray’ (Imaging->Conversion->ColorToGray), it


takes as input a colored image and outputs a corresponding gray scale image.

The third block is a conversion block (Imaging->Conversion->convert). It can change


three different characteristics of the input image:
• Color depth
• Color channel ordering
• Origin

Usually the output of the ‘multimedia file read’ block is a 24 bit images, it means that it
uses 3 channel of 8 bits depth (unsigned). This can be changed in order to perform
different operations. An example can be the creation of a floating point image.

With the partial support of the EU IST Projects CARE HERE (Creating Aesthetically Resonant
Environments for the Handicapped, Elderly and Rehabilitation) no. IST-2001-32729, and MEGA
(Multisensory Expressive Gesture Applications) no. IST-1999-20410 (www.megaproject.org)
The third feature is the origin of the coordinate system of the image. Usually windows
images have a bottom left origin, while some blocks that use routine from the Open
Computer Vision libraries need images with a top left origin. This can be provided by the
convert block.
The fourth block is Imaging->FeatureCalc->CannyCornerDetect and it uses the Canny
corner detection algorithm. This block is implemented through a call to the OpenCV
libraries. It can be useful to consult the CV libraries reference on the sourceforge site in
order to understand the meaning of each parameter.
Because of this last block it is necessary to use the 2 conversion block (ColorToGray and
Convert). Actually it can operate just on gray level images with a top left origin.
The last block is the display block (Imaging->Output->Display). It simply opens a
window to show the images that it receives as inputs. It is possible to resize the output
window, choose the stretching algorithm and also make it full screen. It is possible to go
full screen without changing the screen resolution, but it is not a wise choice many times,
because the image has to be resized in order to fit a possibly very large screen, resulting
in poor performances.

You might also like