The TINA algorithm development libraries have been developed over a number of years to simplify the task of vision algorithm development and evaluation.  They are the result of over 50 man years of vision research at the University of Sheffield, in the UK. 

The libraries have been written in ANSI C and provide an infrastructure for algorithm development.  Full source code is available and can be compiled on any Unix/Linux platform running X using the GNU C compiler gcc.  Functionality in the libraries includes; 

  • Data structures and I/O mechanisms for different image types including char, int, float, double and complex 
  • Functionality to manipulate and display images together with overlay information 
  • Image processing functions such as gradient filters, morphological operators, convolutions structures 
  • Data structures and functionality for mathematical constructs such as vectors, matices and geometric types, as well as many popular and useful minimisation, statistical analysis and many other mathematical routines
  • Low-level vision algorithms such as edge and corner extraction 
  • Functionality to support tool development under the X windows interface 
  • The Department of Electrical and Electronic Engineering at the University of Sheffield offers a range of  downloadable demonstrations of vision algorithms that have been researched and written using the TINA developement libraries.  These can be found by following the link to the TINA  url given below.  Both online and downloadable versions of the TINA user and programmers guides are also available from this site.

Current Version:   3.0

License Type:   Remains the intellectual property of the University of Sheffield, UK.

Home Site:

Source Code Availability:   Yes

Available Binary Packages:

  • Debian Package:   No
  • RedHat RPM Package:   No
  • Other Packages:   No

Targeted Platforms:

Most (all?) Unix workstations, typically Sun Sparc SunOS/Solaris, PC/Linux

Software/Hardware Requirements:

X windows, gcc prefered

Other Links:

Mailing Lists/USENET News Groups:


User Comments:

  • None

See A Screen Shot?

This screen shot shows a top-level TINAtool and 2 Tv screens used to display image data.  TINAtools can display images, graphs and other graphics using Tvs (New Tvtool); adjust the colourmap, print screens, make animations and other assorted display options (View); display 3D data as a surface terrain with various lighting and mapping options (Terrain);  save user interactions with TINA in macros so that sequences of common button and field interactions can be replayed easily. This TINAtool is equiped with the ability to analyse mono and stereo images as well as sequences of mono or stereo images.  It incorporates tools for camera calibration (calib);general image manipulations using a stack based image calculator (imcalc); edge and corner extraction; a skeleton tool which is provides a basic tool outline ready for the user to program.  The bottom Tv contains a grey level image of a toy brick house and the upper Tv shows the results of Canny edge detection performed on this house.  Overlay data such as Canny edges can be imaged over the original image but is shown here separately for clarity.

  SAL Home   |   Computer Graphics, Images & Signals   |   Misc

Comments? SAL@KachinaTech.COM
Copyright © 1995-2001 by Herng-Jeng Jou
Copyright © 1997-2001 by Kachina Technologies, Inc.
All rights reserved.