cv.jit is a collection of max/msp/jitter tools for computer vision applications. The goals of this project are to provide externals and abstractions to assist users in tasks such as image segmentation, shape and gesture recognition, motion tracking, etc. as well as to provide educational tools that outline the basics of computer vision techniques.


Take a look here, for a list of objects currently available.

Last update: version 1.7.2 on 2010-10-13


The latest version of cv.jit is 1.7 and can only be used with Max 5 or later. The 64-bit version of Max is not supported. As I do not have the time to recompile the externals, I am looking for a volunteer to help me with the transition.

Older versions that support Max 4.6 and earlier:


cv.jit is distributed according to the LGPL license.

Download the development files for OSX and Windows, including source and project files. You can also obtain the source code from the Subversion repository at the following address: .

Requires jitter, available from Cycling ’74.


Please e-mail me your comments, suggestions, bug reports, etc. at jmp [at]

cv.jit news

A Simple Eye Tracker For Jitter

A few years ago, I made a rough eye tracker in Jitter with cv.jit for my own use. It wasn’t the most thoroughly advanced approach to the problem but it did the job, and it’s relatively lightweight. I moved on to other projects and I forgot about the patch almost entirely, but from time to […]

Read this entry.

Minor update to cv.jit

I have just released cv.jit version 1.7.1, which fixes two issues. A bug in cv.jit.shift, which also affected cv.jit.touches, was causing memory leaks. Furthermore, some Windows users were seeing 14001 errors when trying to use externals that make use of OpenCV functions. Both problems have now been fixed.

Read this entry.

Using cv.jit.touches: recycling index values

cv.jit.touches, a new object added in the 1.7.0 release, tracks the movement of bright spots in a greyscale image and reports “touch”, “drag” and “release” information ? when regions appear, move or disappear. Each region is assigned a unique ID number, so that even if they move, you can always know where an object is […]

Read this entry.

cv.jit 1.7 is finally out!

The latest version of cv.jit, 1.7.0 is finally out. I say finally because, it’s been on the brim of release for several months now, but life being what it is, I only now managed to put the finishing touches on it. The most obvious change is that the help files have been completely re-written in […]

Read this entry.

A Ruby script for generating Jitter attributes

Manually adding attributes to a Jitter external requires a fair amount of tedious boilerplate. This Ruby script will do most of the boring work for you.

Read this entry.

cv.jit – New update available

A new update to?cv.jit, a collection of Max/Jitter externals for computer vision is now available for download. There is only one new object, cv.jit.snake, which is an implementation of active contour algorithms. Starting with this release,?cv.jit?is now open source. You can now download the source code and project files from the download pages.

Read this entry.