Mimas Toolkit is a C++ computer vision toolkit. It is easy to use and includes tools for edge detection, corner detection, various filters, optic flow, tracking, blob analysis, Web cam tools for real-time applications, and much more. It also includes many implementations of traditional algorithms such as Canny. It was developed for GNU/Linux but as the GUI is largely separate, porting to other platforms should be straightforward.
|Tags||multimedia Graphics Capture Digital Camera Scientific/Engineering Artificial Intelligence Image Recognition Software Development Libraries|
|Operating Systems||POSIX Linux|
Release Notes: Direct transformation algorithms from different YUV formats to greyscale. Various video sources (virtually any video file, DVDs, VCDs, and streaming formats) are accessible. Image files are read using ImageMagick (Magick++), which allows reading and writing of animated GIFs, DICOM stacks (8 bit at the moment), FAX, Postscript, PDF, MPEG, RAS, and more. This release is configured to use OSMesa for off-screen rendering, if it is present on the system. The library now is independent of Qt.
Release Notes: Support for firewire digital cameras (accessed using libdc1394). Shift and rotation estimation using the fourier transform.
Release Notes: Convolution for n-dimensional arrays and images and faster LSI-filters. Operators for images. Image-iterators. Support for mesa off-screen and on-screen rendering. mm_image::setInitVal has been replaced with mm_image::fill (less side-effects). This release implements recognition using moments.