SIP provides image processing, pattern recognition, and computer vision routines for SciLab, a Matlab-like matrix-oriented programming environment. SIP is able to read/write images in almost 90 major formats, including JPEG, PNG, BMP, GIF, FITS, and TIFF. It includes routines for filtering, segmentation, edge detection, morphology, curvature, fractal dimension, distance transforms, multiscale skeletons, and more.
Engauge Digitizer is digitizing software that converts an image showing a graph or map into numbers. The image file can come from a scanner, digital camera, or screenshot. The numbers can be read on the screen, and written or copied to a spreadsheet. Highlights for beginners include an intuitive interface and extensive context-sensitive documentation. Highlights for experts include compensation for image distortion, cartesian and polar coordinates, linear and logarithmic coordinates, automatic scanning, graphical previews, and browser help.
Autopano-SIFT is a helper program for panorama image generation. It automatically generates control point information for a number of image files for use with the hugin panorama generation software. To do this, it utilizes the SIFT (Scale-Invariant Feature Transform) algorithm, a sophisticated image feature matching algorithm.
The Pattern Recognition Application Programmer's Interface aims to be a fully-featured, easy-to-use general C++ framework for various pattern recognition tasks, especially image analysis. It features support for many image formats, well-known image analysis methods, classification and feature analysis tools, XML serialization, etc.
CGAL, the Computational Geometry Algorithms Library, is a large C++ library of geometric data structures and algorithms such as Delaunay triangulations, mesh generation, Boolean operations on polygons, and various geometry processing algorithms. CGAL is used in various areas: computer graphics, scientific visualization, computer aided design and modeling, geographic information systems, molecular biology, medical imaging, robotics and motion planning, and numerical methods.
Moron (Method for Object Recognition of Obscure Nature) is a tool to classify given images based on their content. Technically, it combines feature extraction and machine learning. The classes recognized depend on the version. A typical Moron version tries at least to separate drawn content from photographs (pron) and thus could be adapted as a spam filter for cartoon newsgroups.