libCVD is a very portable and high performance C++ library for computer vision, image, and video processing. The emphasis is on providing simple and efficient image and video handling and high quality implementations of common low-level image processing function. The library is designed in a loosely-coupled manner, so that parts can be used easily in isolation if the whole library is not required. The video grabbing module provides a simple, uniform interface for videos from a variety of sources (live and recorded) and allows easy access to the raw pixel data. Likewise, the image loading/saving module provides simple, uniform interfaces for loading and saving images from bitmaps to 64 bit per channel RGBA images. The image processing routines can be applied easily to images and video, and accelerated versions exist for platforms supporting SSE.
Marvin is an extensible image processing framework for Java. It provides features to manipulate images, to manipulate captured video frames, and to process images with multi-threading. Its features can be extended via plug-ins. Plug-ins can be integrated with the graphical user interface, and their plug-in performance can be analyzed. Every image processing algorithm is developed as a plug-in that can be plugged into the MarvinEditor, an image manipulation program that uses plug-ins developed using Marvin, or into third-party applications. Currently there are 55 plug-ins available.
Bad Peggy searches for damaged JPEG files and validates and verifies pictures for truncation and other blemishes, which sometimes occur when such files are downloaded or restored from bad backups. It's fast, easy to use, and reliable in the analysis it does. It uses all available CPU cores too.
Twibright Registrator removes noise and can quadruple the resolution of a camera in software by matching several pictures together. It can be applied to remove noise, JPEG artifacts, rain, CRT stripes, and passersby. It can enhance night photos and provide the effect of long exposure in daylight. Pictures are matched by removing shift, rotation, zoom, and brightness changes. It features high performance bilinear interpolation, automatic adaptive corrective deconvolution, 32-bit float depth, photometrically linear space, and 16-bit depth PNG output.
GoFigure2 is a cross-platform application for visualization, processing, and analysis of out-of-core multidimensional microscopy data (5D data sets). Users can visualize images, segment cells in 3d, track cells through time, and detect cell divisions to generate lineages. Results are stored in a MySQL database back-end. Once data has been processed, cell-based object features are quantified and can be used for sorting, color-coding, analysis, or exported to external tools. GoFigure2 was developed for biology research including studying the development of embryos (zebrafish and mouse), synthetic biology (signaling), and for drug screening.
Into is a cross-platform machine intelligence application framework written in C++. Into provides a different, fast way to build high-performance applications for image analysis, machine vision, pattern recognition, and artificial intelligence. It features a layered API and more than 20 fully interoperable plug-in modules for accessing image and data sources, powerful feature extractors, classifiers, neural networks, and much more. It also provides Ydin, an innovative execution engine that makes it easy to create dynamic programs that automatically run in parallel, enabling you to create more with less hassle, less code, and less time. Into uses Qt to let you create beautiful user interfaces for your applications with ease.