Системы распознавания

Список ресурсов систем распознавания лиц на 2005 год, список будет обновляться.

Проекты опен сурс, на C++ и других языках программирования. (angl)

The Human Body Project
The Human Body Project allows computers to better understand and interact with people. Using a webcam the system can detect and recognise individuals (face recognition), identify their gaze direction, facial expressions and upper body postures.

Operating System: All 32-bit MS Windows (95/98/NT/2000/XP) Programming Language: C++, Visual Basic

A collection of open source software and documents on machine perception and machine learning. Includes a state of the art face detector (MPISearch), video labeling tools (Score), and tutorials (Kolmogorov Tutorials).

Operating System: All 32-bit MS Windows (95/98/NT/2000/XP), All POSIX (Linux/BSD/UNIX-like OSes), OS Independent (Written in an interpreted language), OS X Programming Language: C++

Face Detector
Program to detect human faces on a digital picture. It uses a MLP neural net that receive relative distances from face distribution clusters of the image space. Written in C++. Requires newmat and libann libraries.

Operating System: All POSIX (Linux/BSD/UNIX-like OSes), Linux Programming Language: C++

MPT is a toolbox that supplies cross-platform libraries for real-time perception primitives, including face detection, eye detection, blink detection, and color tracking.

Operating System: 32-bit MS Windows (NT/2000/XP), All POSIX (Linux/BSD/UNIX-like OSes), OS X Programming Language: C++, MATLAB

Open Biometry
The development of a biometric system and applications e.g. Access Control based on the system to recognize and verify people. The primary goal is face recognition, but other human attributes might get used too in the future.

Operating System: All 32-bit MS Windows (95/98/NT/2000/XP), All POSIX (Linux/BSD/UNIX-like OSes), Linux Programming Language: C

Artificial vision library. Objectives are to make an OCR, fingerprint and face identification as some applications through a general purpose learning and pattern relationships algorithm (Currently performs very basic identification).

Operating System: All POSIX (Linux/BSD/UNIX-like OSes), OS Independent (Written in an interpreted language) Programming Language: C

FaceTracker is a webcam-based system for the recognition of face movement around various angles as well as translation of the face. It is intended to be used under Linux OS. Currently, pan angles can be detected up to 45 degrees.

Operating System: All POSIX (Linux/BSD/UNIX-like OSes), Linux Programming Language: C++

MFFM impl. of silhouette extraction alg.:
Implementation of a Silhouette extraction algorithm [1]. Coded in octave (matlab). [1] M. Yamada, K. Ebihara, and J. Ohya. A New Robust Real-time Method for Extracting Human Silhouettes from Color Images. Int. Conf. on Auto. Face and Gesture Recog., 1998

Operating System: All 32-bit MS Windows (95/98/NT/2000/XP), All POSIX (Linux/BSD/UNIX-like OSes)

Compression of face images impact the performance of face recognition (FR) systems. JPEG Region of Interest (JROI) compression maintains high image quality in facial regions while compressing the background more, with minimal impact on FR performance.

StReAV (Storage and retrieval of A/V):
StReAV is a software which runs on Linux, loaded onto a PDA/handheld, into which the an audio and video capturing tool which could be easily clamped onto the collar of a shirt is connected. Capture or stream your video, even use it for face recognition.

Face Recognition System:

BlackSun will be a face and facial recognition system which will perform face identification and feature tracking on the face. Input can be via standard video input (webcam) or a file.

Operating System: 32-bit MS Windows (95/98), All 32-bit MS Windows (95/98/NT/2000/XP) Programming Language: C++

Face Recognition
Dear Friends this project deals with the appliaction of AI in Face Recognition by applying the concepts of Independent Component Analysis (generalised form of PCA) based upon the recently developed algorithm in 2001.

Our project centers around the major task of face recognition. Ultimately, we would like to be able to take an input image of someone’s face and search for it in some image database.

OCULUS – is a face recognition system which has a plug-in architecture. This allows to integrate into it new face detection and recognition algorythms easily and make experiments with constructed recognition scenarios.

Yarle, a face recognition software

Operating System: All POSIX (Linux/BSD/UNIX-like OSes) Programming Language: C

0 0 Голоса
Оцените статью =)

Вам может также понравиться...

Сообщать о
0 Комментарий
Inline Feedbacks
Смотреть все комментарии
Есть вопросы? Задавайте =)x