arsh-co / facerec Goto Github PK
View Code? Open in Web Editor NEWfacerec mirror repository
Home Page: https://code.google.com/p/facerec/
License: Other
facerec mirror repository
Home Page: https://code.google.com/p/facerec/
License: Other
csuFaceIdEval README -------------------- For detailed information on the algorithms please consult the "The CSU Face Identification Evaluation System User's Guide: Verions 5.0" Compiling the system -------------------- Once unpacking the distribution change into the distribution directory and type "make" # cd csuEvalFaceRec # scripts/runAllTests_feret.sh II. Using the provided scripts ============================== The provided scripts come in two different versions. The "feret" versions execute tests on a standard FERET image set (not provided) while the "scraps" versions execute tests on the much smaller "csuScrapShots" image set which is provided with this distribution for testing purposes. The PGM files for the "csuScrapShots" image set are provided under "data/csuScrapShots/source/pgm". Those for the FERET image set are not provided. For the "feret" scripts to work, it is assumed that the PGM files for the standard FERET sets are copied into the "data/FERET/source/pgm" directory. ------------------------------ SCRIPTS FOR TESTING THE SYSTEM ------------------------------ These two scripts allow you to test the system by running the normalization code and all the experiments (PCA, LDA and Bayesian) sequentially: runAllTests_feret.sh runAllTests_scraps.sh These scripts ought to be executed from the "csuEvalFaceRec" directory: # cd csuEvalFaceRec # scripts/runAllTests_feret.sh Or: # cd csuEvalFaceRec # scripts/runAllTests_scraps.sh In general, after installing the system and compiling the files, you should at least run "runAllTests_scraps.sh" to make sure the system is operating correctly. --------------------- NORMALIZATION SCRIPTS --------------------- The following two scripts execute the process to convert the source PGM files into the normalized the images that are needed to perform the experiments: scripts/runPreprocessing_feret.sh scripts/runPreprocessing_scraps.sh These scripts only need to be executed once. Normalized images will be stored in "data/FERET/normSep2002*" directories and "data/csuScrapShots/normSep2002*" directories. ------------------ EXPERIMENT SCRIPTS ------------------ The following scripts run the individual expriments: scripts/runBayesian_feret.sh scripts/runBayesian_scraps.sh scripts/runLDA_feret.sh scripts/runLDA_scraps.sh scripts/runPCA_feret.sh scripts/runPCA_scraps.sh One script is provided for each variation on the face identification algorithm (PCA, LDA and Bayesian) as well as for the two data sets. Running these experiments will generate distance information in the "distances" directory. ----------------------------------- SCRIPTS FOR GENERATING A RANK CURVE ----------------------------------- This script generates recognition rank curves for the FERET experiment for the fafb, fafc, dup1 and dup2 probe sets: scripts/makeRankCurves_feret.sh These rank curves are saved as text files in the "results" directory.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.