Morphological Shared-Weight Neural Network for Face Recognition

MSNN has the ability to learn feature extraction and perform classification at the same time.

Description

We introduce an algorithm based on the morphological shared-weight neural network. Being nonlinear and translation-invariant, the MSNN can be used to create better generalization during face recognition. Feature extraction is performed on grayscale images using hit-miss transforms that are independent of gray-level shifts. The output is then learned by interacting with the classification process. The feature extraction and classification networks are trained together, allowing the MSNN to simultaneously learn feature extraction and classification for a face. For evaluation, we test for robustness under variations in gray levels and noise while varying the network?s configuration to optimize recognition efficiency and processing time. Results show that the MSNN performs better for grayscale image pattern classification than ordinary neural networks.

One of the current approaches to vision processing, the morphological shared-weight neural network developed by Y. Won*, is investigated here. Our model consists of two network stages: the first stage extracts features using morphological operations; the second stage performs classification of outputs from the last feature extraction layer.

*[1] Y. Won et. al., Morphological Shared-Weight Networks with Applications to Automatic Target Recognition, Electronics and Telecommunications Research Institute, Daejon, South Korea, 1995. http://www.ieeexplore.ieee.org/

• Required Products: Data Acquisition Toolbox; Image Acquisition Toolbox; Image Processing Toolbox; Neural Network Toolbox
• MATLAB release: MATLAB 6.5 (R13)

Other Files

images/database/1.tif,
images/database/2.tif,
images/database/3.tif,
images/database/4.tif,
images/database/5.tif,
images/database/6.tif,
images/database/7.tif,
images/database/8.tif,
images/database/dlefteye1.tif,
images/database/dlefteye2.tif,
images/database/dlefteye3.tif,
images/database/dlefteye4.tif,
images/database/extrarighteye20.tif,
images/database/lefteye1.tif,
images/database/lefteye10.tif,
images/database/lefteye11.tif,
images/database/lefteye12.tif,
images/database/lefteye13.tif,
images/database/lefteye14.tif,
images/database/lefteye15.tif,
images/database/lefteye16.tif,
images/database/lefteye17.tif,
images/database/lefteye18.tif,
images/database/lefteye19.tif,
images/database/lefteye2.tif,
images/database/lefteye20.tif,
images/database/lefteye3.tif,
images/database/lefteye4.tif,
images/database/lefteye5.tif,
images/database/lefteye6.tif,
images/database/lefteye7.tif,
images/database/lefteye8.tif,
images/database/lefteye9.tif,
images/database/righteye1.tif,
images/database/righteye10.tif,
images/database/righteye11.tif,
images/database/righteye12.tif,
images/database/righteye13.tif,
images/database/righteye14.tif,
images/database/righteye15.tif,
images/database/righteye16.tif,
images/database/righteye17.tif,
images/database/righteye18.tif,
images/database/righteye19.tif,
images/database/righteye2.tif,
images/database/righteye20.tif,
images/database/righteye3.tif,
images/database/righteye4.tif,
images/database/righteye5.tif,
images/database/righteye6.tif,
images/database/righteye7.tif,
images/database/righteye8.tif,
images/database/righteye9.tif,
images/database/seed.tif,
images/database/Thumbs.db,
images/database/x1.tif,
images/database/x2.tif,
images/database/x3.tif,
images/database/x4.tif,
images/database/x5.tif,
images/database/x6.tif,
images/database/x7.tif,
images/database/x8.tif,
images/f1/1.tif,
images/f1/2.tif,
images/f1/3.tif,
images/f1/4.tif,
images/f1/5.tif,
images/f1/6.tif,
images/f1/7.tif,
images/f1/8.tif,
images/f1/Thumbs.db,
images/f10/1.tif,
images/f10/2.tif,
images/f10/3.tif,
images/f10/4.tif,
images/f10/5.tif,
images/f10/6.tif,
images/f10/7.tif,
images/f10/8.tif,
images/f10/Thumbs.db,
images/f2/1.tif,
images/f2/2.tif,
images/f2/3.tif,
images/f2/4.tif,
images/f2/5.tif,
images/f2/6.tif,
images/f2/7.tif,
images/f2/8.tif,
images/f2/Thumbs.db,
images/f3/1.tif,
images/f3/2.tif,
images/f3/3.tif,
images/f3/4.tif,
images/f3/5.tif,
images/f3/6.tif,
images/f3/7.tif,
images/f3/8.tif,
images/f3/Thumbs.db,
images/f4/1.tif,
images/f4/2.tif,
images/f4/3.tif,
images/f4/4.tif,
images/f4/5.tif,
images/f4/6.tif,
images/f4/7.tif,
images/f4/8.tif,
images/f4/Thumbs.db,
images/f5/1.tif,
images/f5/2.tif,
images/f5/3.tif,
images/f5/4.tif,
images/f5/5.tif,
images/f5/6.tif,
images/f5/7.tif,
images/f5/8.tif,
images/f5/Thumbs.db,
images/f6/1.tif,
images/f6/2.tif,
images/f6/3.tif,
images/f6/4.tif,
images/f6/5.tif,
images/f6/6.tif,
images/f6/7.tif,
images/f6/8.tif,
images/f6/test/f1-1.tif,
images/f6/test/f1-2.tif,
images/f6/test/f1-3.tif,
images/f6/test/f1-4.tif,
images/f6/test/Thumbs.db,
images/f6/Thumbs.db,
images/f6/train/f1-1.tif,
images/f6/train/f1-2.tif,
images/f6/train/f1-3.tif,
images/f6/train/f1-4.tif,
images/f6/train/Thumbs.db,
images/f7/1.tif,
images/f7/2.tif,
images/f7/3.tif,
images/f7/4.tif,
images/f7/5.tif,
images/f7/6.tif,
images/f7/7.tif,
images/f7/8.tif,
images/f7/Thumbs.db,
images/f8/1.tif,
images/f8/2.tif,
images/f8/3.tif,
images/f8/4.tif,
images/f8/5.tif,
images/f8/6.tif,
images/f8/7.tif,
images/f8/8.tif,
images/f8/Thumbs.db,
images/f9/1.tif,
images/f9/2.tif,
images/f9/3.tif,
images/f9/4.tif,
images/f9/5.tif,
images/f9/6.tif,
images/f9/7.tif,
images/f9/8.tif,
images/f9/test/f2-1.tif,
images/f9/test/f2-2.tif,
images/f9/test/f2-3.tif,
images/f9/test/f2-4.tif,
images/f9/test/Thumbs.db,
images/f9/Thumbs.db,
images/f9/train/f2-1.tif,
images/f9/train/f2-2.tif,
images/f9/train/f2-3.tif,
images/f9/train/f2-4.tif,
images/FaceData/1.tif,
images/FaceData/10.tif,
images/FaceData/11.tif,
images/FaceData/12.tif,
images/FaceData/13.tif,
images/FaceData/14.tif,
images/FaceData/15.tif,
images/FaceData/16.tif,
images/FaceData/17.tif,
images/FaceData/18.tif,
images/FaceData/19.tif,
images/FaceData/2.tif,
images/FaceData/20.tif,
images/FaceData/3.tif,
images/FaceData/4.tif,
images/FaceData/5.tif,
images/FaceData/6.tif,
images/FaceData/7.tif,
images/FaceData/8.tif,
images/FaceData/9.tif,
images/FaceData/a1/10.tif,
images/FaceData/a1/9.tif,
images/FaceData/a1/Thumbs.db,
images/FaceData/a2/11.tif,
images/FaceData/a2/12.tif,
images/FaceData/a2/Thumbs.db,
images/FaceData/a3/13.tif,
images/FaceData/a3/14.tif,
images/FaceData/a3/Thumbs.db,
images/FaceData/a4/17.tif,
images/FaceData/a4/18.tif,
images/FaceData/a4/Thumbs.db,
images/FaceData/a5/15.tif,
images/FaceData/a5/16.tif,
images/FaceData/a5/Thumbs.db,
images/FaceData/a6/19.tif,
images/FaceData/a6/20.tif,
images/FaceData/a6/Thumbs.db,
images/FaceData/face1.bmp,
images/FaceData/face10.bmp,
images/FaceData/face11.bmp,
images/FaceData/face2.bmp,
images/FaceData/lefteye1.tif,
images/FaceData/lefteye10.png,
images/FaceData/lefteye10.tif,
images/FaceData/lefteye10x.tif,
images/FaceData/lefteye11.png,
images/FaceData/lefteye11.tif,
images/FaceData/lefteye11x.tif,
images/FaceData/lefteye12.png,
images/FaceData/lefteye12.tif,
images/FaceData/lefteye12x.tif,
images/FaceData/lefteye13.png,
images/FaceData/lefteye13.tif,
images/FaceData/lefteye13x.tif,
images/FaceData/lefteye14.png,
images/FaceData/lefteye14.tif,
images/FaceData/lefteye14x.tif,
images/FaceData/lefteye15.png,
images/FaceData/lefteye15.tif,
images/FaceData/lefteye16.png,
images/FaceData/lefteye16.tif,
images/FaceData/lefteye17.png,
images/FaceData/lefteye17.tif,
images/FaceData/lefteye18.png,
images/FaceData/lefteye18.tif,
images/FaceData/lefteye19.png,
images/FaceData/lefteye19.tif,
images/FaceData/lefteye2.tif,
images/FaceData/lefteye20.png,
images/FaceData/lefteye20.tif,
images/FaceData/lefteye3.tif,
images/FaceData/lefteye4.tif,
images/FaceData/lefteye5.tif,
images/FaceData/lefteye5x.tif,
images/FaceData/lefteye6.tif,
images/FaceData/lefteye6x.tif,
images/FaceData/lefteye7.tif,
images/FaceData/lefteye8.tif,
images/FaceData/lefteye9.png,
images/FaceData/lefteye9.tif,
images/FaceData/lefteye9x.tif,
images/FaceData/righteye1.tif,
images/FaceData/righteye10.png,
images/FaceData/righteye10.tif,
images/FaceData/righteye10x.tif,
images/FaceData/righteye11.png,
images/FaceData/righteye11.tif,
images/FaceData/righteye11x.tif,
images/FaceData/righteye12.png,
images/FaceData/righteye12.tif,
images/FaceData/righteye12x.tif,
images/FaceData/righteye13.png,
images/FaceData/righteye13.tif,
images/FaceData/righteye14.png,
images/FaceData/righteye14.tif,
images/FaceData/righteye15.png,
images/FaceData/righteye15.tif,
images/FaceData/righteye16.png,
images/FaceData/righteye16.tif,
images/FaceData/righteye17.png,
images/FaceData/righteye17.tif,
images/FaceData/righteye18.png,
images/FaceData/righteye18.tif,
images/FaceData/righteye19.png,
images/FaceData/righteye19.tif,
images/FaceData/righteye2.tif,
images/FaceData/righteye20.png,
images/FaceData/righteye20.tif,
images/FaceData/righteye3.tif,
images/FaceData/righteye4.tif,
images/FaceData/righteye5.tif,
images/FaceData/righteye5x.tif,
images/FaceData/righteye6.tif,
images/FaceData/righteye6x.tif,
images/FaceData/righteye7.tif,
images/FaceData/righteye8.tif,
images/FaceData/righteye9.png,
images/FaceData/righteye9.tif,
images/FaceData/righteye9x.tif,
images/FaceData/Thumbs.db,
images/facedata_eyes/lefteye1.tif,
images/facedata_eyes/lefteye10.tif,
images/facedata_eyes/lefteye11.tif,
images/facedata_eyes/lefteye12.tif,
images/facedata_eyes/lefteye13.tif,
images/facedata_eyes/lefteye14.tif,
images/facedata_eyes/lefteye15.tif,
images/facedata_eyes/lefteye16.tif,
images/facedata_eyes/lefteye17.tif,
images/facedata_eyes/lefteye18.tif,
images/facedata_eyes/lefteye19.tif,
images/facedata_eyes/lefteye2.tif,
images/facedata_eyes/lefteye20.tif,
images/facedata_eyes/lefteye3.tif,
images/facedata_eyes/lefteye4.tif,
images/facedata_eyes/lefteye5.tif,
images/facedata_eyes/lefteye6.tif,
images/facedata_eyes/lefteye7.tif,
images/facedata_eyes/lefteye8.tif,
images/facedata_eyes/lefteye9.tif,
images/facedata_eyes/righteye1.tif,
images/facedata_eyes/righteye10.tif,
images/facedata_eyes/righteye11.tif,
images/facedata_eyes/righteye12.tif,
images/facedata_eyes/righteye13.tif,
images/facedata_eyes/righteye14.tif,
images/facedata_eyes/righteye15.tif,
images/facedata_eyes/righteye16.tif,
images/facedata_eyes/righteye17.tif,
images/facedata_eyes/righteye18.tif,
images/facedata_eyes/righteye19.tif,
images/facedata_eyes/righteye2.tif,
images/facedata_eyes/righteye20.tif,
images/facedata_eyes/righteye3.tif,
images/facedata_eyes/righteye4.tif,
images/facedata_eyes/righteye5.tif,
images/facedata_eyes/righteye6.tif,
images/facedata_eyes/righteye7.tif,
images/facedata_eyes/righteye8.tif,
images/facedata_eyes/righteye9.tif,
images/facedata_eyes/Thumbs.db,
images/facedata_face/1.tif,
images/facedata_face/10.tif,
images/facedata_face/11.tif,
images/facedata_face/12.tif,
images/facedata_face/13.tif,
images/facedata_face/14.tif,
images/facedata_face/15.tif,
images/facedata_face/16.tif,
images/facedata_face/17.tif,
images/facedata_face/18.tif,
images/facedata_face/19.tif,
images/facedata_face/2.tif,
images/facedata_face/20.tif,
images/facedata_face/3.tif,
images/facedata_face/4.tif,
images/facedata_face/5.tif,
images/facedata_face/6.tif,
images/facedata_face/7.tif,
images/facedata_face/8.tif,
images/facedata_face/9.tif,
images/facedata_face/Thumbs.db,
images/id/1.tif,
images/id/10.tif,
images/id/2.tif,
images/id/3.tif,
images/id/4.tif,
images/id/5.tif,
images/id/6.tif,
images/id/7.tif,
images/id/8.tif,
images/id/9.tif,
images/id/err.tif,
images/id/s2.tif,
images/id/Thumbs.db,
images/id2/1.tif,
images/id2/10.tif,
images/id2/2.tif,
images/id2/3.tif,
images/id2/4.tif,
images/id2/5.tif,
images/id2/6.tif,
images/id2/7.tif,
images/id2/8.tif,
images/id2/9.tif,
images/id2/axn.jpg,
images/id2/err.tif,
images/id2/testI_9.tif,
images/id2/Thumbs.db,
images/id3/1.tif,
images/id3/10.tif,
images/id3/2.tif,
images/id3/3.tif,
images/id3/4.tif,
images/id3/5.tif,
images/id3/5origin.tif,
images/id3/6.tif,
images/id3/7.tif,
images/id3/8.tif,
images/id3/9.tif,
images/id3/Thumbs.db,
images/lasttwo/1.tif,
images/lasttwo/10.tif,
images/lasttwo/11.tif,
images/lasttwo/12.tif,
images/lasttwo/13.tif,
images/lasttwo/14.tif,
images/lasttwo/15.tif,
images/lasttwo/16.tif,
images/lasttwo/17.tif,
images/lasttwo/18.tif,
images/lasttwo/19.tif,
images/lasttwo/2.tif,
images/lasttwo/20.tif,
images/lasttwo/3.tif,
images/lasttwo/4.tif,
images/lasttwo/5.tif,
images/lasttwo/6.tif,
images/lasttwo/7.tif,
images/lasttwo/8.tif,
images/lasttwo/9.tif,
images/lasttwo/Thumbs.db,
images/probebase/1.png,
images/probebase/1.tif,
images/probebase/10.tif,
images/probebase/10x.tif,
images/probebase/11.tif,
images/probebase/11x.tif,
images/probebase/12.tif,
images/probebase/12x.tif,
images/probebase/13.tif,
images/probebase/14.tif,
images/probebase/15.tif,
images/probebase/16.tif,
images/probebase/17.tif,
images/probebase/18.tif,
images/probebase/19.tif,
images/probebase/2.png,
images/probebase/2.tif,
images/probebase/20.tif,
images/probebase/3.png,
images/probebase/3.tif,
images/probebase/3x.tif,
images/probebase/4.png,
images/probebase/4.tif,
images/probebase/4x.tif,
images/probebase/5.png,
images/probebase/5.tif,
images/probebase/6.png,
images/probebase/6.tif,
images/probebase/6x.tif,
images/probebase/7.png,
images/probebase/7.tif,
images/probebase/8.png,
images/probebase/8.tif,
images/probebase/9.tif,
images/probebase/9x.tif,
images/probebase/g.tif,
images/probebase/h.tif,
images/probebase/lefteye1.tif,
images/probebase/lefteye10.png,
images/probebase/lefteye10.tif,
images/probebase/lefteye11.png,
images/probebase/lefteye11.tif,
images/probebase/lefteye12.png,
images/probebase/lefteye12.tif,
images/probebase/lefteye13.png,
images/probebase/lefteye13.tif,
images/probebase/lefteye14.png,
images/probebase/lefteye14.tif,
images/probebase/lefteye15.png,
images/probebase/lefteye15.tif,
images/probebase/lefteye16.png,
images/probebase/lefteye16.tif,
images/probebase/lefteye17.png,
images/probebase/lefteye17.tif,
images/probebase/lefteye18.png,
images/probebase/lefteye18.tif,
images/probebase/lefteye19.png,
images/probebase/lefteye19.tif,
images/probebase/lefteye2.tif,
images/probebase/lefteye20.png,
images/probebase/lefteye20.tif,
images/probebase/lefteye3.tif,
images/probebase/lefteye4.tif,
images/probebase/lefteye5.tif,
images/probebase/lefteye6.tif,
images/probebase/lefteye7.tif,
images/probebase/lefteye8.tif,
images/probebase/lefteye9.png,
images/probebase/lefteye9.tif,
images/probebase/q1/11.tif,
images/probebase/q1/12.tif,
images/probebase/q1/Thumbs.db,
images/probebase/q2/13.tif,
images/probebase/q2/14.tif,
images/probebase/q2/Thumbs.db,
images/probebase/q3/17.tif,
images/probebase/q3/18.tif,
images/probebase/q3/Thumbs.db,
images/probebase/q4/15.tif,
images/probebase/q4/16.tif,
images/probebase/q4/Thumbs.db,
images/probebase/q5/10.tif,
images/probebase/q5/9.tif,
images/probebase/q5/Thumbs.db,
images/probebase/q6/19.tif,
images/probebase/q6/20.tif,
images/probebase/q6/Thumbs.db,
images/probebase/rg1.png,
images/probebase/rg2.png,
images/probebase/rg3.png,
images/probebase/rg4.png,
images/probebase/rg5.png,
images/probebase/rg6.png,
images/probebase/rg7.png,
images/probebase/rg8.png,
images/probebase/righteye1.tif,
images/probebase/righteye10.png,
images/probebase/righteye10.tif,
images/probebase/righteye11.png,
images/probebase/righteye11.tif,
images/probebase/righteye12.png,
images/probebase/righteye12.tif,
images/probebase/righteye13.png,
images/probebase/righteye13.tif,
images/probebase/righteye14.png,
images/probebase/righteye14.tif,
images/probebase/righteye15.png,
images/probebase/righteye15.tif,
images/probebase/righteye16.png,
images/probebase/righteye16.tif,
images/probebase/righteye17.png,
images/probebase/righteye17.tif,
images/probebase/righteye18.png,
images/probebase/righteye18.tif,
images/probebase/righteye19.png,
images/probebase/righteye19.tif,
images/probebase/righteye2.tif,
images/probebase/righteye20.png,
images/probebase/righteye20.tif,
images/probebase/righteye3.tif,
images/probebase/righteye4.tif,
images/probebase/righteye5.tif,
images/probebase/righteye6.tif,
images/probebase/righteye7.tif,
images/probebase/righteye8.tif,
images/probebase/righteye9.png,
images/probebase/righteye9.tif,
images/probebase/Thumbs.db,
images/probebase/was3.tif,
images/probebase/was4.tif,
images/probebase/x.tif,
images/probebase/x2.tif,
images/probebase/x33.tif,
images/probebase/xx.tif,
images/probebase/yy.tif,
images/unseen/1.tif,
images/unseen/10.tif,
images/unseen/11.tif,
images/unseen/12.tif,
images/unseen/13.tif,
images/unseen/14.tif,
images/unseen/15.tif,
images/unseen/16.tif,
images/unseen/17.tif,
images/unseen/18.tif,
images/unseen/19.tif,
images/unseen/2.tif,
images/unseen/20.tif,
images/unseen/3.tif,
images/unseen/4.tif,
images/unseen/5.tif,
images/unseen/6.tif,
images/unseen/7.tif,
images/unseen/8.tif,
images/unseen/9.tif,
images/unseen/f2/11.tif,
images/unseen/f2/12.tif,
images/unseen/f2/Thumbs.db,
images/unseen/f3/17.tif,
images/unseen/f3/18.tif,
images/unseen/f3/Thumbs.db,
images/unseen/f4/13.tif,
images/unseen/f4/14.tif,
images/unseen/f4/Thumbs.db,
images/unseen/f5/15.tif,
images/unseen/f5/16.tif,
images/unseen/f5/Thumbs.db,
images/unseen/f6/19.tif,
images/unseen/f6/20.tif,
images/unseen/f6/Thumbs.db,
images/unseen/f7/10.tif,
images/unseen/f7/9.tif,
images/unseen/f7/Thumbs.db,
images/unseen/lefteye1.png,
images/unseen/lefteye1.tif,
images/unseen/lefteye10.png,
images/unseen/lefteye10.tif,
images/unseen/lefteye11.png,
images/unseen/lefteye11.tif,
images/unseen/lefteye12.png,
images/unseen/lefteye12.tif,
images/unseen/lefteye13.png,
images/unseen/lefteye13.tif,
images/unseen/lefteye14.png,
images/unseen/lefteye14.tif,
images/unseen/lefteye15.png,
images/unseen/lefteye15.tif,
images/unseen/lefteye16.png,
images/unseen/lefteye16.tif,
images/unseen/lefteye17.png,
images/unseen/lefteye17.tif,
images/unseen/lefteye18.png,
images/unseen/lefteye18.tif,
images/unseen/lefteye19.png,
images/unseen/lefteye19.tif,
images/unseen/lefteye2.png,
images/unseen/lefteye2.tif,
images/unseen/lefteye20.png,
images/unseen/lefteye20.tif,
images/unseen/lefteye3.png,
images/unseen/lefteye3.tif,
images/unseen/lefteye4.png,
images/unseen/lefteye4.tif,
images/unseen/lefteye5.png,
images/unseen/lefteye5.tif,
images/unseen/lefteye6.png,
images/unseen/lefteye6.tif,
images/unseen/lefteye7.png,
images/unseen/lefteye7.tif,
images/unseen/lefteye8.png,
images/unseen/lefteye8.tif,
images/unseen/lefteye9.png,
images/unseen/lefteye9.tif,
images/unseen/righteye1.png,
images/unseen/righteye1.tif,
images/unseen/righteye10.png,
images/unseen/righteye10.tif,
images/unseen/righteye11.png,
images/unseen/righteye11.tif,
images/unseen/righteye12.png,
images/unseen/righteye12.tif,
images/unseen/righteye13.png,
images/unseen/righteye13.tif,
images/unseen/righteye14.png,
images/unseen/righteye14.tif,
images/unseen/righteye15.png,
images/unseen/righteye15.tif,
images/unseen/righteye16.png,
images/unseen/righteye16.tif,
images/unseen/righteye17.png,
images/unseen/righteye17.tif,
images/unseen/righteye18.png,
images/unseen/righteye18.tif,
images/unseen/righteye19.png,
images/unseen/righteye19.tif,
images/unseen/righteye2.png,
images/unseen/righteye2.tif,
images/unseen/righteye20.png,
images/unseen/righteye20.tif,
images/unseen/righteye3.png,
images/unseen/righteye3.tif,
images/unseen/righteye4.png,
images/unseen/righteye4.tif,
images/unseen/righteye5.png,
images/unseen/righteye5.tif,
images/unseen/righteye6.png,
images/unseen/righteye6.tif,
images/unseen/righteye7.png,
images/unseen/righteye7.tif,
images/unseen/righteye8.png,
images/unseen/righteye8.tif,
images/unseen/righteye9.png,
images/unseen/righteye9.tif,
images/unseen/Thumbs.db,
Final_V3/AREA1.mat,
Final_V3/AREA2.mat,
Final_V3/AREA3.mat,
Final_V3/B.mat,
Final_V3/C.mat,
Final_V3/convolution.m,
Final_V3/convolutionnex.m,
Final_V3/detect.m,
Final_V3/detecteyes.m,
Final_V3/draw_lines.m,
Final_V3/eyecrop_testim.m,
Final_V3/eyesearch.m,
Final_V3/eyesearch_amend.m,
Final_V3/final_dissertation.pdf,
Final_V3/geteyelevel.m,
Final_V3/HH.mat,
Final_V3/imline.m,
Final_V3/imrect.m,
Final_V3/J.mat,
Final_V3/lefteye.mat,
Final_V3/logsigfx.m,
Final_V3/M.mat,
Final_V3/main.m,
Final_V3/maxposition.m,
Final_V3/MN.mat,
Final_V3/msnn1.m,
Final_V3/msnn2.m,
Final_V3/N.mat,
Final_V3/prescale.m,
Final_V3/Q.mat,
Final_V3/R.mat,
Final_V3/readimage.m,
Final_V3/righteye.mat,
Final_V3/split.m,
Final_V3/spot.mat,
Final_V3/spotdot.mat,
Final_V3/tansigfx.m,
Final_V3/traindata_newfinal.m,
Final_V3/traineyes_datafinal.m,
Final_V3/traineyes_testSHIFT.m,
Final_V3/traineyes_valfinal.asv,
Final_V3/traineyes_valfinal.m,
Final_V3/traintest_newfinal.m,
Final_V3/wint.mat,
Final_V3/wintface.mat,
Final_V3/wp.mat,
Final_V3/wq.mat,
Final_V3/XX.mat,
Final_V3/zint.mat,
Final_V3/zintface.mat,
Final_V3/zp.mat,
Final_V3/zq.mat

[li xiaomao]

when I run the main.m ,then click Recognition by Whole Image button,there are errros as "C:\images\f10\1.tif" does not exist.So I find there are not f10 f9 and so on floders in the images folder

[David McLaxlan]

Copy any photo (I believe there are many in the other folders) that belongs to the same person, as long as they are not the same. You are supposed to learn from this guy, and not copy the whole thing. Try to be a wee bit flexible, okay?

[li xiaomao]

there is not validation.m file,when I select 9

[li xiaomao]

tank you ! David ,I know ,but it costs me a lot of time to found different pictures of the same peole.

[Ethan Png]

Dear Mr Li, Mr McLaxlan, and all researchers,

Thanks for all your comments and questions.
I posted this in a hurry. Sorry for the inconvenience caused.

I am delighted to inform you that there is no "validation.m" at all. The 9th button on the menu uses "detecteyes.m".

Mr Li, all the complete photo folders can be found at the link below:
http://groups.yahoo.com/group/aiface/

[li xiaomao]

Thank you very much! For my english is bad,I can not how to expresss my acknowledgement.
I became a member of your group in yahoo,but my reserch is not on this.I find you method of MSNN maybe have usefulness for my research.

[Stanislav Dimov]

Dear Mr. Png,

I find Your work on the MSNN network for face recognition as exellent and very interesting.I'm Professor at the Technical University in Sofia, Bulgarien , Department of Computer science. I would ask for:
1/ Send me more materials about MSNN especially for pattern recognition, gray scale image processing.I need these materials for my students.
2/ I'm ready to collaborate with You on the field of application of MSNN for pattern recognition and image processing, especially on the adaptive and/or probabalistic neural networks /PNN/. If You are interested for collaboration , please send per e-mail Yours oppinion !

With best regards

Yours
Dr. S. Dimov

[sneha mehta]

dear sir
i found your material really intersting . i am a student of engineering. sir, i would be highly obliged if you would send me more material on MSNN .
hoping for an early response.
thanking you.
sneha mehta
 

[sneha mehta]

dear sir
i received your mail regarding MSNN.Thank you so much for responding.
sir, i was having some trouble regarding linking of the different programs.
It would be of such great help to me sir if you could let me know the detailed procedure of executing it.
sir, i know it would be a trouble for you but sir please if you could do me this favor.
thanking you
hoping for an early response.

[Ethan Png]

Dear Sneha,

You need to refer thoroughly to the "files" folder in:
http://groups.yahoo.com/group/aiface/

The core program is only the MSNN training loop. How you compare the trained output values is completely up to your fancy.

Regards,
Ethan Png

[dari mohamed]

utilser pour un projet de fin d'etude

[galal galal]

 

[Vergisri Selvamaney]

an excellent work!!! it's simply superb programming

[Surekha Paneerselvam]

The work is excellent. But when i run the code I fine there is no proper database. Where can i get the database. Please help me

[Surekha Paneerselvam]

Sir,
I would like to know how to validate the results. The "validation.m" does not exist at all. I will be grate ful if u Can mail me at the earliest.

[Ethan Png]

Sorry guys, there are no servers at this moment for you to access the photos. If you need to download all the photos, you may access Cambridge's or MIT's website. If you encounter problems such as ltx or lty, it could be size problems or detection problems. Just resize those images/component images in any photoeditor. In fact I could fine-tune that method of eye detection (convo), but had really no time to improve it. (It can be done if you go back to image processing maths. Heheh.) As I said, the main idea of this thesis is the core program msnn.m. I am sure you intelligent guys can find better ways to compare the trained network with the test image. : )
 
I have recently updated this site (the link below). Phew! After so many months, I finally have the time to administer this site! You can download the PDF version from today!
http://groups.yahoo.com/group/aiface/

I will try to answer your questions one by one. Cheers.

[vinayak rao]

Please help me in validating the results. The "validation.m" does not exist . It would be kind of you if u can mail me at the earliest.

[Gaurav Gupta]

The work is excellent...but i have a small problem running the code (option 9) there is not validation.m file , when I select 9 ...hoping for an early response... thanking you..Gaurav

[Rohmad Basuki]

Dear Mr. Ethan png,
(sorry my English not so good)
I'd tried your MSNN project out.
But, there were several things i want to ask:
1). Why the 'test image' placed at one folder with 'train image'?
2). I'd try to replace the \F10\8.tif with \F6\8.tif,\F1\8.tif,\F2\8.tif etc, but the result program is '100% ACCURACY'.
They were different identity of image, your MSNN could not detect it.
Why it could be happened?
3). Regarding to my 2nd question and after i tried your MSNN many times, i concluse that the MENU 1, MENU 2, MENU 3 and MENU 4 for whole image is not an Artifical Neural network system, but just showing the image.

4). I'd try to adjust the TIFF image at your face database to very extreme condition (Unrecognized condition by human eyes and brain), but your system still recognize it 100 %. Please give us your explanation, when your MSNN could get the wrong result?

sorry if i got wrong with my questions.
thank you.

[James Blake]

I see some of the reviews are from engineers. Unfortunately some of the questions are ridiculous and I can't beleive you are blatantly copying the code. You cannot call yourself engineers but instead reverse-engineers. Try to learn from and not copy.

[cathlin w]

³ç°Ýing

[Johnson Elangbam]

 

[Chuleeporn Kanthong]

Thanks you .

[Minh Hoang]

 

[nguyen vinh]

very good

[udhaya kumar]

there is not validation.m file,when I select 9

[Utkarsh Rathore]

 

[Christian Sanchez]

The work is excellent, but I have problems with the extraction of HH.mat file because the file appears damaged. You may send it to me via e-mail to [e-mail], [e-mail], [e-mail]. Thanks you.

[Raymond Cheng]

Thanks for sharing.

[Tow Bas]

I have downloaded all the images used in this research from this (http://cvc.yale.edu/) link, but all are in .pgm format. How i will convert them into .gif or .tif or .jpg for Windows operating system? Or how I will download them in gif/tif or jpg format?