Character Recognition Example (III):Training a Simple NN for classification: edu_imgresize(bw2) - File Exchange

Code covered by the BSD License

Highlights from
Character Recognition Example (III):Training a Simple NN for classification

charGUI(varargin) CHARGUI M-file for charGUI.fig
charGUI2(varargin) CHARGUI2 M-file for charGUI2.fig
edu_createnn(P,T)
edu_imgcrop(bw) Find the boundary of the image
edu_imgpreprocess(I) Extra lines compare to example2 to extract all the components into an
edu_imgresize(bw2) This function will take the cropped binary image and change it to 5 x 7
char1.m
char2.m
char3.m
rearrangeCharGUI.m
View all files

from Character Recognition Example (III):Training a Simple NN for classification by Tan Chin Luh
This demo shows some examples for image pre-processing before the recognition stage.

edu_imgresize(bw2)

function lett = edu_imgresize(bw2)
% This function will take the cropped binary image and change it to 5 x 7
% character representation in single vector.

bw_7050=imresize(bw2,[70,50]);
for cnt=1:7
    for cnt2=1:5
        Atemp=sum(bw_7050((cnt*10-9:cnt*10),(cnt2*10-9:cnt2*10)));
        lett((cnt-1)*5+cnt2)=sum(Atemp);
    end
end

lett=((100-lett)/100);
lett=lett';

Highlights from Character Recognition Example (III):Training a Simple NN for classification

Highlights from
Character Recognition Example (III):Training a Simple NN for classification