classData=tableRead('class.txt', 2);
for i=1:length(classData)
	items=split(classData(i).filename, '-');
	classData(i).range=[eval(items{1}), eval(items{2})];
end

% Get image data
imageData=recursiveFileList('D:\users\jang\books\dcpr\appNote\leafId\Leaves', 'jpg');
for i=1:length(imageData)
	[~, imageData(i).mainName]=fileparts(imageData(i).name);
	imageData(i).mainName=eval(imageData(i).mainName);
end
% Assign class label
allMainName=[imageData.mainName];
for i=1:length(classData)
	range=classData(i).range;
	for j=range(1):range(2);
		index=find(allMainName==j);
		if length(index)~=1, keyboard; end
		imageData(index).output=i;
	end
end

% Feature extraction
if ~exist('ds.mat', 'file')
	for i=1:length(imageData)
		fprintf('%d/%d: imFile=%s\n', i, length(imageData), imageData(i).path);
		imageData(i).fea=feaExtract(imageData(i).path);
	end
	ds.input=[imageData.fea];
	ds.output=[imageData.output];
	ds.inputName={'a/p', 'eccentricity', 'major/minor', 'a/ca', 'mean', 'variance'};
	ds.outputName={classData.CommonName};
	save ds ds
else
	load ds.mat
end

[classSize, classLabel]=dsClassSize(ds, 1);
rr=knncLoo(ds); fprintf('rr=%g%% for ds\n', rr*100);
figure; dsProjPlot2(ds);
ds2=ds; ds2.input=inputNormalize(ds2.input);
figure; dsProjPlot2(ds2);
[rr, computed]=knncLoo(ds2); fprintf('rr=%g%% for ds2\n', rr*100);
confMat=confMatGet(ds2.output, computed);
opt=confMatPlot('defaultOpt');
opt.className=ds.outputName;
opt.mode='both';
figure; confMatPlot(confMat, opt);
figure; inputSelectSequential(ds2, inf, 'knnc', 1);

% Exhaustive search of classifiers
opt=perfCv4classifier('defaultOpt');
opt.foldNum=10;
tic; [perfData, bestId]=perfCv4classifier(ds2, opt, 1); toc
structDispInHtml(perfData, 'Performance of various classifiers via cross validation');
% === Display the confusion matrix
confMat=confMatGet(ds.output, perfData(bestId).bestComputedClass);
opt=confMatPlot('defaultOpt');
opt.className=ds.outputName;
figure; confMatPlot(confMat, opt);