Seite - 160 - in Document Image Processing

J. Imaging 2018,4, 39 First, theconfusionmatrix that isobtainedfromtheMLPbasedclassifieronthedatasetbyusing MLGfeaturealongwith theoverall accuracy ispresented. Then, the result generatedby the same classifierontheHOGandElliptical featuresetsappliedonthesamedataset isalsopresented.Results have been cross-validated for the classifier parameter values to obtain the optimal results for the datasetandthevaluesareprovidedin theresult section. TheMLGfeatureset consistingof60 featurevalues forevery input image is fed into theMLP classifierwith30hidden layerneuronsanda learningrateof0.8.Here,500 iterationsareallowedwith anerror toleranceof0.1. Theoverall accuracyobtained is91.42%andtheconfusionmatrixgenerated in this case isgiven inTable1. TheR columnin the table refers to the rejectionof the inputby the recognitionmodulebut theclassconfidences thatareassociatedwith themgetaccountedforduring thecombinationprocess. TheHOGfeature set, consistingof80 featurevalues for every inputdata, is fed into theMLP classifierwith40hiddenlayerneuronsanda learningrateof0.8. Sameerror toleranceandthenumber of iterations,asapplied incaseofMLGfeatures,areallowedhere.Amaximumrecognitionaccuracy of78.04%hasbeennoted. Theconfusionmatrix is showninTable2. TheElliptical featureset containing58 featurevaluesderivedfromeach imagedata formsthe training set for theMLP classifierwith 30 hidden neuronswith a learning rate of 0.7. The error toleranceandnumberof iterations remain thesameas thepreviouscases. Anaccuracyof79.2%is achievedandrepresented in theconfusionmatrixgiven inTable3. Table1.Classificationresults forHOGfeaturesetwithMLPClassifier. Class Class A B C D E F G H I J K L R A 345 9 6 22 13 21 64 42 27 0 44 7 27 B 27 548 0 7 9 0 1 0 1 0 7 0 0 C 0 0 557 0 6 13 1 19 2 1 0 1 38 D 38 4 0 516 3 3 4 0 9 0 20 3 10 E 10 6 1 12 449 26 5 2 0 0 13 76 30 F 30 0 23 3 46 417 33 36 6 1 4 1 27 G 27 2 15 10 12 16 446 34 12 1 24 1 10 H 10 0 27 17 16 41 8 420 28 11 14 8 38 I 38 2 4 16 0 10 34 33 455 0 8 0 0 J 0 0 17 0 7 0 0 16 0 553 1 6 38 K 38 6 5 35 22 14 42 31 0 2 404 1 2 L 2 2 14 6 15 24 1 9 0 13 5 509 0 Table2.Classificationresults forMLGfeaturesetwithMLPClassifier. Class Class A B C D E F G H I J K L R A 528 0 2 13 1 1 19 9 5 0 12 10 0 B 0 576 0 6 0 0 0 0 0 0 3 15 1 C 1 0 596 0 0 0 1 1 1 0 0 0 2 D 2 9 0 574 0 0 0 0 1 0 0 14 0 E 0 0 0 0 592 6 0 1 0 0 0 1 0 F 0 0 2 0 16 553 0 20 0 9 0 0 4 G 4 0 9 3 0 1 528 15 26 0 10 4 7 H 7 0 5 0 5 30 8 512 16 1 8 8 12 I 12 0 7 1 0 0 12 2 560 0 4 2 0 J 0 0 0 0 3 4 0 5 0 588 0 0 19 K 19 3 1 7 2 0 24 2 4 0 527 11 3 L 3 2 25 29 24 9 4 21 18 4 13 448 0 160