1 /*M///////////////////////////////////////////////////////////////////////////////////////
2 //
3 // IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
4 //
5 // By downloading, copying, installing or using the software you agree to this license.
6 // If you do not agree to this license, do not download, install,
7 // copy or use the software.
8 //
9 //
10 // License Agreement
11 // For Open Source Computer Vision Library
12 //
13 // Copyright (C) 2014, Itseez Inc, all rights reserved.
14 // Third party copyrights are property of their respective owners.
15 //
16 // Redistribution and use in source and binary forms, with or without modification,
17 // are permitted provided that the following conditions are met:
18 //
19 // * Redistribution's of source code must retain the above copyright notice,
20 // this list of conditions and the following disclaimer.
21 //
22 // * Redistribution's in binary form must reproduce the above copyright notice,
23 // this list of conditions and the following disclaimer in the documentation
24 // and/or other materials provided with the distribution.
25 //
26 // * The name of the copyright holders may not be used to endorse or promote products
27 // derived from this software without specific prior written permission.
28 //
29 // This software is provided by the copyright holders and contributors "as is" and
30 // any express or implied warranties, including, but not limited to, the implied
31 // warranties of merchantability and fitness for a particular purpose are disclaimed.
32 // In no event shall the Itseez Inc or contributors be liable for any direct,
33 // indirect, incidental, special, exemplary, or consequential damages
34 // (including, but not limited to, procurement of substitute goods or services;
35 // loss of use, data, or profits; or business interruption) however caused
36 // and on any theory of liability, whether in contract, strict liability,
37 // or tort (including negligence or otherwise) arising in any way out of
38 // the use of this software, even if advised of the possibility of such damage.
39 //
40 //M*/
41
42 #include <iostream>
43 #include <opencv2/opencv_modules.hpp>
44
45 #ifdef HAVE_OPENCV_TEXT
46
47 #include "opencv2/datasets/tr_chars.hpp"
48 #include <opencv2/core.hpp>
49 #include "opencv2/text.hpp"
50 #include "opencv2/imgproc.hpp"
51 #include "opencv2/imgcodecs.hpp"
52
53 #include <cstdio>
54 #include <cstdlib> // atoi
55
56 #include <string>
57 #include <vector>
58
59 using namespace std;
60 using namespace cv;
61 using namespace cv::datasets;
62 using namespace cv::text;
63
main(int argc,char * argv[])64 int main(int argc, char *argv[])
65 {
66 const char *keys =
67 "{ help h usage ? | | show this message }"
68 "{ path p |true| path to dataset description file ( list_English_Img.m ) and Img folder.}";
69 CommandLineParser parser(argc, argv, keys);
70 string path(parser.get<string>("path"));
71 if (parser.has("help") || path=="true")
72 {
73 parser.printMessage();
74 return -1;
75 }
76
77 Ptr<TR_chars> dataset = TR_chars::create();
78 dataset->load(path);
79
80 // ***************
81 // dataset. train, test contain information about each element of appropriate sets and splits.
82 // For example, let output first elements of these vectors and their sizes for last split.
83 // And number of splits.
84 int numSplits = dataset->getNumSplits();
85 printf("splits number: %u\n", numSplits);
86
87 vector< Ptr<Object> > &currTrain = dataset->getTrain(numSplits-1);
88 vector< Ptr<Object> > &currTest = dataset->getTest(numSplits-1);
89 vector< Ptr<Object> > &currValidation = dataset->getValidation(numSplits-1);
90 printf("train size: %u\n", (unsigned int)currTrain.size());
91 printf("test size: %u\n", (unsigned int)currTest.size());
92 printf("validation size: %u\n", (unsigned int)currValidation.size());
93
94
95 // WARNING: The order of classes' labels is different in Chars74k and in the output of our classifier
96 string src_classes = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"; // labels order as in the clasifier output
97 string tar_classes = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"; // labels order as in the Chars74k dataset
98
99 Ptr<OCRHMMDecoder::ClassifierCallback> ocr = loadOCRHMMClassifierCNN("OCRBeamSearch_CNN_model_data.xml.gz");
100
101 int numOK = 0;
102 int upperNumOK = 0;
103
104 for (unsigned int i=0; i<(unsigned int)currTest.size(); i++)
105 {
106 TR_charsObj *exampleTest = static_cast<TR_charsObj *>(currTest[i].get());
107 printf("processed image: %u, name: %s\n", i, exampleTest->imgName.c_str());
108 printf(" label: %u,", exampleTest->label);
109
110 string imfilename = path+string("/Img/")+exampleTest->imgName.c_str()+string(".png");
111 Mat image = imread(imfilename);
112 vector<int> out_classes;
113 vector<double> out_confidences;
114 ocr->eval(image, out_classes, out_confidences);
115 int prediction = 1 + tar_classes.find_first_of(src_classes[out_classes[0]]);
116 printf(" prediction: %u\n", prediction);
117
118 if (exampleTest->label == prediction)
119 numOK++;
120
121 char l = tar_classes[exampleTest->label];
122 char p = tar_classes[prediction];
123 if (toupper(l) == toupper(p))
124 upperNumOK++;
125 }
126
127 printf("\n---------------------------------------------\n");
128 printf("Chars74k Classification Accuracy (case-sensitive): %f\n",(float)numOK/currTest.size());
129 printf("Chars74k Classification Accuracy (case-insensitive): %f\n",(float)upperNumOK/currTest.size());
130
131 return 0;
132 }
133
134 #else
135
main()136 int main()
137 {
138 std::cerr << "OpenCV was built without text module" << std::endl;
139 return 0;
140 }
141
142 #endif // HAVE_OPENCV_TEXT
143