add test-tesseract-cpp

test-tesseract-cpp/.gitignore

@@ -0,0 +1,2 @@
+nbproject
+build

test-tesseract-cpp/CMakeLists.txt

@@ -0,0 +1,20 @@
+cmake_minimum_required (VERSION 3.1)
+set (CMAKE_CXX_STANDARD 11)
+project (test-tesseract)
+add_executable(Basic basic.cpp)
+target_link_libraries (Basic lept tesseract)
+
+add_executable(GetComponent getcomp.cpp)
+target_link_libraries (GetComponent lept tesseract)
+
+add_executable(WordIter worditer.cpp)
+target_link_libraries (WordIter lept tesseract)
+
+add_executable(BasicCn basiccn.cpp)
+target_link_libraries (BasicCn lept tesseract)
+
+add_executable(Osd osd.cpp)
+target_link_libraries (Osd lept tesseract)
+
+add_executable(ClassIter clsiter.cpp)
+target_link_libraries (ClassIter lept tesseract)

test-tesseract-cpp/basic.cpp

@@ -0,0 +1,30 @@
+#include <tesseract/baseapi.h>
+#include <leptonica/allheaders.h>
+
+int main()
+{
+    char *outText;
+
+    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
+    // Initialize tesseract-ocr with English, without specifying tessdata path
+    if (api->Init(NULL, "eng")) {
+        fprintf(stderr, "Could not initialize tesseract.\n");
+        exit(1);
+    }
+
+    // Open input image with leptonica library
+    Pix *image = pixRead("../test.png");
+    api->SetImage(image);
+    // Get OCR result
+    outText = api->GetUTF8Text();
+    printf("OCR output:\n%s", outText);
+
+    // Destroy used object and release memory
+    api->End();
+    delete [] outText;
+    pixDestroy(&image);
+
+    return 0;
+}
+
+

test-tesseract-cpp/basiccn.cpp

@@ -0,0 +1,30 @@
+#include <tesseract/baseapi.h>
+#include <leptonica/allheaders.h>
+
+int main()
+{
+    char *outText;
+
+    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
+    // Initialize tesseract-ocr with English, without specifying tessdata path
+    if (api->Init(NULL, "chi_sim")) {
+        fprintf(stderr, "Could not initialize tesseract.\n");
+        exit(1);
+    }
+
+    // Open input image with leptonica library
+    Pix *image = pixRead("../testcn.png");
+    api->SetImage(image);
+    // Get OCR result
+    outText = api->GetUTF8Text();
+    printf("OCR output:\n%s", outText);
+
+    // Destroy used object and release memory
+    api->End();
+    delete [] outText;
+    pixDestroy(&image);
+
+    return 0;
+}
+
+

test-tesseract-cpp/clsiter.cpp

@@ -0,0 +1,49 @@
+#include <tesseract/baseapi.h>
+#include <leptonica/allheaders.h>
+
+int main() {
+
+    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
+    // Initialize tesseract-ocr with English, without specifying tessdata path
+    if (api->Init(NULL, "eng")) {
+        fprintf(stderr, "Could not initialize tesseract.\n");
+        exit(1);
+    }
+
+    // Open input image with leptonica library
+    Pix *image = pixRead("../test.png");
+    api->SetImage(image);
+    api->SetVariable("save_blob_choices", "T");
+    //api->SetRectangle(37, 228, 548, 31);
+    api->Recognize(NULL);
+
+    tesseract::ResultIterator* ri = api->GetIterator();
+    tesseract::PageIteratorLevel level = tesseract::RIL_SYMBOL;
+    if (ri != 0) {
+        do {
+            const char* symbol = ri->GetUTF8Text(level);
+            float conf = ri->Confidence(level);
+            if (symbol != 0) {
+                printf("symbol %s, conf: %f", symbol, conf);
+                bool indent = false;
+                tesseract::ChoiceIterator ci(*ri);
+                do {
+                    if (indent) printf("\t\t ");
+                    printf("\t- ");
+                    const char* choice = ci.GetUTF8Text();
+                    printf("%s conf: %f\n", choice, ci.Confidence());
+                    indent = true;
+                } while (ci.Next());
+            }
+            printf("---------------------------------------------\n");
+            delete[] symbol;
+        } while ((ri->Next(level)));
+    }
+    // Destroy used object and release memory
+    api->End();
+    pixDestroy(&image);
+
+    return 0;
+}
+
+

test-tesseract-cpp/getcomp.cpp

@@ -0,0 +1,36 @@
+#include <tesseract/baseapi.h>
+#include <leptonica/allheaders.h>
+
+int main() {
+
+    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
+    // Initialize tesseract-ocr with English, without specifying tessdata path
+    if (api->Init(NULL, "eng")) {
+        fprintf(stderr, "Could not initialize tesseract.\n");
+        exit(1);
+    }
+
+    // Open input image with leptonica library
+    Pix *image = pixRead("../test.png");
+    api->SetImage(image);
+
+    Boxa* boxes = api->GetComponentImages(tesseract::RIL_TEXTLINE, true, NULL, NULL);
+    printf("Found %d textline image components.\n", boxes->n);
+    for (int i = 0; i < boxes->n; i++) {
+        BOX* box = boxaGetBox(boxes, i, L_CLONE);
+        api->SetRectangle(box->x, box->y, box->w, box->h);
+        char* ocrResult = api->GetUTF8Text();
+        int conf = api->MeanTextConf();
+        fprintf(stdout, "Box[%d]: x=%d, y=%d, w=%d, h=%d, confidence: %d, text: %s",
+                i, box->x, box->y, box->w, box->h, conf, ocrResult);
+    }
+
+
+    // Destroy used object and release memory
+    api->End();
+    pixDestroy(&image);
+
+    return 0;
+}
+
+

test-tesseract-cpp/osd.cpp

@@ -0,0 +1,29 @@
+#include <tesseract/baseapi.h>
+#include <leptonica/allheaders.h>
+
+int main() {
+    tesseract::Orientation orientation;
+    tesseract::WritingDirection direction;
+    tesseract::TextlineOrder order;
+    float deskew_angle;
+
+    PIX *image = pixRead("../test.png");
+    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
+    api->Init(NULL, "eng");
+    api->SetPageSegMode(tesseract::PSM_AUTO_OSD);
+    api->SetImage(image);
+    api->Recognize(0);
+
+    tesseract::PageIterator* it = api->AnalyseLayout();
+    it->Orientation(&orientation, &direction, &order, &deskew_angle);
+    printf("Orientation: %d;\nWritingDirection: %d\nTextlineOrder: %d\n" \
+         "Deskew angle: %.4f\n",
+            orientation, direction, order, deskew_angle);
+    api->End();
+    pixDestroy(&image);
+
+
+    return 0;
+}
+
+

test-tesseract-cpp/worditer.cpp

@@ -0,0 +1,36 @@
+#include <tesseract/baseapi.h>
+#include <leptonica/allheaders.h>
+
+int main() {
+    char *outText;
+
+    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
+    // Initialize tesseract-ocr with English, without specifying tessdata path
+    if (api->Init(NULL, "eng")) {
+        fprintf(stderr, "Could not initialize tesseract.\n");
+        exit(1);
+    }
+
+    // Open input image with leptonica library
+    Pix *image = pixRead("../test.png");
+    api->SetImage(image);
+    api->Recognize(0);
+    tesseract::ResultIterator* ri = api->GetIterator();
+    tesseract::PageIteratorLevel level = tesseract::RIL_WORD;
+    if (ri != 0) {
+        do {
+            const char* word = ri->GetUTF8Text(level);
+            float conf = ri->Confidence(level);
+            int x1, y1, x2, y2;
+            ri->BoundingBox(level, &x1, &y1, &x2, &y2);
+            printf("word: '%s';  \tconf: %.2f; BoundingBox: %d,%d,%d,%d;\n",
+                    word, conf, x1, y1, x2, y2);
+            delete[] word;
+        } while (ri->Next(level));
+    }
+    api->End();
+    pixDestroy(&image);
+    return 0;
+}
+
+