这个程序演示Tesseract OCR按单词识别字符。
不仅显示识别结果，还找出每个单词的bounding box(边界框/包围盒)。
输入图片：
程序运行后会在CMD里打印识别结果：
结果太长，我只截了一部分。
第一行的意思是：单词“this的置信度是94.57，对应的矩形边界框的左上角坐标是(36,92),右下角坐标是(96,116).
把前两个单词对应的矩形框绘制到输入图片里，大概就是这样：
代码：
#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); } Pix *image = pixRead("phototest.tif"); 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)); } // Destroy used object and release memory api->End(); delete api; delete [] outText; pixDestroy(&image); return 0; }