Don't create an empty lstmf file

If Tesseract cannot find text in the input image, it should not write an empty lstmf file. This problem was reported in issue tesseract-ocr#2741. Signed-off-by: Stefan Weil <sw@weilnetz.de>
wanghaipeng789 · Nov 1, 2019 · 94d0f77 · 94d0f77
1 parent 6f31c3b
commit 94d0f77
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/src/ccmain/linerec.cpp b/src/ccmain/linerec.cpp
@@ -61,6 +61,10 @@ void Tesseract::TrainLineRecognizer(const STRING& input_imagename,
     return;
   }
   TrainFromBoxes(boxes, texts, block_list, &images);
+  if (images.NumPages() <= 0) {
+    tprintf("Failed to read pages from %s\n", input_imagename.c_str());
+    return;
+  }
   images.Shuffle();
   if (!images.SaveDocument(lstmf_name.c_str(), nullptr)) {
     tprintf("Failed to write training data to %s!\n", lstmf_name.c_str());