Ignore images that are contained in others
This commit is contained in:
parent
8ece616229
commit
0ed7f2b622
@ -102,6 +102,17 @@ public class PdfSegmentationService {
|
|||||||
page.setLandscape(isLandscape || isRotated);
|
page.setLandscape(isLandscape || isRotated);
|
||||||
page.setPageNumber(pageNumber);
|
page.setPageNumber(pageNumber);
|
||||||
List<PdfImage> mergedList = processImages(stripper.getImages());
|
List<PdfImage> mergedList = processImages(stripper.getImages());
|
||||||
|
|
||||||
|
List<PdfImage> imagesInImage = new ArrayList<>();
|
||||||
|
for(PdfImage image: mergedList){
|
||||||
|
for (PdfImage inner: mergedList){
|
||||||
|
if(image != inner && image.getPosition().contains(inner.getPosition().getX(), inner.getPosition().getY(), inner.getPosition().getWidth(), inner.getPosition().getHeight())){
|
||||||
|
imagesInImage.add(inner);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
mergedList.removeAll(imagesInImage);
|
||||||
|
|
||||||
page.setImages(mergedList);
|
page.setImages(mergedList);
|
||||||
|
|
||||||
tableExtractionService.extractTables(cleanRulings, page);
|
tableExtractionService.extractTables(cleanRulings, page);
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user