| | |
| | | from Ocr import Paper |
| | | from sklearn.externals import joblib |
| | | |
| | | from glob import glob |
| | | |
| | | settings = {"sid_mask": "11xx0xxx", "answer_treshold": 0.25} |
| | | settings = {"sid_mask": "61xx0xxx", "answer_treshold": 0.25} |
| | | classifier = joblib.load("filename.joblib") |
| | | |
| | | #p = Paper(filename="testpage300dpi_scan1.png") |
| | | #p=Paper(filename='sizif111.tif', sid_classifier=classifier, settings=settings) |
| | | p=Paper(filename='processed_scans/20141016095134535_0006.tif', sid_classifier=classifier, settings=settings) |
| | | #p=Paper(filename='processed_scans/20141016095134535_0006.tif', sid_classifier=classifier, settings=settings) |
| | | #p=Paper(filename='processed_scans/20151111080408825_0001.tif', sid_classifier=classifier, settings=settings) |
| | | p=Paper(filename='processed_scans/20151028145444607_0028.tif', sid_classifier=classifier, settings=settings) |
| | | |
| | | # print(p.QRData) |
| | | # print(p.errors) |
| | |
| | | |
| | | |
| | | print(p.get_paper_ocr_data()) |
| | | exit(0) |
| | | filelist = glob("processed_scans/*.tif") |
| | | for f in filelist: |
| | | print(f,Paper(filename=f, sid_classifier=classifier, settings=settings).get_paper_ocr_data()) |
| | | |