Improving the robustness of all three algorithms. Again...

Samo Penic

2018-11-17 6fde5fba87aaf2f2ad8c4af08a59454f06d8dc30

 aoiOcr.py

@@ -6,8 +6,8 @@
settings = {"sid_mask": "64xx0xxx", "answer_treshold": 0.25}
classifier = joblib.load("filename.joblib")

# p = Paper(filename="testpage300dpi_scan1.png")
#p=Paper(filename='sizif111.tif', sid_classifier=classifier, settings={"sid_mask": "11xx0xxx", "answer_treshold": 0.25})
#p = Paper(filename="testpage300dpi_scan1.png")
p=Paper(filename='sizif111.tif', sid_classifier=classifier, settings={"sid_mask": "11xx0xxx", "answer_treshold": 0.25})
#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)
@@ -20,7 +20,7 @@
    "processed_scans/20141021095744144_0009.tif",
    "processed_scans/20141028095553745_0018.tif",
]
p=Paper(filename=pa[6], sid_classifier=classifier, settings=settings)
#p=Paper(filename=pa[6], sid_classifier=classifier, settings=settings)

# print(p.QRData)
# print(p.errors)
@@ -33,7 +33,7 @@


print(p.get_paper_ocr_data())

exit(0)
filelist = glob("processed_scans/*.tif")
for f in sorted(filelist):
    print("processing: {}".format(f))