Development of the ocr part of AOI
Samo Penic
2018-11-17 82ec6d384adcc4ca543661c8bb2cec38e836e91b
aoiOcr.py
@@ -1,13 +1,27 @@
from Ocr import Paper
from sklearn.externals import joblib
from glob import glob
settings = {"sid_mask": "61xx0xxx", "answer_treshold": 0.25}
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=settings)
p=Paper(filename='processed_scans/20141016095134535_0006.tif', sid_classifier=classifier, settings=settings)
#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)
pa = [
    "processed_scans/20141016095134535_0006.tif",
    "processed_scans/20141016095134535_0028.tif",
    "processed_scans/20141016095134535_0028.tif",
    "processed_scans/20141016095134535_0037.tif",
    "processed_scans/20141021095744144_0005.tif",
    "processed_scans/20141021095744144_0009.tif",
    "processed_scans/20141028095553745_0018.tif",
    "processed_scans/20151013180545275_0011.tif"
]
p=Paper(filename=pa[7], sid_classifier=classifier, settings=settings)
# print(p.QRData)
# print(p.errors)
@@ -20,3 +34,13 @@
print(p.get_paper_ocr_data())
exit(0)
filelist = glob("processed_scans/*.tif")
for f in sorted(filelist):
    print("processing: {}".format(f))
    print(
        f,
        Paper(
            filename=f, sid_classifier=classifier, settings=settings
        ).get_paper_ocr_data(),
    )