Development of the ocr part of AOI
Samo Penic
2018-11-21 9c222b2a0b151e7219e30f0145aa92872890d838
aoiOcr.py
@@ -1,10 +1,13 @@
from Ocr import Paper
from aoi_ocr.Ocr import Paper
from sklearn.externals import joblib
import pkg_resources
path = '/filename.joblib'  # always use slash
filepath = pkg_resources.resource_filename('aoi_ocr', path)
from glob import glob
settings = {"sid_mask": "64xx0xxx", "answer_threshold": 0.25}
classifier = joblib.load("filename.joblib")
settings = {"sid_mask": "11x0xxxx", "answer_threshold": 0.25}
classifier = joblib.load(filepath)
#p = Paper(filename="testpage300dpi_scan1.png")
#p=Paper(filename='sizif111.tif', sid_classifier=classifier, settings={"sid_mask": "11xx0xxx", "answer_threshold": 0.25})
@@ -23,7 +26,8 @@
    "processed_scans/20160408140801098_0004.tif",
    "processed_scans/20160510075445995_0026.tif"
]
p=Paper(filename=pa[9], sid_classifier=classifier, settings=settings)
#p=Paper(filename=pa[9], sid_classifier=classifier, settings=settings)
p=Paper(filename='test3.tif', sid_classifier=classifier, settings=settings)
# print(p.QRData)
# print(p.errors)
@@ -37,7 +41,7 @@
print(p.get_paper_ocr_data())
exit(0)
filelist = glob("processed_scans/*.tif")
wrong_sid=0;
total=0
@@ -52,4 +56,4 @@
    if total%10 == 0:
        print("Total:{}, wrong SID: {}".format(total,wrong_sid))
print("Total:{}, wrong SID: {}".format(total,wrong_sid))
print("Total:{}, wrong SID: {}".format(total,wrong_sid))