Development of the ocr part of AOI
Samo Penic
2018-11-21 5460bf601a854c842342a740df0f6d36ad785bbc
aoiOcr.py
@@ -1,8 +1,9 @@
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)
path = "/filename.joblib"  # always use slash
filepath = pkg_resources.resource_filename("aoi_ocr", path)
from glob import glob
@@ -24,16 +25,16 @@
    "processed_scans/20141028095553745_0018.tif",
    "processed_scans/20151013180545275_0011.tif",
    "processed_scans/20160408140801098_0004.tif",
    "processed_scans/20160510075445995_0026.tif"
    "processed_scans/20160510075445995_0026.tif",
]
#p=Paper(filename=pa[9], sid_classifier=classifier, settings=settings)
p=Paper(filename='test3.tif', sid_classifier=classifier, settings=settings)
p = Paper(filename="test3.tif", sid_classifier=classifier, settings=settings)
# print(p.QRData)
# print(p.errors)
# print(p.getSkewAngle())
# print(p.locateUpMarkers())
# print(p.locateUpMarkers())%%
# print(p.locateRightMarkers())
# print(p.answerMatrix)
# p.get_enhanced_sid()
@@ -43,15 +44,17 @@
exit(0)
filelist = glob("processed_scans/*.tif")
wrong_sid=0;
wrong_sid = 0
total=0
for f in sorted(filelist):
    print("processing: {}".format(f))
    p=Paper(filename=f, sid_classifier=classifier, settings=settings).get_paper_ocr_data()
    p = Paper(
        filename=f, sid_classifier=classifier, settings=settings
    ).get_paper_ocr_data()
    print(f,p)
    if(p['page_no']==0):
    if p["page_no"] == 0:
        total+=1
    if(len(p['errors'])!=0):
    if len(p["errors"]) != 0:
        wrong_sid+=1
    if total%10 == 0:
        print("Total:{}, wrong SID: {}".format(total,wrong_sid))