From 02e0f7bc51acfa06e7299919b54b56a3c7eca02b Mon Sep 17 00:00:00 2001
From: Samo Penic <samo.penic@gmail.com>
Date: Fri, 16 Nov 2018 18:22:33 +0000
Subject: [PATCH] Initial version of sid recognition. Cutting the numerals is not perfect yet.
---
aoiOcr.py | 6 ++
sid_process.py | 33 ++++++++++++++--
.idea/sonarIssues.xml | 5 ++
Ocr.py | 21 +++++++---
4 files changed, 54 insertions(+), 11 deletions(-)
diff --git a/.idea/sonarIssues.xml b/.idea/sonarIssues.xml
index c014979..60f73dd 100644
--- a/.idea/sonarIssues.xml
+++ b/.idea/sonarIssues.xml
@@ -13,6 +13,11 @@
<set />
</value>
</entry>
+ <entry key="/a.dummy">
+ <value>
+ <set />
+ </value>
+ </entry>
<entry key="$PROJECT_DIR$/Ocr.py">
<value>
<set />
diff --git a/Ocr.py b/Ocr.py
index 0da4497..35c6729 100644
--- a/Ocr.py
+++ b/Ocr.py
@@ -1,17 +1,18 @@
from pyzbar.pyzbar import decode
-from sid_process import enhanceSID
+from sid_process import getSID
import cv2
import numpy as np
import math
class Paper:
- def __init__(self, filename=None):
+ def __init__(self, filename=None, sid_classifier=None):
self.filename = filename
self.invalid = None
self.QRData = None
self.errors = []
self.warnings = []
+ self.sid_classifier=sid_classifier
if filename is not None:
self.loadImage(filename)
self.runOcr()
@@ -137,8 +138,8 @@
loc_filtered_x, loc_filtered_y = zip(
*sorted(zip(loc_filtered_x, loc_filtered_y))
)
- # loc=[loc_filtered_y,loc_filtered_x]
- # remove duplicates
+ # loc=[loc_filtered_y,loc_filtered_x]
+ # remove duplicates
a = np.diff(loc_filtered_x) > 40
a = np.append(a, True)
loc_filtered_x = np.array(loc_filtered_x)
@@ -213,5 +214,13 @@
self.answerMatrix.append(oneline)
def get_enhanced_sid(self):
- es= enhanceSID(self.img[int(0.04*self.imgHeight):int(0.08*self.imgHeight), int(0.7*self.imgWidth):int(0.99*self.imgWidth)])
- cv2.imwrite("enhancedSID.png",es)
\ No newline at end of file
+ if self.sid_classifier is None:
+ return "x"
+ es = getSID(
+ self.img[
+ int(0.045 * self.imgHeight) : int(0.085 * self.imgHeight),
+ int(0.7 * self.imgWidth) : int(0.99 * self.imgWidth),
+ ],
+ self.sid_classifier,
+ )
+ return es
diff --git a/aoiOcr.py b/aoiOcr.py
index c8bc97b..72ed3b9 100644
--- a/aoiOcr.py
+++ b/aoiOcr.py
@@ -1,8 +1,12 @@
from Ocr import Paper
+from sklearn.externals import joblib
+classifier = joblib.load('filename.joblib')
#p=Paper(filename='testpage300dpi_scan1.png')
-p=Paper(filename='sizif111.tif')
+p=Paper(filename='sizif111.tif', sid_classifier=classifier)
+#p=Paper(filename='processed_scans/20141016095134535_0028.tif')
+
print(p.QRData)
print(p.errors)
diff --git a/sid_process.py b/sid_process.py
index 210cfe7..90d9b33 100644
--- a/sid_process.py
+++ b/sid_process.py
@@ -1,6 +1,10 @@
import cv2
import numpy as np
from skimage import morphology,img_as_ubyte
+from sklearn import svm
+from sklearn.externals import joblib
+
+
"""
(1) The text is an array of chars (in row-major order) where
@@ -57,19 +61,18 @@
return np.ones((x, y), np.uint8)
-def enhanceSID(image):
+def getSID(image, classifier):
image=255-image
image=img_as_ubyte(image>100)
cv2.imwrite("enSID0.png", image)
# Remove noise
image = cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel(2,2), iterations=1)
# Closing. Connect non connected parts
- image = cv2.morphologyEx(image, cv2.MORPH_CLOSE, kernel(5, 5), iterations=2)
+ image = cv2.morphologyEx(image, cv2.MORPH_CLOSE, kernel(5, 3), iterations=4)
# Again noise removal after closing
+
image = cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel(8,8), iterations=1)
# Skeletonization
- ##For thinning I am using erosion
- ##image = cv2.erode(image,kernel(4,4),iterations = 40)
image = img_as_ubyte(morphology.thin(image>128))
cv2.imwrite("enSID1.png",image)
# Stub removal (might not be necessary if thinning instead of skeletonize is used above
@@ -80,4 +83,26 @@
# Thining again
image = img_as_ubyte(morphology.skeletonize(image>0.5))
image = cv2.morphologyEx(image, cv2.MORPH_DILATE, kernel(10, 10))
+
+ im2,ctrs, hier = cv2.findContours(image.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+ sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])
+
+ #classifier = joblib.load('filename.joblib')
+
+ sid_no=""
+ for i, ctr in enumerate(sorted_ctrs):
+ # Get bounding box
+ x, y, w, h = cv2.boundingRect(ctr)
+ # Getting ROI
+ if(w<h/2):
+ sid_no=sid_no+"1"
+ continue
+ roi = image[y:y+h, x:x+w]
+ roi = img_as_ubyte(roi < 128)
+ roi = cv2.resize(roi,(32,32))
+
+ #cv2.rectangle(image,(x,y),( x + w, y + h ),(0,255,0),2)
+ cv2.imwrite('sid_no_{}.png'.format(i), roi)
+ sid_no=sid_no+str(classifier.predict(roi.reshape(1,-1)/255.0)[0])
+ print(sid_no)
return image
--
Gitblit v1.9.3