recognition is a bit more robust....

Samo Penic

2018-11-16 ac766ed5ec375a384da5c454103aef055aa9344a

recognition is a bit more robust....

 aoiOcr.py

@@ -6,8 +6,8 @@
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_0028.tif')
#p=Paper(filename='sizif111.tif', sid_classifier=classifier, settings=settings)
p=Paper(filename='processed_scans/20141016095134535_0006.tif', sid_classifier=classifier, settings=settings)

# print(p.QRData)
# print(p.errors)

 sid_process.py

@@ -79,6 +79,32 @@
    return sid_no


def segment_by_sid_len(image,sid_len, classifier):
    sid_no=""
    #find biggest block of pixels

    image1=cv2.morphologyEx(image,cv2.MORPH_DILATE, kernel(5,25), iterations=3)
    cv2.imwrite("sidblock1.png",image1)
    im2, ctrs, hier = cv2.findContours(
        image1.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
    )
    sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.contourArea(ctr)) #get bigges contour
    x, y, w, h = cv2.boundingRect(sorted_ctrs[-1])
    image=image[y:y+h,x+25:x+w-25]
    cv2.imwrite("sidblock2.png",image)
    imgHeight, imgWidth = image.shape[0:2]
    numWidth=int(imgWidth/(sid_len))
    for i in range(0,sid_len):
        num=image[:,i*numWidth:(i+1)*numWidth]
        num = img_as_ubyte(num < 128)
        num = cv2.resize(num, (32, 32))

        # cv2.rectangle(image,(x,y),( x + w, y + h ),(0,255,0),2)
        cv2.imwrite("sid_no_{}.png".format(i), num)
        sid_no = sid_no + str(classifier.predict(num.reshape(1, -1) / 255.0)[0])
    return sid_no


def getSID(image, classifier, sid_mask):
    image = 255 - image
    image = img_as_ubyte(image > 100)
@@ -89,7 +115,9 @@
    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)
    #image = cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel(8, 8), iterations=1)
    image = cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel(3, 3), iterations=1)

    # Skeletonization
    image = img_as_ubyte(morphology.thin(image > 128))
    cv2.imwrite("enSID1.png", image)
@@ -101,18 +129,21 @@
    # Thining again
    image = img_as_ubyte(morphology.skeletonize(image > 0.5))
    image = cv2.morphologyEx(image, cv2.MORPH_DILATE, kernel(10, 10))

    cv2.imwrite("enhancedSID.png",image)
    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])

    sid_no = ""
    sid_len = 0
    if sid_mask is not None:
        if len(sid_mask)==len(sorted_ctrs):
            sid_no=segment_by_contours(image,sorted_ctrs,classifier)
        else:
            print("Ooops have to find another way")
    #sid_len = len(sid_mask)
    #sid_no = segment_by_sid_len(image, sid_len, classifier)
    #if sid_mask is not None:
    print(len(sid_mask),len(sorted_ctrs))
    #if len(sid_mask)==len(sorted_ctrs):
    sid_no=segment_by_contours(image,sorted_ctrs[1:],classifier)
    print(sid_no)
    if(len(sid_no)!=len(sid_mask)):
        print("Ooops have to find another way")
        sid_no=segment_by_sid_len(image,len(sid_mask),classifier)
    return sid_no