ashutoshraj / signaturerecognition Goto Github PK

In StrokeFilter.py file function def strokeFilter(im, orient, freq, kx, ky): is giving error on following line

sigmax = 1 / unfreq[0] * kx 
sigmay = 1 / unfreq[0] * ky

Error Stack -

File "D:\OCR\signature_extractor-master\signature_verifier\verifier\__init__.py", line 12, in verify
    kp1, des1 = extractKeypoints(img1)
  File "D:\OCR\signature_extractor-master\signature_verifier\verifier\ExtractKeypoints.py", line 42, in extractKeypoints
    img = preprocessing(img)
  File "D:\OCR\signature_extractor-master\signature_verifier\verifier\Preprocessing.py", line 26, in preprocessing
    newim = strokeFilter(normim, orientim, freq, kx, ky)
  File "D:\OCR\signature_extractor-master\signature_verifier\verifier\StrokeFilter.py", line 21, in strokeFilter
    sigmax = 1 / unfreq[0] * kx
IndexError: index 0 is out of bounds for axis 0 with size 0

Which algorithm you use in strokeOrient method and StrokeFequency Library ?

Hello, I had tried to run your code but for some of the images, the output is coming wrong. Can you please let me know what preprocessing steps are required on images for correct output ?

Hello I seem to hit an error from _tkinter.TclError: no display name and no $DISPLAY environment variable despite the fact I'm running with the --visual=False. What can I be missing?

gabor_filter = np.array(np.zeros((180 / angleInc, filt_rows, filt_cols)))
TypeError: 'float' object cannot be interpreted as an integer

While running the code with default values, this error shows up and prevents program to run further
I tried resolving it by using
gabor_filter = np.array(np.zeros((int(180/angleInc), (filt_rows), (filt_cols)), dtype = int))

but this shows another error

for o in range(0, 180 / angleInc):
TypeError: 'float' object cannot be interpreted as an integer

I looked for a solution online and found this

Replacing this part

for o in range(0,180/angleInc):`
    rot_filt = scipy.ndimage.rotate(reffilter,-(o*angleInc + 90),reshape = False)
    gabor_filter[o] = rot_filt

by this

angle_for_iter = (0,180/angleInc)
start_angle, last_angle = angle_for_iter
start_angle = int(start_angle)
last_angle = int(last_angle)
	
for o in range(start_angle, last_angle):
    rot_filt = scipy.ndimage.rotate(reffilter,-(o*angleInc + 90),reshape = False)
    gabor_filter[o] = rot_filt

after this is done we get an error in match

matches = sorted(bf.match(des1, des2), key=lambda match: match.distance)
cv2.error: OpenCV(4.1.0) C:\projects\opencv-python\opencv\modules\core\src\batch_distance.cpp:275: error: (-215:Assertion failed) type == src2.type() && src1.cols == src2.cols && (type == CV_32F || type == CV_8U) in function 'cv::batchDistance'

and i am stuck at this