Rashmi's profile - activity

@berak Thank you so much..

As i am struggling to fine tune HoughCircles for my application, i want to see method code which opencv is using for circle detection. Quality of detecting circle for good image also very bad. I want to check how circles are sorted. Kindly do the needful or provide some reference.

I am developing commercial software for reading images and finding region of interest by passing top left corner coordinates and bottom right coordinates of rectangle then crop the image.Some client provides samples like 100 dpi, 200 dpi or 400 dpi images of same image. Because these kind of images, my coordinates lie somewhere else. How can i fix a problem to find actual area of interest for different dpi of images and find exact ROI? Give some rough idea to solve it.

first = [1025,1000]
last = [1550,1400]
image = cv2.imread("db/SGBAU/pink OMR/200.jpg")
def ROI_extract(first_corner,last_corner,image):
#croping ROI
ROI_img = image[first_corner[1]:last_corner[1],first_corner[0]:last_corner[0]]
cv2.imwrite(os.path.join('db/','ROI.png'), ROI_img)
return ROI_img

in this code i am not getting how are you generating result image where alphabets are printed on filled circle. after that how are you decoding alphabets in single string?

yeah..i solved this issue.Thank you very much. pnts = np.array(points) rect = cv2.minAreaRect(pnts) box = cv2.cv.BoxPoints(rect) box1 = np.int0(box) cv2.drawContours(resized,[box1],0,(0,255,0),2)

rect = cv2.minAreaRect(points) box = cv2.cv.BoxPoints(rect) box = np.int0(box) cv2.drawContours(img,[box],0,(0,0,255),2)

i have written like this but error is coming like TypeError: points is not a numpy array, neither a scalar

i have to first save this center points of rectangle in one variable then i can pass that variable inside minAreaRect. Is it r8?

I have image which contain 12 center point of rectangle. I am not getting how to code for image rotation from that point.C:\fakepath\deskew.png.Please help me with some code in opencv and python

i am going to make software which can detect image and check image alignment and make it proper. Is we require reference image? what will be the case if reference image is also not in correct position? I want to clear the concept of image alignment?

@essamzaky Is hough transform give best result for deskew of image?

@pi-null-mezon thank you for the solution.i will try and let you know how it working

In OMR, if scanned OMR is not in correct position then how can i deskew the image and search exact location of roll number rectangle?i want to extract information from different rectangle based on bubble selection. i need help to sort out this problem.

i need solution in python itself. in my case after detecting black circle it will be evaluated as candidate roll number. so code will print roll number. i am facing problem to decoding circle as it is image. i am very new in this domain. Please help me out

Can i get this code in python with open cv? i am not able to understand it..

i want solution in python as m not good in java

I am working on OMR and i am detecting circle who are selected by student. Now i am not getting how to get the selected numbered circle which marked by student.I am looking solution/idea for opencv 2.3.12 and python

C:\fakepath\circlesample1.png