Ask Your Question

Atado's profile - activity

2017-01-20 07:27:30 -0500 asked a question SimpleBlobDetector - Extract Rectangle

Hey, im trying to find some rectangle blobs in Android and thought i could use the SimpleBlobDetector for that.

The image im searching in looks like this: image description

Im trying to detect the position of the blue filled rectangles left to the "X"es. I played a bit with the SimpleBlobDetector Settings but i cant get it to detect the rectangles.

Could someone help me to find the right settings? Or is there a better way to detect those small rectangles (or alternative the 'X'es than the SimpleBlobDetector?

Best regards

2017-01-19 01:15:27 -0500 commented answer Extract writing from colorful background

Thats a nice result, thank you!

2017-01-19 01:15:15 -0500 received badge  Scholar (source)
2017-01-18 07:29:49 -0500 received badge  Student (source)
2017-01-18 07:21:13 -0500 received badge  Editor (source)
2017-01-18 07:20:37 -0500 asked a question Extract writing from colorful background

Hey, im trying to extract a handwritten sum from a colorful background. So as a result i'd like to have a binary image with the sum black and the colorful background should be all filtered out and set to white.

The image looks like this: image description

I tried various treshholds, grabcut, color filters and morphologic operations to improve quality but i cant get a decent result.

I could maybe filter for "only" black in HSV color space, but in other images the sum might be written in blue. Maybe someone knows how to get the best possible result here.

Best regards

2016-10-11 01:29:19 -0500 asked a question Extract area inside rectangle

Hey,

i have some Bitmaps in an Android App which always contain some kind of rectangle in the right part of the image. The rectangle is not fully closed tho. Inside this rectangle theres some numbers. Basically i want to delete everything in that image except for the part inside the rectangle.

Example image: Input

Now i would like to detect the rectangle on the right and just keep the stuff inside it. So basically just the things inside the red box: Output

Since im new to OpenCV i dont really have an idea whats the best way of doing this. Maybe its important to say, that the images can also be slighty rotated so the rectangle is not always perfect horizontally or at the exact same spot.

Hope you can give me some tips how to accomplish this. Best regards

2016-09-22 07:06:16 -0500 received badge  Enthusiast
2016-09-12 04:51:39 -0500 commented answer Dropout red color and binarize image (Android)

Thanks alot for your answer. I think i managed to implement the first 4 steps but im stucking at the last one. Im not really sure what u mean with "Now apply a mask and set that mask to white, then merge both images together." Hope you can help me. Best regards

2016-09-12 02:35:21 -0500 received badge  Supporter (source)
2016-09-09 04:47:03 -0500 asked a question Dropout red color and binarize image (Android)

Hey, im new to OpenCV and i'd like to use it in my Android Application.

In the app i have to process some images of transactions like this: Example image

I want to filter/dropout the red form color and then binarize the image.

Later i need some OCR to recognize some numbers in the footer etc. so thought i use this to improve the quality of the image:

Imgproc.morphologyEx(mat, mat, Imgproc.MORPH_OPEN, Imgproc.getStructuringElement(Imgproc.MORPH_RECT, new Size(2, 2)));
    Imgproc.morphologyEx(mat, mat, Imgproc.MORPH_CLOSE, Imgproc.getStructuringElement(Imgproc.MORPH_RECT, new Size(2, 2)));

The opening should remove the noise in the image and the closing after should improve the written values on the image.

Im not sure tho whats the best way to accomplish the first part (filtering the red form color and binarizing the image). Hope you can give me some tips.

Best regards