Blob detection defective displays

OpenMV Products
1

Hello,

i’m relatively new in this topic. Hope someone can help me out.

I would like to detect defective displays from a device.

The camera is permanentely mounted in the test equipement and show the picture of the display.

I would like now to detect defective parts of the display via blob detection.

Here is a picture of what the camera see’s.

campic
campic785×1095 79.2 KB

Now i’ve tried to recognize the gray areas via blob detection with this code:

import sensor, image, time, pyb

areax = 150
areay = 100
hys = (0, 100, 8, 127, -128, 127)
hys_sw = (200, 255)
#hys_sw = (80, 100, 120, 140, 140, 180)
r = ((640//2)-(areax//2), (480//2)-(areay//2), areax, areay) # 50x50 center of QVGA.
are_thr = areax * areay

print(r)

sensor.reset()
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.VGA)
sensor.skip_frames(time = 2000)

clock = time.clock()

while(True):
    clock.tick()
    img = sensor.snapshot()

 #   img.draw_rectangle(r, color = (127,127,127))

    # Find blobs with a minimal area of 50x50 = 2500 px
    # Overlapping blobs will be merged
    blobs = img.find_blobs([hys_sw], area_threshold=are_thr, merge=True)

    # Draw blobs
    for blob in blobs:
        # Draw a rectangle where the blob was found
        img.draw_rectangle(blob.rect(), color=(127,127,127))
        # Draw a cross in the middle of the blob
        img.draw_cross(blob.cx(), blob.cy(), color=(127,127,127))

        print("blobs found")

    pyb.delay(100) # Pauses the execution for 100ms
    print(clock.fps())

All was i get is this:

fail_m

Only two white areas left and right.

What i’m doing wrong? I’v changed the threshold between 100 and 130 but it helped not out.

Can somebody help me.

Thanks.

2

Hello again,

found the solution for myself.

The threshold area was to big. Reducing these helped.

3

Hi there,

you have to pass
invert=0 for white blobs
invert=1 for black blobs
inside the blobs tool.