How do I define the bottom row?

조회 수: 4 (최근 30일)
Stelios Fanourakis
Stelios Fanourakis 2019년 3월 18일
댓글: Stelios Fanourakis 2019년 3월 18일
Hi
I have acquired several ultrasound images with different pin sizes, for a validation test of mine.
I know the real pin size, and that would be my ground truth. The problem is that when I plot the results of the segmented image (see attached image) in excel file (I export numerical pixel values to excel, the green mask contour, and just plot it), the obvious bottom line where the standoff polymer meets the table and is delined by the green contour is not actually the correct boundary for the accurate pin height measurement.
For instance, if I define the bottom row, where the contour lies horizontally, then I get around 0,42 mm error. The true boundary is approximately 10 pixels above the contour line. How can I justify this to my professor? He won't accept it. As he can see the visible green boundary, at the specific line, he will believe that this line is the correct no matter what and it's me that I must doing something wrong.
But that's not the truth. I have tried hundreds of times and every time I get around that error when I define bottom row as where the contour lies.
I just need to find a reason to justify to my supervisor, that the actual boundary of standoff-desk is approximately 10 pixels higher than it shows and the bright constrast that is being seen on the image is just artifact.
Any other explanation please?
  댓글 수: 2
Walter Roberson
Walter Roberson 2019년 3월 18일
It would help if we also had a copy of that image without the green line, and if we had more details as to how you are processing the image.
Stelios Fanourakis
Stelios Fanourakis 2019년 3월 18일
@Walter, here is the image without the contour. I need to define a bottom row (horizontally, where the standoff supposely meets the table) and from that row up until the tip of the pin I count the pixels to estimate the pin height. I know the actual pin height, and this is my ground truth. So, more or less with a minor error, such as ±5% it should come up. For instance, if I have a 2.5 mm pin, then I should get results from 2,37 - 2,62 mm.
As I explained earlier, the above mm band, I get it only when I define the bottom row a bit upper than ideally seems to the eye of the beholder. Slightly upper than the white sharp contrast line.
I just cannot explain why it cannot be the white sharp line where denotes the boundaries of the standoff material and the desk

댓글을 달려면 로그인하십시오.

답변 (0개)

카테고리

Help CenterFile Exchange에서 Feature Detection and Extraction에 대해 자세히 알아보기

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by