String classification with opencv

I am working on a project for classifying images, I have extracted curved lines from the image using edge detection and must classify them based on their curvature.

For example, in the image below there are 3 types of lines, the left line has good curvature, the middle one has good curvature, and the right line has very bad curvature.

curves

thanks for the help

+5
source share
2 answers

I see several possible measures for addition:

Try an approximate line with an approximate window, and then check how many segments of the approximate line, fewer segments are the best line. (This can lead to problems in most left-handed cases when a row contains several segments)

,

.

+4

, , , , , "" "" . ( ). , , . , , , , . .

, , 2.4.2 http://oa.upm.es/4837/1/MARCOS_NIETO_DONCEL.pdf

!

+5

All Articles