object recognition - best approach for template matching of binary (edge) images -


to skimage , opencv gurus, given:

  1. scene image

enter image description here

  1. template image

enter image description here

what best approach find cross in scene image ? these output smoothing, , canny filters. now, tried kinds of examples in skimage, , opencv template matching results not satisfactory.

my ideal solution rotation, translation invariant (scale invariant bonus) . there way convert contour points , them registration point cloud ? more accurate ? thought ransac how give inputs ransac?

thanks

my approach solving similar problem create large set of rotated , scaled variations of template image , use opencv's matchtemplate function.

i recommend preprocessing step of filling detected , closed contours (for both template , scene image) white since largely black template image might create false positives in black regions of scene image.


Comments

Popular posts from this blog

multithreading - Exception in Application constructor -

React Native allow user to reorder elements in a scrollview list -

windows - CertCreateCertificateContext returns CRYPT_E_ASN1_BADTAG / 8009310b -