Multi-scale crest line extraction based on half Gaussian Kernels

Abstract

Crest line extraction has always been a challenging task in image processing and its applications. It is possible to detect ridges and valleys in images using second order filters. In order to estimate crest lines of variable widths, a multiscale analysis of the image is required. In this paper we propose a new ridge/valley detection method in images based on the difference of rotating Gaussian semi filters adapted in a multi-scale process. Due to the directional filters, we obtain a new ridge/valley anisotropic detector enabling very precise detection of ridge/valley of varied widths. Moreover, as the detector filters compute the two directions of crest lines, even highly bended crest lines are correctly extracted. Numerical comparisons with other oriented Gaussian filters and results on real images validate the interest of this method.

Edge detection: a review of dissimilarity evaluations and a proposed normalized measure

“…2 for more details. Computing only FPs and FNs enables a segmentation assessment to be performed [35] [36]. Yet, combining at least these two quantities enables…”

“…In the crest lines case [37], true edges are chosen in the middle of the ridge or of the valley when the width of the ridge/valley is equal to a odd number (i.e. at the maxima -top of ridges-or minima -bottom of valleys- [36] ). Finally, for a single real or synthetic image, as several contour chains constituting the ground truth depend on several positions of the true pixels, thus the combinations of the boundary pixel placements are numerous, so many chains could be created/chosen.…”

A New Normalized Supervised Edge Detection Evaluation

“…Finally, a wrong threshold of the segmentation could generate both FPs and FNs. Computing only FPs and FNs enables a segmentation assessment [6] [7], and a reliable edge detection should minimize the following indicators [3]: Additionally, the P erf ormance measure P * m presented in Table 1 considers directly at the same time the three entities T P , F P and F N to assess an a binary image. The obtained score reflects the percentage of statistical errors.…”

A quantitative error measure for the evaluation of roof edge detectors

“…Finally, a failing threshold of the segmentation could create both FPs and FNs. Computing only FPs and FNs [19] [22] or combining these two statistics allows to display evaluations like Receiver Operating Characteristic (ROC) [23] or Precision-Recall (PR) [6]. As illustrated in Fig.…”