Ridge Detection by Image Filtering Techniques: A Review and an Objective Analysis

Abstract

Ridges (resp., valley) are the useful geometric features due to their wide varieties of applications, mainly in image analysis problems such as object detection, image segmentation, scene understanding, etc. Many characterizations have contributed to formalize the ridge notion. The signification of each characterization rely however on its actual application. The objective analysis of ridge characterized as thin and complex image structure is thus essentially important, for choosing which parameter's values correspond to the suitable configuration to obtain accurate results and optimal performance. In this article an extensive analysis followed by a supervised and objective comparison of different filtering-based ridge detection techniques is led. Furthermore, the optimal parameter configuration of each filtering techniques aimed for image salient feature analysis tool have been objectively investigated, where each chosen filter's parameters corresponds to the width of the desired ridge or valley. At last, the comparative evaluations and analysis results are reported on both synthetic images, distorted with various types of noises and real images.

Repeatability Evaluation of Keypoint Detection Techniques in Tracking Underwater Video Frames

“…Generally, in image filtering, the first or second derivatives may be utilized to determine corners in an image. Considering a gray-level image I, its partial derivatives are: These image derivatives can be calculated by convolving the image with the [1 0 -1] or the [1 0 -2 0 1] masks in the x and/or y directions for the first and second derivatives, respectively [20]. The first derivatives are useful for the detection of step and ramp edges, whereas the second derivatives are convenient for the contour extraction of types: line, roof edges as ridge/valley features.…”

Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks

“…It should be emphasized that introducing a new skeletonization method is not the focus of this paper, though Fig. 2 Object skeletons (from simple to complex) in various applications: a farmland ridge detection for agricultural robot navigation (Li and Qu, 2018;Shokouh et al, 2021), b character recognition (Bag et al, 2011;Zhang et al, 2015), and c plant analysis (Bucksch, 2014;Sharma et al, 2021) SkeView can be extended for this purpose. This is because our proposed strategy is applied semi-automatically, and therefore is not suitable for real-time (or quasi real-time) skeleton extraction in various applications.…”

Practically Implementation of Information Loss: Sensitivity, Risk by Different Feature Selection Techniques

“…The selection out comes helps in improvement of learning rate and accuracy [4], complexity level and learning period reduces also simple understandable results representation only if optimal features selection carried out [5], [6]. Dimensionality reduction implemented by two different ways one is features extraction and other is features selection [7]- [9]. The reduction is an essential part for learning algorithms to perform its best by removal of noisy data.…”