Shape Descriptor Based on Curvature

Romero-González, Julio-Alejandro; Herrera-Navarro, Marcela; Jiménez-Hernández, Hugo

doi:10.4236/oalib.1108422

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shape can also be described by computing an overall curvature of a plant. The curvature is one of the contourbased descriptors which primarily focuses on the local information that inherently lies in the morphological structure and is necessary for understanding the shape of an object [40]. The curvature of a curve at a boundary point is defined as the rate of change in the direction of a tangent at the point with respect to the arc length [41].…”

Section: Shape Curvaturementioning

confidence: 99%

A machine learning framework for the identification of crops and weeds based on shape curvature and texture properties

Agarwal

2023

Preprint

View full text Add to dashboard Cite

Identification of weeds in a crop is a challenging problem for designing an automotive weed management system. Due to similar and indistinguishable properties between crop and weed, rather than single, various type of information is required for the successful discrimination of weeds against crops. This paper presents a machine learning-enabled weed classification system based on the fusion of handcrafted shape and texture features of a plant at the feature level. The shape features include several shape factors, region-based (Hu moment invariants), and contour-based descriptors (Fourier descriptors and shape curvature). Texture features include GLCM and LBP. A series of experiments are conducted to investigate the utility of shape curvature in the classification of weeds against crops. Furthermore, the potential of shape features including shape curvature and texture features has been examined by modeling the four classifiers, namely, SVM, KNN, MLP, and Naïve Bayes by using the 10-fold cross-validation approach. The classifiers are compared based on performance metrics- accuracy, error rate, recall, specificity, precision, and F1-score. Experimental results show that the SVM classifier achieved 93.67% overall accuracy with shape curvature features in the classification between crop and weed. In addition, the SVM classifier achieved 99.33% overall accuracy with the integration of shape with shape curvature and texture features.

show abstract

Section: Shape Curvaturementioning

confidence: 99%

A machine learning framework for the identification of crops and weeds based on shape curvature and texture properties

Agarwal

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…It is possible to determine the shape by the outlines in a 2D picture, for example using curvature, and differentiate among for example a mug, a dog, a car or a tree regardless of the rotation [10].…”

Section: Introductionmentioning

confidence: 99%

Shape functions to scanner comparison

Pajerová,

Koptiš

2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

In the optical scanning, the processed data are in the form of point clouds that can be organised into the triangular meshes and can represent the surface with the given inaccuracy of the scanner. Meshes of special surfaces (such as sphere or ball bar) are used for the scanner calibration, qualification and verification. These artefacts restrict the calibration process, because their sizes must be periodically calibrated by the relevant institutions.The aim of this paper is to present new possibilities for optical laser scanner accuracy comparison. Three types of laser scanners with different accuracies were used. The calibration sphere was used to compare the results of the deviations (the commonly used method for scanner accuracy verification) from calibrated value with the results of new methods that use shape functions measuring distances, cone heights or curvatures. The measurement system analysis was used to verify that these functions can be used for scanners comparison. The comparison of shape distributions obtained from results of shape functions in the form of polylines was used to compare scanners according to their accuracies. The comparison of shape distribution results was done using ranges and Minkowski $${L}_{1}$$ L 1 norm.

show abstract

Shape Descriptor Based on Curvature

Cited by 2 publications

References 0 publications

A machine learning framework for the identification of crops and weeds based on shape curvature and texture properties

A machine learning framework for the identification of crops and weeds based on shape curvature and texture properties

Shape functions to scanner comparison

Contact Info

Product

Resources

About