A Fourier Descriptor of 2D Shapes Based on Multiscale Centroid Contour Distances Used in Object Recognition in Remote Sensing Images

Zheng, Yujun; Guo, Baolong; Chen, Zhijie; Li, Cheng

doi:10.3390/s19030486

Cited by 19 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FMSCCD [19] 37.33% IDSC-WFW (a weighted Fourier and wavelet-like descriptor based on inner distance shape context) [34] 49.36% DIR [17] 46.45% AP & BAP [18] 52.79% MDM [16] 35.81% FPD (farthest point distance) [35] 26.63% FD [15] 27.97% FASD & FMSCCD (fast angle scale descriptor and FMSCCD) [19] 37.85% FD-ASD (Fourier descriptor-angle scale descriptor) [36] 27.44% ASD & CCD (angle scale descriptor and centroid contour distance) [36] 39.30% SC + DP [14] 67.27% IDSC + DP [13] 70.99% HSC (Hierarchical string cuts) [37] 56.80% SCN (ours) 75.39%…”

Section: Methods Classification Accuracymentioning

confidence: 99%

“…FMSCCD [19] 87.98% IDSC-WFW [34] 93.66% DIR [17] 88.20% MDM [16] 87.32% FPD [35] 77.16% FD [15] 82.40% FASD & FMSCCD [19] 91.04% FDASD [36] 87.32% ASD & CCD [36] 85.14% MLBP (modified LBP) [38] 96.83% SCN (ours) 94.46%…”

Section: Methods Classification Accuracymentioning

confidence: 99%

“…More importantly, it is a global shape descriptor. Fourier descriptor based on multiscale centroid contour distance (FMSCCD) [19] is a frequency domain descriptor based on the centroid contour distance (CCD) method, multiscale description, and Fourier transform.…”

Section: Traditional Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

SCN: A Novel Shape Classification Algorithm Based on Convolutional Neural Network

et al. 2021

Self Cite

View full text Add to dashboard Cite

Shape classification and matching is an important branch of computer vision. It is widely used in image retrieval and target tracking. Shape context method, curvature scale space (CSS) operator and its improvement have been the main algorithms of shape matching and classification. The shape classification network (SCN) algorithm is proposed inspired by LeNet5 basic network structure. Then, the network structure of SCN is introduced and analyzed in detail, and the specific parameters of the network structure are explained. In the experimental part, SCN is used to perform classification tasks on three shape datasets, and the advantages and limitations of our algorithm are analyzed in detail according to the experimental results. SCN performs better than many traditional shape classification algorithms. Accordingly, a practical example is given to show that SCN can save computing resources.

show abstract

Section: Methods Classification Accuracymentioning

confidence: 99%

Section: Methods Classification Accuracymentioning

confidence: 99%

See 1 more Smart Citation

SCN: A Novel Shape Classification Algorithm Based on Convolutional Neural Network

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Computer-assisted methods allow the measurements of multiple magnitudes of objects, but often the measurements are made in two dimensions [16,17]. Thus, when applying artificial vision methods [18], figures are represented by the coordinates of a set of points in the plane, that can be submitted to algebraic transformations and compared with a set of figures in databases. Plant organs, in general, and seeds in particular, have a similarity with geometric objects, and the comparison between both 2D images, the plant structure, and the geometric model, provides a direct method for the quantitative description of shapes.…”

Section: A Conceptual Aspectmentioning

confidence: 99%

Seed Geometry in the Arecaceae

2020

View full text Add to dashboard Cite

Fruit and seed shape are important characteristics in taxonomy providing information on ecological, nutritional, and developmental aspects, but their application requires quantification. We propose a method for seed shape quantification based on the comparison of the bi-dimensional images of the seeds with geometric figures. J index is the percent of similarity of a seed image with a figure taken as a model. Models in shape quantification include geometrical figures (circle, ellipse, oval…) and their derivatives, as well as other figures obtained as geometric representations of algebraic equations. The analysis is based on three sources: Published work, images available on the Internet, and seeds collected or stored in our collections. Some of the models here described are applied for the first time in seed morphology, like the superellipses, a group of bidimensional figures that represent well seed shape in species of the Calamoideae and Phoenix canariensis Hort. ex Chabaud. Oval models are proposed for Chamaedorea pauciflora Mart. and cardioid-based models for Trachycarpus fortunei (Hook.) H. Wendl. Diversity of seed shape in the Arecaceae makes this family a good model system to study the application of geometric models in morphology.

show abstract

“…Burla et al [18] developed two modifi ed Fourier descriptors methods for fast detection of surface defects on microlens arrays, one kind of micro-optical elements. Zheng et al [19] introduced a revised Fourier descriptors based on multiscale centroid contour distance to recognize objects in remote sensing images. The theory of this approach is straightforward and computational effi ciency.…”

Section: Literature Reviewmentioning

confidence: 99%

Effective image models for inspecting profile flaws of car mirrors with applications

Peter¹,

Lin²,

Lin³

2020

J Appl Eng Science

View full text Add to dashboard Cite

Since car mirrors are standard accessories with cars, the demand for car mirrors is growing and manufacturers also pay more emphasis on the increase of product quality. Common appearance fl aws of car mirrors include: scratches, bubbles, pinholes causing surface fl aw type and burrs,damaged edges causing profi le fl aw type. Currently, the inspection tasks are conducted by human inspectors. Since the profi le fl aws will cause structural damages of car mirrors and reduce ability to withstand stress, the level of damage suffered even more than the surface fl aws. In addition, the angle diversity of capturing images makes it hard to implement automatic optical inspection. Therefore, this study develops an automated profi le fl aw detection system for car mirrors to replace visual inspection personnel. This study proposes a self-contrast defect detection method for the profi le fl aw inspection of car mirrors. It is not required to provide a standard fl awless sample in detection process and derive information compared with testing samples. The proposed method fi rst extracts the contour information of the testing image by Fourier descriptors. Then, after some middle and high-frequency coeffi cients were fi ltered out, an approximated contour image can be rebuilt from the Fourier domain for comparing with the testing image. Finally, the fl aw districts are easily separated by image subtraction. Experimental results demonstrate that the fl aw inspection rate reaches 85.05%, and the incorrect alert rate is smaller than 0.07%, and the correct classifi cation rate is up to 97.47%.

show abstract

A Fourier Descriptor of 2D Shapes Based on Multiscale Centroid Contour Distances Used in Object Recognition in Remote Sensing Images

Cited by 19 publications

References 22 publications

SCN: A Novel Shape Classification Algorithm Based on Convolutional Neural Network

SCN: A Novel Shape Classification Algorithm Based on Convolutional Neural Network

Seed Geometry in the Arecaceae

Effective image models for inspecting profile flaws of car mirrors with applications

Contact Info

Product

Resources

About