Fractal Dimension Based Texture Analysis of Digital Images

Shanmugavadivu, P.; Sivakumar, V.

doi:10.1016/j.proeng.2012.06.348

Cited by 61 publications

(26 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chengsheng Yuan [12] proposed to apply the fractal dimension into the field of blade recognition, as a method of leaf texture feature extraction to represent the texture complexity and self-similarity of the leaf image, so that the leaf identification can be better effect. P. Shanmugavadivu and V. Sivakumar [13] proposed an algorithm for calculating the fractal dimension of digital images, comparing the fractal dimensions of these images and proving that fractal dimension is an ideal tool for measuring image roughness. YingChao Zhang et al [14] use fractal edge detecting method for extracting edge features of characters, fractal edge feature with three other features (loop region, a projection histogram moment) in combination, in conjunction with a classifier, for recognizing handwritten numerals Methods.…”

Section: Computer Engineering and Applicationsmentioning

confidence: 99%

A Review of the Application of Fractal in Recognition

Yuan¹,

Liu²,

Zhou³

2017

Proceedings of the 2017 International Conference on Material Science, Energy and Environmental Engineering (MSEEE 2017)

View full text Add to dashboard Cite

Abstract. Based on the fractal theory, this paper briefly reviews the origin and definition of fractal theory, and the concept of fractal dimension and its main calculation method. Then select one of the applications of fractal theory, in the application of recognition, to have a literature review. This paper summarizes the domestic and foreign research literature in recent 5 years, it is found that fractal recognition is involved in image, signal and waveform, but there is no breakthrough in the recognition of text information. Therefore, this paper proposes to use fractal ideas for text information recognition.

show abstract

Section: Computer Engineering and Applicationsmentioning

confidence: 99%

A Review of the Application of Fractal in Recognition

Yuan¹,

Liu²,

Zhou³

2017

Proceedings of the 2017 International Conference on Material Science, Energy and Environmental Engineering (MSEEE 2017)

View full text Add to dashboard Cite

show abstract

“…Fractal geometry of nature was first proposed by Mandelbrot to describe the objects exhibiting the self-similarity at all scales [10]. The concept of fractal dimension (FD) is widely used for texture analysis and classification and results in good performance [11,12]. FD is a simple indicator of measuring the roughness and self-similarity of shape and texture.…”

Section: Fractal and Dimensionmentioning

confidence: 99%

Seed Identification of Gramineous Grass Based on Difference of Local Fractal Dimensions

Pan¹,

Chen²,

Ma³

et al. 2016

Open Cyber

View full text Add to dashboard Cite

This work proposes an approach based on the difference of local fractal dimension (DLFD) for seed identification of gramineous grass, rather than shape and color of the seeds. Being an important forge category of grassland, gramineous grass has been rarely investigated for the automated identification task by the researchers. Three main steps are involved in the extraction of DLFD. At first, the ROI image is equally divided into local blocks, and the fractal dimension of the partitions are calculated. Based on the average fractal dimension of all the blocks, the DLFD can then be obtained by subtracting the individual fractal dimension and the average, magnifying the contrast of the self-similarity of the images. Euclidean Distance and the nearest neighbor classifier are finally used for similarity measurement and classification. The novelty of the approach lies in applying fractal geometry in forage seed identification, a quite new area for pattern recognition. The experimental results demonstrate the effectiveness of the proposed method by some comparative analysis.

show abstract

“…For the past 10 years, many scientists have been trying to research fractal characteristic of fibrous porous media via SEM technology [3], but it was very difficult to exactly measure packing density of media, the relationship between fractal dimension and fiber diameter and packing density cannot be obtained via SEM technology. So that, we developed a VBA computer program to produce a 3-D virtual non-woven material with three directions or two direction randomly distributed straight and curved fiber.…”

Section: Introductionmentioning

confidence: 99%

Fractal characteristic of virtual fibrous porous media

Fu¹,

Fu²

2016

Proceedings of the 2015 International Conference on Mechanical Science and Engineering

View full text Add to dashboard Cite

Fractal theory is a very effective method for investigating pore-structure of fibrous porous materials, which build a bridge between micro-morphology and macro-performance. Fractal dimension was calculated based on the fractal theory and combined with computer virtual building model technology, which was explored to describe the pore structure of virtual fibrous porous materials. The geometric model construction program was completed to generate virtual filter media which has straight fiber and bending fiber. These fibers are randomly distributed in two directions or three directions. A variety of virtual fibrous media were used to calculate packing density or porosity and fractal dimension. The fractal dimension of 2D or 3D pore structure was calculated by the soft and the effects of packing density or porosity on fractal dimension were also discussed. Fractal dimension of the two-dimensional cross-sectional view, plan view or section view has the same form of expression, their coefficients was different with the variation in position observations. The results show that the fractal dimension decreases continuously with the increase of fiber diameter, but it increases gradually with the packing density increasing. Furthermore, the relationships between the fractal dimension and the fiber diameter and packing density were obtained.

show abstract

Fractal Dimension Based Texture Analysis of Digital Images

Cited by 61 publications

References 6 publications

A Review of the Application of Fractal in Recognition

A Review of the Application of Fractal in Recognition

Seed Identification of Gramineous Grass Based on Difference of Local Fractal Dimensions

Fractal characteristic of virtual fibrous porous media

Contact Info

Product

Resources

About