Extracting a new fractal and semi-variance attributes for texture images

Yousif, Suhad A.; Abdul-Wahed, Hussam Yahya; Al-Saidi, Nadia M. G.

doi:10.1063/1.5136199

Cited by 8 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Taking the image block as the object of calculation, we set 3 directions starting from the upper left corner, and set 9 steps in each direction, the semi-variance texture feature is a combination of half the expected value of the sum of the squares of the differences between the gray values of two points at all steps (step = 1 − 9) in all directions (direction = 1 − 3) [22], [23], [24].…”

Section: ) Local Spatial Association Featurementioning

confidence: 99%

Projection Mapping Segmentation Block: A Fusion Approach of Pointcloud and Image for Multi-Objects Classification

Meng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

There is an increasing trend towards multi-modal sensor fusion to improve the perception capability of autonomous vehicles, such as the fusion of light detection and ranging (LiDAR) pointcloud and camera image data. In this work, we proposed the early-fusion method of projection mapping segmentation blocks, which is a method to map spatial pointcloud segmentation blocks and image pixel segmentation blocks to each other according to the projection relationship. The local spatial association feature and the local semi-variance texture feature were additionally designed for feature extraction, and each pair of segmentation blocks is used as a processing unit for feature extraction. Finally, the classification task was completed by Support Vector Machines (SVM) algorithm. We compared the classification results of the single pointcloud without fusion and pointcloud+image fusion under two segmentation methods: boxbased and sector ring hexahedron-based. Our findings suggest that the data fusion classification method based on sector ring hexahedron segmentation not only improves classification accuracy but also reduces computational resources, yielding encouraging results.

show abstract

Section: ) Local Spatial Association Featurementioning

confidence: 99%

Projection Mapping Segmentation Block: A Fusion Approach of Pointcloud and Image for Multi-Objects Classification

Meng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Color moments are a representation of color features that describe the surface properties of an image region corresponding to an object [30]. Texture features exhibit the regular characteristics of pixel distribution and arrangement in an image, which are usually obtained by statistical means, such as the Fourier transform of image regions and grayscale covariance matrix [31][32][33]. As a kind of statistic to describe the spatial variability of random variables, semi-variance depends on the distance and direction of discrete points and reflects the autocorrelation between points, which provides an unbiased description of the spatial variation scale and pattern of image regions by describing the instability of image regions.…”

Section: Box Classification With Svmmentioning

confidence: 99%

A Model for Urban Environment Instance Segmentation with Data Fusion

Meng

et al. 2023

Sensors

View full text Add to dashboard Cite

Fine-grained urban environment instance segmentation is a fundamental and important task in the field of environment perception for autonomous vehicles. To address this goal, a model was designed with LiDAR pointcloud data and camera image data as the subject of study, and the reliability of the model was enhanced using dual fusion at the data level and feature level. By introducing the Markov Random Field algorithm, the Support Vector Machine classification results were optimized according to the spatial contextual linkage while providing the model with the prerequisite of the differentiation of similar but foreign objects, and the object classification and instance segmentation of 3D urban environments were completed by combining the Mean Shift. The dual fusion approach in this paper is a method for the deeper fusion of data from different sources, and the model, designed more accurately, describes the categories of items in the environment with a classification accuracy of 99.3%, and segments the different individuals into groups of the same kind of objects without instance labels. Moreover, our model does not have high computational resource and time cost requirements, and is a lightweight, efficient, and accurate instance segmentation model.

show abstract

“…The normally used method to extract the fractal feature of packaging materials is to employ the material micromorphology in the preparation process, surface, or fracture morphology of packaging material, and the test data in the property change process of packaging material (e.g., acoustic emission (AE) signal [ 18 ]) to carry out image gray processing and noise reduction processing, respectively. Common methods for calculating fractal dimension include the box counting method [ 19 ], correlation dimension method [ 20 ], Hurst index method [ 21 ], slit island method [ 22 ], yard stick method [ 23 ], area-perimeter method [ 24 ], Sierpiński carpet method [ 25 ], semi-variance method [ 26 ], and power spectral density [ 27 ] (PSD) method. The main methods to obtain object image are scanning electron microscope [ 28 ] (SEM), transmission electron microscope [ 29 ] (TEM), atomic force microscope [ 30 ] (AFM), and other imaging techniques.…”

Section: Basic Theory Of Fractalmentioning

confidence: 99%

Review about the Application of Fractal Theory in the Research of Packaging Materials

Duan

Mao

et al. 2021

Materials

View full text Add to dashboard Cite

The work is intended to summarize the recent progress in the work of fractal theory in packaging material to provide important insights into applied research on fractal in packaging materials. The fractal analysis methods employed for inorganic materials such as metal alloys and ceramics, polymers, and their composites are reviewed from the aspects of fractal feature extraction and fractal dimension calculation methods. Through the fractal dimension of packaging materials and the fractal in their preparation process, the relationship between the fractal characteristic parameters and the properties of packaging materials is discussed. The fractal analysis method can qualitatively and quantitatively characterize the fractal characteristics, microstructure, and properties of a large number of various types of packaging materials. The method of using fractal theory to probe the preparation and properties of packaging materials is universal; the relationship between the properties of packaging materials and fractal dimension will be a critical trend of fractal theory in the research on properties of packaging materials.

show abstract

Extracting a new fractal and semi-variance attributes for texture images

Cited by 8 publications

References 5 publications

Projection Mapping Segmentation Block: A Fusion Approach of Pointcloud and Image for Multi-Objects Classification

Projection Mapping Segmentation Block: A Fusion Approach of Pointcloud and Image for Multi-Objects Classification

A Model for Urban Environment Instance Segmentation with Data Fusion

Review about the Application of Fractal Theory in the Research of Packaging Materials

Contact Info

Product

Resources

About