Imatge de la portada

Investigations on segmentation-based fractal texture for texture classification in the presence of Gaussian noise

Guardat en:
Publicat a:PLoS One vol. 20, no. 1 (Jan 2025), p. e0315135
Autor principal: Tiwari, Shamik
Altres autors: Sharma, Akhilesh Kumar, Izzatdin Abdul Aziz, Gupta, Deepak, Jain, Antima, Mahdin, Hairulnizam, Athithan, Senthil, Hidayat, Rahmat
Publicat:
Public Library of Science
Matèries:
Feature extraction
Deep learning
Fractal analysis
Multilayers
Degradation
Segmentation
Normal distribution
Medical imaging
Neural networks
Fractals
Decomposition
Image degradation
Image processing
Classification
Statistical analysis
Statistical models
Fractal models
Image analysis
Image segmentation
Computer vision
Image retrieval
Retrieval
Image classification
Statistical methods
Random noise
Methods
Algorithms
Texture
Information retrieval
Environmental
Accés en línia:Citation/Abstract
Full Text
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
Resum:Texture is a significant component used for several applications in content-based image retrieval. Any texture classification method aims to map an anonymously textured input image to one of the existing texture classes. Extensive ranges of methods for labeling image texture were proposed earlier. However, computing the performance of these methods in the presence of various degradations is always an open area of discussion. Image noise is always a dominant factor among various image degradation factors, affecting the performance of these methods and making texture classification challenging. Therefore, it is essential to investigate the interpretation of these methods in the presence of prominent degradation factors such as noise. Applications for Segmentation-Based Fractal Texture Features (SFTF) include image classification, texture generation, and medical image analysis. They are beneficial for examining textures with intricate, erratic patterns that are difficult to characterize using conventional statistical techniques accurately. This paper assesses two texture feature extraction methods based on SFTF and statistical moment-based texture features in the presence and absence of Gaussian noise. The SFTF and statistical moments-based handcrafted features are passed to a multilayer feed-forward neural network for classification. These models are evaluated on natural textures from Kylberg Texture Dataset 1.0. The results show the superiority of segmentation-based fractal analysis over other approaches. The average accuracy rates using the SFTF are 99% and 97% in the absence and presence of Gaussian noise, respectively.
ISSN:1932-6203
DOI:10.1371/journal.pone.0315135
Font:Health & Medical Collection