.png){kind=icon}
返回
A novel pixel range calculation technique for texture classification
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-022-12186-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this article, a fractal base method has been implemented as a texture descriptor. As, fractal deals with self-similarity, the proposed method is able to find the similarity of local patterns of various images of similar group and discriminate the images of dissimilar patterns. Images are converted to binary images by using the concept of local binary pattern. In this paper we have proposed a new approach for texture classification called Pixel Range Calculation (PRC) method, which has been implemented by converting the color images to gray images. Four benchmarking datasets, such as, ALOT (Amsterdam Library Of Textures), UMD (University of MarylanD), KTH-TIPS2b (Kungliga Tekniska Hogskolan-Textures under varying Illumination, Pose and Scale) and UIUC (University of Illinois at Urbana-Champaign) has been used for our experimental purpose. The proposed method along with two state of art method namely, Gliding Box Method (GBM) and Multi Fractal Spectrum (MFS) has been implemented and tested on the above-mentioned datasets. The experimental results based on the classification accuracy show the PRC technique of fractal dimension estimation method out performs the GBM and MFS. It has been observed that the computational complexity of PRC method is much less than other two state of art methods.
Keyword:
Fractal dimension
Texture classification
Local binary pattern
Pixel range calculation
Multi fractal Spectrum
Gliding box
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
PLBP: An effective local binary patterns texture descriptor with pyramid representation.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Retracted: Extra Dose of Vitamin C Based on a Daily Supplementation Shortens the Common Cold: A Meta‐Analysis of 9 Randomized Controlled Trials撤回：基于每日补充剂量的维生素C额外剂量可缩短普通感冒病程：一项包含9项随机对照试验的Meta分析
OAAI
OAAI分享收藏
查看更多内容