Texture Classification Using Dense Micro-block Difference (DMD)

Mehta, Rakesh; Егиазарян, Карен

doi:10.1007/978-3-319-16808-1_43

Cited by 11 publications

(11 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results show that our method achieves better classification accuracy and generalisation performance than existing methods. [63] 62.4 VZ-MR8 [63] 93.5 CLBP_S/M/C [30] 98.9 MLEP [64] 75.6 WLD [65] 91.1 CoALBP [40] 98.0 MS-BIF [66] 71.6 MLEP [64] 96.4 PRICoLBP [41] 98.4 LHS [67] 73.0 WMFS [68] 96.6 VZ-MR8 [63] 93.5 COV-LBPD [69] 74.9 COV-LBPD [69] 98.0 BIF [66] 95.8 scLBP [70] 78.4 BIF [66] 98.5 M-BIMF [71] 95.6 SIFT [72] 76.6 SIFT [72] 97.3 SIFT [72] 98.1 DMD [54] 79.2 DMD [54] 98.0 DMD [54] 98.9…”

Section: Discussionmentioning

confidence: 99%

Co‐occurrence matching of local binary patterns for improving visual adaption and its application to smoke recognition

Yuan

Shi

Xia

et al. 2018

IET Computer Vision

View full text Add to dashboard Cite

It is challenging to recognize smoke from visual scenes due to large variations of smoke colors, textures and shapes. To improve robustness, we propose a novel feature extraction method based on similarity and dissimilarity matching measures of Local Binary Patterns (LBP). Given two bit-sequences of an LBP code pair, the similarity and dissimilarity matching measures are defined as the ratios of the 1-1 bitwise matching number to the 0-0 bitwise matching number and the 1-0 number to the 0-1 number, respectively. To capture local code variations, we calculate the measures between LBP codes of a center pixel and its neighbors. Then we compare each measure with its global mean to propose Similarity Matching based Local Binary Patterns (SMLBP) and Dissimilarity Matching based Local Binary Patterns (DMLBP). Since SMLBP and DMLBP extract spatial variations of the 1st order LBP codes, they actually represent the 2nd order variations of pixel values. Furthermore, we adopt different mapping modes and multi-scale neighborhoods to obtain rotation and scale invariances. Finally, we concatenate the histograms of LBP, SMLBP and DMLBP to generate a feature vector containing 1st and 2nd order information. Experiments show that our method obviously outperforms existing methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Co‐occurrence matching of local binary patterns for improving visual adaption and its application to smoke recognition

Yuan

Shi

Xia

et al. 2018

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…vl feat's (http://www.vlfeat.org) implementation of DenseSIFT is utilised. DMD: Dense Micro-block difference is a local feature extraction and texture classification technique proposed by Mehta and Egiazarian [49]. It captures the local structure from image patches (9 × 9 to 15 × 15 pixels) at high scales.…”

Section: Iris Texture Classification (Itc)mentioning

confidence: 99%

“…We utilize the Improved Fisher Vector Encoding (IFV) scheme [51] in the same way as it is done in [52,49]. IFV is usually used in object recognition.…”

Section: Feature Encodingmentioning

confidence: 99%

Identifying iris sensors from iris images

Debiasi¹,

Kauba²,

Uhl³

2017

Iris and Periocular Biometric Recognition

View full text Add to dashboard Cite

“…The images used as samples for training and testing our classifier are part of dataset called KTH-TIPS that were firstly used by E. Hayman in 2004 [43] and shortly after that became available for public use. Since then this library of images has been widely used, as long as others, as examples of textures for image processing, analyzing, filtering and, of course, classification [44], [45], [46].…”

Section: About the Kth-tips Datasetmentioning

confidence: 99%

Texture Classification based on Spectral Analysis and Haralick Features

Valentin

Albuquerque

et al. 2016

View full text Add to dashboard Cite

In this work we discuss a method to classify a set of texturized images based on the extraction of their Haralick Features. This kind of Classification is capable of providing texture-based measurements (such as contrast or correlation) and use them as main parameters to classify the same type of patterns in other images. In order to improve the classification success ratio a spectral analysis of the textures and, therefore, the use of filters, before the classification step, is proposed here. In this work the classification success has been evaluated using Mean and Canny filters. On the other hand, the Principal Component Analysis is used to optimize the features extracted for the patterns on each image, before introduced into the classifier. With this method the classifying success ratio for the KTH-TIPS subset and 10,000 different permutations was increased-in averagefrom 72.28% to 84.25%.

show abstract

Texture Classification Using Dense Micro-block Difference (DMD)

Cited by 11 publications

References 29 publications

Co‐occurrence matching of local binary patterns for improving visual adaption and its application to smoke recognition

Co‐occurrence matching of local binary patterns for improving visual adaption and its application to smoke recognition

Identifying iris sensors from iris images

Texture Classification based on Spectral Analysis and Haralick Features

Contact Info

Product

Resources

About