# Unsupervised Local Binary Pattern Histogram Selection Scores for Color Texture Classification

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Feature Selection Scores

#### 2.1. Unsupervised Feature Selection Scores

#### 2.1.1. Variance Score

#### 2.1.2. Laplacian Score

- ${\left({x}_{i}^{r}-{x}_{j}^{r}\right)}^{2}$ is the squared Euclidean distance between the rth feature of two images ${I}_{i}$ and ${I}_{j}$,
- ${s}_{ij}$ is the similarity measure between ${I}_{i}$ and ${I}_{j}$ using all the input feature space composed by the D features. It is defined by: ${s}_{ij}=exp\left(-\frac{{\u2225{\mathbf{x}}_{i}-{\mathbf{x}}_{j}\u2225}^{2}}{2{t}^{2}}\right)$, where ${\u2225{\mathbf{x}}_{i}-{\mathbf{x}}_{j}\u2225}^{2}$ represents the squared Euclidean distance between ${\mathbf{x}}_{i}$ and ${\mathbf{x}}_{j}$ in the D-dimensional initial feature space [30,31]. The parameter t has to be tuned in order to represent the local dispersion of the data [32],
- ${d}_{i}$ represents a local density measure defined by: ${d}_{i}={\sum}_{j=1}^{N}{s}_{ij}$,
- and ${\overline{f}}^{r}$ is the weighted feature average: ${\overline{f}}^{r}=\frac{{\sum}_{i=1}^{N}{x}_{i}^{r}{d}_{i}}{{\sum}_{i=1}^{N}{d}_{i}}$.

## 3. Histogram Selection Scores

#### 3.1. Adapted Variance Score

#### 3.2. Adapted Laplacian Score

## 4. LBP Histogram Selection for Color Texture Classification

#### 4.1. Candidate Color Texture Descriptors

#### 4.2. Histogram Selection

## 5. Experiments

#### 5.1. Comparison of the Histogram Selection Scores

#### 5.2. Comparison of the Histogram Ranks

#### 5.3. Comparison with the State of the Art

## 6. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Tuceryan, M.; Jain, A.K. Texture analysis. In Handbook of Pattern Recognition and Computer Vision; Chen, C.H., Pau, L.F., Wang, P.S.P., Eds.; World Scientific Publishing Co.: Singapore, 1998; pp. 207–248. [Google Scholar]
- Bianconi, F.; Harvey, R.; Southam, P.; Fernandez, A. Theoretical and experimental comparison of different approaches for color texture classification. J. Electron. Imaging
**2011**, 20, 043006. [Google Scholar] [CrossRef] - De Wouwer, G.V.; Scheunders, P.; Livens, S.; van Dyck, D. Wavelet correlation signatures for color texture characterization. Pattern Recognit.
**1999**, 32, 443–451. [Google Scholar] [CrossRef] [Green Version] - Porebski, A.; Vandenbroucke, N.; Macaire, L. Supervised texture classification: Color space or texture feature selection? Pattern Anal. Appl. J.
**2013**, 16, 1–18. [Google Scholar] [CrossRef] - Arvis, V.; Debain, C.; Berducat, M.; Benassi, A. Generalization of the cooccurrence matrix for colour images: Application to colour texture classification. Image Anal. Stereol.
**2004**, 23, 63–72. [Google Scholar] [CrossRef] - Tang, J.; Alelyani, S.; Liu, H. Feature selection for classification: A review. In Data Classification Algorithms and Applications; Aggarwal, C., Ed.; CRC Press: Boca Raton, FL, USA, 2014; pp. 37–64. [Google Scholar]
- He, X.; Cai, D.; Niyogi, P. Laplacian Score for Feature Selection. In Advances in Neural Information Processing Systems; MIT Press: Vancouver, Canada, December 2005; pp. 507–514. [Google Scholar]
- Kalakech, M.; Biela, P.; Macaire, L.; Hamad, D. Constraint scores for semi-supervised feature selection: A comparative study. Pattern Recognit. Lett.
**2011**, 32, 656–665. [Google Scholar] [CrossRef] - Sandid, F.; Douik, A. Robust color texture descriptor for material recognition. Pattern Recognit. Lett.
**2016**, 80, 15–23. [Google Scholar] [CrossRef] - Fernandez, A.; Alvarez, M.X.; Bianconi, F. Texture Description Through Histograms of Equivalent Patterns. J. Math. Imaging Vis.
**2012**, 45, 76–102. [Google Scholar] [CrossRef] [Green Version] - Alvarez, S.; Vanrell, M. Texton theory revisited: A bag-of-words approach to combine textons. Pattern Recognit.
**2012**, 45, 4312–4325. [Google Scholar] [CrossRef] - Liu, L.; Fieguth, P.; Guo, Y.; Wang, X.; Pietikäinen, M. Local binary features for texture classification: Taxonomy and experimental study. Pattern Recognit.
**2017**, 62, 135–160. [Google Scholar] [CrossRef] - Pietikäinen, M.; Hadid, A.; Zhao, G.; Ahonen, T. Computer Vision Using Local Binary Patterns; Springer: Berlin, Germany; London, UK, 2011. [Google Scholar]
- Ojala, T.; Pietikäinen, M.; Mäenpää, T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell.
**2002**, 7, 971–987. [Google Scholar] [CrossRef] - Mäenpää, T.; Ojala, T.; Pietikäinen, M.; Soriano, M. Robust texture classification by subsets of local binary patterns. In Proceedings of the 15th International Conference on Pattern Recognition, Barcelona, Spain, 3–7 September 2000; pp. 947–950. [Google Scholar]
- Liao, S.; Law, M.; Chung, C. Dominant local binary patterns for texture classification. IEEE Trans. Image Process.
**2009**, 18, 1107–1118. [Google Scholar] [CrossRef] [PubMed] - Bianconi, F.; González, E.; Fernández, A. Dominant local binary patterns for texture classification: Labelled or unlabelled? Pattern Recognit. Lett.
**2015**, 65, 8–14. [Google Scholar] [CrossRef] - Fu, X.; Shi, M.; Wei, H.; Chen, H. Fabric defect detection based on adaptive local binary patterns. In Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO2009), Guilin, China, 19–23 December 2009; pp. 1336–1340. [Google Scholar]
- Nanni, L.; Brahnam, S.; Lumini, A. Selecting the best performing rotation invariant patterns in local binary/ternary patterns. In Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition, Las Vegas, NV, USA, 12–15 July 2010; pp. 369–375. [Google Scholar]
- Doshi, N.P.; Schaefer, G. Dominant multi-dimensional local binary patterns. In Proceedings of the IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC2013), Kunming, China, 5–8 August 2013. [Google Scholar]
- Guo, Y.; Zhao, G.; Pietikäinen, M.; Xu, Z. Descriptor learning based on fisher separation criterion for texture classification. In Asian Conference on Computer Vision; Springer: Berlin/Heidelberg, Germany, 2010; pp. 1491–1500. [Google Scholar]
- Guo, Y.; Zhao, G.; Pietikäinen, M. Discriminative features for texture description. Pattern Recognit.
**2012**, 45, 3834–3843. [Google Scholar] [CrossRef] - Chan, C.; Kittler, J.; Messer, K. Multispectral local binary pattern histogram for component-based color face verification. In Proceedings of the IEEE Conference on Biometrics: Theory, Applications and Systems, Crystal City, VA, USA, 27–29 September 2007; pp. 1–7. [Google Scholar]
- Dalal, N.; Triggs, B. Histograms of oriented gradients for human detection. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, 20–25 June 2005; pp. 886–893. [Google Scholar]
- Tan, X.; Triggs, B. Enhanced local texture feature sets for face recognition under difficult lighting conditions. IEEE Trans. Image Process.
**2010**, 19, 1635–1650. [Google Scholar] [PubMed] - Hussain, S.; Triggs, B. Feature sets and dimensionality reduction for visual object detection. In British Machine Vision Conference; BMVA Press: London, UK, 2010; pp. 112.1–112.10. [Google Scholar]
- Porebski, A.; Vandenbroucke, N.; Hamad, D. LBP histogram selection for supervised color texture classification. In Proceedings of the 20th IEEE International Conference on Image Processing, Melbourne, Australia, 15–18 September 2013; pp. 3239–3243. [Google Scholar]
- Kalakech, M.; Porebski, A.; Vandenbroucke, N.; Hamad, D. A new LBP histogram selection score for color texture classification. In Proceedings of the 5th IEEE international Workshops on Image Processing Theory, Tools and Applications, Orleans, France, 10–13 November 2015. [Google Scholar]
- Porebski, A.; Hoang, V.T.; Vandenbroucke, N.; Hamad, D. Multi-color space local binary pattern-based feature selection for texture classification. J. Electron. Imaging
**2018**, 27, 011010. [Google Scholar] - Luxburg, U.V. A tutorial on spectral clustering statistics and computing. Stat. Comput.
**2007**, 17, 395–416. [Google Scholar] [CrossRef] - Ng, A.Y.; Jordan, M.; Weiss, Y. On spectral clustering: analysis and an algorithm. In Proceedings of the Advances in Neural Information Processing Systems, Vancouver, Canada, 3–8 December 2001; pp. 849–856. [Google Scholar]
- Zelink-Manor, L.; Perona, P. Self-tuning spectral clustering. In Proceedings of the Advances in Neural Information Processing Systems, Cambridge, MA, USA, 5 May 2005; pp. 1601–1608. [Google Scholar]
- Rubner, Y.; Puzich, J.; Tomasi, C.; Buhmann, J.M. Empirical evaluation of dissimilarity measures for color and texture. Comput. Vis. Image Underst.
**2001**, 84, 25–43. [Google Scholar] [CrossRef] - Bianconi, F.; Bello-Cerezo, R.; Napoletano, P. Improved opponent color local binary patterns: An effective local image descriptor for color texture classification. J. Electron. Imaging
**2017**, 27, 011002. [Google Scholar] [CrossRef] - Liu, L.; Lao, S.; Fieguth, P.; Guo, Y.; Wang, X.; Pietikainen, M. Median robust extended local binary pattern for texture classification. IEEE Trans. Image Process.
**2016**, 25, 1368–1381. [Google Scholar] [CrossRef] [PubMed] - Jain, A.; Zongker, D. Feature selection: Evaluation, application and small sample performance. IEEE Trans. Pattern Anal. Mach. Intell.
**1997**, 19, 153–158. [Google Scholar] [CrossRef] - Dash, M.; Liu, H. Feature selection for classification. Intell. Data Anal.
**1997**, 1, 131–156. [Google Scholar] [CrossRef] [Green Version] - Liu, H.; Yu, L. Toward integrating feature selection algorithms for classification and clustering. IEEE Trans. Knowl. Data Eng.
**2005**, 17, 491–502. [Google Scholar] [Green Version] - Ojala, T.; Mäenpää, T.; Pietikäinen, M.; Viertola, J.; Kyllönen, J.; Huovinen, S. Outex new framework for empirical evaluation of texture analysis algorithms. In Proceedings of the 16th International Conference on Pattern Recognition, Quebec City, QC, Canada, 11–15 August 2002; pp. 701–706. [Google Scholar]
- Backes, A.R.; Casanova, D.; Bruno, O.M. Color texture analysis based on fractal descriptors. Pattern Recognit.
**2012**, 45, 1984–1992. [Google Scholar] [CrossRef] [Green Version] - Lakmann, R. Barktex Benchmark Database of Color Textured Images. Koblenz-Landau University. Available online: ftp://ftphost.uni-koblenz.de/outgoing/vision/Lakmann/BarkTex (accessed on 28 September 2018).
- Porebski, A.; Vandenbroucke, N.; Macaire, L.; Hamad, D. A new benchmark image test suite for evaluating color texture classification schemes. Multimed. Tools Appl. J.
**2013**, 70, 543–556. [Google Scholar] [CrossRef] - Mäenpää, T.; Pietikäinen, M. Classification with color and texture: jointly or separately? Pattern Recognit. Lett.
**2004**, 37, 1629–1640. [Google Scholar] [CrossRef] [Green Version] - Casanova, D.; Florindo, J.; Falvo, M.; Bruno, O.M. Texture analysis using fractal descriptors estimated by the mutual interference of color channels. Inf. Sci.
**2016**, 346, 58–72. [Google Scholar] [CrossRef] - Pietikäinen, M.; Mäenpää, T.; Viertola, J. Color texture classification with color histograms and local binary patterns. In Proceedings of the 2nd International Workshop on Texture Analysis and Synthesis, Copenhagen, Denmark, 1 June 2002; pp. 109–112. [Google Scholar]
- Qazi, I.; Alata, O.; Burie, J.C.; Moussa, A.; Fernandez, C. Choice of a pertinent color space for color texture characterization using parametric spectral analysis. Pattern Recognit.
**2011**, 44, 16–31. [Google Scholar] [CrossRef] - Iakovidis, D.; Maroulis, D.; Karkanis, S. A comparative study of color-texture image features. In Proceedings of the 12th International Workshop on Systems, Signals & Image Processing (IWSSIP’05), Chalkida, Greece, 22–24 September 2005; pp. 203–207. [Google Scholar]
- Liu, P.; Guo, J.; Chamnongthai, K.; Prasetyo, H. Fusion of color histogram and lbp-based features for texture image retrieval and classification. Inf. Sci.
**2017**, 390, 95–111. [Google Scholar] [CrossRef] - Maliani, A.D.E.; Hassouni, M.E.; Berthoumieu, Y.; Aboutajdine, D. Color texture classification method based on a statistical multi-model and geodesic distance. J. Vis. Commun. Image Represent.
**2014**, 25, 1717–1725. [Google Scholar] [CrossRef] - Guo, J.-M.; Prasetyo, H.; Lee, H.; Yao, C.C. Image retrieval using indexed histogram of void-and-cluster block truncation coding. Signal Process.
**2016**, 123, 143–156. [Google Scholar] [CrossRef] - Ledoux, A.; Losson, O.; Macaire, L. Color local binary patterns: compact descriptors for texture classification. J. Electron. Imaging
**2016**, 25, 1–12. [Google Scholar] [CrossRef] - Xu, Q.; Yang, J.; Ding, S. Color texture analysis using the wavelet-based hidden markov model. Pattern Recognit. Lett.
**2005**, 26, 1710–1719. [Google Scholar] [CrossRef] - Martínez, R.A.; Richard, N.; Fernandez, C. Alternative to colour feature classification using colour contrast ocurrence matrix. In Proceedings of the 12th International Conference on Quality Control by Artificial Vision SPIE, Le Creusot, France, 3–5 June 2015; pp. 1–9. [Google Scholar]
- Hammouche, K.; Losson, O.; Macaire, L. Fuzzy aura matrices for texture classification. Pattern Recognit.
**2016**, 53, 212–228. [Google Scholar] [CrossRef] [Green Version] - Oliveira, M.W.D.; da Silva, N.R.; Manzanera, A.; Bruno, O.M. Feature extraction on local jet space for texture classification. Phys. A Stat. Mech. Appl.
**2015**, 439, 160–170. [Google Scholar] [CrossRef] - Florindo, J.; Bruno, O. Texture analysis by fractal descriptors over the wavelet domain using a best basis decomposition. Phys. A Stat. Mech. Appl.
**2016**, 444, 415–427. [Google Scholar] [CrossRef] - Sandid, F.; Douik, A. Dominant and minor sum and difference histograms for texture description. In Proceedings of the 2016 International Image Processing, Applications and Systems (IPAS), Hammamet, Tunisia, 5–7 November 2016; pp. 1–5. [Google Scholar]
- Wang, J.; Fan, Y.; Li, N. Combining fine texture and coarse color features for color texture classification. J. Electron. Imaging
**2017**, 26, 9. [Google Scholar]

**Figure 1.**Classification accuracy R

_{d}according to the number d of ranked histograms on Outex-TC-00013.

**Figure 3.**Classification accuracy R

_{d}according to the number d of ranked histograms on NewBarkTex.

**Table 1.**Summary of the terms and the scores used in feature selection and their corresponding histogram selection adaptation.

Feature Selection | Histogram Selection | |
---|---|---|

Dataset | Dataset of N color texture images defined in a D-dimensional feature space | Dataset of N color texture images defined in a $(Q\times D)$-dimensional histogram space |

Data matrix | $\mathbf{X}=\left({x}_{i}^{r}\right)$; $i=1,\dots ,N$; $r=1,\dots ,D$ ${x}_{i}^{r}$ is the rth feature value of the ith image ${I}_{i}$ | $\mathbf{H}=\left({\mathbf{h}}_{i}^{r}\right)$; $i=1,\dots ,N$; $r=1,\dots ,D$ ${\mathbf{h}}_{i}^{r}$ is the rth histogram extracted from the ith image ${I}_{i}$ |

Row | ${\mathbf{x}}_{i}=\left({x}_{i}^{1},\dots ,{x}_{i}^{D}\right)$ | ${\mathbf{h}}_{i}=\left[{\mathbf{h}}_{i}^{1}\dots {\mathbf{h}}_{i}^{r}\dots {\mathbf{h}}_{i}^{D}\right]$ with ${\mathbf{h}}_{i}^{r}=\left({h}_{i}^{r}(1),\dots ,{h}_{i}^{r}(k),\dots ,{h}_{i}^{r}(Q)\right)$ |

Column | ${\mathbf{f}}^{r}={\left({x}_{1}^{r},\dots ,{x}_{N}^{r}\right)}^{T}$ | ${\mathbf{h}}^{r}={\left[{\mathbf{h}}_{1}^{r}\dots {\mathbf{h}}_{i}^{r}\dots {\mathbf{h}}_{N}^{r}\right]}^{T}$ |

Selection | The most discriminant features ${\mathbf{f}}^{r}$ among the D available ones | The most discriminant histograms ${\mathbf{h}}^{r}$ among the D available ones |

Distance | ${\left({x}_{i}^{r}-{x}_{j}^{r}\right)}^{2}$ is the squared Euclidean distance between the two images ${I}_{i}$ and ${I}_{j}$ using the considered feature ${\mathbf{f}}_{r}$ | ${J}^{2}({\mathbf{h}}_{i}^{r},{\mathbf{h}}_{j}^{r})$ is the squared Jeffrey distance between the two images ${I}_{i}$ and ${I}_{j}$ using the considered histogram ${\mathbf{h}}^{r}$ $J({\mathbf{h}}_{i}^{r},{\mathbf{h}}_{j}^{r})={\sum}_{k=1}^{Q}{h}_{i}^{r}(k)log\left(\frac{{h}_{i}^{r}(k)}{\frac{{h}_{i}^{r}(k)+{h}_{j}^{r}(k)}{2}}\right)+{h}_{j}^{r}(k)log\left(\frac{{h}_{j}^{r}(k)}{\frac{{h}_{i}^{r}(k)+{h}_{j}^{r}(k)}{2}}\right)$ |

Similarity | ${s}_{ij}$ evaluates the similarity between the images ${I}_{i}$ and ${I}_{j}$ in the D-dimensional input space ${s}_{ij}=exp\left(-\frac{{\u2225{\mathbf{x}}_{i}-{\mathbf{x}}_{j}\u2225}^{2}}{2{t}^{2}}\right)$ | $S({\mathbf{h}}_{i},{\mathbf{h}}_{j})$ evaluates the similarity between the images ${I}_{i}$ and ${I}_{j}$ in the $(Q\times D)$-dimensional input space using the histogram intersection $S({\mathbf{h}}_{i},{\mathbf{h}}_{j})={\sum}_{k=1}^{Q\times D}min\left({h}_{i}(k),{h}_{j}(k)\right)$ |

Mean | ${\mu}^{r}=\frac{{\sum}_{i=1}^{N}{x}_{i}^{r}}{N}$ | ${\overline{\mathbf{h}}}^{r}=\left({\overline{h}}^{r}(1),\dots ,{\overline{h}}^{r}(k),\dots ,{\overline{h}}^{r}(Q)\right)$ with ${\overline{h}}^{r}(k)=\frac{1}{N}{\sum}_{i=1}^{N}{h}_{i}^{r}(k)$ |

Variance Score | ${V}^{r}=\frac{1}{N}{\sum}_{i=1}^{N}{\left({x}_{i}^{r}-{\mu}^{r}\right)}^{2}$ | $A{V}^{r}=\frac{1}{N}{\sum}_{i=1}^{N}{J}^{2}\left({\mathbf{h}}_{i}^{r},{\overline{\mathbf{h}}}^{r}\right)$ |

Degree | ${d}_{i}={\sum}_{j=1}^{N}{s}_{ij}$ | ${D}_{i}={\sum}_{j=1}^{N}S({\mathbf{h}}_{i},{\mathbf{h}}_{j})$ |

Weighted average | ${\overline{f}}^{r}=\frac{{\sum}_{i=1}^{N}{x}_{i}^{r}{d}_{i}}{{\sum}_{i=1}^{N}{d}_{i}}$ | ${\overline{\mathbf{a}}}^{r}=\left({\overline{a}}^{r}(1),\dots ,{\overline{a}}^{r}(k),\dots ,{\overline{a}}^{r}(Q)\right)$ with ${\overline{a}}^{r}(k)=\frac{{\sum}_{i=1}^{N}{h}_{i}^{r}(k){D}_{i}}{{\sum}_{i=1}^{N}{D}_{i}}$ |

Laplacian Score | ${L}^{r}=\frac{{\sum}_{i=1}^{N}{\sum}_{j=1}^{N}{\left({x}_{i}^{r}-{x}_{j}^{r}\right)}^{2}{s}_{ij}}{{\sum}_{i=1}^{N}{\left({x}_{i}^{r}-{\overline{f}}^{r}\right)}^{2}{d}_{i}}$ | $A{L}^{r}=\frac{{\sum}_{i=1}^{N}{\sum}_{j=1}^{N}{J}^{2}({\mathbf{h}}_{i}^{r},{\mathbf{h}}_{j}^{r})S({\mathbf{h}}_{i},{\mathbf{h}}_{j})}{{\sum}_{i=1}^{N}{J}^{2}({\mathbf{h}}_{i}^{r},{\overline{\mathbf{a}}}^{r}){D}_{i}}$ |

**Table 2.**Accuracy ${R}_{\widehat{d}}$ (%) reached with the $\widehat{d}$-dimensional selected local binary pattern (LBP) histogram subspace, according to the different supervised and unsupervised scores on the Outex-TC-00013 set (the dimension of the histogram space is $D\times Q=9\times 256$ without selection).

$\mathit{AV}$ | $\mathit{AL}$ | $\mathit{ASL}$ | $\mathit{ICS}$ | Without | |||||
---|---|---|---|---|---|---|---|---|---|

Score | Score | Score | Score | Selection | |||||

${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | ${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | ${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | ${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | $\mathit{R}$ | |

$RGB$ | 93.25% | 8 | $\overline{)\mathbf{93.38}\mathbf{\%}}$ | 8 | $\overline{)\mathbf{93.38}\mathbf{\%}}$ | 8 | 92.94% | 9 | 92.94% |

$YUV$ | 89.56% | 9 | 91.03% | 7 | 91.03% | 7 | 89.56% | 9 | 89.56% |

${I}_{1}{I}_{2}{I}_{3}$ | 88.67% | 8 | 88.82% | 8 | 88.97% | 6 | 88.97% | 8 | 88.68% |

$HSV$ | 90.44% | 9 | 91.91% | 5 | 91.91% | 5 | 91.03% | 8 | 90.44% |

**Table 3.**Accuracy ${R}_{\widehat{d}}$ (%) reached with the $\widehat{d}$-dimensional selected LBP histogram subspace, according to the different supervised and unsupervised scores on the USPTex set (the dimension of the histogram space is $D\times Q=9\times 256$ without selection).

$\mathit{AV}$ | $\mathit{AL}$ | $\mathit{ASL}$ | $\mathit{ICS}$ | Without | |||||
---|---|---|---|---|---|---|---|---|---|

Score | Score | Score | Score | Selection | |||||

${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | ${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | ${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | ${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | $\mathit{R}$ | |

$RGB$ | 89.53% | 9 | 90.92% | 5 | 91.27% | 4 | 90.58% | 7 | 89.53% |

$YUV$ | 76.79% | 9 | $\overline{)\mathbf{93.19}\mathbf{\%}}$ | 3 | $\overline{)\mathbf{93.19}\mathbf{\%}}$ | 3 | $\overline{)\mathbf{93.19}\mathbf{\%}}$ | 3 | 76.79% |

${I}_{1}{I}_{2}{I}_{3}$ | 75.31% | 9 | 92.06% | 3 | 92.06% | 3 | 92.06% | 3 | 75.31% |

$HSV$ | 83.25% | 9 | 90.40% | 3 | 90.40% | 3 | 88.92% | 5 | 83.35% |

**Table 4.**Accuracy ${R}_{\widehat{d}}$ (%) reached with the $\widehat{d}$-dimensional selected LBP histogram subspace, according to the different supervised and unsupervised scores on the NewBarkTex set (the dimension of the histogram space is $D\times Q=9\times 256$ without selection).

$\mathit{AV}$ | $\mathit{AL}$ | $\mathit{ASL}$ | $\mathit{ICS}$ | Without | |||||
---|---|---|---|---|---|---|---|---|---|

Score | Score | Score | Score | Selection | |||||

${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | ${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | ${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | ${\mathit{R}}_{\widehat{\mathit{d}}}$ | $\widehat{\mathit{d}}$ | $\mathit{R}$ | |

$RGB$ | 73.16% | 9 | $\overline{)\mathbf{81.37}\mathbf{\%}}$ | 4 | $\overline{)\mathbf{81.37}\mathbf{\%}}$ | 4 | $\overline{)\mathbf{81.37}\mathbf{\%}}$ | 4 | 73.16% |

$YUV$ | 71.81% | 9 | 79.17% | 7 | 79.17% | 7 | 79.17% | 7 | 71.81% |

${I}_{1}{I}_{2}{I}_{3}$ | 71.68% | 9 | 79.41% | 7 | 79.41% | 7 | 79.41% | 7 | 71.69% |

$HSV$ | 70.59% | 9 | 81% | 3 | 81% | 3 | 81% | 3 | 70.59% |

**Table 5.**Histogram ranks using the proposed scores with the different color spaces and for the three databases.

OuTex | USPTex | BarkTex | ||
---|---|---|---|---|

$AV$-score | 2 4 3 6 8 7 1 5 9 | 5 4 6 8 7 9 2 3 1 | 3 7 6 8 4 2 5 1 9 | |

$AL$-score | 9 1 5 8 7 6 3 4 2 | 1 3 2 9 7 8 6 4 5 | 9 1 5 2 4 8 6 7 3 | |

$RGB$ | $ASL$-score | 9 1 5 8 7 6 4 3 2 | 1 2 3 7 4 9 6 8 5 | 9 5 1 2 4 8 6 7 3 |

$ICS$-score | 8 7 1 9 5 3 4 2 6 | 3 1 2 8 7 9 4 5 6 | 9 1 5 2 8 4 6 7 3 | |

$AV$-score | 8 4 6 2 7 3 1 9 5 | 8 7 9 4 5 6 1 3 2 | 8 6 4 7 2 3 9 5 1 | |

$AL$-score | 5 9 1 3 7 6 2 4 8 | 3 2 1 4 5 6 7 9 8 | 3 1 2 5 9 7 4 6 8 | |

$YUV$ | $ASL$-score | 1 9 5 6 8 3 7 2 4 | 3 2 1 4 5 6 9 7 8 | 3 2 7 4 1 5 9 6 8 |

$ICS$-score | 3 6 7 8 2 1 4 9 5 | 3 2 1 5 4 6 9 7 8 | 3 2 7 4 1 5 9 6 8 | |

$AV$-score | 8 6 7 4 3 2 1 5 9 | 8 7 9 5 6 4 1 2 3 | 8 6 4 7 2 5 3 9 1 | |

$AL$-score | 9 5 1 2 4 3 7 6 8 | 3 1 2 5 4 6 9 7 8 | 3 2 1 5 9 7 4 6 8 | |

${I}_{1}{I}_{2}{I}_{3}$ | $ASL$-score | 1 9 5 6 8 2 3 4 7 | 2 3 1 6 4 5 9 7 8 | 1 3 2 5 9 7 4 6 8 |

$ICS$-score | 2 4 3 6 7 8 1 9 5 | 3 2 1 5 4 6 9 8 7 | 3 2 7 4 1 5 9 6 8 | |

$AV$-score | 3 2 6 8 7 4 1 5 9 | 6 4 7 9 5 8 1 2 3 | 8 7 2 4 6 3 1 9 5 | |

$AL$-score | 9 5 1 7 4 3 2 8 6 | 3 2 1 8 7 4 5 9 6 | 5 9 1 4 2 3 6 7 8 | |

$HSV$ | $ASL$-score | 1 5 9 8 6 7 4 3 2 | 2 3 1 7 4 9 8 6 5 | 5 1 9 4 2 3 6 7 8 |

$ICS$-score | 7 8 6 1 3 4 9 5 2 | 3 2 7 4 1 8 5 9 6 | 5 1 9 6 2 4 3 8 7 |

Features | Color Space | Classifier | R (%) |
---|---|---|---|

3D-adaptive sum and difference histograms [9] | $ISH$ | SVM | 95.8 |

3D color histogram [43] | $HSV$ | 1-NN | 95.4 |

Fractal descriptors [44] | $RGB$ | LDA | 95.0 |

EOCLBP with selection thanks to the $AL$-score | $RGB$ | SVM | 94.9 |

Haralick features [5] | $RGB$ | 5-NN | 94.9 |

3D color histogram [45] | $RGB$ | 3-NN | 94.7 |

3D color histogram [46] | I-$HLS$ | 1-NN | 94.5 |

Haralick features [11] | $RGB$ | 1-NN | 94.1 |

EOCLBP/C [47] | $HSV$ | SVM | 93.5 |

EOCLBP with selection thanks to the $AL$-score | $RGB$ | 1-NN | 93.4 |

EOCLBP with selection thanks to the $ASL$-score [28] | $RGB$ | 1-NN | 93.4 |

EOCLBP [27] | $RGB$ | 1-NN | 92.9 |

Reduced Size Chromatic Co-occurrence Matrices [4] | $HLS$ | 1-NN | 92.5 |

Between color component LBP histogram [43] | $RGB$ | 1-NN | 92.5 |

Color histogram + LBP-based features [48] | $RGB$ | 1-NN | 90.3 |

Wavelet coefficients [49] | ${L}^{*}{a}^{*}{b}^{*}$ | BDC | 89.7 |

Autoregressive models + 3D color histogram [46] | I-$HLS$ | 1-NN | 88.9 |

Halftoning local derivative pattern + Color histogram [50] | $RGB$ | 1-NN | 88.2 |

Autoregressive models [46] | ${L}^{*}{a}^{*}{b}^{*}$ | 1-NN | 88.0 |

Within color component LBP histogram [43] | $RGB$ | 1-NN | 87.8 |

Mixed color order LBP [51] | $RGB$ | 1-NN | 87.1 |

Features from wavelet transform [52] | $RGB$ | 7-NN | 85.2 |

Color contrast occurrence matrix [53] | $RGB$ | 1-NN | 82.6 |

Fuzzy aura matrices [54] | $RGB$ | 1-NN | 80.2 |

Features | Color Space | Classifier | R (%) |
---|---|---|---|

Color histogram + LBP-based features [48] | $RGB$ | 1-NN | 95.9 |

Local jet + LBP [55] | Luminance | LDA | 94.3 |

Halftoning local derivative pattern + Color histogram [50] | $RGB$ | 1-NN | 93.9 |

EOCLBP with selection thanks to the $AL$-score | $YUV$ | 1-NN | 93.2 |

EOCLBP with selection thanks to the $AL$-score | $YUV$ | SVM | 87.9 |

Fractal descriptors [56] | Luminance | LDA | 85.6 |

Mixed color order LBP [51] | $RGB$ | 1-NN | 84.2 |

Features | Color space | Classifier | R (%) |
---|---|---|---|

Dominant and minor sum and difference histograms [57] | $RGB$ | SVM | 89.6 |

EOCLBP with selection thanks to the $AL$-score | $RGB$ | SVM | 84.9 |

Fine Texture and Coarse Color Features [58] | $HSV$ | NSC | 84.3 |

3D-adaptive sum and difference histograms [9] | $RGB$ | SVM | 82.1 |

EOCLBP with selection thanks to the $AL$-score | $RGB$ | 1-NN | 81.4 |

EOCLBP with selection thanks to the $ICS$-score [27] | $RGB$ | 1-NN | 81.4 |

EOCLBP with selection thanks to the $ASL$-score [28] | $RGB$ | 1-NN | 81.4 |

Mixed color order LBP [51] | $RGB$ | 1-NN | 77.7 |

© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Kalakech, M.; Porebski, A.; Vandenbroucke, N.; Hamad, D.
Unsupervised Local Binary Pattern Histogram Selection Scores for Color Texture Classification. *J. Imaging* **2018**, *4*, 112.
https://doi.org/10.3390/jimaging4100112

**AMA Style**

Kalakech M, Porebski A, Vandenbroucke N, Hamad D.
Unsupervised Local Binary Pattern Histogram Selection Scores for Color Texture Classification. *Journal of Imaging*. 2018; 4(10):112.
https://doi.org/10.3390/jimaging4100112

**Chicago/Turabian Style**

Kalakech, Mariam, Alice Porebski, Nicolas Vandenbroucke, and Denis Hamad.
2018. "Unsupervised Local Binary Pattern Histogram Selection Scores for Color Texture Classification" *Journal of Imaging* 4, no. 10: 112.
https://doi.org/10.3390/jimaging4100112