Spatially weighted order binary pattern for color texture classification

Song, Tianyou; Feng, Jie; Wang, Shiyan; Xie, Yurui

doi:10.1016/j.eswa.2019.113167

Cited by 32 publications

(20 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods construct image descriptors by concatenating all feature histograms extracted from each color channel. The inter‐channel feature extraction methods include maLBP [ 29 ] , mdLBP [ 29 ] , QLRBP [ 31 ] , LBPC [ 32 ] , SWOBP [ 33 ] and our CCBP. In addition, two non‐LBP‐based methods ( i.e ., Dense color histogram (DCH) [ 42 ] and Color name (CN) [ 43 ] ) are also compared.…”

Section: Methodsmentioning

confidence: 99%

“…The results demonstrate that CCBP is robust to image rotation as well as Gaussian noise. [12] 88.45 77.06 55.88 39.56 32.35 22.94 CLBP [13] 84.12 76.62 67.28 58.24 53.24 41.69 SLGP [16] 76.76 76.40 59.85 45.88 41.84 36.91 LTP [17] 93.75 90.66 75.59 58.90 47.72 35.81 NRLBP [18] 88.01 87.21 87.06 82.94 77.13 67.43 BRINT [20] 79.41 75.59 71.92 69.34 68.01 63.75 maLBP [29] 82.87 76.99 57.50 46.18 36.03 26.62 mdLBP [29] 86.40 81.47 58.16 42.64 36.03 27.43 QLRBP [31] 81.47 28.60 19.56 16.18 15.96 14.26 LBPC [32] 84.40 73.60 61.18 52.43 45.52 35.66 SWOBP [33] 94.71 90.44 81.47 74.48 73.90 64.27 DCH [42] 91.32 90.88 87.82 84.67 82.86 77.72 CN [43] 82 [12] 88.02 81.83 69.44 57.04 50.06 36.72 CLBP [13] 95.07 85.61 72.54 61.14 54.71 42.90 SLGP [16] 89.23 84.84 69.17 55.65 47.80 39.31 LTP [17] 94.09 90.53 85.87 80.45 75.62 66.53 NRLBP [18] 67.34 66.98 64.90 64.69 61.28 54.28 BRINT [20] 91.16 89.44 84.47 79.94 76.45 66.53 maLBP [29] 85.09 80.80 66.49 54.86 47.93 37.22 mdLBP [29] 85.45 82.77 68.13 56.88 48.58 37.93 QLRBP [31] 56.34 19.95 14.24 12.18 11.79 11.70 LBPC [32] 43.76 43.62 36.64 31.83 28.27 22.64 SWOBP [33] 89.60 88.88 85.21 80.12 77.98 73.45 DCH [42] 88.35 86.61 83.42 81.61 79.77 76.86 CN [43] 79 3) Results on the KTH-TIPS2-b database As shown in Table 4, the compared methods show competitive classification results on the KTH-TIPS2-b database. When images are slightly corrupted by noise (i.e., SNR=100), SWOBP works better than CCBP 3 (64.56% vs. 62.32% in classification accuracy), and they are followed by LTP (60.97%) and BRINT (60.10%).…”

Section: Classification Accuracy (%)mentioning

confidence: 99%

“…Song et al . [ 33 ] proposed Spatially weighted order binary pattern (SWOBP) which explores the joint information of color orders and local color differences to encode multi‐channel color images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Color Context Binary Pattern Using Progressive Bit Correction for Image Classification

Song

Feng

et al. 2021

Chinese J of Electronics

View full text Add to dashboard Cite

Local binary pattern (LBP) is sensitive to noise. Noise‐resistant LBP (NRLBP) addresses this problem by thresholding local neighboring pixels into three‐valued states (i.e., 0, 1 and uncertain bits) and recovering uncertain bits via an error‐correction mechanism. In this paper, we extend NRLBP to deal with color images and propose a robust color image descriptor called Color context binary pattern (CCBP). In CCBP, we employ scale context and neighbor context to progressively correct the encoded bits. First, we encode intra‐channel local neighboring pixels into three‐valued states in scale space and use majority voting to correct all states across scales. Then, we compute inter‐channel color feature distances and correct the uncertain bits via neighboring bit propagation. Finally, we construct the image descriptor by concatenating all histograms based on the corrected binary codes. Experiments on four benchmark databases demonstrate the robustness of CCBP for color image classification under very low signal‐to‐noise ratio levels.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Classification Accuracy (%)mentioning

confidence: 99%

See 1 more Smart Citation

Color Context Binary Pattern Using Progressive Bit Correction for Image Classification

Song

Feng

et al. 2021

Chinese J of Electronics

View full text Add to dashboard Cite

show abstract

“…In order to demonstrate the effectiveness of our proposed method, we compare it with the last texture characterization method, SWOBP [58], on CUReT and KTH-TIPS texture datasets. The experimental results are shown in Table 4.…”

Section: Comparisons With Other Methodsmentioning

confidence: 99%

Completed Extremely Nonnegative DMD for Color Texture Classification

et al. 2020

View full text Add to dashboard Cite

Dense micro-block difference (DMD) has achieved good performance in gray texture representation and classification. However, its performance is not satisfactory when representing color texture. To alleviate this problem, we propose a novel color texture representation method based on Completed Extremely Nonnegative DMD (CEN-DMD) in this paper. In particular, we first use DMD to model interchannel features and interchannel features of color texture images. Considering that negative value is meaningless in a digital image, we perform a nonnegative operation during the difference process. Due to that the maximum value in a nonnegative difference patch represents a significant difference, we construct the Extremely Nonnegative DMD (EN-DMD) by fusing the maximum values of the intrachannel features and the maximum of interchannel features, and further build Completed Extremely Nonnegative DMD (CEN-DMD) by fusing EN-DMDs at five scales and the global feature of the color texture images. Finally, the Fisher Vector is used to encode the CEN-DMD to obtain a color texture descriptor. Experimental results on five published standard color texture datasets (CUReT, Colored Brodatz, VisTex, USPTex and KTH-TIPS) reveal that CEN-DMD is effective when compared to the thirteen representative color texture classification methods. INDEX TERMS color texture representation, dense micro-block difference (DMD), extremely nonnegative multiresolution, texture classification

show abstract

“…Song et al. [41] worked on the classification of textures for which they have proposed a spatially weighted order binary pattern (SWOBP) by introducing a colour gradient channel and exploring a multi‐channel colour order pattern for finding features from images. Local multiple patterns (LMP) feature descriptor proposed by Wankou et al.…”

Section: Related Workmentioning

confidence: 99%

Towards accurate classification of skin cancer from dermatology images

Gautam

Raman

2021

IET Image Processing

View full text Add to dashboard Cite

Skin cancer is the most well-known disease found in the individuals who are exposed to the Sun's ultraviolet (UV) radiations. It is identified when skin tissues on the epidermis grow in an uncontrolled manner and appears to be of different colour than the normal skin tissues. This paper focuses on predicting the class of dermascopic images as benign and malignant. A new feature extraction method has been proposed to carry out this work which can extract relevant features from image texture. Local and gradient information from x and y directions of images has been utilized for feature extraction. After that images are classified using machine learning algorithms by using those extracted features. The efficacy of the proposed feature extraction method has been proved by conducting several experiments on the publicly available image dataset 2016 International Skin Imaging Collaboration (ISIC 2016). The classification results obtained by the method are also compared with state-of-the-art feature extraction methods which show that it performs better than others. The evaluation criteria used to obtain the results are accuracy, true positive rate (TPR) and false positive rate (FPR) where TPR and FPR are used for generating receiver operating characteristic curves.

show abstract

Spatially weighted order binary pattern for color texture classification

Cited by 32 publications

References 55 publications

Color Context Binary Pattern Using Progressive Bit Correction for Image Classification

Color Context Binary Pattern Using Progressive Bit Correction for Image Classification

Completed Extremely Nonnegative DMD for Color Texture Classification

Towards accurate classification of skin cancer from dermatology images

Contact Info

Product

Resources

About