基于金字塔分解和扇形局部均值二值模式的魯棒紋理分類方法
doi: 10.11999/JEIT170884
基金項(xiàng)目:
國(guó)家自然科學(xué)基金(61702065, 61671095),信號(hào)與信息處理重慶市市級(jí)重點(diǎn)實(shí)驗(yàn)室建設(shè)項(xiàng)目(CSTC2009CA2003)
Robust Texture Classification Method Based on Pyramid Decomposition and Sectored Local Mean Binary Pattern
Funds:
The National Natural Science Foundation of China (61702065, 61671095), The Project of Key Laboratory of Signal and Information Processing of Chongqing (CSTC2009 CA2003)
-
摘要: 針對(duì)傳統(tǒng)局部二值模式(LBP)的特征鑒別力有限和噪聲敏感性問題,該文提出一種基于金字塔分解和扇形局部均值二值模式的紋理特征提取方法。首先,將原始圖像進(jìn)行金字塔分解,得到對(duì)應(yīng)于不同分解級(jí)別的低頻和高頻(差分)圖像。為提取兼具鑒別力和穩(wěn)健性的特征,進(jìn)一步采用閾值化處理技術(shù)將高頻圖像轉(zhuǎn)化為正、負(fù)高頻圖。然后,基于局部均值操作提出一種扇形局部均值二值模式(SLMBP),用于計(jì)算各級(jí)分解圖像的紋理特征碼。最后,對(duì)紋理特征碼進(jìn)行跨頻帶的聯(lián)合編碼和跨級(jí)別的直方圖加權(quán),從而獲得最終的紋理特征。在公開的3個(gè)紋理數(shù)據(jù)庫(kù)(Outex, Brodatz和UIUC)上進(jìn)行分類實(shí)驗(yàn),結(jié)果表明該文所提方法能夠有效地提高紋理圖像在無(wú)噪聲環(huán)境和含高斯噪聲環(huán)境下的分類精度。Abstract: The traditional Local Binary Pattern (LBP) has limited feature discrimination and is sensitive to the noise. In order to alleviate these problems, this paper proposes a method to extract texture features based on pyramid decomposition and sectored local mean binary pattern. First, the pyramid decomposition is performed on the original image to obtain low-frequency and high-frequency (difference) images with different decomposition levels. To extract robust yet discriminative features, thresholding technique is further used to transform the high-frequency images into positive and negative high-frequency images. Then, based on local averaging operations, Sectored Local Mean Binary Pattern (SLMBP) is proposed and used to compute texture feature codes at different decomposition levels. Finally, the texture features are obtained by joint coding across frequency bands and by histogram weighting across decomposition levels. Experiments on three publicly available texture databases (Outex, Brodatz and UIUC) demonstrate that the proposed method can effectively improve the classification accuracy of texture images both in noise-free conditions and in the presence of different levels of Gaussian noise.
-
WEN Dengwei, ZHANG Dongbo, TANG Hongzhong, et al. HEp-2 cell classification by fusing texture and shape features [J]. Journal of Electronics Information Technology, 2017, 39(7): 1599-1605. doi: 10.11999/JEIT161090. 文登偉, 張東波, 湯紅忠, 等. 融合紋理與形狀特征的HEp-2細(xì)胞分類[J]. 電子與信息學(xué)報(bào), 2017, 39(7): 1599-1605. doi: 10. 11999/JEIT161090. AL-SAHAF H, AL-SAHAF A, XUE B, et al. Automatically evolving rotation-invariant texture image descriptors by genetic programming[J]. IEEE Transactions on Evolutionary Computation, 2017, 21(1): 83-101. doi: 10.1109/TEVC.2016. 2577548. JIA S, HU J, ZHU J S, et al. Three-dimensional local binary patterns for hyperspectral imagery classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(4): 2399-2413. doi: 10.1109/TGRS.2016.2642951. SONG T C, LI H L, MENG F M, et al. Exploring space- frequency co-occurrences via local quantized patterns for texture representation[J]. Pattern Recognition, 2015, 48(8): 2621-2632. doi: 10.1016/j.patcog.2015.03.003. WANG H, SANG M Y, HAN D K, et al. A feature descriptor based on the local patch clustering distribution for illumination-robust image matching[J]. Pattern Recognition Letters, 2017, 94: 46-54. doi: 10.1016/j.patrec.2017.05.010. LIU L, FIEGUTH P W, GUO Y L, et al. Local binary features for texture classification: Taxonomy and experimental study[J]. Pattern Recognition, 2017, 62: 135-160. doi: 10.1016/j.patcog.2016.08.032. OJALA T, PIETIKNEN M, and MENP T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987. doi: 10.1109 /TPAMI.2002.1017623. GUO Z H and ZHANG L. A completed modeling of local binary pattern operator for texture classification[J]. IEEE Transactions on Image Processing, 2010, 19(6): 1657-1663. doi: 10.1109/TIP.2010.2044957. PAN Z B, LI Z Y, FAN H C, et al. Feature based local binary pattern for rotation invariant texture classification[J]. Expert Systems with Applications, 2017, 88(12): 238-248. doi: 10.1016/j.eswa.2017.07.007. SONG T C, LI H L, MENG F M, et al. Noise-robust texture description using local contrast patterns via global measures[J]. IEEE Signal Processing Letters, 2014, 21(1): 93-96. doi: 10.1109/LSP.2013.2293335. REN J F, JIANG X D, and YUAN J S. Noise-resistant local binary pattern with an embedded error-correction mechanism [J]. IEEE Transactions on Image Processing, 2013, 22(10): 4049-4060. doi: 10.1109/TIP.2013.2268976. LIU L, LONG Y, FIEGUTH P W, et al. BRINT: Binary rotation invariant and noise tolerant texture classification[J]. IEEE Transactions on Image Processing, 2014, 23(7): 3071-3084. doi: 10.1109/TIP.2014.2325777. ZHANG M and GUNTURK B K. Multiresolution bilateral filtering for image denoising[J]. IEEE Transactions on Image Processing, 2008, 17(12): 2324-2333. doi: 10.1109/TIP.2008. 2006658. ZHAO Y, JIA W, HU R X, et al. Completed robust local binary pattern for texture classification[J]. Neurocomputing, 2013, 106(4): 68-76. doi: 10.1016/j.neucom.2012.10.017. ZHAO Y, HUANG D S, and JIA W. Completed local binary count for rotation invariant texture classification[J]. IEEE Transactions on Image Processing, 2012, 21(10): 4492-4497. doi: 10.1109/TIP.2012.2204271. TAN X Y and TRIGGS B. Enhanced local texture feature sets for face recognition under difficult lighting conditions[J]. IEEE Transactions on Image Processing, 2010, 19(6): 1635-1650. doi: 10.1109/TIP.2010.2042645. HE J, JI H, and YANG X. Rotation invariant texture descriptor using local shearlet-based energy histograms[J]. IEEE Signal Processing Letters, 2013, 20(9): 905-908. doi: 10.1109/LSP.2013.2267730. KHELLAH F M. Texture classification using dominant neighborhood structure[J]. IEEE Transactions on Image Processing, 2011, 20(11): 3270-3279. doi: 10.1109/TIP.2011. 2143422. SHAKOOR M H and TAJERIPOUR F. Noise robust and rotation invariant entropy features for texture classification [J]. Multimedia Tools and Applications, 2017, 76(6): 8031-8066. doi: 10.1007/s11042-016-3455-6. -
計(jì)量
- 文章訪問數(shù): 1490
- HTML全文瀏覽量: 149
- PDF下載量: 166
- 被引次數(shù): 0