融合紋理與形狀特征的HEp-2細(xì)胞分類

文登偉; 張東波; 湯紅忠; 許海霞

doi:10.11999/JEIT161090

融合紋理與形狀特征的HEp-2細(xì)胞分類

doi: 10.11999/JEIT161090

1.
(湘潭大學(xué)信息工程學(xué)院湘潭 411105) ②(機(jī)器人視覺感知與控制國(guó)家工程實(shí)驗(yàn)室長(zhǎng)沙 410012)

基金項(xiàng)目:

國(guó)家自然科學(xué)基金(61602397)，湖南省自然科學(xué)基金(2017JJ2251, 2017JJ3315)，湖南省重點(diǎn)學(xué)科建設(shè)項(xiàng)目

計(jì)量
- 文章訪問數(shù): 1614
- HTML全文瀏覽量: 145
- PDF下載量: 359
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-10-17
- 修回日期: 2017-04-06
- 刊出日期: 2017-07-19

HEp-2 Cell Classification by Fusing Texture and Shape Features

1.
(Institute of Information Engineering, Xiangtan University, Xiangtan 411105, China)

Funds:

The National Natural Science Foundation of China (61602397), The Natural Science Foundation of Hunan Province (2017JJ2251, 2017JJ3315), The Key Discipline Construction Project of Hunan Province

摘要

摘要: 間接免疫熒光(IIF)HEp-2細(xì)胞圖像分析是自身免疫疾病診斷的重要依據(jù)，然而由于類內(nèi)的變化與類間的相似性，HEp-2細(xì)胞染色模式分類具有很大難度。該文提出一種結(jié)合紋理和形狀信息的有效分類方法，借鑒CLBP原理，提出具有完整信息描述能力的局部三值模式CLTP(Completed Local Triple Pattern)描述子來提取紋理信息，同時(shí)采用IFV(Improved Fisher Vector)模型和Rootsift特征來描繪形狀信息，通過紋理和形狀信息的結(jié)合，最終訓(xùn)練得到SVM分類器在ICPR 2012與ICIP 2013數(shù)據(jù)集上進(jìn)行了對(duì)比試驗(yàn)。結(jié)果表明，所提方法在細(xì)胞級(jí)測(cè)試中優(yōu)于其它方法，擁有競(jìng)爭(zhēng)性的分類性能。
- HEp-2 /
- 局部三值模式 /
- 改進(jìn)的Fisher向量
Abstract: Indirect Immuno Fluorescence (IIF) HEp-2 cell image analysis is an important basis for the diagnosis of autoimmune diseases. However, due to the great changes in the class and the similarity between the categories, HEp-2 cell staining pattern classification is a difficult problem. This paper presents an effective classification method based on the texture and shape information, learning from the principle of CLBP, a descriptor extracting texture information is proposed to describe the Complete information of the Local Triple Pattern (CLTP). Moreover, using Improved Fisher Vector (IFV) model and Rootsift feature, the shape information can be described. Through the combination of the texture and shape information, an SVM classifier is finally trained and an experiment is conducted in ICPR 2012 and ICIP 2013 data sets. Experiment results show that this method is superior over other methods in the cell level test and present competitive performance.
- HEp-2 /
- Local triple pattern /
- Improved Fisher Vector (IFV)

HTML全文

參考文獻(xiàn)(24)

TAALIMI A, ENSAFI S, QI Hairong, et al. Multimodal dictionary learing and joint sparse representation for HEp-2 cell classification[C]. 18th International Conference, Munich, Germany, 2015, 9351: 308-315. doi: 10.1007/978-3-319-24574- 4_37.

ENSAFI S, LU Shijian, KASSIM A A, et al. Accurate HEp-2 cell classification based on sparse bag of words coding[J]. Computerized Medical Imaging and Graphics, 2016. doi: 10.1016/j.compmedimag.2016.08.002.

HOBSON P, LOVELL B C, PERCANNELLA G, et al. HEp-2 staining pattern recognition at cell and specimen levels: Datasets, algorithms and results[J]. Pattern Recognition Letters, 2016, 82: 12-15. doi: 10.1016/j.patrec. 2016.07.013.

KUSHWAHA AKS, SRIVASTAVA S, and SRIVASTAVA R. Multi-view human activity recognition based on silhouette and uniform rotation invariant local binary patterns[J]. Multimedia Systems, 2016: 1-17. doi: 10.1007/s00530-016- 0505-x.

QI Xianbiao, ZHAO Guoying, CHEN Jie, et al. HEp-2 cell classification: The role of Gaussian scale space theory as a pre-processing approach[J]. Pattern Recognition Letters, 2016, 82(1): 36-43. doi: 10.1016/j.patrec.2015.12.011.

LIU Anan, LU Yao, SU Yuting, et al. HEp-2 cells classification via clustered multi-task learning[J]. Neurocomputing, 2016, 195(26): 195-201. doi: 10.1016/j. neucom.2015.06.108.

PONOMAREV G V and KAZANOV M D. Classification of ANA HEp-2 slide images using morphological features of stained patterns[J]. Pattern Recognition Letters, 2016, 82: 79-84. doi: 10.1016/j.patrec.2016.03.010.

OJALA T, PIETIKAAINEN M, and HARWOOD D. A comparative study of texture measures with classification based on featured distributions[J]. Pattern Recognition, 1996, 29(1): 51-59. doi: 10.1016/0031-3203(95)00067-4.

GUO Zhenhua and ZHANG Lei. 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.

NOSAKA R, OHKAWA Y, and FUKUI K. Feature extraction based on co-occurrence of adjacent local binary pterns[J]. Advances in Image Video Technology-Pacific Rim Symposium, 2011, 7088: 82-91. doi: 10.1007/978-3-642- 25346-1_8.

QI Xianbiao, XIAO Rong, LI Chunguang, at al. Pairwise rotation invariant co-occurrence local binary pattern[J]. IEEE Transactions on Pattern Analysis and Machine Itegence, 2014, 36(11): 2199-2213. doi: 10.1109/TPAMI.2014. 2316826.

VARMA M and ZISSERMAN A. A statistical approach to texture classification from single images[J]. International Journal of Computer Vision, 2005, 62(1): 61-81. doi: 10.1007 /s11263-005-4635-4.

HARALICK RM, SHANMUGAM K, and DINSTEIN I. Textural features for image classification[J]. IEEE Transtions on Systems, Man Cybernetics, 1973, 3(6): 610-621. doi: 10.1109/TSMC.1973.4309314.

PINHEIRO A M G. Image descriptors based on the edge orientation[C]. The Fourth International Work shop on Semantic Media Adaptation and Personalization, San Sebastain, Spain, 2009: 73-78. doi: 10.1109/SMAP.2009.27.

SIM D G, KIM H K, and PARK R H. Invariant texture retrieval using modified Zernike moments[J]. Image and Vision Computing, 2004, 22(4): 331342. doi: 10.1016/j. imavis.2003.11.003.

BIANCONI F, FERNANDEZ A, and MANCINI A. Assessment of rotation-invariant texture classification through Gabor filters and discrete Fourier transform [C]. Proceedings of 20th International Congress on Graphical Engineering, Valencia, Spain, 2008.

CATALDO S D, BOTTINO A, ISLAM I U, et al. Subclass discriminant analysis of morphological and textural features for HEp-2 staining pattern classification[J]. Pattern Recognition, 2014, 47(7): 2389-2399. doi: 10.1016/j.patcog. 2013.09.024.

PONOMAREV G V, ARLAZAROV V L, GELFAND M S, et al. ANA HEp-2 cells image classification using number, size, shape and localization of targeted cell regions[J]. Pattern Recognition, 2014, 47(7): 2360-2366. doi: 10.1016/j.patcog. 2013.09.027.

STOKLASA R, MAJTNER T, and SVOBODA D. Efficient k-NN based HEp-2 cells classifier[J]. Pattern Recognition, 2014, 47(7):2409-2418. doi: 10.1016/j.patcog.2013.09.021.

SNELL V, CHRISTMAS W, and KITTLER J. HEp-2 fluorescence pattern classification[J]. Pattern Recognition, 2014, 47(7): 2338-2347. doi: 10.1016/j.patcog.2013.10.012.

QI Xianbiao, XIAO Rong, LI Chunguang, et al. HEp-2 cell classification via fusing texture and shape information[OL]. https://arxiv.org/pdf/1502.04658v1.pdf.

THEODORAKOPOULOS I, KASTANIOTIS D, et al. HEp-2 cells classification via sparse representation of textural features fused into dissimilarity space[J]. Pattern Recognition, 2013, 47(7): 2367-2378. doi: 10.1016/j.patcog.2013.09.026.

KONG Xiangfei, LI Kuan, CAO Jingjing, et al. HEp-2 cell pattern classification with discriminative dictionary learning [J]. Pattern Recognition, 2014, 47(7): 2379-2388. doi: 10. 1016/j.patcog.2013.09.025.

NOSAKA R and FUKUI K. HEp-2 cell classification using rotation invariant co-occurrence among local binary patterns[J]. Pattern Recognition, 2014, 47(7): 2428-2436. doi: 10.1016/j.patcog.2013.09.018.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)