计算机工程与科学 ›› 2024, Vol. 46 ›› Issue (03): 488-498.
吕伏1,2,韩晓天2,冯永安2,项梁2
收稿日期:
2023-02-12
修回日期:
2023-06-01
接受日期:
2024-03-25
出版日期:
2024-03-25
发布日期:
2024-03-15
基金资助:
Lv Fu1,2,HAN Xiao-tian2,FENG Yong-an2,XIANG Liang2
Received:
2023-02-12
Revised:
2023-06-01
Accepted:
2024-03-25
Online:
2024-03-25
Published:
2024-03-15
摘要: 现有基于深度学习的图像分类方法普遍缺少纹理特征的针对性,分类精度较低,难以同时适用于简单纹理和复杂纹理分类。提出一种基于自适应纹理特征融合的深度学习模型,能够结合类间差异性纹理特征做出分类决策。首先,根据纹理特征的最大类间差异性,构建图像的纹理特征图像;然后,采用原始图像与特征鲜明的纹理特征图像并行训练改进的双线性模型,获取双通道特征;最后,基于决策融合构建自适应分类模块,连接原图与纹理集的平均池化特征图进行通道权重提取,根据通道权重融合2个并行神经网络模型的分类向量,得到最优融合分类结果。在KTH-TIPS,KTH-TIPS-2b,UIUC和DTD 4个公共纹理数据集上对模型的分类性能进行评估,分别得到了99.98%、99.95%、99.99%和67.09%的准确率,表明所提模型具有普遍高效的识别性能。
吕伏, 韩晓天, 冯永安, 项梁. 基于自适应纹理特征融合的纹理图像分类方法[J]. 计算机工程与科学, 2024, 46(03): 488-498.
Lv Fu, HAN Xiao-tian, FENG Yong-an, XIANG Liang. A texture image classification method based on adaptive texture feature fusion[J]. Computer Engineering & Science, 2024, 46(03): 488-498.
[1] | Ojala T,Pietikainen M,Maenpaa 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. |
[2] | Haralick R M, Shanmugam K,Dinstein I H.Textural features for image classification[J].IEEE Transactions on Systems,Man,and Cybernetics,1973,SMC-3(6):610-621. |
[3] | Charalampidis D,Kasparis T.Wavelet-based rotational invariant roughness features for texture classification and segmentation[J].IEEE Transactions on Image Processing,2002,11(8):825-837. |
[4] | Zhang W,Shan S,Gao W,et al.Local Gabor binary pattern histogram sequence (LGBPHS):A novel non-statistical model for face representation and recognition[C]∥Proc of 2005 IEEE International Conference on Computer Vision,2005:786-791. |
[5] | Liu L,Lao S,Fieguth P W,et al.Median robust extended local binary pattern for texture classification[J].IEEE Transactions on Image Processing,2016,25(3):1368-1381. |
[6] | Calonder M,Lepetit V,Ozuysal M,et al.BRIEF:Computing a local binary descriptor very fast[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,34(7):1281-1298. |
[7] | Rublee E,Rabaud V,Konolige K,et al.ORB:An efficient alternative to SIFT or SURF[C]∥Proc of 2011 International Conference on Computer Vision,2011:2564-2571. |
[8] | Lowe D G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60:91-110. |
[9] | Bay H,Tuytelaars T, van Gool L.SURF:Speeded up robust features[J].Lecture Notes in Computer Science,2006,3951:404-417. |
[10] | Novitasari D C R,Lubab A,Sawiji A,et al.Application of feature extraction for breast cancer using one order statistic,GLCM,GLRLM,and GLDM[J].Advances in Science,Technology and Engineering Systems Journal,2019,4(4):115-120. |
[11] | 欧利国,李汶龙,刘必林,等.基于计算机视觉的3种金枪鱼属鱼类表型纹理特征分析[J].中国水产科学,2022,29(5):770-780. |
Ou Li-guo,Li Wen-long,Liu Bi-lin,et al.Analysis of phenotype texture features of three Thunnus species based on computer vision [J].Journal of Fishery Sciences of China,2022,29(5):770-780. | |
[12] | 刘涛,尹志强,雷经发,等.金属疲劳损伤过程中表面形貌的多分辨特征提取[J].激光与光电子学进展,2022,59(8):444-453. |
Liu Tao,Yin Zhi-qiang,Lei Jing-fa,et al.Multiresolution feature extraction of surface topography in metal fatigue damage process[J].Laser & Optoelectronics Progress,2022,59(8):444-453. | |
[13] | 包姣,刘力夫,曹九稳.基于振动的超高速碰撞识别与定位 [J].Frontiers of Information Technology & Electronic Engineering,2022,23(4):515-530. |
Bao Jiao,Liu Li-fu,Cao Jiu-wen,Vibration-based hypervelocity impact identification and localization [J].Frontiers of Information Technology & Electronic Engineering,2022,23(4):515-530. | |
[14] | Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90. |
[15] | Cimpoi M,Maji S,Vedaldi A.Deep filter banks for texture recognition and segmentation[C]∥Proc of 2015 IEEE Conference on Computer Vision and Pattern Recognition,2015:3828-3836. |
[16] | Simonyan K, Zisserman A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014. |
[17] | Szegedy C,Liu W,Jia Y,et al.Going deeper with convolutions[C]∥Proc of 2015 IEEE Conference on Computer Vision and Pattern Recognition,2015:1-9. |
[18] | Lin T Y,RoyChowdhury A,Maji S.Bilinear CNN models for fine-grained visual recognition[C]∥Proc of 2015 IEEE International Conference on Computer Vision,2015:1449-1457. |
[19] | Lin T Y,Maji S.Visualizing and understanding deep texture representations[C]∥Proc of 2016 IEEE Conference on Computer Vision and Pattern Recognition,2016:2791-2799. |
[20] | Zhou T,Ruan S,Canu S.A review:Deep learning for medical image segmentation using multi-modality fusion[J].Array,2019,3-4:100004. |
[21] | The KTH-TIPS image database[EB/OL].[2004-05-07]. https://www.csc.kth.se/cvap/databases/kth-tips/kth_tips.pdf. |
[22] | The KTH-TIPS2-2b image database[EB/OL]. [2006-06-09]. https://www.csc.kth.se/cvap/databases/kth-tips/kth-tips2.pdf. |
[23] | Lazebnik S,Schmid C,Ponce J.A sparse texture representation using local affine regions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(8):1265-1278. |
[24] | Cimpoi M,Maji S,Kokkinos I,et al.Describing textures in the wild[C]∥Proc of 2014 IEEE Conference on Computer Vision and Pattern Recognition,2014:3606-3613. |
[25] | Ruichek Y.Attractive-and-repulsive center-symmetric local binary patterns for texture classification[J].Engineering Applications of Artificial Intelligence,2019,78:158-172. |
[26] | Ghazouani H, Barhoumi W.Genetic programming-based learning of texture classification descriptors from local edge signature[J].Expert Systems with Applications,2020,161:113667. |
[27] | Amirolad A,Arashloo S R,Amirani M C.Multi-layer local energy patterns for texture representation and classification[J].The Visual Computer,2016,32:1633-1644. |
[28] | Hazgui M,Ghazouani H,Barhoumi W.Genetic programming- based fusion of HOG and LBP features for fully automated texture classification[J].The Visual Computer,2022,38(2):457-476. |
[29] | Hu Y,Long Z,AlRegib G.Scale selective extended local binary pattern for texture classification[C]∥Proc of 2017 IEEE International Conference on Acoustics,Speech and Signal Processing,2017:1413-1417. |
[30] | Liu L,Fieguth P W,Hu D,et al.Fusing sorted random projections for robust texture and material classification[J].IEEE Transactions on Circuits and Systems for Video Technology,2014,25(3):482-496. |
[31] | Mehta R,Egiazarian K.Texture classification using dense micro-block difference[J].IEEE Transactions on Image Processing,2016,25(4):1604-1616. |
[32] | Crosier M,Griffin L D.Using basic image features for texture classification[J].International Journal of Computer Vision,2010,88(3):447-460. |
[33] | Hong X P,Zhao G Y,Pietikinen M,et al.Combining LBP difference and feature correlation for texture description[J].IEEE Transactions on Image Processing,2014,23(6):2557-2568. |
[34] | Chen J,Shan S,He C,et al.WLD:A robust local image descriptor[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,32(9):1705-1720. |
[35] | Ji L,Ren Y,Liu G,et al.Training-based gradient LBP feature models for multiresolution texture classification[J].IEEE Transactions on Cybernetics,2017,48(9):2683-2696. |
[36] | Sifre L,Mallat S.Rotation,scaling and deformation invariant scattering for texture discrimination[C]∥Proc of 2013 IEEE Conference on Computer Vision and Pattern Recognition,2013:1233-1240. |
[37] | Varma M,Zisserman A.A statistical approach to material classification using image patch exemplars[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,31(11):2032-2047. |
[38] | Xu Y,Huang S B,Ji H,et al.Combining powerful local and global statistics for texture description[C]∥Proc of 2009 IEEE Conference on Computer Vision and Pattern Recognition,2009:573-580. |
[39] | Ryu J,Hong S,Yang H S.Sorted consecutive local binary pattern for texture classification[J].IEEE Transactions on Image Processing,2015,24(7):2254-2265. |
[40] | Nguyen V L, Vu N S, Gosselin P H. A handcrafted normalized-convolution network for texture classification[C]∥Proc of the IEEE International Conference on Computer Vision Workshops,2017:1238-1245. |
[41] | Fujieda S,Takayama K,Hachisuka T.Wavelet convolutional neural networks for texture classification[J].arXiv:1707.07394,2017. |
[42] | Chatfield K,Simonyan K,Vedaldi A,et al.Return of the devil in the details:Delving deep into convolutional nets[J].arXiv:1405.3531,2014. |
[43] | Andrearczyk V,Whelan P F.Using filter banks in convolutional neural networks for texture classification[J].Pattern Recognition Letters,2016,84:63-69. |
[44] | Allain C,Cloitre M.Characterizing the lacunarity of random and deterministic fractal sets[J].Physical Review A,1991,44(6):3552. |
[45] | de Souza J, Rostirolla S P.A fast MATLAB program to estimate the multifractal spectrum of multidimensional data:Application to fractures[J].Computers & Geosciences,2011,37(2):241-249. |
[46] | Ranganath A,Senapati M R,Sahu P K.Classification of textures using pixel range calculation method[C]∥Proc of 2021 International Conference on Computing,Communication,and Intelligent Systems,2021:652-657. |
[1] | 罗月童, 李超, 周波, 张延孔. 面向工业缺陷分类的交互式易混淆缺陷分离方法研究[J]. 计算机工程与科学, 2024, 46(03): 463-470. |
[2] | 吉旭瑞, 魏德健, 张俊忠, 张帅, 曹慧. 中文电子病历信息提取方法研究综述[J]. 计算机工程与科学, 2024, 46(02): 325-337. |
[3] | 黄泽彪, 董德尊, 齐星云. Gloo+:利用在网计算技术加速分布式深度学习训练[J]. 计算机工程与科学, 2024, 46(01): 28-36. |
[4] | 邱晓梦, 王琳, 谷文俊, 宋伟, 田浩来, 胡誉. 光流法修正的时序图像语义分割模型[J]. 计算机工程与科学, 2024, 46(01): 102-110. |
[5] | 崔浩, 万亚平, 钟华, 聂明星, 肖杨. 基于LoRa设备的人体活动识别研究[J]. 计算机工程与科学, 2024, 46(01): 111-121. |
[6] | 张骞, 陈紫强, 孙宗威, 赖镜安. 融合高分辨率网络的雾天目标检测算法[J]. 计算机工程与科学, 2023, 45(11): 1970-1981. |
[7] | 刘雨墨, 刘剑飞, 郝禄国, 曾文彬. 基于多尺度特征融合网络的HEVC帧内编码单元快速划分研究[J]. 计算机工程与科学, 2023, 45(11): 1991-1998. |
[8] | 李卓璇, 周亚同. 改进DBNet的电商图像文字检测算法研究[J]. 计算机工程与科学, 2023, 45(11): 2008-2017. |
[9] | 马志峰, 张浩, 刘劼. 基于深度学习的短临降水预报综述[J]. 计算机工程与科学, 2023, 45(10): 1731-1753. |
[10] | 张耐, 张晨亮, 柳永翔, 陈聪, 黄艳婷. 基于模型混合的智能交易行为异常检测[J]. 计算机工程与科学, 2023, 45(09): 1639-1647. |
[11] | 郭艺, 何廷年, 李爱斌, 毛君宇. 融合GA-CART和Deep-IRT的知识追踪模型[J]. 计算机工程与科学, 2023, 45(09): 1691-1700. |
[12] | 马思远, 焦佳辉, 任晟岐, 宋伟. 基于注意力机制的城市多元空气质量数据缺失值填充[J]. 计算机工程与科学, 2023, 45(08): 1354-1364. |
[13] | 易啸, 马胜, 肖侬. 深度学习加速器在不同剪枝策略下的运行优化[J]. 计算机工程与科学, 2023, 45(07): 1141-1148. |
[14] | 康宇晗, 时洋, 陈照云, 文梅. 面向迈创+MatrixZone异构系统的深度学习编程框架[J]. 计算机工程与科学, 2023, 45(07): 1149-1158. |
[15] | 刘浩翰, 孙铖, 贺怀清, 惠康华. 基于改进YOLOv3的金属表面缺陷检测[J]. 计算机工程与科学, 2023, 45(07): 1226-1235. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||
湘公网安备 43010502000083号
湘ICP备10006030号
版权所有 © 《计算机工程与科学》 编辑部
地址:中国湖南省长沙市开福区德雅路109号(410073) 电话:0731-87002567 Email: jsjgcykx@vip.163.com
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn