基于加强模糊聚类的航空行李图像超像素分割

罗其俊; 曹志芬; 牛国臣

doi:10.7527/S1000-6893.2020.24333

航空学报 >

2020 , Vol. 41 >Issue S2: 724333 - 724333

DOI: https://doi.org/10.7527/S1000-6893.2020.24333

基于加强模糊聚类的航空行李图像超像素分割

罗其俊 ,
曹志芬 ,
牛国臣

展开

中国民航大学机器人研究所, 天津 300300

收稿日期: 2020-06-01

修回日期: 2020-06-03

网络出版日期: 2020-06-18

基金资助

天津市教委科研计划（2019KJ118）

收起

Super-pixel segmentation of air baggage image based on enhanced fuzzy clustering

LUO Qijun ,
CAO Zhifen ,
NIU Guochen

Expand

Robotics Institute, Civil Aviation University of China, Tianjin 300300, China

Received date: 2020-06-01

Revised date: 2020-06-03

Online published: 2020-06-18

Supported by

Scientific Research Planning Project of Tianjin Education Commission (2019KJ118)

Fold

摘要

在自助行李托运系统拍摄的行李图像库中检索错误运输的行李时，图像背景会严重影响检索精度。针对该问题提出了一种加强模糊聚类算法（EnFCM）的超像素分割方法，实现了行李目标区域的提取。通过多尺度形态学重建梯度图像，设计了自适应上限尺度的分水岭超像素预分割算法，得到多个独立的超像素区域。对超像素图像进行直方图统计，并结合分水岭分割参数和实际行李图像内容的类别数量进行超像素的加强模糊聚类，得到行李区域。通过多个实际行李图像的分割实验验证了算法的有效性，平均分割精度达到93%，超过多个典型的分割算法。

关键词： 多尺度重建; 自适应尺度; 超像素预分割; 彩色图像分割; EnFCM模糊聚类

本文引用格式

罗其俊 , 曹志芬 , 牛国臣 . 基于加强模糊聚类的航空行李图像超像素分割[J]. 航空学报, 2020 , 41(S2) : 724333 -724333 . DOI: 10.7527/S1000-6893.2020.24333

Abstract

In the baggage image database captured by the self-service baggage check-in system, the image background seriously affects the retrieval accuracy of wrongly transported baggage. To solve this problem, a super-pixel segmentation method based on Enhanced Fuzzy C-Means Clustering Method (EnFCM) is proposed to extract the target baggage area. Through multi-scale morphological reconstruction of gradient images, an adaptive upper scale watershed super-pixel pre-segmentation algorithm is designed to obtain multiple independent super-pixel regions. Based on the histogram statistics of the super-pixel image, combined with the watershed segmentation parameters and the number of categories of the actual baggage image content, the EnFCM segmentation is conducted to extract the baggage area. The segmentation experiments of several real baggage images verify the effectiveness of the algorithm with the average segmentation accuracy reaching 93%, surpassing that of several typical segmentation algorithms.

Key words： multi-scale reconstruction; adaptive scale; super-pixel pre-segmentation; color image segmentation; EnFCM

参考文献

[1] 王告, 俞申亮, 巨志勇, 等. 一种改进Grabcut算法的彩色图像分割方法[J]. 软件导刊, 2019, 18(6):171-175, 2. WANG G, YU S L, JU Z Y, et al. An improved Grabcut algorithm for color image segmentation[J]. Software Guide, 2019, 18(6):171-175, 2(in Chinese).
[2] 高丽, 杨树元, 李海强. 一种基于标记的分水岭图像分割新算法[J]. 中国图象图形学报, 2007(6):1025-1032. GAO L, YANG S Y, LI H Q. New unsupervised image segmentation via marker-based watershed[J]. Journal of Image and Graphics, 2007(6):1025-1032(in Chinses).
[3] 胡学刚, 段瑶. 基于FCM聚类的自适应彩色图像分割算法[J]. 计算机工程与设计, 2018, 39(7):1984-1989. HU X G, DUAN Y. Adaptive color image segmentation algorithm based on FCM clustering[J]. Computer Engineering and Design, 2018, 39(7):1984-1989(in Chinese).
[4] 尹诗白, 孔垂涵, 王一斌. 模糊相关图割的非监督层次化彩色图像分割[J]. 中国图象图形学报, 2018, 23(9):1326-1334. YIN S B, KONG C H, WANG Y B. Unsupervised hierarchical color image segmentation through fuzzy correlation and graph cut[J]. Journal of Image and Graphics, 2018, 23(9):1326-1334(in Chinese).
[5] 雷涛, 连倩, 加小红, 等. 基于快速SLIC的图像超像素算法[J]. 计算机科学, 2020, 47(2):143-149. LEI T, LIAN Q, JIA X H, et al. Fast simple linear iterative clustering for image superpixel algorithm[J]. Computer Science, 2020, 47(2):143-149(in Chinese).
[6] MISHRA S, PANDA M. Bat algorithm for multilevel colour image segmentation using entropy-based thresholding[J]. Arabian Journal for Science and Engineering, 2018, 43(12):7285-7314.
[7] 鲁秋菊, 拓守恒. 自适应步长下多阈值彩色图像的全局分割方法[J]. 吉林大学学报(理学版), 2019, 57(1):82-88. LU Q J, TUO S H. Global segmentation method for multi-threshold color images under adaptive step size[J]. Journal of Jilin University (Science Edition), 2019, 57(1):82-88(in Chinese).
[8] 吴军, 王龙龙. 基于遗传变异的鸟群图像分割算法[J]. 计算机工程与设计, 2019, 40(4):134-139 WU J, WANG L L. Bird swarm image segmentation algorithm based on genetic variation[J]. Computer Engineering and Design, 2019, 40(4):134-139(in Chinese).
[9] 周凯红, 乔新新, 李福敏. 基于支持向量机的彩色图像分割研究[J]. 现代电子技术, 2019, 42(18):103-106, 111. ZHOU K H, QIAO X X, LI F M. Research on color segmentation based on support vector machine[J]. Modern Electronics Technique, 2019, 42(18):103-106, 111(in Chinese).
[10] YANG Z L, YUE J, LI Z B, et al. Vegetable image retrieval with fine-tuning VGG model and image hash[J]. IFAC Papers OnLine, 2018, 51(17):280-285.
[11] WU Z F, SHEN C H, VAN DEN HENGEL A. Wider or deeper:Revisiting the ResNet model for visual recognition[J]. Pattern Recognition, 2019, 90:119-133.
[12] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab:Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. ArXiv, 2018, 40(4):834-848.
[13] JIANG M X, DENG C, SHAN J S, et al. Hierarchical multi-modal fusion FCN with attention model for RGB-D tracking[J]. Information Fusion, 2019, 50:1-8.
[14] LIU M Y, TUZEL O, RAMALINGAM S, et al. Entropy rate superpixel segmentation[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition. New York:IEEE, 2011:2097-2104.
[15] 刘响. 基于均值漂移和GrowCut的彩色图像自动分割研究[D]. 镇江:江苏大学, 2018. LIU X. Research on automatic segmentation of color images based on mean shift and GrowCut[D]. Zhenjiang:Jiangsu University, 2018(in Chinese).
[16] YIN J, LIU Z H, JIN Z, et al. Kernel sparse representation based classification[J]. Neurocomputing, 2012, 77(1):120-128.
[17] 王宇, 陈殿仁, 沈美丽, 等. 基于形态学梯度重构和标记提取的分水岭图像分割[J]. 中国图象图形学报, 2008, 13(11):2176-2180. WANG Y, CHEN D R, SHEN M L, et al. Watershed segmentation based on morphological gradient reconstruction and marker extraction[J]. Journal of Image and Graphics, 2008, 13(11):2176-2180(in Chinese).
[18] LEI T, JIA X, ZHANG Y, et al. Significantly fast and robust fuzzy C-means clustering algorithm based on morphological reconstruction and membership filtering[J]. IEEE Transactions on Fuzzy Systems, 2018, 26(5):3027-3041.
[19] KRINIDIS S, CHATZIS V. A robust fuzzy local information C-means clustering algorithm[J]. IEEE Transactions on Image Processing, 2010, 19(5):1328-1337.
[20] 左利云, 罗成煜, 左右祥. 基于EnFCM的海量图像聚类分割算法的并行研究[J]. 微型机与应用, 2015, 34(15):55-58. ZUO L J, LUO C Y, ZUO Y X. Paralleled segmentation cluster algorithm based on EnFCM for large-scale image[J]. Microcomputer & Its Applications, 2015, 34(15):55-58(in Chinese).
[21] 王春瑶, 陈俊周, 李炜. 超像素分割算法研究综述[J]. 计算机应用研究, 2014, 31(1):6-12. WANG C Y, CHEN J Z, LI W. Review on superpixel segmentation algorithms[J]. Application Research of Computers, 2014, 31(1):6-12(in Chinese).
[22] LEI T, JIA X, ZHANG Y, et al. Superpixel-based fast fuzzy C-means clustering for color image segmentation[J]. IEEE Transactions on Fuzzy Systems, 2018, 27:1753-1766.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献