基于多源大数据分析的图像特征智能识别模型

doi:10.13229/j.cnki.jdxbgxb20211312

吉林大学学报(工学版) ›› 2023, Vol. 53 ›› Issue (2): 555-561.doi: 10.13229/j.cnki.jdxbgxb20211312

基于多源大数据分析的图像特征智能识别模型

樊敏¹(),宋世军²()

^1.西南交通大学土木工程学院，成都 610031
^2.西南交通大学交通运输与物流学院，成都 610031

收稿日期:2021-12-01 出版日期:2023-02-01 发布日期:2023-02-28
通讯作者: 宋世军 E-mail:fanmin2312@yeah.net;swjtulab@163.com
作者简介:樊敏（1979-），男，讲师，工程师，博士.研究方向：工程项目管理，施工监控，智能建造.E-mail：fanmin2312@yeah.net
基金资助:
国家自然科学基金项目(51508476)

Intelligent recognition model of image features based on multi⁃source big data analysis

Min FAN¹(),Shi-jun SONG²()

^1.School of Civil Engineering，Southwest Jiaotong University，Chengdu 610031，China
^2.School of Transportation and Logistics，Southwest Jiaotong University，Chengdu 610031，China

Received:2021-12-01 Online:2023-02-01 Published:2023-02-28
Contact: Shi-jun SONG E-mail:fanmin2312@yeah.net;swjtulab@163.com

摘要/Abstract

摘要：

针对图像受噪声影响导致特征识别精度下降的问题，提出了基于多源大数据分析的图像特征智能识别模型。根据改进的自适应二维中值滤波法，对所有小窗口内像素排查，过滤噪声，若检测到未被噪声污染的像素则直接输出，在单尺度模糊数学基础上，利用三高斯模型经过迭代处理均匀图像亮度值，将邻域中心点灰度取值分解为实部、虚部，提取局部二值特征和Brushlet特征，将邻近两个像素灰度值作减法运算，根据启发因子与灰度梯度最大值，智能识别图像特征。仿真实验结果表明：所提模型在图像不清楚情况下能均衡调节分辨率，且保证信息完整，识别结果精准有效，抗噪能力强。

关键词: 中值滤波, 三高斯模型, 环绕函数, 局部二值模式特征, Brushlet域复特征, 集域自适应快速算法

Abstract:

Due to the influence of image noise， the accuracy of image feature recognition is reduced. Therefore， an intelligent image feature recognition model based on multi-source big data analysis is proposed. According to the improved adaptive two-dimensional median filtering method， all pixels in the small window are checked and the noise is filtered. If the pixels that are not polluted by noise are detected， they are directly output. On the basis of single scale fuzzy mathematics， the three Gaussian model is used to iteratively process the uniform image brightness value， The gray value of the neighborhood center point is decomposed into the real part and the imaginary part， the local binary feature and the Brushlet feature are extracted， the gray value of the adjacent two pixels is subtracted， and the image features are intelligently recognized according to the heuristic factor and the maximum gray gradient. The simulation results show that the proposed model can adjust the resolution evenly when the image is unclear， and ensure the integrity of information， accurate and effective recognition results， and strong anti noise ability.

Key words: median filtering, three Gaussian model, surround function, local binary mode characteristics, brushlet domain complex feature, set domain adaptive fast algorithm

中图分类号:

TP391

樊敏,宋世军. 基于多源大数据分析的图像特征智能识别模型[J]. 吉林大学学报(工学版), 2023, 53(2): 555-561.

Min FAN,Shi-jun SONG. Intelligent recognition model of image features based on multi⁃source big data analysis[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(2): 555-561.

图/表 3

图1

图2

表1

参考文献 20

1	李明超, 刘承照, 张野, 等. 耦合颜色和纹理特征的矿物图像数据深度学习模型与智能识别方法[J]. 大地构造与成矿学, 2020, 44(2): 203-211.
	Li Ming-chao, Liu Cheng-zhao, Zhang Ye, et al. A deep learning and intelligent recognition method of image data for rock mineral and its implementation[J]. Geotectonica et Metallogenia, 2020, 44(2): 203-211.
2	韦超现. 基于视觉传达的多帧图像特征目标跟踪仿真[J]. 计算机仿真, 2021, 38(1): 404-407, 420.
	Wei Chao-xian. Multi-frame image feature tracking simulation based on visual communication[J]. Computer Simulation, 2021, 38(1): 404-407, 420.
3	陈汶滨, 曾渌麟. 基于谱域特征提取与线性回归分类的智能人脸识别算法[J]. 计算机应用研究, 2019, 36(10): 3116-3120.
	Chen Wen-bin, Zeng Lu-lin. Intelligent face recognition algorithm based on spectral feature extraction and linear regression classification[J]. Application Research of Computers, 2019, 36(10): 3116-3120.
4	范宇宾, 郭唯娜, 柯长青. 纹理特征辅助的SAR影像冰川识别[J]. 冰川冻土, 2019, 41(6): 1326-1334.
	Fan Yu-bin, Guo Wei-na, Ke Chang-qing.Texture-assisted glacier recognition based on SAR image[J]. Journal of Glaciology and Geocryology, 2019, 41(6): 1326-1334.
5	Zhang Y, Li M, Han S, et al. Intelligent identification for rock-mineral microscopic images using ensemble machine learning algorithms[J]. Sensors, 2019, 19(18): 3914.
6	丁慧洁. 基于非下采样剪切波特征提取的SAR图像目标识别方法[J]. 探测与控制学报, 2020, 42(1): 75-80.
	Ding Hui-jie. SAR target recognition based on non-subsampled shearlet transform(NSST) feature extraction[J]. Journal of Detection & Control, 2020, 42(1): 75-80.
7	Sun H, Zhu F, Hao Y, et al. Unified optimization for multiple active object recognition tasks with feature decision tree[J]. Journal of Intelligent & Robotic Systems, 2021, 103(2): 1-15.
8	钱银中, 沈一帆. 姿态特征与深度特征在图像动作识别中的混合应用[J]. 自动化学报, 2019, 45(3): 626-636.
	Qian Yin-zhong, Shen Yi-fan.Hybrid of pose feature and depth feature for action recognition in static image[J].Acta Automatica Sinica, 2019, 45(3): 626-636.
9	Wu C, Jiang P, Ding C, et al. Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network[J]. Computers in Industry, 2019, 108: 53-61.
10	董志鹏, 王密, 李德仁, 等. 遥感影像目标的尺度特征卷积神经网络识别法[J].测绘学报, 2019, 48(10): 1285-1295.
	Dong Zhi-peng, Wang Mi, Li De-ren,et al. Object detection in remote sensing imagery based on convolutional neural networks with suitable scale features[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48 (10): 1285-1295.
11	Wu X, Sun C, Zou T, et al. SVM-based image partitioning for vision recognition of AGV guide paths under complex illumination conditions[J]. Robotics and Computer-Integrated Manufacturing, 2020, 61(2): 101856
12	郜峰利, 陶敏, 李雪妍, 等. 基于深度学习的CT影像脑卒中精准分割[J]. 吉林大学学报:工学版, 2020, 50(2): 678-684.
	Gao Feng-li, Tao Min, Li Xue-yan, et al. Accurate segmentation of stroke in CT image based on deep learning[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(2): 678-684.
13	Hassan M, Ali S, Alquhayz H, et al. Developing intelligent medical image modality classification system using deep transfer learning and LDA[J]. Scientific Reports, 2020, 10(1): 012868.
14	Hassaballah M, Alshazly H A, Ali A A. Ear recognition using local binary patterns: a comparative experimental study[J]. Expert Systems with Applications, 2019, 118: 182-200.
15	王柯俨, 胡妍, 王怀, 等. 结合天空分割和超像素级暗通道的图像去雾算法[J]. 吉林大学学报:工学版, 2019, 49(4): 1377-1384.
	Wang Ke-yan, Hu Yan, Wang Huai, et al. Image dehazing algorithm by sky segmentation and superpixel-level dark channel[J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4):1377-1384.
16	Wang Z, Liu X, He Z, et al. Intelligent detection of flip chip with the scanning acoustic microscopy and the general regression neural network[J]. Microelectronic Engineering, 2019, 217(9): 111127.
17	闫建阳, 陈小虎, 陈俊康. 基于铁谱图像异类特征融合的磨损类型识别方法[J]. 润滑与密封, 2020, 45(3): 113-120.
	Yan Jian-yang, Chen Xiao-hu, Chen Jun-kang. Wear type recognition method based on heterogeneous feature fusion of iron spectrum images[J]. Lubrication Engineering, 2020, 45(3): 113-120.
18	李军军, 曹建农, 程贝贝, 等. 联合像素与多尺度对象的高分辨率遥感影像谱聚类分割[J]. 吉林大学学报:工学版, 2019, 49(6): 2098-2108.
	Li Jun-jun, Cao Jian-nong, Cheng Bei-bei, et al. High spatial resolution remote sensing imagery segmentation based on combination of pixels and multi-scale objects using spectral clustering[J]. Journal of Jilin University (Engineering and Technology Edition), 2019, 49(6): 2098-2108.
19	Al-Shemarry M S, Li Y, Abdulla S. An efficient texture descriptor for the detection of license plates from vehicle images in difficult conditions[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(2): 553-564.
20	Liu X, Jing W, Zhou M, et al. Multi-scale feature fusion for coal-rock recognition based on completed local binary pattern and convolution neural network[J]. Entropy, 2019, 21(6): 21060622.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

算法	精度	对比度	信息熵	所用时间/s
k-means	88.25	28.45	6.74	9.05
模糊数学	78.94	28.54	7.66	12.34
本文	94.52	37.46	9.90	7.12

[1]	托乎提努尔,张海龙,王杰,王娜,冶鑫晨,王万琼. 基于图形处理器的高速中值滤波算法[J]. 吉林大学学报(工学版), 2019, 49(3): 979-985.
[2]	郭立民,陈鑫,陈涛. 基于AlexNet模型的雷达信号调制类型识别[J]. 吉林大学学报(工学版), 2019, 49(3): 1000-1008.
[3]	段,孙同景,李振华, 黄长伟, 张光先. 全数字逆变电源IIR Butterworth数字滤波[J]. 吉林大学学报(工学版), 2009, 39(增刊2): 311-0314.

基于多源大数据分析的图像特征智能识别模型

Intelligent recognition model of image features based on multi⁃source big data analysis

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 3

参考文献 20

相关文章 3

Metrics

本文评价

推荐阅读 10