[1]王 燕,曹建芳,李艳飞.融合混合优化组合的大规模场景图像分类算法[J].计算机技术与发展,2019,29(09):86-91.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 017]
　WANG Yan,CAO Jian-fang,LI Yan-fei.A Classification Algorithm for Large-scale Scene Images Fusing Hybrid Optimization and Combination[J].,2019,29(09):86-91.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 017]
点击复制

融合混合优化组合的大规模场景图像分类算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年09期
页码:
86-91
栏目:
智能、算法、系统工程
出版日期:
2019-09-10

文章信息/Info

Title:
A Classification Algorithm for Large-scale Scene Images Fusing Hybrid Optimization and Combination
文章编号:
1673-629X(2019)09-0086-06
作者:
王 燕1 ; 曹建芳1; 2 ; 李艳飞2
1. 忻州师范学院 计算机系,山西 忻州 034000; 2. 太原科技大学 计算机科学与技术学院,山西 太原 030024
Author(s):
WANG Yan1 ; CAO Jian-fang1; 2 ; LI Yan-fei2
1. Department of Computer,Xinzhou Teachers University,Xinzhou 034000,China; 2. School of Computer Science and Technology,Taiyuan University of Science and Technology,Taiyuan 030024,China
关键词:
混合优化; Adaboost 算法; 集群环境; MapReduce 并行编程模型; 分类模型
Keywords:
hybrid optimization; Adaboost algorithm; cluster environment; MapReduce parallel programming model; classification model
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 09. 017
摘要:
图像获取设备的普及和网络技术的发展导致数字图像迅速增长,面对海量图像,传统的单节点架构的分类算法性能急剧下降。 针对上述问题,以场景图像为研究对象,提出了一种集群环境下的融合混合优化和组合技术的大规模图像分类方法。 将 ABC 算法和 PSO 算法优化后的 SVM 作为弱分类器,由 Adaboost 算法组合弱分类器输出构建强分类器;利用 Hadoop 平台下的 MapReduce 并行编程模型对算法进行并行化设计,提出 P-Adaboost-(ABC-PSO-SVM)算法,构造了大规模场景图像的自动分类模型。 多组对比实验表明,相对于传统的单机平台下的分类算法,当图像数量达到 50 000 时,该算法在 SUN Database 场景图像库上的平均分类准确率达 87.6%,训练耗时仅为 98s。 实验结果充分说明,该算法适合大规模场景图像的自动分类预测。
Abstract:
The popularity of image acquisition devices and the development of network technology have resulted in the rapid growth of digital images. In the face of large amounts of images,the performance of classification algorithms under traditional single machine platforms has dropped dramatically. To solve the above problems,we propose a classification algorithm for large-scale scene images fusing hybrid optimization and combination technology in a cluster environment. Taking SVM optimized by ABC algorithm and PSO algorithm as weak classifiers,we use Adaboost algorithm to build a strong classifier through combining the outputs of weak classifiers. Then the MapReduce parallel programming model in the Hadoop platform is applied to carry on parallel design to the proposed algorithm,namely P-Adaboost-(ABC-PSO-SVM) algorithm. Finally, the automatic classification model for large-scale scene images is constructed. Compared with the traditional classification algorithms using single platform,the experiment shows that the average classification accuracy of the proposed algorithm is 87.6% and the training time is only 98 seconds in the SUN Database when the image number reaches 50 000. The experimental results further verify that the proposed algorithm is suitable for automatic classification and prediction for large-scale scene images.

相似文献/References:

[1]张礼雄,张忠林.视频中多目标车辆的检测与跟踪方法研究[J].计算机技术与发展,2018,28(07):125.[doi:10.3969/ j. issn.1673-629X.2018.07.027]
　ZHANG Li-xiong,ZHANG Zhong-lin.Research on Method of Detection and Tracking of Multi-objective Vehicle Based on Video[J].,2018,28(09):125.[doi:10.3969/ j. issn.1673-629X.2018.07.027]
[2]史双飞,张 震.基于决策的人脸检测与自动跟踪方法[J].计算机技术与发展,2019,29(09):35.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 007]
　SHI Shuang-fei,ZHANG Zhen.A Method of Face Detection and Automatic Tracking Based on Decision Making[J].,2019,29(09):35.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 007]
[3]乔旭坤,李 顺,李 君,等.基于机器学习的硬盘故障预测研究[J].计算机技术与发展,2022,32(06):215.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 036]
　QIAO Xu-kun,LI Shun,LI Jun,et al.Research on Hard Disk Failure Prediction Based on Machine Learning[J].,2022,32(09):215.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 036]

更新日期/Last Update: 2019-09-10