A Combinatorial Solution to Point Symbol Recognition.

A Combinatorial Solution to Point Symbol Recognition.
复制标题

点符号识别的组合解决方案

DOI:
10.3390/s18103403
复制
发表时间:
2018-10-11
期刊:
Sensors (Basel, Switzerland)
影响因子:
--
通讯作者:
Qi Y
Qi Y
中科院分区:
其他
文献类型:
--
作者:
Quan Y;Shi Y;Miao Q;Qi Y

文献摘要

参考文献

相似文献

近年来的研究表明,点符号识别是地图数字化领域的一项重要任务。对于符号的识别,一般需要用特定的标准对符号进行比较,逐个找到与每个已知符号最相似的符号。大部分作品只能识别单个符号,少数作品是同时处理多个符号,识别精度较低。鉴于这两个不足,本文提出了一种深度迁移学习架构,其任务是使用AlexNet学习符号分类器。针对数据集不足的情况,我们开发了一种使用MNIST数据集对模型进行预训练的迁移学习方法,弥补了训练数据集小的问题,增强了模型的泛化能力。在识别之前,对地图中的点符号进行预处理,粗筛出疑似点符号的区域。我们展示了使用点符号图像的显著改进,以保持高性能,能够同时处理更多类别的符号。
Recent work has shown that recognizing point symbols is an essential task in the field of map digitization. For the identification of symbols, it is generally necessary to compare the symbols with a specific criterion and find the most similar one with each known symbol one by one. Most of the works can only identify a single symbol, a small number of works are to deal with multiple symbols simultaneously with a low recognition accuracy. Given the two deficiencies, this paper proposes a deep transfer learning architecture, where the task is to learn a symbol classifier with AlexNet. For the insufficient dataset, we develop a method for transfer learning that uses a MNIST dataset to pretrain the model, which makes up for the problem of small training dataset and enhances the generalization of the model. Before the recognition process, preprocessing the point symbols in the map to coarse screening out the areas suspected of point symbols. We show a significant improvement over using point symbol images to keep a high performance in being able to deal with many more categories of symbols simultaneously.
DOI: 10.1109/tgrs.2018.2862899
发表时间: 2019-02-01
影响因子: 8.2
作者:
Wang, Qi;He, Xiang;Li, Xuelong
通讯作者: Li, Xuelong
DOI: 10.1137/15m104373x
发表时间: 2017-01-01
影响因子: 2.1
作者:
Camassa, Roberto;Kuang, Dongyang;Lee, Long
通讯作者: Lee, Long
地形图处理的引导超像素方法
DOI: 10.1109/tgrs.2016.2567481
发表时间: 2016-11-01
影响因子: 8.2
作者:
Miao, Qiguang;Liu, Tiange;Yang, Yun
通讯作者: Yang, Yun
DOI: 10.1007/s00500-017-2503-0
发表时间: 2018-04-01
期刊: SOFT COMPUTING
影响因子: 4.1
作者:
Liu, Yujie;Huang, He;Huang, Tingwen
通讯作者: Huang, Tingwen
DOI: 10.1109/34.754622
发表时间: 1999-03-01
影响因子: 23.6
作者:
Cai, JH;Liu, ZQ
通讯作者: Liu, ZQ