| 基于iOS系统的观赏植物识别 |
| |
| 引用本文： | 王礼,洪祖兵,方陆明,陈珣,吴超. 基于iOS系统的观赏植物识别[J]. 浙江农林大学学报, 2018, 35(5): 900-907. DOI: 10.11833/j.issn.2095-0756.2018.05.015 |
| |
| 作者姓名： | 王礼 洪祖兵 方陆明 陈珣 吴超 |
| |
| 作者单位： | 1.浙江农林大学 信息工程学院, 浙江 杭州 3113002.浙江农林大学 浙江省林业智能监测与信息技术研究重点实验室, 浙江 杭州 3113003.浙江省仙居县林业局, 浙江 仙居 317300 |
| |
| 基金项目： | 浙江省科技厅重点研发计划资助项目2018C02013 |
| |
| 摘 要： | 为了解决公众识别校园内观赏植物的问题，基于iOS操作系统设计了一款利用叶片识别观赏植物的应用程序(APP)。建立了本地SQLite数据库，存储叶片的特征数据及与校园文化相关的植物属性信息。系统运行流程:通过iPhone拍照获取植物的叶片图像，转化为灰度图后，运用OTSU法分割出叶片区域，再提取叶片的颜色、形状、纹理等10种特征，运用支持向量机(SVM)分类器识别叶片并在iPhone上展示相应的图片和文字信息。结果显示:所选8种实验观赏植物叶片的平均识别率为92%，平均用时2.6 s。该系统简单便捷，为校园观赏植物基于叶片的手机自动识别提供了实现方法，有助于发挥观赏植物在大学校园的科学价值和独特人文价值。
|
| 关 键 词： | 植物学 信息处理 iOS 叶片 特征提取 图像识别 |
| 收稿时间： | 2017-11-07 |
iOS-based recognition of ornamental plants |
| |
| WANG Li,HONG Zubing,FANG Luming,CHEN Xun,WU Chao. iOS-based recognition of ornamental plants[J]. Journal of Zhejiang A&F University, 2018, 35(5): 900-907. DOI: 10.11833/j.issn.2095-0756.2018.05.015 |
| |
| Authors: | WANG Li HONG Zubing FANG Luming CHEN Xun WU Chao |
| |
| Affiliation: | 1.School of Information Engineering, Zhejiang A & F University, Hangzhou 311300, Zhejiang, China2.Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology, Zhejiang A & F University, Hangzhou 311300, Zhejiang, China3.Forestry Enterprise of Xianju County, Xianju 317300, Zhejiang, China |
| |
| Abstract: | In order to help the public to recognize ornamental plants on the campus, an APP (application) used for recognition of ornamental plants by utilizing the laminas was designed based on the iOS operating system. The local SQLite database was established to store the feature data of the laminas and the attribute information of the plants related to campus culture. The images of the laminas of the plants were acquired by taking photos with iPhone, which were then converted to grey-scale maps. The OTSU method was utilized to segment regions for the laminas, and 10 features of the laminas such as color, shape and texture were extracted. The laminas were then recognized with the support vector machines (SVM) classifier, and corresponding image and text information were displayed on iPhone. According to research findings, the average recognition rate of laminas of the 8 selected ornamental plants was 92 per cent, with average recognition time of 2.6 s. The system is simple and convenient, providing a method for realizing automatic mobile recognition of campus ornamental plants based on laminas. In addition, it gives full play to scientific values and unique humanistic values of ornamental plants on the campus. |
| |
| Keywords: | |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《浙江农林大学学报》浏览原始摘要信息 |
|
点击此处可从《浙江农林大学学报》下载免费的PDF全文 |
|
