本文已被：浏览 1552次 下载 1433次
Received:August 26, 2018 Revised:September 20, 2018
Received:August 26, 2018 Revised:September 20, 2018
中文摘要: 针对印刷领域印刷品的识别问题，设计了一种基于浅层特征的视觉识别系统.浅层特征适用于对精准特定目标的识别，SIFT是一种被广泛使用且效果良好的浅层特征.该系统首先建立一个小型样本图像数据库，然后采用SIFT算法进行特征提取并与样本图像进行匹配识别.另外，该系统实现了在线学习的功能.经过实验验证，该系统可以实时、准确的实现对印刷品内容的识别.
Abstract:Aiming at the problem of the recognition of print content in the printing field, a visual identity system based on shallow features is designed. Shallow feature is applicable to the recognition of specific target. SIFT is a widely used and effective shallow feature. The system first establishes a sample image database, uses SIFT algorithm to extract features, finally identifies by matching with sample features. In addition, the system implements online learning functions. After experimental verification, the system can realize the identification of print content in real time and accurately.
keywords: shallow features image retrieval near-duplicate detection feature matching online learning
文章编号： 中图分类号： 文献标志码：
基金项目:辽宁省重点研发计划（2018225096）；中国科学院沈阳分院-山东省科学院青年科学家合作伙伴项目
引用文本：
谢成亮,王鸿亮,何薇薇,赵杰,王帅.基于浅层特征的印刷品分拣识别系统.计算机系统应用,2019,28(2):62-67
XIE Cheng-Liang,WANG Hong-Liang,HE Wei-Wei,ZHAO Jie,WANG Shuai.Print Sorting Recognition System Based on Shallow Features.COMPUTER SYSTEMS APPLICATIONS,2019,28(2):62-67
谢成亮,王鸿亮,何薇薇,赵杰,王帅.基于浅层特征的印刷品分拣识别系统.计算机系统应用,2019,28(2):62-67
XIE Cheng-Liang,WANG Hong-Liang,HE Wei-Wei,ZHAO Jie,WANG Shuai.Print Sorting Recognition System Based on Shallow Features.COMPUTER SYSTEMS APPLICATIONS,2019,28(2):62-67
