图书馆藏书整架辅助系统的设计

Design on the books shelving system for library

在智慧图书馆技术提升、智能化过程中,整架一直是图书馆服务优化中重要且繁重的工作。为了提高乱架整理的效率,进一步优化服务质量,本文利用深度学习在计算机视觉上的应用,结合物联网和云技术,设计开发了整架辅助系统,包括前端图像采集系统和部署在云端的深度学习平台。系统利用巡检人员携带的全景相机采集图像,发送到云端;云端后台处理程序结合书架定位,对图像按搁板进行图像分割,识别书脊后分割为独立的书脊图像;再在该图像中进行索书号和文字识别,以获得图书的信息;最后用该信息来判断乱架图书的位置。试验证明,该系统识别准确,能辅助人员实现图书乱架整理的智能化,提高工作效率。

In the process of intelligent library technology upgrading and intelligentization,the whole library has always been an important and heavy work in library service optimization.In order to improve the efficiency of clutter arrangement and further optimize the quality of service,this paper uses the application of deep learning in computer vision and combines the Internet of Things and cloud technology to design and develop the whole auxiliary system,including the front-end image acquisition system and the deep learning platform deployed in the cloud.The system uses the panoramic camera carried by the inspection personnel to collect images and send them to the cloud.Combined with the positioning of bookshelf,the cloud background processing program segmented the image according to the shelf,and segmented the image into independent spine after identifying the spine.In order to obtain the information of books,call number and character recognition are carried out in the image.Finally,the information is used to judge the location of the disorderly books.The experiment proves that the system is accurate and can assist the staff to realize the intelligentization of book clutter arrangement and improve the work efficiency.