基于网络爬虫的青花瓷文物图像数据集设计与构建

Design and Construction of Blue-and-White Porcelain Image Dataset Based on Web Crawler

深度学习模型结构复杂,利用其进行图像分类需要庞大的数据量,图像数据集的规模和质量直接影响模型的效果,同时人工获取文物图像时,存在诸多不便。该文利用网络爬虫技术在故宫博物院官网批量获取不同年代的青花瓷文物图像,大大提高工作效率,然后对获取的文物图像进行全方位的分析和处理,为用户之后进行不同年代的青花瓷图像分类提供数据源。

The structure of deep learning model is complex.Using it for image classification requires a huge amount of data.The scale and quality of image data set directly affect the effect of the model.At the same time,there are many inconveniences when manually obtaining cultural relic images.Through web crawler,we obtained images of blue-and-white porcelain from various dynasties in batch from Palace Museum official website,which greatly improves efficiency.We conduct an all-around analysis and processing of these images,thereby provide a data source for any users when classifying blue-and-white porcelain images from different dynasties.