Implemented a searching engine (both text-based and image-based), and set up a website to illustrate. Members include Hua Zeyu, Liu Hanwen and Liu Yuwei. 🌈🌈🌈
Crawled text and pictures from official websites of National Museum of China, the Palace Museum, and Shaanxi History Museum.
web.py is used.
Thanks to 🌸 Zeyu, our website seems to be very high-level!
Apply Lucene to establish text index and to search. Word segmentation work is done by jieba.
Based on this blog, use structural and colored features to match queried picture in the picture library. Also can match some unstored similar pictures.
Liu Hanwen also implemented some multimedia functions, such as voice-text conversion, OCR and some face detection work, which haven't been attached to final version of our website.
requirements:
- Lucene
- web.py
- opencv
- blabla
There has been a long time since we finish this work and I have forgotten the details... You can deploy your environment according to the codes and error info. Wish you good luck😜!