Technologies and Improvements of Image Search Service for Handwritten Character Patterns on Japanese Historical Documents

摘要

The service presented in this paper searches two digital archives of handwritten character pattern images on Japanese historical documents. Any binary character pattern image consisting of black character shapes and white background becomes a search key. The system owns a web-based user-interface, dictionaries of character shape feature vectors extracted from the archives, and character shape similarity evaluation modules, and runs independently from metadata formats of the archives. The service displays a list of similar character pattern image for each of the archives. The images in the lists link to the archives that provide more information of the character patterns. We present the technical details and improvements of the service. Since character shapes on historical documents contain noises, we have employed a noise absorber process for the shape evaluation. The service has received more than 30,000 search requests for a month since it was introduced to the public. For each key, processing time of the shape evaluation is less than one second, and other processes including security checking need another several seconds. As an improvement, we have updated the user-interface for better usability of smartphones. Also, we have created and distributed an application for smartphones to support creating the binary image keys. Users of about 2,900 Apple IDs had downloaded the application. We introduce the latest version of the application that we will soon distribute at the Apple App Store. Evaluating the service and analyzing the search requests are our future tasks.