forked from FuxiJia/InvoiceDatasets
-
Notifications
You must be signed in to change notification settings - Fork 0
jfma-USTC/InvoiceDatasets
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Two public datasets of the camera-captured invoice images for key word spotting Currently, there is no public dataset of the camera-captured invoice images. In order to enable the comparison among different text detection and word spotting algorithms, we collect two datasets containing taxi and value added tax(VAT) invoices from different provinces in China and they are publicly available now. One is called the taxi invoice dataset (TID for short), which consists of 104 and 140 categories of key words and characters. Note that the key words of taxi invoices vary greatly between provinces and we collect samples from 25 different provinces. The other is called VATID (value added tax invoice dataset) consisting of 24 and 57 types of key words and characters. For these two datasets, we randomly select fifty percent of the images as the training set and the rest are assigned to the testing set.
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published