1. there is an emerging potential project inside china (outside of shanghai)
2. software that does duplicate, and near duplicate document detection. The document is Chinese text document. (the simplist form of the problem is: given a collection of documents (in a folder), and another new document, find if the new document is "similar" in content to anyone in the existing collection.
3. Similarly, there is a need to do image file detection. The images are mostly pictures with people in it. There may be slight variations to the angles when the snapshot is made.
If interested, please contact: mrjuntao@gmail.com
