Learning Model

[Benehiko]

The OCR system needs to learn from success stories. An idea is to write to an SQLite database created by the OCR system. This system will add only the license plate slice to the database.

Will be made threadable for quick access on multiple occasions. Since we might have to process multiple images at the same time.

[Benehiko]

The backend support for this has been implemented in the latest development build. Backend support includes:

• Custom image object
• SQLite support for multiple databases
• READ and WRITE support for License plate slice

[Benehiko]

Use Neural network to build links between incomplete text and their "predicted" values. This might increase optimal output.