Table of Contents
Mobile Technology V3
History Mobile V3.0
- Release Date: February 2009
New in Mobile V3 Technology
Images fed to the ABBYY Mobile OCR Engine are typically taken with a camera built into a mobile phone. These images are often skewed. The MSDK must correct image the skew for better and faster OCR results. In ABBYY Mobile OCR Engine 3.0, image pre-processing corrects the skew as well as binarises the image. For successful skewing correction, images should not be skewed by more than 5-7 degrees. This feature can be disabled.
New Document Аnalysis
ABBYY Mobile OCR Engine 3.0 includes new Document Аnalysis (DA). The new DA analyzes documents in their entirety and produces a set of blocks, each having its own internal structure. The new DA detects noise more reliably and make OCR faster and more accurate as a result. This is particularly important for images obtained with mobile phone cameras.
The previous SDK versions read texts only left to right and top to bottom, merging all the data thus obtained into one linear array. The new ABBYY Mobile OCR Engine automatically detects text columns. The DA detects the borders of the text blocks and reads each block separately. Thus recognition is performed left to right and top to bottom only within the boundaries of a separate block.
Additional of new Business Card Recognition Languages
- Portuguese (Brazilian),
- Swedish and
Improved Memory Management
RAM operations were optimised. When the application is running, additional RAM can be allocated without stopping the application. No need to allocate large amounts of RAM in advance.
Products based on Mobile V3 Technology
- ABBYY FotoTranslate for Symbian
- No tags, yet