What is SmartReco-C?
SmartReco-C ...
- is a high quality, flexible and fast ICR/OCR software for the recognition of single handwritten or machine-printed characters or symbols in binary images.
- does not have to be painstakingly trained by the user, but has powerful classifiers which are developed and configured by RecoScript.
- is not an end user product, but a subprogram library for software developers.
- requires the presence of segmented single characters or symbols.
- can be used as a central basis component of a line reader or as an additional recognizer in a voting system.
- is based on complex mathematic transformations and provides a very high standard of recognition reliability.
- has been implemented in ANSI-C. Java und C# developers are supported by relevant wrappers.
- features three functions which can be very easily integrated, and the use of which resembles file handling with fopen, fread and fclose:
- src_open opens a character or symbol classifier,
- src_read reads a character or symbol with the aid of the classifier,
- src_close closes the classifier and frees the corresponding memory.
- was designed platform independent and is now available as a static or dynamic C library for Windows/X86 (32-bit), Windows/X64 (64-bit), Linux/X86 (32-bit) and Linux/X64 (64-bit).
----------------------------------------
The following diagram illustrates the call of the function src_read in a typical SmartReco-C application (line reader):
The handwritten word "WORLD" contained in a binary image is to be read.
First src_open is used to open the required classifier (e.g. handprint alphanumeric USA).
All single characters are then extracted by the application program and processed with src_read, where one character and the corresponding classifier handle must be passed per call. src_read generates a result data record for each character, which among others contains a list of possible unicodes with corresponding quality values (probabilities). Using its context knowledge and the quality values from the result data records of the single characters, the program then forms the required word "WORLD".
