Thanks for downloading Dynamsoft Label Recognizer Package!
Your download will start shortly. If your download does not begin, click here to retry.
First released: 11-30-2021
Improved the performance of the MRZ scenario. The recognition speed is improved by about 70%.
Added character normalization modes to normalize the text. This feature will improve the read rate when processing the text in nonstandard fonts like dot matrix.
New parameter control and recognition methods are added to fit more usage scenarios.
First released: 08-26-2021
- Added image processing modes to enhance the usage scenarios like MRZ reading:
- Texture area detection
- Color Conversion
- Grayscale image processing
Added dictionary-based correction. The dictionary is minimal and customizable to only cover a scenario-oriented vocabulary.
Improved the overall performance by replacing Caffe engine with OpenCV dnn engine
Improved the readability of recognizing skewed characters.
Improved the MRZ reading performance.
- Added a
corelibrary. Migrated the core structs/classes from the LabelRecognizer library to the
|2.0.0||C/C++ / .NET / Java / Android / iOS|
First released: 05-18-2021
Added timeout mechanism. DLR checks at a few points whether the elapsed time for the current image is longer than its value. If so, DLR will end the flow. Timeout prevents one image from costing too much time.
- Added parameters for lines filtering:
LineStringLengthRangeis used to define the minimum and maximum string length when running the recognition process on a specific line.
MaxLineCharacterSpacingis used to control the spacing between characters treated as one line.
Improved the regular expression parameter by supporting more RegEx pattern syntaxes.
Improved the recognition accuracy when dealing with skewed and italics characters.
- Improved the recognition accuracy for serif fonts.
|1.2.0||C/C++ / .NET / Android / iOS|
|1.2.1||C/C++ / .NET / Java / Android / iOS|
First released: 02-24-2021
- Supports text recognition from BMP, JPEG, PNG and single-page TIFF files.
- Supports zonal OCR and provides three ways to localize text areas:
- Pre-define an area manually in pixel or percentage.
- Specify an area relative to the barcode zone, which allows you to recognize accompanying texts near the barcode.
- Specify an area relative to blocks which share the same colour or uses the same font colour. A common example would be a price tag, where the text of interest is always on a yellow square background, the yellow square can serve as the reference region.
- Supports specifying a regular expression to improve recognition accuracy and robustness.
|1.0.0||C/C++ / .NET / Android / iOS|
First released: 12-10-2020
This page is compatible for: