Release Highlights

Stay updated with Dynamsoft's latest product features and enhancements.
Be the first to know when new releases and updates go live.

MAR 04, 2025|WORKFLOW IMPROVEMENTS

WORKFLOW IMPROVEMENTS

Restructured the parameter control hierarchy

DCV3.0

DBR11.0

Restructured the parameter control hierarchy at all levels for finer scope definition and more granular process management, with the stage level newly added.

CVTemplate
ROI
Task
Section
Stage
ImageParameter

CaptureVision Template

CaptureVision Template

Name

ImageSourceName

OutputOriginalImage

ImageROIProcessingNameArray

SemanticProcessingNameArray

MaxParallelTasks

Timeout

MinImageCaptureInterval

CaptureVision Template

ROI Definition

Name

TaskSettingNameArray

BaseTargetROIDefName

Location

EnableResultsDeduplication

CaptureVision Template

BarcodeReaderTask

Name

ExpectedBarcodesCount

BarcodeFormatIds

DPMCodeReadingModes

TextResultOrderModes

BaseBarcodeReaderTaskSettingName

BarcodeFormatSpecificationNameArray

SectionArray

CaptureVision Template

BarcodeDecodingSection

Section

ImageParameterName

StageArray

CaptureVision Template

ResistDeformationStage

Stage

DeformationResistingModes

CaptureVision Template

ImageParameter

Name

ApplicableStages

ScaleImage Stage

ConvertToGrayscale Stage
ColourConversionModes

EnhanceGrayscale Stage

BinarizeImage Stage

...

WORKFLOW IMPROVEMENTS

Flexible section combinations

DCV3.0

DBR11.0

Enabled custom combinations and sequences of sections, increasing flexibility and operational customization under specific conditions.

MAR 04, 2025|DEEP LEARNING INTEGRATION

DEEP LEARNING INTEGRATION

Deblurring barcodes

DCV3.0

DBR11.0

Improved the reading rate of 1D barcode by introducing a new deblurring deep-learning model.

MAR 04, 2025|ALGORITHM ENHANCEMENTS

ALGORITHM ENHANCEMENTS

Enabled deduplication at the ROI level

DCV3.0

DBR11.0

Enabled deduplication at the Region of Interest (ROI) level to consolidate results from multiple tasks.

ALGORITHM ENHANCEMENTS

Multi-step recognition and validation

DCV3.0

Enhanced the text recognition workflow by integrating improved multi-step recognition processes and validation methods.

TextLine Recognition Model

F2N09 AU6

Character Feature scorer

F2N09 AU6

Confusable Character Corrector

F2NO9 AU6

Character Recognition Model

F2HO9 AU6

Character Overlapping Matcher

F2HO9 AU6

Regex Corrector

P2HO9 AU6

Dictionary-Based Corrector

P2HO9 AUG

1, TextLine Recognition Model

Goal: Recognize a text-line using an end-to-end CRNN model.

Step Result: The initial recognition result was "F2N09 AU6"

2, Character Feature Scorer

Goal: Analyze individual character feature scores and identify suspicious characters.

Step Result: Characters "N" and "0" were flagged as suspicious.

3, Confusable Character Corrector

Goal: Correct confusable characters such as (0, o, O), (l, i, 1), etc., based on standard font characteristics.

Step Result: "0" was corrected to "O".

4, Character Recognition Model

Goal: Recognize characters with low feature scores.

Step Result: "N" was corrected to "H", but the model’s confidence score is low.

5, Character Overlapping Matcher

Goal: Recognize broken or overlapping characters with both low feature scores and low model confidence scores.

Step Result: "N" was corrected to "H".

6, Regex Corrector

Goal: Correct misrecognized characters by applying regex patterns.

Regex Pattern: "^P.*"

Step Result: "F" was corrected to "P".

7, Dictionary-based Corrector

Goal: Correct misrecognized characters by matching against a custom dictionary.

Dictionary: "AUG"

Step Result: "AU6" was corrected to "AUG".

ALGORITHM ENHANCEMENTS

Improved the CODE_128 and DataMatrix

DCV3.0

DBR11.0

Improved the CODE_128 and DataMatrix DeepAnalysis algorithms for better decoding accuracy and performance.

ALGORITHM ENHANCEMENTS

Support for CODE_32, MATRIX_25, KIX, and TELEPEN Barcodes

DCV3.0

DBR11.0

Added support for new barcode types: CODE_32, MATRIX_25, KIX, and TELEPEN.