v5.2

API:

• Added the ability to select a mode of the recognition process (captureMode):
  • automatic (Auto)
  • start video mode using the Capture button (CaptureVideo)
  • manual mode for processing a single frame (CaptureFrame)
• Added the ability to set the maximum time for document recognition, after which the recognition process ends automatically (timeout)
• In some scenarios, you can manually correct the borders of the detected document when using the automatic recognition mode via the showScanner function (manualCrop)
• In some scenarios, you can manually correct the borders of the detected document when using the recognizeImage function (manualCrop)
• Added the ability to limit the document tilt angle (perspectiveAngle)
• Added the ability to set the minimum allowed DPI of a document in the image (minDPI)
• Added the ability to display metadata while reading a document (showMetadataInfo)
• Added the ability to get an integral image (integralImage)
• Added SDK localization in 8 new languages: Italian, Polish, Arabic, Vietnamese, Czech, Portuguese, Thai, Turkish
• Added a new function getTextFieldValueByType to quickly get values from the results by specifying RGLFieldType and RGLResultType
• Added a new function getTextFieldValueByType to quickly get values from the results by specifying RGLFieldtype, RGLResultType and original properties
• Added a new function getTextFieldValueByType to quickly get values from the results by specifying RGLFieldtype and original properties.
• In RGLDocumentReaderResults, added the morePagesAvailable status indicating that the document contains other pages
• In RGLDocumentReaderResults, added the time spent on reading the document RFID chip (elapsedTimeRFID)
• In RGLDocumentReaderResults, added the time spent on document recognition (elapsedTime)
• In RGLDocumentReaderResults, added a new property processingFinishedStatus indicating the current status of the recognition process (RGLProcessingFinishedStatus))
• In RGLDocumentReaderValue, added a new property indicating recognition probability (0%-100%) (probability)
• Added new values to the RGLFieldType parameter:
  • RGLFieldTypeFt_URL
  • RGLFieldTypeFt_Caliber
  • RGLFieldTypeFt_Model
  • RGLFieldTypeFt_Make
  • RGLFieldTypeFt_NumberOfCylinders
  • RGLFieldTypeFt_SurnameOfHusbandAfterregistration
  • RGLFieldTypeFt_SurnameOfWifeAfterRegistration
  • RGLFieldTypeFt_DateOfBirthOfWife
  • RGLFieldTypeFt_DateOfBirthOfHusband
  • RGLFieldTypeFt_CitizenshipOfFirstPerson
  • RGLFieldTypeFt_CitizenshipOfSecondPerson
  • RGLFieldTypeFt_CVV
• Redesigned the error structure when working with the SDK, now most errors are returned as NSError objects
• Fixed minor issues

Core:

• Added capability to read both sides of bank cards in CreditCard scenario (multipageProcessing)
• Added correct depersonalization support for all platforms with applying blur over the field areas. Depersonalization configuration options extended with allTextFields and allGraphicFields (dePersonalize)
• Document type recognition:
  • Improved with new NN under the hood. Smaller size, better quality results
  • New functionality implemented to better differentiation between document series based on document data
• OCR:
  • Added support for Arabic, Bengali, Korean, Hindi, Sinhala, Tamil, and Thai languages
  • Refactored to optimize and remove redundant code and make it smaller in size
  • Fixed issue with Azeri Ə character returned Cyrillic instead of Latin
• MRZ:
  • Added new parsers:
    • Armenia visa
    • Saudi Arabia visa
  • Updated parsers:
    • Kuwait ID card
    • Romania ID card
  • Improved reading on images with color noise over MRZ
  • Fixed issue with setting validity for the fields that were not actually validated
• Barcode:
  • Updated Guatemala Passport parser
  • Fixed issue with Qatar ID card code reading
• Text data parsing and validation:
  • Added content validation for Romanian CNP number (personal number)
  • Added date validation for RGLFieldTypeFt_DateOfBirthOfWife & RGLFieldTypeFt_DateOfBirthOfHusband fields
  • Added separate calculated RGLFieldTypeFt_Category field when processing bank cards number presenting issuer payment system
  • Fixed issues with parsing registration stamp data into specific fields for Russian Federation domestic passports
  • Fixed issue with visual vs MRZ comparison for values that contain ‘
  • Fixed issue with ^ symbol in RGLFieldTypeFt_Surname, RGLFieldTypeFt_Given_Names and RGLFieldTypeFt_Surname_And_Given_Names in lexical analysis results
• Image QA
  • Image quality assessment NNs (focus and glares) were updated for better result quality, smaller size, and improved performance
  • Glare presence over text fields prevents process series finish in OCR enabled scenarios
• Code quality improved with lots of small issues fixed

v5.1

API:

• Added capability of reading the document's RFID chip.

• Added the ability to change the standard images of the following buttons:

  • Torch button
  • Close button
  • Capture button
  • Change frame button
  • Camera switch button

• Added capability of changing camera frame corners radius.

• Added capability of changing the design type of the beginning and end of the camera frame line.

• Added capability of changing the margin between the camera frame and the preview edge.

• Added capability of changing aspect ratio of the camera frame.

• Added capability of changing the layout position of the camera frame.

• Added capability of creating your custom status in the camera window, as well as setting the position for it.

• Added the ability to set the type of barcode parser (barcodeParserType).

• Added capability of accessing the document's RFID chip using CAN.

• Added processing of critical errors that may occur when processing an RFID chip, such as an invalid key (MRZ, CAN), after which the scanning session should be interrupted.

• Added capability of reading the document spread (doublePageSpread).

• Added dark theme support for all UI elements.

• Added capability of deleting a database from a device (db.dat) (removeDatabase).

• Added the ability to cancel database downloads while performing the prepareDatabase and runAutoUpdate functions (cancelDBUpdate).

• Added capability of using external certificates (addPKDCertificates) - they can be added both during initialization and in runtime. Also added the ability to delete certificates from memory (clearPKDCertificates).

• Implemented serialization and deserialization of the DocumentReaderResults object.

• Added capability of processing multiple document images (recognizeImages).

• Added capability of saving the RFID session for debugging (debugSaveRFIDSession).

• Added mrzPosition, barcodePosition properties to RGLDocumentReaderResults.

• Added capability of changing the standard strings localization when integrating the SDK inside the dynamic framework.

• Added barcode format check, the results of which are returned to RGLDocumentReaderAuthenticityResult.

• Added new enums RGLCheckDiagnose, RGLDocFormat, RGLPKDResourceType.

• Added rfidScenario property.

• Added the following Core types: MRZRFID, BarcodeMRZRFID, OCRRFID, FullRFID.

• AutoSettings property has been added to the RGLRFIDScenario settings structure, which allows you to automatically change the scenario settings depending on the type and results obtained during scanning of the last document. Default value is true.

• Added new LCID enum members:

  • RGLLCIDArabicArmenian,
  • RGLLCIDChineseHongKongSAR,
  • RGLLCIDChineseMacaoSAR,
  • RGLLCIDChineseSingapore,
  • RGLLCIDChineseTaiwan,
  • RGLLCIDDivehi,
  • RGLLCIDGujarati,
  • RGLLCIDHindiIndia,
  • RGLLCIDJapanese,
  • RGLLCIDKannada,
  • RGLLCIDKonkani,
  • RGLLCIDKorean,
  • RGLLCIDMarathi,
  • RGLLCIDPunjabi,
  • RGLLCIDSanskrit,
  • RGLLCIDSyriac,
  • RGLLCIDTamil,
  • RGLLCIDTelugu,
  • RGLLCIDThaiThailand,
  • RGLLCIDCtcSimplified,
  • RGLLCIDCtcTraditional.

• Added a new RGLDocReaderFrame enum member RGLDocReaderFrameDocument.

• Added RGLSecurityFeatureType enum members:

  • RGLSecurityFeatureTypeFill,
  • RGLSecurityFeatureTypeFalseLuminescence,
  • RGLSecurityFeatureTypeHoloSimple,
  • RGLSecurityFeatureTypeHoloVerifyStatic,
  • RGLSecurityFeatureTypeHoloVerifyMultiStatic,
  • RGLSecurityFeatureTypeHoloVerifyDinamic,
  • RGLSecurityFeatureTypePatternNotInterrupted,
  • RGLSecurityFeatureTypePatternNotShifted,
  • RGLSecurityFeatureTypePatternSameColors,
  • RGLSecurityFeatureTypePatternIRInvisible,
  • RGLSecurityFeatureTypePhotoSizeCheck,
  • RGLSecurityFeatureTypeBarcode,
  • RGLSecurityFeatureTypePatternDifferentLinesThickness,
  • RGLSecurityFeatureTypePortraitComparisonRFIDvsCamera,
  • RGLSecurityFeatureTypeGhostPhoto,
  • RGLSecurityFeatureTypeClearGhostPhoto,
  • RGLSecurityFeatureTypeInvisibleObject,
  • RGLSecurityFeatureTypeLowContrastObject,
  • RGLSecurityFeatureTypePhotoColor,
  • RGLSecurityFeatureTypePhotoShape,
  • RGLSecurityFeatureTypePhotoCorners

• Added new RGLAuthenticity enum members:

  • RGLAuthenticityIRB900,
  • RGLAuthenticityAxialProtection,
  • RGLAuthenticityUVFibers,
  • RGLAuthenticityIRVisibility,
  • RGLAuthenticityOCRSecurityText,
  • RGLAuthenticityPhotoEmbedType,
  • RGLAuthenticityHolograms,
  • RGLAuthenticityPhotoArea,
  • RGLAuthenticityBarcodeFormatCheck.

• Available scenarios for document processing are presented as constants in the RGLExternalConstants file.

• Updated error statuses associated with the license.

• Fixed issues in the operation of the prepareDatabase and runAutoUpdate functions.

• Fixed logic of isCameraSessionIsPaused.

• Updated RGLPosition properties.

• Fixed generation of final results. Now RGLDocumentReaderTextField contains RGLDocumentReaderValue values from all pages of the read document for all RGLResultType result types.

Core:

• Massive improvements in performance and quality across all modules.
• Document detection and crop
  • Added capability to locate and recognize double page spread of the document in one image. There are passports, that have meaningful data not only on the data page, but also on the second page of the spread. To get the data from both pages in one go we have implemented this “Double page spread” mode. Disabled by default.
  • Added capability of smart detection of the document by its recognition. Document can be in any orientation, flat or with perspective distortion, hold in the hands like a book, etc. This greatly improves success rate on mobile and service use cases. Can be enabled/disabled in process parameters. By default, enabled for processing of static images and disabled for processing series of images from camera on mobile.
  • Optimized ID2 Visa stickers cropping from passport page.
• Document type recognition
  • Improved performance of document type recognition by multiple algorithm optimizations.
  • Improved quality of document type recognition. Now document images with corrupted proportions, not fully visible in image, with high perspective distortion are correctly recognized in most possible cases.
  • Improved recognition of documents with non-standard proportions.
  • Improved algorithm of image resolution determination by using data from templates (laminated documents).
• OCR
  • Added scenario OcrFree for arbitrary text OCR, based on provided parameters. You can define field definition template using mask and recognize any data, not only on documents.
  • Added support for Armenian alphabet (lcid 1067).
  • Added support for Malta language (lcid 1082).
  • Added bank cards recognition in specific scenario.
  • Added recognition of registration stamp (address) in Russian Federation domestic passports.
  • Added recognition of CCC/CTC codes for China / Hong Kong documents.
  • Improved recognition of text with multiple languages in one field.
  • Improved recognition of special symbols, like @, ≤, ≥, *, _, etc.
  • All alphabets recognition is now based on neural networks (including Greek, Georgian, Azeri/Turkish).
  • All NN were re-trained on significantly larger datasets to ensure better recognition accuracy.
  • Improved recognition time.
  • Document templates were revisited for each field to assure correctness and high recognition accuracy based on statistics.
  • Perforated numbers OCR now available on all platforms (Ukraine domestic passport).
  • Optimized serial OCR recognition mode from multiple frames, based on recognition probability and matching results between frames.
  • Internal resource usage optimization that allowed to reduce memory impact and package size.
• Text data parsing and validation
  • Added content validation for Belarus personal number.
  • Added parsing of Russian Federation registration address text into separate fields.
  • Added transliteration into Latin characters of all Cyrillic characters for Russian Federation domestic passports.
  • Added generation of MRZ for Russian Federation domestic passports without MRZ by its data.
  • Added generation of text name of issuing authority by its code for Russian Federation domestic passports.
  • Added date validation for revision `RGLFieldTypeF...

v5.0

API:

• The DocReader class is now a singleton.
• API completely rewritten in Objective-C. From now on SDK is compatible with any Swift version.
• Added a new Core framework type DocType.
• Added a new scenario Capture, which allows obtaining a frame from the camera without image processing.
• Added possibility to set a separate scenario for the capture button (captureButtonScenario).
• Added barcode parsing results (DocumentReaderBarcodeResult).
• Added possibility to set the measurement system in the final results: (processParams.measureSystem).
• Added possibility to get a full original image from which the final document image was obtained. (processParams.returnUncroppedImage = true).
• Added possibility to change the status text of the tooltip (customization.resultStatus).
• Added possibility to change the alpha of the background mask around the frame (customizattion.backgroundMaskAlpha).
• Added new GraphicFieldType enum member
  • gf_Portrait_Of_Child
• Added new FieldType enum members:
  • ft_Date_First_Renewal
  • ft_Date_Second_Renewal
• Added French localization.
• Added new property DocReader.shared.license that contains information about the current license:
  • expiryDate: license expiration date
  • countryFilter: codes of countries whose documents are available for OCR (if the array is empty, it means that  there are no restrictions on countries).
• Updated the logic of the Ocr scenario. Now it always returns a correct image of the document.
• Changed the logic of layout of the pictures for the startup animation (helpAnimationImage), multi-page animation (multipageFrontAnimationImage, multipageBackAnimationImage) and background frame (borderBackgroundImage). Now it is possible to change the contentMode property for all the images listed above.
• Updated the logic of capture button operation. Added timers of button display after the start of scanning (showCaptureButtonDelayFromStart) or after the detection of document boundaries (showCaptureButtonDelayFromDetect). By default, their values are 5 and 10 seconds, respectively.
• Changed the structure of the results. Now most of them contain the property pageIndex, which contains the index of the page from which the result was obtained.
• The documentType property in the final result DocumentReaderResults is now an array that contains information about each page that has been read.
• In the enum GraphicFieldType, the value gf_DocumentFront is replaced by the gf_DocumentImage value. The value gf_DocumentRear has been deleted. Now, to obtain the back side of the document, the pageIndex property of the graphic field (DocumentReaderGraphicField) should be used.
• Corrected the logic of calculating the final field validity status (CheckResult).
• Fixed the logic of the MrzAndLocate scenario. Now it stops working only after detecting the MRZ and detecting the borders of the document containing this MRZ.
• Fixed the logic of the customization properties statusPositionMultiplier and resultStatusPositionMultiplier.

Core:

• Added OCR capability of Chinese Simplified and Traditional. Corresponding document templates updated.
• Greatly improved OCR for next code pages (alphabets) and corresponding document templates updated:
  • Cyrillic (Belarusian, Bulgarian, Kazakh, Russian, Serbian, Ukrainian),
  • Baltic (Estonian, Latvian, Lithuanian),
  • Vietnamese,
  • Western European/Latin (English, French, Spanish, Portuguese, Dutch, Finnish, Icelandic, Italian, Norwegian, Swedish),
  • Georgian,
  • Turkish (Turkish, Azeri, Uzbek),
  • Hebrew.
• Improved OCR of the documents with floating inconsistent personalization.
• Implemented validation check between Issuing authority and document series in RussianFederation passports
• Added new MRZ parsers:
  • Antigua and Barbuda Id Card,
  • Aruba DL,
  • Cuba ID card,
  • Ecuador ID card,
  • Uruguay ID card.
• Added new barcode parsers:
  • Botswana Residence permit,
  • Cuba ID card,
  • Ghana DL,
  • Israel Entry/Exit permit,
  • Jamaica ID card,
  • Nicaragua Passport,
  • Mozambique Visa and Emergency certificate,
  • Togo ID card.
• Improved recognition of non-ICAO format documents and laminated documents. Now we are not limited to standard ID sizes.
• Fixed issue with Aztec codes detection.
• Fixed issue with 9999 year in Date of expiry in Spanish ID cards.
• Fixed issue with documents without expiration term in Bulgaria, Bolivia, Viet Nam.
• Fixed issue with special symbols in text fields when performing partial value comparison to other sources.
• Fixed issue with weight conversion if field contains code instead of actual weight value.
• Fixed issue with country code incorrect validation in specific cases.
• Fixed different minor issues with specific documents MRZ reading and correction.
• 550 new documents added.
• 244 countries and territories / 7572 documents included.

v4.2

• Added possibility to edit the horizontal position of statusLabel and resultStatusLabel in CameraViewController using the corresponding properties in Customization.
• DocReaderFrame enum updated. Now it contains the following members:
  - scenarioDefault
  - max
  - none
• Added the skipFocusingFrames property to Functionality. It is used to skip processing frames while the device camera is focusing.
• Added the disableFocusingCheck property to Functionality. It is used to disable checking whether a document is in focus before its processing starts.
• Enhanced the performance of CameraViewController through frame buffering. Now the frames are continuously transferred from the camera for further processing.
• Added German localization.
• Added a button switching between cameras during document processing. Added the showCameraSwitchBtn property to Functionality.
• Fixed errors in the CameraViewController customization.
• Great improvements of OCR for Latin, Cyrillic, Hebrew, Vietnamese and Balkan alphabets, both speed and accuracy.
• Added new MRZ parsers:
  - Mozambique ID card,
  - Estonia Residence permit.
• Added new barcode parsers:
  - Haiti ID card,
  - Canada ID card.
• Added new GraphicFieldType enum member gf_Stamp.
• Added new FieldType members:
  - ft_Mother_Surname,
  - ft_Mother_GivenName,
  - ft_Father_Surname,
  - ft_Father_GivenName,
  - ft_Mother_DateOfBirth,
  - ft_Father_DateOfBirth,
  - ft_Mother_PersonalNumber,
  - ft_Father_PersonalNumber,
  - ft_Mother_PlaceOfBirth,
  - ft_Father_PlaceOfBirth,
  - ft_Mother_CountryOfBirth,
  - ft_Father_CountryOfBirth.
• 243 countries and territories / 7037 documents included.
• 268 new documents added.