These release notes are relevant for the following products:
• MegaMatcher 9.0 Standard / Extended SDK
• VeriFinger 9.0 Standard / Extended SDK
• VeriLook 9.0 Standard / Extended SDK
• VeriEye 9.0 Standard / Extended SDK
• VeriSpeak 9.0 Standard / Extended SDK
List of releases:
- March 23, 2017 (Revision 162703)
- February 20, 2017 (Revision 161389)
- December 6, 2016 (Revision 158289)
- October 18, 2016 (Revision 156043)
- August 26, 2016 (Revision 153687)
- July 8, 2016 (Revision 151305)
- June 2, 2016 (Revision 149646)
- June 1, 2016 (Revision 149575)
See also the list of release notes for previous versions.
March 23, 2017
Product revision: 162703
- Fixed issues when using Android on devices with dual SIM cards.
- Fixed many small bugs and issues.
- Updated device initialization to optimize it so that devices which are not plugged are not loaded. This should reduce memory usage and reduce number of possible conflicts between different device libraries.
February 20, 2017
Product revision: 161389
- Fixed wrapper (Java and C#) related to FMCRecord and FMRecord.
- Fixed encoding issue in client-server communication.
- Fixed a number of issues in tutorials.
- Added tutorials for CreateMinexCompliantTemplate and NTemplateToFMRecord.
- Added missing gradle scripts for neurotec-biometrics-gui-android component usage in samples.
- Updated Java sample and tutorial pom scripts to clean native libraries before copying new ones.
- Updated device manufacturers' SDKs on Android for Credence ID, Green Bit and SecuGen.
December 6, 2016
Product revision: 158289
- Fixed an issue with rare crash on Android when listing Subjects.
- Fixed a number of minor bugs and issues.
- Added ICAO face capture support on Android.
- Added VLC library support as an option to read RTSP and file video streams.
- Addded NeuBio MARS02 fingerprint reader support.
- Updated Canon EOS module to support more newer devices.
- Improved NBiometricClient remote communication performance.
October 18, 2016
Product revision: 156043
- Fixed an issue with faces generalization.
- Fixed an issue with face extraction from stream and template creation when stream frame count is less than Faces.MaximalDurationInFrames value.
- Multiple fixes in token face image creation.
- Fixed an issue with Face Verification component showing dark image on some Samsung devices.
- Fixed rare Face Verification component crash on iOS.
- Fixed long delay in some scenarios when capturing from RTSP cameras.
- Fixed ISO template extraction using standard license to work also with NServer.
- Fixed ANTemplate to make ANT_USE_TWO_DIGIT_IDC flag work.
- Fixed licensing crash on Windows XP.
- Fixed rare crash on Android, usually when exiting application.
- Fixed Futronic support on ARM-V8 (64-bit) platform.
- Fixed a number of minor bugs and issues.
- Facial feature points detection now uses a new, smaller data file for the algorithm, which is now more accurate; the new data file should be used now for all face extraction operations.
- Added support for Gradle 3.0 on Android.
Added support for new fingerprint readers:
- SecuGen Hamster Pro
- SecuGen Hamster Pro Duo CL
- SecuGen Hamster Pro Duo SC PIV
- Suprema BioMini Plus2
- Improved segmentation of irises in images with rotated eyes.
- Improved performance of voice template matching.
- Improved performance when working with SQLite database.
- Updated iOS samples to support Xcode 8.
- Updated fingerprint scanner integrations updated for Dermalog, Nitgen, Suprema RealScan and SecuGen devices.
- Improved capturing from camera on Android.
- Updated ANTemplate to have non-strict read on by default in samples.
August 26, 2016
Product revision: 153687
- Fixed video capturing from camera which could cause crash on Windows 10.
- Fixed multiple issues in JavaAbisSample.
- Added Gradle support for all Java and Android projects (including Android Studio).
- Added reduced size NDF files for medium and large face template generation (recommended for using in mobile devices or applications where file size is crucial). The NDF files with reduced size have a "Lite" suffix in the filenames.
- Added C++ tutorials.
- Added Integrated Biometrics Kojak device support.
- Improved ICAO-compliant face capturing (see Faces or Abis samples).
- Updated JPEG file reading to allow processing more broken files.
July 8, 2016
Product revision: 151305
- Fixed crash on FaceVerification API occurring when capturing was cancelled.
- Added returning face quality during capturing on FaceVerification API.
- Added additional search paths for data files on MacOSX.
- Improved iOS FaceVerification sample.
- Improved diagnostic messaging on Android.
- Reduced needed data file size in some scenarios.
June 2, 2016
Product revision: 149646
- Fixed several minor bugs and issues.
June 1, 2016
Product revision: 149575
The first release of MegaMatcher 9.0 SDK line.
The version numbers were raised to 9.0 to be unified for all products.
- New face recognition algorithm. The new VeriLook face recognition algorithm provides five times higher accuracy in identifying full frontal faces and 10 to 15 times higher accuracy for unconstrained facial recognition (captured in lower resolution, with complex illumination, expressions and head rotations). This not only improves the user experience by resulting in fewer errors, it makes the product significantly easier to use and apply to a much broader range of face recognition applications, such as conducting automated facial image searches in large databases without the need for manual review. In order to use new high-quality algorithm, face templates have to be extracted using large (recommended for PC) or medium (recommended for mobile devices) template size. Face templates extracted using previous version extractor are still recognized, but to take advantage of the new algorithm, it is recommended to reenroll them.
- New and improved facial features. New facial attributes are supported: beard and mustache. More accurate estimation of facial attributes, including gender, smile, closed eyes, open mouth, glasses and dark glasses are also included.
- Improved iris extraction algorithm. The improved iris algorithm provides better extraction speed and iris segmentation quality. It can accurately detect eyelids and can be used to locate irises in images that are captured in both the NIR range and in visible light. The iris image quality estimation is adapted to ISO/IEC 29794-6:2015 standard.
- New Face Verification component. The new Face Verification component greatly simplifies both the technical and commercial use of facial recognition technology for user authentication purposes. The easy-to-use, intuitive interface makes it highly suitable for use in mobile banking transactions and other applications which require both high security and simplicity. The component is optimized to make it easier to enroll and verify faces captured from cameras. Optional liveness detection determines if the system is viewing a live person vs. a photograph. A specialized API simplifies integration into variety of solutions, and component pricing makes the face verification component economical for large-scale deployments on millions of devices.
- Unified product versions. From Neurotechnology Biometric product line 9.0, all biometric products – MegaMatcher SDK, VeriFinger SDK, VeriLook SDK, VeriEye SDK, VeriSpeak SDK and MegaMatcher Accelerator – will have the same version number. It should make simpler to understand and use together different products.
- New NImageRecoverer tool can be used to retrieve all supported images (including WSQ, JPEG 2000, etc.) from any file. It is useful to recover images in case some standard record is partially corrupt. It can be also used in simple scenarios where only images are needed to be read.
- NTemplateMerge function is provided to merge any templates into a single one.
- pgd licensing service is no longer required for Linux. As in all other platforms, full licensing functionality is embedded inside libraries for easier deployment. It can, however, still be used in special scenarios such as gateway mode.