SentiSight Embedded is designed for
developers who want to use computer vision-based object recognition in their
applications for smartphones, tablets and other mobile devices. Through manual or fully automatic object learning it enables searching for
learned objects in images or videos from built-in cameras with PC-like accuracy.
SentiSight Embedded is available as a
software development kit that provides for the development of object recognition
applications for the devices that are running Android OS.
Advantages of SentiSight Embedded
• Innovative algorithm, that is tolerant to
appearance, object scale, rotation and pose.
• PC-level accuracy of object detection and
processing with mobile devices.
• Smatphone built-in cameras are suitable for
obtaining object images.
• Compatability and interoperability with
PC-side SentiSight-based products.
• Reasonable prices, flexible licensing and
free customer support.
• Object learning and recognition processes.
In the learning phase, SentiSight algorithms extract specific object features
from a video stream or single image and save them to an object model. Object recognition requires no user interaction apart from providing providing a
video file with the object or pointing a camera to a scene where the object is presented or will appear. Read more
• SentiSight Embedded algorithm and
technology capabilities. SentiSight implements advanced visual-based object
learning and recognition technology. It can be used for a wide range of tasks
and includes two different algorithms for object recognition. Both algorithms
perform simultaneous multiple object recognition. Read more
• SentiSight Embedded 1.2 SDK contents. The SDK
provides for the development of object recognition systems for devices that are
running Android OS. SentiSight Embedded is able to capture images and video
streams from cameras that are built-in in Android devices. Java programming
samples and tutorials are included. Read more
• System requirements. A smartphone or tablet
or other device that is running Android 2.3 (API 9) OS or newer is required. 1 GHz processor
recommended for object processing in less than 1 second. Hardware
floating-point support is required. Read more
• Technical specifications and reliability
tests. A SentiSight Embedded-based Java application processes an image with an
object in less than 1 second. The tests with ALOI database showed that the the
recognition rate is 98% - 99% at 0.1% FAR for objects with well defined intenal
structure. Read more
• Download. SentiSight Embedded 30-day SDK Trial and
technology presentation video are available for downloading.
• Licensing options. To develop a SentiSight
Embedded-based product, an integrator should obtain SentiSight Embedded 1.2 SDK. A
license for a SentiSight Embedded component installation is required for each
device or computer that runs a SentiSight-based application. Single computer
licenses and enterprise licenses are available. Read more
• Prices. SentiSight Embedded SDK costs ¢æ 339.
Prices for additional installation licenses depend on quantity. Read more
SentiSight Embedded related products
• SentiSight SDK –
for development of PC-based object recognition systems. SentiSight SDK
based software produces the same object models as the SentiSight Embedded SDK,
thus both SDKs can be used for developing object recognition systems with
client-side software running on smartphones and connecting to the remote
• SentiSculpt SDK - for development of PC-based systems which perform 3D object models creation from regular images.