Object recognition for robotics and computer vision
SentiSight is intended for developers who want to use computer vision-based object recognition in their applications.
Through manual or fully automatic object learning it enables searching for learned objects in images from almost any camera, webcam, still picture or live video in an easy, yet versatile, way.
SentiSight is available as a software development kit that provides for the development of object recognition systems for Microsoft Windows or Linux platforms.
Download SentiSight SDK brochure (PDF)
Complete information, including technical specifications, licensing and prices.
The 15-page brochure can be printed on both Letter and A4 paper.
File size: 1.7 Megabytes. Updated on: August 27, 2013.
Advantages of SentiSight
- Reliable, innovative algorithm that is tolerant of variation in appearance, object scale, rotation and pose.
- Accurate detection, processing and tracking of objects in real-time.
- Webcams or other low cost cameras are suitable for obtaining object images.
- Available as multiplatform SDK that supports multiple programming languages.
- Reasonable prices, flexible licensing and free customer support.
Technology and SDK
SentiSight's object learning and recognition process.
In the learning phase, SentiSight algorithms extract specific object features from a video stream or single image and save them to an object model.
Both manual and automatic object learning are available.
Object recognition requires no user interaction apart from providing a video file where the object is present or pointing a camera to a scene where the object is presented or will appear.
SentiSight's 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, are able to utilize multi-core CPUs and are capable of real-time operation.
SentiSight 3.2 SDK.
The SDK provides for the development of object recognition systems for Microsoft Windows or Linux platforms, and includes programming tutorials in several programming languages.
A Device Manager library is included for simultaneous capture from multiple cameras.
SentiSight requires a computer with x86 (32-bit) or x86-64 (64-bit) processor that supports SSE2.
Best performance is achieved on systems with 64-bit processors that support the SSSE3 instruction set.
Microsoft Windows and Linux are supported.
A webcam or IP camera may be used for object image capture.
SentiSight is able process a single frame in 0.014 seconds during object learning, and perform recognition at speeds of 160,000 - 290,000 object models per second when using the blob recognition algorithm without color usage mode on 320 x 240 pixel images.
Reliability and performance tests.
The SentiSight algorithm was tested with images from the ALOI database.
SentiSight's recognition rate is 98 % - 99 % for objects with well-defined internal structure, and 70 % - 99 % for other objects; image processing speed is dependent on image size, the algorithm used and number of threads available for matching.
The SentiSight algorithm demo application, 30-day SDK Trial and technology presentation video are available for downloading.
Licensing, prices and ordering
To develop a SentiSight-based product, an integrator should obtain the SentiSight 3.2 SDK.
A license for a SentiSight installation is required for each PC or each server CPU that runs a SentiSight-based application.
Single computer licenses and enterprise licenses are available.
The SentiSight SDK costs € 339.
Prices for additional installation licenses depend on quantity.
To determine the cost of ordered products and their shipping charges, use the
Credit cards, PayPal and bank transfers are acceptable.
Order SentiSight SDK online.
SentiSight related products
SentiSight Embedded SDK – a product for object recognition on Android smartphones, tablets and other mobile devices.
Produces object models that are the same as those in the SentiSight SDK, thus can be also used for developing client-side mobile applications for systems with a server-side based on the SentiSight SDK.
- NVeiler Video Filter – a plug-in for the VirtualDub video processing application that is able to detect and hide faces in videos; the SentiSight algorithm is used for the face and object-tracking feature of the plug-in.
- NPointer – a freeware application for gesture-based computer control that captures hand movements with a webcam. Can also accept voice commands.
AFIS or multi-biometric fingerprint, iris, face and voice identification for large-scale systems.
Face identification for PC, mobile and Web solutions.
Fingerprint identification for PC, mobile and Web solutions.
Iris identification for PC, mobile and Web solutions.
Speaker recognition for PC, mobile and Web applications.
Ready-to-use robotics development kit.
More products for developers:
- NCheck Bio Attendance – an attendance control application that uses fingerprint or face biometrics to perform persons identification.
- NVeiler Video Filter – a plug-in for VirtualDub that automatically detects faces in a frame, tracks the faces (or other objects) in subsequent frames and hides them.
- NPointer – a freeware application for gesture- and voice-based computer control that captures hand movements with a webcam and accepts voice commands.