FIELD: physics.
SUBSTANCE: invention relates to the computer equipment. Such a result is achieved by the fact that the method for classifying touching includes obtaining frame data representing a plurality of frames captured by a touch sensitive device, analyzing frame data for determining a corresponding blob in each frame from a plurality of frames, wherein blobs indicate a touch event, calculating a plurality of feature sets for a touch event, wherein each feature set specifies characteristics of the corresponding blob in each frame from a plurality of frames, and determining a type of touch event by classifying machine self-learning, configured to provide multiple non-prediction classification based on plurality of feature sets for a plurality of frames, wherein each non-prediction classification estimate indicates a level of uncertainty in the machine self-study classification.
EFFECT: technical result consists in improvement of accuracy of data input.
15 cl, 5 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD OF DETECTING HUMAN OBJECTS IN VIDEO (VERSIONS) | 2013 |
|
RU2635066C2 |
SYSTEM FOR RECOGNITION AND TRACKING OF FINGERS | 2012 |
|
RU2605370C2 |
BEHAVIOUR RECOGNITION SYSTEM | 2008 |
|
RU2475853C2 |
CLASSIFICATION OF TOUCH INPUT AS UNINTENTIONAL OR INTENTIONAL | 2015 |
|
RU2704871C2 |
INACTIVE AREA FOR TOUCH SURFACE BASED ON CONTEXTUAL INFORMATION | 2015 |
|
RU2705431C2 |
METHOD AND DEVICE FOR FAST ACCESS TO DEVICE FUNCTIONS | 2012 |
|
RU2582854C2 |
DETECTING OBJECTS FROM VISUAL SEARCH REQUESTS | 2017 |
|
RU2729956C2 |
APPARATUS AND METHOD OF CLASSIFYING MOVEMENT OF OBJECTS IN MONITORING ZONE | 2009 |
|
RU2509355C2 |
METHOD AND SYSTEM FOR RECOGNITION OF THE EMOTIONAL STATE OF EMPLOYEES | 2021 |
|
RU2768545C1 |
MULTI-CHANNEL AUDIO SIGNAL CLASSIFIER | 2014 |
|
RU2648632C2 |
Authors
Dates
2020-01-14—Published
2015-07-07—Filed