Touch point classification method and device based on equipment screen

Abstract

The invention relates to a touch point classification method and device based on an equipment screen; the method comprises the following steps: calibrating equipment; collecting data in a preset period according to calibration, and calibrating the screen position in an image according to the collected data; determining the collected data to cover the equipment screen in a preset threshold, stopping data acquisition, and defining the collected data as training data; carrying out protocol and cleaning operations for the training data, thus forming a training sample; selecting a single class classifier, defining input, output and kernel functions, assigning and training kernel function parameters, and forming a classifier; using the formed classifier to classify touch points obtained by the equipment through the screen, thus obtaining a classification result; using the classification result to determine the touch points. A conventional method cannot accurately determine the touch points; the touch point classification method can solve said problems, can effectively identify noisy points or effective touch points in the touch points, thus providing high accuracy, flexibility and usability.

Description

technical field [0001] The present invention relates to the technical field of touch device detection, in particular to a method and device for classifying touch points based on device screens. Background technique [0002] As we all know, in touchable interactive large-screen systems, the recognition of touch points is the core issue. The most commonly used method is to set a fixed area and perimeter threshold. The light spots in all positions in the photos taken by the camera are judged by this threshold. Those within the range are valid touch points, otherwise they are invalid. [0003] But in actual use, this method will include a lot of noise, such as strip noise and so on. What's more serious is the problem of near-large and far-small problems caused by the camera. The light spots closer to the camera appear larger in the photos; the laser surface shot by the laser has the problem that the light spots closer to the laser appear larger. Under the influence of these tw...

AI Technical Summary

Problems solved by technology

What's more serious is that the near-large and far-small problems caused by the camera are larger in the photo if the light spot is closer to the camera; the laser surface shot by the laser has the problem that the light spot closer to the laser appears larger

Under the influence of these two factors, the following situation becomes urgent to be solved: it is difficult to determine a set of fixed thresholds applicable to all situations; After the light spot includes a sufficiently tight threshold, some noises that are far away from the camera and have a weak light-gathering surface but a large area will become difficult to distinguish

Images