Sight-line interaction method suitable for touch controlling

Abstract

The invention discloses a sight-line interaction method suitable for touch controlling, and belongs to the technical field of video and multimedia signal processing. According to the sight-line interaction method, human-eye area images are input to a CNN, the images are subjected to characteristic extracting and dimension reduction through convolution and down-sampling operation, and the limitation of a traditional sight-line estimation method in which an eyeball model is established through a high-definition camera and an additive infrared device is improved. In an image collecting stage, a human-eye database has the diversity of illumination, skin colors and forms through image collection at different positions of different individuals in different time periods, and a system meets the requirements of different individuals under multiple conditions; the classification accuracy is greatly increased.

Description

technical field [0001] The invention relates to a line-of-sight interaction method suitable for touch control, and belongs to the technical field of video and multimedia signal processing. [0002] technical background [0003] Human-computer interaction technology is one of the fastest-growing fields in user interface research. At present, the more common human-computer interaction methods include traditional interaction methods such as keyboards, mice, and cameras. However, with the continuous development of artificial intelligence technology, many non-contact interaction methods have emerged, such as gesture recognition. Compared with the traditional contact interaction method, the non-contact interaction method has the advantages of safety and sanitation, and is more and more used in all aspects of life. [0004] The line-of-sight interaction method involved in the present invention is a kind of non-contact human-computer interaction. The so-called line-of-sight intera...

AI Technical Summary

Problems solved by technology

However, such methods aim to obtain accurate gaze direction, and in the training process of machine learning, regression methods are often used; this makes the training process of this type of method complex, the adjustment of network parameters is difficult, and the accuracy of gaze direction obtained Relatively poor

At the same time, most of the human eye image databases used in these methods are not collected under the scene of gazing at the screen, so it is not ideal for screen-based touch applications.

Images