Method and device for grouping flow chart strokes based on eye movement data

Abstract

The invention discloses a method and a device for grouping flow chart strokes based on eye movement data. In this method, when the user draws a process sketch, the eye movement data is obtained from the eye tracker; then the fixation point set is obtained according to the analysis of the eye movement data; then the calorific value of each point on the screen is calculated according to the fixation point set; The calorific value of each point above is filtered with a threshold to obtain a hotspot set; after that, a cluster analysis is performed on the hotspot set to obtain a hotspot set; finally, the hotspot center is used as the center point to gradually expand outward to query the closed area in the expanded area of ​​the center point. Strokes, set the strokes forming the enclosed area as the stroke group corresponding to the hot zone. The invention can be carried out synchronously with the drawing of the flow chart, has fast stroke grouping speed and high accuracy, and lays a solid foundation for subsequent recognition. During the drawing process, there are no requirements for factors such as stroke order and drawing time, or additional constraints such as pauses between symbols, which greatly improves the user experience.

Description

technical field [0001] The invention relates to stroke recognition, in particular to the application of eye movement data analysis in stroke recognition. Background technique [0002] Sketch recognition is the recognition of hand-drawn graphics, using computers to recognize hand-drawn diagrams, such as flowcharts, UML diagrams, circuit diagrams, etc. Human-computer interaction based on sketch recognition allows users to express and transmit information in a visual form, which is natural and intuitive, easy to understand and easy to operate. In sketch recognition, stroke grouping is an important content. The so-called grouping of strokes refers to how to divide the strokes into several stroke groups that can form entity units in the sketch of multiple entities. After the strokes are grouped, the strokes in the stroke group can be further identified. For example, in a hand-drawn circuit diagram, by grouping strokes, the strokes of the hand-drawn sketch are divided into sepa...

AI Technical Summary

Problems solved by technology

The information form used by this method is relatively single, so it is difficult to break through the performance bottleneck of the stroke grouping method

Images