Gesture Recognition Using Edge Angle Statistics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional unarmed gesture recognition systems face challenges in accuracy when dealing with images that include both foreground and background, requiring significant system resources and being sensitive to background changes, and are dependent on hand movement for detection.
Innovation Solution
A gesture recognition method and system that generates a multi-background model to dynamically filter out the background from images, obtaining object images with edges, and compares the included angles' statistics to match gesture characteristics with predefined templates for accurate recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If unarmed gesture recognition is performed directly on images with foreground and background, then user convenience is improved, but system resources are excessively consumed and recognition accuracy deteriorates
Solution Approach 1:
The patent segments the image processing task by separating foreground object detection from background. It uses edge detection to identify object contours and extracts the foreground region of interest, thereby reducing the processing area and improving recognition accuracy while maintaining ease of operation.
Solution Approach 2:
The patent extracts the foreground object from the complete image by detecting edges and identifying the region containing the gesture. This extraction process removes unnecessary background information, reducing system resource consumption and improving recognition precision.
2Measurement precision
If preset background model or moved target detection is used to improve gesture recognition performance, then recognition accuracy is improved, but the system becomes sensitive to background changes and requires hand movement
Solution Approach 1:
The patent employs dynamic threshold adjustment based on local image characteristics rather than fixed background models. The edge detection and region extraction adapt to different lighting and background conditions, making the system more versatile and less sensitive to background changes while maintaining high recognition accuracy.
Data Source
AI summary
Gesture recognition methods and systems are provided. First, a plurality of gesture templates are provided, wherein each gesture template defines a first gesture characteristic and a corresponding specific gesture. Then, a plurality of images is obtained, and a multi-background model is generated accordingly. At least one object image is obtained according to the multi-background model, wherein the object image includes at least an object having a plurality of edges. The included angles of any two adjacent edges of the object image are gathered as statistics to obtain a second gesture characteristic corresponding to the object image. The second gesture characteristic of the object image is compared with the first gesture characteristic of each gesture template. The specific gesture corresponding to the first gesture characteristic is obtained, when the second gesture characteristic is similar to the first gesture characteristic.