Skin Color Based Gesture Recognition Without Additional Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture recognition technologies face challenges with sensor-based methods requiring additional sensors and high computation for hand detection, leading to difficulties in integration and high error rates, while artificial vision-based methods struggle with accurate skin color identification.
Innovation Solution
A user interface apparatus and method utilizing artificial vision technology that detects hand movements by learning skin color from a reference face area, accumulating movement information from image frames, and filtering unintended movements to create a user interface screen without additional sensors and with low error detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor-based methods are used for gesture recognition, then measurement precision is improved, but device complexity increases due to requiring additional sensors
Solution Approach 1:
The patent replaces sensor-based mechanical detection systems with an artificial vision-based optical system. Instead of using accelerometers, gyroscopes, or haptic sensors attached to the user, the system uses a camera to capture images and detect hand gestures through skin color analysis and movement tracking, thereby eliminating the need for additional sensors while maintaining gesture recognition capability
Solution Approach 2:
The patent creates a visual copy of the hand gesture through image capture and processing. By capturing images of the user's hand and analyzing skin color regions in these visual copies, the system can detect gestures without physical sensors, substituting optical information for mechanical sensing
2Device complexity
If artificial vision-based methods are used for gesture recognition, then device complexity is reduced, but measurement precision deteriorates due to high error rates in skin color detection
Solution Approach 1:
The patent segments the image processing into distinct stages: skin color detection to identify potential hand regions, movement detection to track changes between frames, and gesture recognition to interpret the movement patterns. This segmentation allows each stage to be optimized independently, improving overall accuracy while maintaining system simplicity
Solution Approach 2:
The patent performs preliminary skin color learning by capturing images of the user's face or hand to establish a reference skin color profile before actual gesture detection begins. This preliminary action creates a customized color threshold that adapts to the specific user's skin tone, significantly improving detection accuracy for subsequent gesture recognition
3Measurement precision
If sensor-based methods are used for gesture recognition, then measurement precision is improved, but use of energy increases due to high computation requirements
Solution Approach 1:
The patent applies partial action by focusing computational resources only on regions of the image that contain skin-colored pixels or show movement. Instead of processing entire frames at high computational cost, the system identifies and processes only the relevant hand regions, reducing energy consumption while maintaining detection accuracy
Data Source
AI summary
A movement recognition method and a user interface are provided. A skin color is detected from a reference face area of an image. A movement-accumulated area, in which movements are accumulated, is detected from sequentially accumulated image frames. Movement information corresponding to the skin color is detected from the detected movement-accumulated area. A user interface screen is created and displayed using the detected movement information.