Hand Gesture Recognition Using Adaptive Edge Detection and Binarization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile terminals face challenges in timely processing of gesture recognition data due to complex imaging conditions and limited hardware capabilities, such as low image contrast and excessive noise, which hinder accurate finger segmentation and tracking.
Innovation Solution
A method that involves receiving a video stream, determining the background, performing image differencing, binarizing the foreground using learned sigmoid functions for threshold determination based on contrast and brightness, and refining the binarization process to estimate hand region and fingertip location using shape moments and image skeletonization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional image processing methods are used for gesture recognition on mobile terminals, then the system structure remains simple, but the processing speed is too slow and accuracy is insufficient due to low image contrast and excessive noise
Solution Approach 1:
The patent segments the gesture recognition process into multiple specialized modules: background subtraction module, edge detection module, contour extraction module, and gesture classification module. This segmentation allows each module to be optimized independently for speed and accuracy, resolving the contradiction between processing speed and system complexity by distributing computational tasks across modular components.
Solution Approach 2:
The patent performs preliminary actions by pre-processing images with edge detection and background subtraction before main gesture recognition. The system also pre-loads gesture templates and pre-computes lookup tables for common gestures. These preliminary actions reduce the computational burden during real-time processing, improving processing speed without proportionally increasing system complexity.
2Measurement precision
If high powered infrared light emitting diode and high powered camera are used, then image quality and contrast improve, but the device size and power consumption increase
Solution Approach 1:
The patent changes the parameter of light wavelength by using infrared illumination instead of visible light. This allows the system to achieve better contrast for hand gestures (which reflect infrared differently than skin tones) while using lower powered LEDs and cameras optimized for infrared detection, thus improving image quality without increasing device size.
Solution Approach 2:
The patent replaces the need for high-powered optical hardware with sophisticated image processing algorithms. By using computational methods for enhancing image contrast, reducing noise, and extracting gesture features, the system achieves high measurement precision without relying on high-powered infrared LEDs and cameras, thereby avoiding increased device size and power consumption.
3Measurement precision
If complex image processing algorithms are applied to improve hand region detection accuracy, then detection precision improves, but processing time increases
Solution Approach 1:
The patent implements dynamic processing where the complexity of algorithms is adjusted based on real-time conditions. For example, if the background is stable and lighting conditions are good, simpler algorithms are used. When conditions deteriorate, more complex algorithms are activated. This dynamic adaptation maintains high detection accuracy while minimizing processing time by avoiding unnecessary computational complexity in favorable conditions.
Solution Approach 2:
The patent applies partial processing by focusing computational resources only on regions of interest. After initial background subtraction, the system identifies potential hand regions and applies complex edge detection and contour analysis only to those specific areas rather than the entire image. This partial action maintains high detection accuracy for hand regions while significantly reducing overall processing time.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods, apparatuses, and computer program products are herein provided for enabling hand gesture recognition using an example infrared (IR) enabled mobile terminal. One example method may include determining a hand region in at least one captured frame using an adaptive omnidirectional edge operator (AOEO). The method may further include determining a threshold for hand region extraction using a recursive binarization scheme. The method may also include determining a hand location using the determined threshold for the extracted hand region in the at least one captured frame. The method may also include determining a fingertip location based on the determined hand location. Similar and related example apparatuses and example computer program products are also provided.