Standard Camera Gesture Recognition via HSV Skin Tone Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current hand gesture interfaces in human-machine interaction are limited by the need for specialized equipment and lack robustness in interpreting multifaceted, intuitive commands, restricting seamless user immersion in machine environments.

Innovation Solution

A system that utilizes existing camera setups to identify, track, and analyze bare hands and their poses without specialized cameras, enabling rich, multi-hand gesture interfaces with ambient light, and provides a library of electronic commands for controlling computer functionalities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If specialized cameras and equipment are used for gesture recognition, then measurement precision and reliability are improved, but device complexity and cost increase

Engineering Contradiction:
Improvegesture recognition precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies universality by enabling standard cameras to perform multiple functions - both capturing video content and recognizing hand gestures simultaneously. The gesture recognition system processes standard video feeds without requiring specialized imaging equipment, allowing a single camera to serve dual purposes and eliminating the need for separate specialized gesture-capturing devices.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent uses copying by creating a processed representation of the video feed that highlights hand regions. Instead of requiring specialized sensors, the system generates a copied or processed version of the standard video image that emphasizes skin-tone regions and hand contours, enabling gesture recognition through software-based image transformation rather than hardware specialization.

Inventive Principle:
Principle #26Copying

2Reliability

If specialized equipment is required for hand gesture interfaces, then reliability is improved, but ease of operation and accessibility deteriorate

Engineering Contradiction:
Improvegesture interface reliabilityVSAvoidinterface accessibility
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system applies self-service by using the user's existing environment (standard cameras already present in videoconferencing setups) to provide gesture recognition functionality. The user doesn't need to acquire or set up specialized equipment - the system leverages what is already available, making the technology accessible without requiring users to obtain additional proprietary devices.

Inventive Principle:
Principle #25Self-service

3Device complexity

If existing camera setups are used without specialized equipment, then device complexity is reduced, but measurement precision and gesture recognition accuracy worsen

Engineering Contradiction:
Improvesystem simplicityVSAvoidhand pose recognition accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies parameter changes by transforming the video image parameters - specifically converting to HSV color space and adjusting saturation thresholds to isolate skin tones. The system modifies image processing parameters dynamically, using saturation-based filtering and histogram analysis to enhance hand region detection accuracy without changing the physical camera hardware, thereby maintaining simplicity while improving precision through software parameter optimization.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS9111138B2System and method for gesture interface control
Publication Date: 2015.08.18 CISCO TECHNOLOGY INC
  • US9111138B2 patent drawing
  • US9111138B2 patent drawing
  • US9111138B2 patent drawing

AI summary

A method is provided in one example and includes generating a histogram associated with at least one object; receiving image data; comparing the image data to the histogram in order to determine if at least a portion of the image data corresponds to the histogram; identifying a pose associated with the object; and triggering an electronic command associated with the pose. In more particular embodiments, the image data is evaluated in order to analyze sequences of poses associated with a gesture that signals the electronic command to be performed.