Face Region Based Action Detection for Reduced Processing Load

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing user interfaces, such as those employing GUI, can be cumbersome for users not accustomed to using pointing devices, leading to reduced operability and potential resource bottlenecks in processing capabilities, causing delays or failure in executing other device functions.

Innovation Solution

An information processing device that detects a face region in an image and sets action regions nearby, allowing for the detection of predetermined user actions by comparing image data to detection information, thereby reducing the processing load and improving user interface efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If image processing is performed on the entire imaged image to detect gesture actions, then gesture detection capability is improved, but processing capability requirements increase and resource bottlenecks occur

Engineering Contradiction:
Improvegesture detection capabilityVSAvoidprocessing capability requirements
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent divides the imaged image into multiple regions of interest (ROIs) based on detected face positions and action areas. Instead of processing the entire image, the system selectively processes only these identified regions, thereby reducing computational load while maintaining gesture detection accuracy for relevant actions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different processing strategies to different regions of the image. By identifying face regions and associated action areas, the system concentrates processing resources on these local regions where gestures are most likely to occur, rather than uniformly processing the entire image.

Inventive Principle:
Principle #3Local quality

2Ease of operation

If calculating resources are diverted to user interface processing, then user operability is improved, but other device functions experience insufficient resources and processing delays

Engineering Contradiction:
Improveuser operabilityVSAvoidother device function execution
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The patent applies partial action by processing only the necessary portions of the image (face regions and action areas) rather than the entire image. This selective processing reduces the computational resources consumed by the user interface, leaving adequate resources for other device functions while still providing intuitive gesture-based control.

Inventive Principle:
Principle #16Partial or excessive action

3Measurement precision

If the entire imaged image is processed to detect user actions, then action detection accuracy is improved, but processing time increases causing unreasonable waiting periods

Engineering Contradiction:
Improveaction detection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary detection of face regions and action areas before performing the main gesture detection processing. This preliminary action identifies the relevant regions in advance, allowing the subsequent processing to focus only on these pre-identified areas, thereby reducing overall processing time while maintaining detection accuracy.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9513712B2Information processing device and information processing method
Publication Date: 2016.12.06 SATURN LICENSING LLC
  • US9513712B2 patent drawing
  • US9513712B2 patent drawing
  • US9513712B2 patent drawing

AI summary

A processing device and method is provided. According to an illustrative embodiment, the device and method is implemented by detecting a face region of an image, setting at least one action region according to the position of the face region, comparing image data corresponding to the at least one action region to the detection information for purposes of determining whether or not a predetermined action has been performed, and generating a notification when it is determined that the predetermined action has been performed.