Display Panel Block Analysis for Face Image Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing display apparatus face recognition techniques using AI algorithms are prone to biased results due to training subject or trainer intentions, and lack internal algorithms or structures for effective face recognition.

Innovation Solution

A display apparatus with integrated components for face recognition, including a driving controller that divides the display panel into blocks, calculates skin color inclusion ratios, determines face regions, and performs image quality processing using equations and face matching data to enhance recognition accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If face recognition is performed using external AI algorithms, then face recognition capability is provided, but recognition accuracy is reduced due to bias from training subject or trainer intentions

Engineering Contradiction:

Improveface recognition accuracyVSAvoidindependence of recognition system

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The display apparatus performs face recognition independently using its own driving controller without relying on external AI algorithms. The controller calculates skin color inclusion ratios and determines face regions autonomously, eliminating bias from external training data while maintaining recognition capability

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent changes the approach from using pre-trained AI models to calculating skin color inclusion ratios using specific equations (i_cr1, i_cr2, i_cr3, i_cr4) with adjustable parameters (p_aa1-p_aa4, p_bb1-p_bb4, k). This allows the system to adapt to different conditions while maintaining independence

Inventive Principle:

Principle #35Parameter changes

2Productivity

If the display panel is divided into multiple panel blocks for processing, then face region detection efficiency is improved, but processing complexity increases

Engineering Contradiction:

Improveface region detection efficiencyVSAvoidprocessing algorithm complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The display panel is divided into multiple panel blocks, allowing parallel processing of different regions. The driving controller calculates skin color inclusion ratios for each block independently, improving detection efficiency while managing complexity through modular processing

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of processing the entire display panel uniformly, the system focuses calculations on specific panel blocks that may contain face regions. This partial action approach improves efficiency by avoiding unnecessary calculations in regions without faces

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12462600B2Display apparatus and method of driving the same

Publication Date: 2025.11.04 SAMSUNG DISPLAY CO LTD

AI summary

A display apparatus includes: a display panel including a plurality of pixels; a data driver which applies data voltages to the pixels; a gate driver which applies gate signals to the pixels; and a driving controller which controls the data driver and the gate driver. The driving controller divides the display panel into a plurality of panel blocks, calculates a skin color inclusion ratio of each of the panel blocks based on input image data, determines at least one face region candidate block among the panel blocks based on the skin color inclusion ratio, determines a face region block of the at least one face region candidate block based on the at least one face region candidate block and face matching data, and performs image quality processing on the face region block.