Facial Feature Extraction for Accurate Cast Information Display

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for providing cast information in VOD are time-consuming and prone to errors, especially when human management is involved, leading to potential waste and inaccuracies in disclosing information before moving images are released.

Innovation Solution

A person information display apparatus that includes a characteristic extraction unit for facial features, a correspondence information extraction unit for matching extracted features with pre-stored data, an exclusion candidate setting unit for filtering analogous information, and a display unit for accurate and rapid presentation of cast information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If human management is used to specify and register cast information, then accurate information can be provided, but the operation takes a very long time

Engineering Contradiction:
Improveaccuracy of cast informationVSAvoidoperation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the mechanical human management system with an automated computer-based system that uses facial characteristic extraction and pattern matching algorithms to identify cast members, eliminating manual review while maintaining accuracy through automated comparison of facial features against a database

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically extracting facial characteristics from moving images, comparing them with pre-stored characteristic information, and registering cast information without requiring human intervention at each step, thus significantly reducing operation time while maintaining accuracy

Inventive Principle:
Principle #25Self-service

2Productivity

If cast information is registered in advance before determining disclosure, then information can be provided quickly, but the operation becomes wasteful if moving images are not disclosed

Engineering Contradiction:
Improvespeed of information provisionVSAvoidwaste of operation
Core Design Contradiction:
ProductivityVSLoss of energy

Solution Approach 1:

The system performs preliminary extraction of facial characteristics and preparation of characteristic information from moving images before the disclosure decision is made, so that when disclosure is confirmed, the cast information can be immediately provided without delay, while avoiding complete processing if disclosure is not planned

Inventive Principle:
Principle #10Preliminary action

3Loss of time

If automated extraction is used to reduce operation time, then speed is improved, but errors may occur in extracted information

Engineering Contradiction:
Improveoperation timeVSAvoidaccuracy of extracted information
Core Design Contradiction:
Loss of timeVSReliability

Solution Approach 1:

The system incorporates feedback mechanisms where extracted facial characteristics are compared against pre-stored characteristic information in a database, and the matching results are verified through multiple comparison iterations to ensure accuracy, allowing automated processing while maintaining high reliability

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs preliminary extraction and storage of accurate facial characteristic information during the production phase, creating a reference database that can be reliably used for automated matching later, thus ensuring accuracy is established before the speed-critical matching phase

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10657417B2Person information display apparatus, a person information display method, and a person information display program
Publication Date: 2020.05.19 AMBASS INC
  • US10657417B2 patent drawing
  • US10657417B2 patent drawing
  • US10657417B2 patent drawing

AI summary

The invention includes: a characteristic extraction unit for extracting facial characteristics of persons from moving image data; correspondence information extraction unit for extracting characteristic information corresponding to facial characteristics extracted by characteristic extraction unit from pre-stored characteristic information on faces of multiple persons; exclusion candidate setting unit for setting, to an exclusion candidate, characteristic information selected in accordance with an input of a user or a predetermined criterion among analogous characteristic information if multiple characteristic information extracted by the correspondence information extraction unit is analogous; and a person information output unit for displaying, on a display unit, information indicating a person corresponding to characteristic information extracted by the correspondence information extraction unit and set to the exclusion candidate by the exclusion candidate setting unit, as well as information indicating a person corresponding to the characteristic information extracted by the correspondence information extraction unit and not set to the exclusion candidate.