Subtitle Region Recognition via Repetition Rate Screening

Solution Overview

Problem

Existing methods for extracting subtitles from short videos require significant manual labor, as they involve manually marking subtitle regions and using optical character recognition (OCR) technology for text recognition.

Innovation Solution

A method and apparatus for automatically recognizing subtitle regions in videos by obtaining candidate subtitle regions based on text content display, applying a subtitle region screening policy to filter these regions, and selecting the region with the lowest repetition rate and longest display duration as the subtitle region.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual marking method is used to extract subtitles, then accuracy of subtitle region identification is improved, but labor cost and time consumption increase significantly

Engineering Contradiction:

Improvesubtitle region identification accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system automatically identifies subtitle regions by analyzing text content characteristics (repetition rate, display duration, position) without requiring manual intervention. The computer device performs self-service by autonomously extracting subtitles through automated region identification and text recognition.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual marking process with an automated computer vision system that uses OCR technology and algorithmic analysis of text characteristics to identify subtitle regions, eliminating the need for human operators to manually mark regions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If manual marking method is used to extract subtitles, then accuracy of subtitle region identification is improved, but labor resources increase

Engineering Contradiction:

Improvesubtitle region identification accuracyVSAvoidautomation level

Core Design Contradiction:

Measurement precisionVSExtent of automation

Solution Approach 1:

The system automatically identifies subtitle regions by analyzing text content characteristics (repetition rate, display duration, position) without requiring manual intervention. The computer device performs self-service by autonomously extracting subtitles through automated region identification and text recognition.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual marking process with an automated computer vision system that uses OCR technology and algorithmic analysis of text characteristics to identify subtitle regions, eliminating the need for human operators to manually mark regions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated OCR technology is applied without manual marking, then labor cost decreases, but accuracy of subtitle region identification deteriorates

Engineering Contradiction:

Improvesubtitle extraction efficiencyVSAvoidsubtitle region identification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies different analysis criteria to different regions by evaluating text characteristics (repetition rate, display duration, position) specific to subtitle regions. The system identifies regions where text appears at consistent positions with high repetition rates and long display durations, which are characteristic of subtitle regions rather than other text elements.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes the parameters used for region identification from generic text detection to specific subtitle characteristics including repetition rate threshold, display duration threshold, and position-based filtering. These parameter changes enable accurate differentiation between subtitle regions and other text regions.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12236696B2Method and apparatus for recognizing subtitle region, device, and storage medium

Publication Date: 2025.02.25 TENCENT TECHNOLOGY (SHENZHEN) CO LTD

AI summary

A method and an apparatus for recognizing a subtitle region, a device, and a storage medium are provided, relating to the field of computer vision technologies of artificial intelligence. The method includes: recognizing a video to obtain n candidate subtitle regions, the candidate subtitle regions being regions in which text contents are displayed in the video, and n being a positive integer; and screening the n candidate subtitle regions according to a subtitle region screening policy to obtain the subtitle region, the subtitle region screening policy being used for determining a candidate subtitle region in which text contents have a repetition rate being lower than a repetition rate threshold and have a longest total display duration as the subtitle region. By using the method and apparatus, device, and system, labor resources required for subtitle region recognition can be saved.