Line-by-Line Character Recognition Using Video Stream Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current OCR technologies on handheld devices require additional hardware to process characters line by line, as they treat two-dimensional images as page-by-page inputs, deviating from the natural reading habit and limiting their use to business card recognition.

Innovation Solution

A method that integrates consecutive images captured by a two-dimensional camera, removing overlapping parts to create a single image for OCR software, allowing for line-by-line character recognition without additional hardware, using edge detection and shape matching to ensure accurate character output.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a two-dimensional camera module is used to capture images, then the device complexity is reduced and ease of operation is improved, but the characters cannot be recognized line by line and additional hardware assistance is needed

Engineering Contradiction:
Improveease of operationVSAvoiddevice complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent segments the continuous video stream into individual character or line segments by detecting edges and identifying boundaries between different characters. This segmentation allows the system to process and recognize characters sequentially line by line, transforming a two-dimensional image input into a one-dimensional character sequence output without requiring additional hardware.

Inventive Principle:
Principle #1Segmentation

2Productivity

If images are processed page by page, then the device complexity is reduced, but the character recognition does not conform to people's habit of processing characters line by line

Engineering Contradiction:
ImproveproductivityVSAvoidease of operation
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The patent introduces dynamic processing by analyzing the video stream frame by frame and detecting motion and edges to identify character boundaries. This dynamic approach allows the system to adaptively segment characters as they appear in the video stream, enabling line-by-line recognition that conforms to natural reading habits while maintaining efficient processing.

Inventive Principle:
Principle #15Dynamics

3Productivity

If a line camera is used to read and input line segments, then the characters can be arranged line by line and recognized consecutively, but the device complexity increases due to additional hardware

Engineering Contradiction:
ImproveproductivityVSAvoiddevice complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent uses the existing two-dimensional camera to capture images, then processes these images through edge detection and segmentation algorithms to extract character information. This approach creates a virtual line-by-line scanning effect by processing the two-dimensional image data sequentially, eliminating the need for physical line camera hardware while achieving the same functional result.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS8401335B2Method for outputting consecutive characters in video-recording mode
Publication Date: 2013.03.19 ASUSTEK COMPUTER INC
  • US8401335B2 patent drawing
  • US8401335B2 patent drawing
  • US8401335B2 patent drawing

AI summary

The invention discloses a method for outputting consecutive characters in a video-recording mode. The method includes obtaining a first image and a second image from an object, comparing the first image and the second image to obtain a third image which is the overlapping part of the first image and the second image, removing the third image from the second image to generate a fourth image, integrating the fourth image with the first image to obtain a fifth image and recognize characters on the fifth image by OCR software and output the characters of the fifth image.