NC Program Conversion Device Using OCR and Format Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing character recognition devices struggle to accurately convert handwritten or printed NC programs from images into executable code, often mistaking characters and resulting in non-functional program codes due to incorrect recognition and lack of specific formatting knowledge.

Innovation Solution

An NC-program conversion device with an OCR processing unit, storage units for numerical and code formats, and a character-string segmenting unit that associates alphabetic letters with numbers and effective characters to segment recognized character strings into functional program codes, utilizing a numeral-letter conversion list to correct mistaken characters and generate executable NC programs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If OCR processing is applied to recognize character strings from images, then character recognition speed is improved, but recognition accuracy deteriorates due to mistaken character recognition

Engineering Contradiction:
Improvecharacter recognition speedVSAvoidcharacter recognition accuracy
Core Design Contradiction:
SpeedVSMeasurement precision

Solution Approach 1:

The system uses stored format information as feedback to verify and correct OCR recognition results. The character string segmenting unit continuously compares recognized characters against the stored numerical-form and code-form formats, using this feedback loop to identify and correct recognition errors while maintaining high processing speed.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs preliminary action by storing common NC program format patterns (numerical-form with alphabetic letters followed by numbers, code-form with program codes and effective characters) in advance. This pre-prepared format knowledge enables rapid verification and correction of OCR results without requiring complex real-time analysis.

Inventive Principle:
Principle #10Preliminary action

2Ease of operation

If general character recognition is used, then ease of operation is improved, but manufacturing precision deteriorates due to inability to generate correctly formatted NC program codes

Engineering Contradiction:
Improveease of converting images to textVSAvoidNC program code formatting accuracy
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The system applies local quality by implementing format-specific processing rules for different parts of the character string. The character string segmenting unit identifies specific patterns (alphabetic letters followed by numbers, program codes followed by effective characters) and applies appropriate segmentation and correction rules to each local segment, ensuring each part conforms to NC program standards.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system changes parameters by transforming the character string structure from general text format to specific NC program format. The character string segmenting unit modifies the arrangement, spacing, and formatting parameters of recognized characters to match the target NC program code structure, converting unstructured text into precisely formatted executable codes.

Inventive Principle:
Principle #35Parameter changes

3Device complexity

If simple character replacement is applied, then device complexity is reduced, but reliability deteriorates due to inability to handle format-specific correction needs

Engineering Contradiction:
Improvecomplexity of correction mechanismVSAvoidaccuracy of code conversion
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system uses segmentation by dividing the character string processing into distinct segments: numerical-form segments (alphabetic letters with number of digits) and code-form segments (program codes with effective characters). The character string segmenting unit processes each segment type with appropriate rules, improving reliability through structured handling of different code formats without requiring overly complex unified processing.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS10410080B2NC-program conversion device
Publication Date: 2019.09.10 FANUC LTD
  • US10410080B2 patent drawing
  • US10410080B2 patent drawing
  • US10410080B2 patent drawing

AI summary

An NC-program conversion device includes an OCR processing unit that recognizes a character string from an input image; a first storage unit that stores one alphabetic letter and the number of digits of a number subsequent to the alphabetic letter, in an associated manner; a second storage unit that stores a program code that is composed of a combination of one alphabetic letter and a two-character number and an effective character that is composed of one alphabetic letter subsequent to the program code, in an associated manner; and a character-string segmenting unit that refers to the first storage unit and the second storage unit, to segment each line of the character string, which is recognized by the OCR processing unit, as program codes stored in the first storage unit in an associated manner.