Automated Object Counting via Characteristic Image Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for estimating the number of objects with elongated shapes, such as reinforcement steel bars, are either labor-intensive and prone to errors (manual counting) or inaccurate and inconvenient (weight-based counting), lacking a convenient, accurate, and cost-effective solution.

Innovation Solution

A method utilizing a processing module to generate a characteristic image from an image of objects with substantially-circular end faces, applying image processing techniques like binary, thinning, and erosion to calculate the number of characteristic patterns, thereby estimating the number of objects automatically and accurately.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual counting is used, then labor cost and time are incurred, but counting accuracy deteriorates when there is a huge quantity of objects

Engineering Contradiction:

Improvecounting accuracyVSAvoidtime-consuming

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical counting with an automated image processing system that uses computer vision algorithms to detect and count objects, eliminating human labor while improving accuracy and speed

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a digital copy (image) of the objects and processes this copy through image processing algorithms to determine the number of objects, avoiding the need to physically interact with or move the actual objects

Inventive Principle:

Principle #26Copying

2Measurement precision

If weighing method is used, then counting can be performed, but accuracy ranges only between 93% and 95% and repeatedly moving objects causes inconvenience

Engineering Contradiction:

Improvecounting accuracyVSAvoidconvenience

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces the mechanical weighing process with an optical image processing system, eliminating the need to physically move objects for weighing while achieving higher accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses a digital image copy of the objects instead of physically handling the objects for measurement, avoiding the inconvenience of repeatedly moving objects while maintaining high accuracy

Inventive Principle:

Principle #26Copying

3Measurement precision

If manual counting is used, then objects can be counted, but considerable labor cost is incurred

Engineering Contradiction:

Improvecounting capabilityVSAvoidlabor cost

Core Design Contradiction:

Measurement precisionVSEase of manufacture

Solution Approach 1:

The patent replaces manual labor with an automated image processing system that uses computers and algorithms to perform counting, eliminating labor costs while maintaining counting capability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent processes a digital copy of the objects through image processing algorithms, eliminating the need for human operators to manually count objects and thereby reducing labor costs

Inventive Principle:

Principle #26Copying

Data Source

PatentUS9519960B2Method for estimating a number of objects

Publication Date: 2016.12.13 NATIONAL APPLIED RESEARCH LABORATORIES

AI summary

A method for estimating a number of objects is to be implemented by a processing module, and is utilized to estimate a number of a plurality of objects having elongated shapes based on an image of the objects that contains substantially-circular end faces of the objects. The method includes steps of generating a characteristic image based on the image of the objects, the characteristic image containing a plurality of characteristic patterns which are associated with the end faces of the objects, calculating a number of the characteristic patterns based on the characteristic image, and obtaining an estimated number of the objects based on at least the number of the characteristic patterns thus calculated.