Dual-Platform Weighing System with Object Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image recognition technologies in weighing systems suffer from low precision and accuracy, especially when objects are adhered together, stacked, or in environments with poor imaging effects due to shadows or varying light conditions.

Innovation Solution

A new weighing system and method that utilizes a division of labor between two scale platforms, where one platform is dedicated to object recognition using an object recognition area and image recognition, while the other platform focuses on weighing, thereby optimizing the fit of the image to the algorithm and improving recognition precision and accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If image recognition is performed on objects placed on the entire platform top, then the recognition area is large, but the imaging effect is poor due to shadows, strong or weak light, and the recognition precision and accuracy are low

Engineering Contradiction:
Improverecognition areaVSAvoidrecognition precision and accuracy
Core Design Contradiction:
Area of stationary objectVSMeasurement precision

Solution Approach 1:

The patent divides the weighing scale into two separate platform tops: one dedicated to object recognition and another for weighing. This segmentation allows the recognition platform to be optimized specifically for imaging conditions, avoiding the interference of shadows and lighting issues that occur when the entire platform is used for both purposes. The recognition platform can be positioned and illuminated optimally without compromising the weighing function.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates a localized optimization by providing a dedicated recognition platform top with specific imaging conditions tailored for object recognition. This local quality improvement ensures that the recognition area has optimal lighting and shadow conditions specifically designed for image capture, while the weighing platform maintains its weighing function without being affected by imaging requirements.

Inventive Principle:
Principle #3Local quality

2Area of stationary object

If objects are adhered together or stacking phenomenon occurs, then the object recognition becomes more difficult, but using the entire platform top for recognition increases the likelihood of such phenomena

Engineering Contradiction:
Improverecognition areaVSAvoidobject recognition difficulty
Core Design Contradiction:
Area of stationary objectVSDifficulty of detecting and measuring

Solution Approach 1:

By separating the recognition function from the weighing function onto different platform tops, the patent reduces the likelihood of objects being adhered together or stacking. Objects placed on the recognition platform are more likely to be individually positioned and visible, as the platform is optimized for recognition rather than bulk weighing, thereby reducing recognition difficulty.

Inventive Principle:
Principle #1Segmentation

3Productivity

If multiple scales are used for double-scale counting, then the weighing capacity is improved, but the operation complexity increases due to manual determination of article category and counting

Engineering Contradiction:
Improveweighing capacityVSAvoidoperation complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent merges the object recognition function with the weighing system by integrating an image recognition device into the weighing scale. This combination allows the system to automatically recognize object categories and perform counting functions, eliminating the need for manual determination of article categories and reducing operation complexity while maintaining the productivity benefits of multiple scales.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system performs self-service by automatically recognizing objects, determining their categories, and performing counting operations without requiring manual intervention. The image recognition device automatically captures images, processes them to identify objects, and integrates this information with the weighing data, allowing the system to service itself rather than requiring operator input for category determination and counting.

Inventive Principle:
Principle #25Self-service

4Productivity

If image recognition is used to directly recognize objects on the weighing platform, then the external input step is eliminated and efficiency is improved, but the recognition precision and accuracy are low under complex conditions

Engineering Contradiction:
Improveoperational efficiencyVSAvoidrecognition precision and accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent resolves this contradiction by segmenting the scale into two separate platform tops: one optimized for image recognition with controlled lighting and positioning, and another for weighing. This segmentation maintains the operational efficiency benefit of automatic recognition while improving precision and accuracy by providing optimal imaging conditions that reduce the impact of shadows and lighting variations.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS12306032B2Weighing system and weighing method with object recognition
Publication Date: 2025.05.20 METTLER TOLEDO (CHANGZHOU) MEASUREMENT TECH CO LTD
  • US12306032B2 patent drawing
  • US12306032B2 patent drawing

AI summary

A weighing method comprises the steps of: recognizing one or more objects to be detected on a first scale platform top (A) or within an object recognition area of the first scale platform top (A), and weighing the objects to be detected that are placed on a second scale platform top (B). A weighing system comprises at least two scales having scale platform tops utilizing the weighing method outlined above. The weighing method reduces the difficulty of algorithm recognition by increasing the degree to which the object on the weighting platform fits the algorithm, reduces the complexity of operation flow and the time required, and effectively increases the precision and accuracy of object recognition.