Optical Sensor Grid Segmentation for Insulin Dose OCR

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current insulin injection devices require manual user involvement for monitoring and recording dose information, which can lead to errors, especially for users with poor eyesight, and do not facilitate easy electronic data storage and transmission.

Innovation Solution

An optical sensor system with a grid of photosensitive cells captures two distinct images of the dosage window using different subsets of cells, processed using multiple optical character recognition algorithms to enhance reliability and resilience, minimizing the impact of defective cells and improving accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual monitoring and recording of dose information is used, then user involvement is required for accurate dose tracking, but this increases user burden and possibility of mistakes

Engineering Contradiction:
Improvedose tracking accuracyVSAvoiduser burden
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system enables automatic self-monitoring of dose information through optical sensing and OCR technology. The device automatically captures images of the dosage window, processes the dose information using OCR algorithms, and records the data without requiring manual user intervention, thereby eliminating user burden while maintaining accurate dose tracking

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical recording operations with an automated optical-electronic system. The optical sensor captures images, the processor executes OCR algorithms to convert visual dose information into digital data, and the system automatically stores and transmits this information, substituting manual operations with automated technological processes

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If a single image is captured using all photosensitive cells, then the image capture process is simple, but defective photosensitive cells can cause errors in optical character recognition

Engineering Contradiction:
ImproveOCR accuracyVSAvoidimage capture process
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent divides the photosensitive cell array into multiple subsets, where each subset captures a separate image of the dosage window. This segmentation allows the system to process multiple images and select the most reliable one for OCR, or combine results from multiple images to improve recognition accuracy and reduce the impact of defective cells

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system captures multiple images in advance using different subsets of photosensitive cells as a backup mechanism. If one image contains errors due to defective cells, the system has alternative images ready to ensure accurate OCR recognition, thereby cushioning against potential recognition failures

Inventive Principle:
Principle #11Beforehand cushioning (Prior cushioning)

3Ease of operation

If dose information is displayed through a dose window for visual reading, then the information is easily accessible, but users with poor eyesight cannot accurately determine the dose reading

Engineering Contradiction:
Improvedose reading accessibilityVSAvoiddose reading accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent replaces visual reading of dose information with automated optical recognition. The optical sensor captures an image of the dosage window, and the processor executes OCR algorithms to automatically read and interpret the dose information, converting visual data into digital information that can be displayed in various formats accessible to users with different visual abilities

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates a digital copy of the visual dose information through image capture and OCR processing. This digital copy can be displayed on screens, transmitted to mobile devices, or presented in alternative formats, providing multiple access points for users with varying visual capabilities

Inventive Principle:
Principle #26Copying

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system increases the reliability and accuracy of dose reading, reduces user burden, and facilitates easier electronic data storage and transmission by providing a combined confidence value for accurate dose display.

Implementation Method 1

an optical sensor having a plurality of photosensitive cells arranged in a grid, wherein the optical sensor is configured to: capture a first image using a first subset of the photosensitive cells

Methodology Applied
Scientific EffectPhotoelectric Effect: Photoelectric Effect

Data Source

PatentEP3166492B1Apparatus for capturing and processing images
Publication Date: 2022.04.06 SANOFI AVENTIS DEUT GMBH
  • EP3166492B1 patent drawingFigure 1a
  • EP3166492B1 patent drawingFigure 1b~2a
  • EP3166492B1 patent drawingFigure 2b~2c

AI summary

An apparatus comprising an optical sensor having a plurality of photosensitive cells arranged in a grid, wherein the optical sensor is configured to capture a first image using a first subset of the photosensitive cells and to capture a second image using a second subset of the photosensitive cells, the second subset not including any of the photosensitive cells in the first subset, wherein the apparatus is configured to process the first and second images using at least one optical character recognition algorithm.