Optical Braille Recognition Using Line Sensor Triangulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting Braille patterns, especially at high speeds during manufacturing, face challenges in achieving high processing speed and accuracy while minimizing technical effort, particularly in ensuring correct positioning and height of Braille elevations to prevent misinterpretation.
Innovation Solution
The solution involves taking individual images of Braille elevations at a shorter distance than the diameter of the elevations, allowing for precise determination of their position and height, and reducing data processing by reading only relevant image data from optical sensors, such as using a CMOS sensor to read out only partial areas of interest, and processing data in real-time to ensure accurate and efficient detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a high-resolution area sensor with 512x512 pixels is used to detect Braille elevations, then the measurement precision and reliability of Braille detection are improved, but the processing time and complexity increase significantly, making real-time detection at high speeds difficult
Solution Approach 1:
The patent extracts only the essential information needed for Braille detection by using a line sensor instead of a full area sensor. This reduces the data volume from 512x512 pixels to a one-dimensional scan line, while still capturing sufficient information about elevation positions and heights through the light section method.
Solution Approach 2:
The patent segments the detection process into multiple sequential line scans that are combined to form a complete 2D image of the Braille pattern. This allows the system to process data in smaller increments rather than capturing and processing all pixels simultaneously, reducing the time complexity of image processing.
2Productivity
If the scanning frequency is increased to achieve real-time detection at high object speeds, then the productivity and detection speed are improved, but the minimum time between individual scans and data processing time become limiting factors
Solution Approach 1:
The patent replaces complex mechanical scanning systems with an optical-based light section method combined with a line sensor. This substitution enables faster data acquisition because optical methods can capture elevation information instantaneously as the object passes through the light section, without mechanical movement delays.
Solution Approach 2:
The patent performs preliminary processing of the light section data to extract only the relevant elevation information (position and height of Braille dots) before completing the full image reconstruction. This preliminary extraction of key parameters reduces the overall processing time and enables faster detection cycles.
3Reliability
If multiple individual scans are performed at short time intervals to ensure complete coverage of Braille elevations, then the measurement precision and reliability are improved, but the quantity of data to be processed increases
Solution Approach 1:
The patent extracts only the essential elevation information from multiple scans by identifying and recording only the positions and heights of Braille dots that exceed a threshold. This selective extraction reduces the data volume significantly compared to storing and processing complete image frames from multiple scans.
Solution Approach 2:
The patent performs a sufficient number of scans to ensure complete coverage of all Braille elevations, accepting some redundancy in the data. This partial excess in scanning ensures that no Braille dot is missed, while the subsequent data processing filters out redundant information to maintain efficiency.
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
This approach enables reliable and efficient detection of Braille patterns with high precision and speed, reducing the risk of overlooking elevations and improving the accuracy of Braille recognition, even at high object speeds, by minimizing data processing time and hardware requirements.
Implementation Method 1
A fan-shaped light beam, i.e. spread out in only one plane, is applied to the surface to be examined and observed at an angle
Implementation Method 2
observed at an angle, usually an acute angle, to the direction of irradiation, so that the course of the image of the fan-shaped beam on the surface shows any elevations there
Data Source
Figure 1a
Figure 1b
Figure 2a~2b
AI summary
The method involves receiving a lenticular image (4) of a light beam (3) on a surface (2) of an object (1) by a detection device (6) arranged at a triangulation angle to a line of sight (5). An individual image detection is implemented under relative movement of the object and the image in a moving direction (7) transverse to an extension direction of the image. A result data is calculated from the individual data, and the repetition of the detection takes place such that a distance of the individual image in the moving direction is not larger than a diameter of a Braille embossment.