Touch Sensor Patch Segmentation via Watershed Algorithm
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Touch sensor panels face challenges in accurately interpreting touch events due to varying finger positions, orientations, and force applications, leading to difficulties in properly merging touch patches and determining finger orientations.
Innovation Solution
The application of a watershed algorithm to touch sensor panel pixels, combined with background elimination, smoothing, and a primary merge algorithm, to identify and merge touch patches based on pixel counts and orientations, while using centroids and bounding boxes to enhance accuracy and reduce noise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If a watershed algorithm is applied to all pixels including background pixels, then complete coverage of the touch panel is achieved, but processing complexity and computational load increase significantly
Solution Approach 1:
The patent extracts and eliminates background pixels from consideration before applying the watershed algorithm. By identifying and removing pixels with little or no touch values, the algorithm processes only relevant touch area pixels, reducing computational load while maintaining accurate touch patch identification.
2Quantity of substance
If merging criteria are made more aggressive to combine small patches, then fewer patches remain but accuracy decreases due to merging unrelated patches
Solution Approach 1:
The patent applies different merging criteria based on local characteristics of patches. Small patches are evaluated differently from large patches, and merging decisions consider local factors such as proximity to other patches, orientation consistency, and whether patches are part of a continuous touch object. This localized approach maintains accuracy while reducing patch count appropriately.
3Productivity
If centroids are calculated for all patches including partial patches at edges, then complete patch analysis is performed, but accuracy decreases due to incomplete data from partial patches
Solution Approach 1:
The patent performs preliminary identification and classification of partial patches at panel edges before centroid calculation. By detecting patches that are truncated by panel boundaries and applying corrective measures such as phantom pixel duplication, the system prepares accurate centroid calculations in advance, ensuring both completeness and precision.
4Stability of the object's composition
If smoothing is applied to connect overly segmented patches, then patch continuity improves but noise and false connections may be introduced
Solution Approach 1:
The patent applies smoothing selectively and partially, focusing only on regions where over-segmentation is detected. By applying smoothing algorithms with controlled intensity and scope, the system connects genuinely fragmented patches while avoiding excessive smoothing that would create false connections or introduce noise into legitimate patch boundaries.
Data Source
AI summary
The application of a watershed algorithm to pixels and their touch values obtained from a scan of a touch sensor panel to determine patches corresponding to images of touch is disclosed. Prior to applying the watershed algorithm, background pixels having little or no touch values can be eliminated. A primary merge algorithm can then merge adjacent patches together when the saddle point between them is shallow as compared to the peak represented by the patches. However, if two candidate patches for merging have a total number of pixels below a certain threshold, these two patches may not be merged under the assumption that the patches might have been caused by different fingertips. Conversely, if two candidate patches for merging have a total number of pixels above a certain threshold, these two patches can be merged under the assumption that the patches were caused by a single thumb or palm.