Image Processing for Separating Adjacent Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine vision systems face challenges in accurately detecting and discriminating multiple objects in images, particularly when objects are adjacent or overlapping, with varying sizes and shapes, which complicates the process of object recognition and assessment in applications like material handling.
Innovation Solution
An image processing system that includes an object separation engine capable of autonomous processing, determining non-empty and empty cells, global convex hulls, voids, and separation lines to separate overlapping objects, allowing for the identification of distinct object boundaries and further assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional image processing methods are used to detect multiple objects, then the system can handle simple cases, but it fails to accurately discriminate adjacent or overlapping objects with varying sizes and shapes
Solution Approach 1:
The patent segments the image into a grid of cells, where each cell is independently analyzed to determine if it contains an object portion. This segmentation allows the system to handle objects of varying sizes and shapes by treating each cell as a discrete unit, thereby improving both measurement precision for object discrimination and adaptability to different object configurations.
2Measurement precision
If the system processes images to accurately separate adjacent objects, then object discrimination accuracy improves, but computational complexity and processing time increase
Solution Approach 1:
By dividing the image into a grid of cells and processing each cell independently to determine object presence, the patent reduces computational complexity compared to analyzing the entire image as a single unit. The segmentation approach allows for efficient parallel processing while maintaining accurate object boundary detection through the convex hull and separation line algorithms.
Solution Approach 2:
The patent applies partial action by focusing computational resources only on non-empty cells that contain object portions, rather than processing the entire image uniformly. This selective approach reduces overall computational complexity while maintaining precision in object boundary detection for the relevant regions.
3Measurement precision
If the system uses detailed analysis to discriminate overlapping objects, then object recognition accuracy improves, but processing speed decreases
Solution Approach 1:
The patent achieves a balance between precision and speed by segmenting the image into cells and using efficient algorithms (convex hull computation and separation line determination) that operate on the segmented data. This segmentation enables parallel processing of multiple cells simultaneously, maintaining high processing speed while achieving accurate object separation through the systematic analysis of cell configurations.
Data Source
AI summary
Image processing to discriminate imaged objects that are adjacent or overlapping. Non-empty cells of the image that contain portions of the objects, and empty cells that lack any portions of the objects, are all determined. A global convex hull is defined to surround the non-empty cells of the image. Voids, including at least a first void and a second void, are found within the global convex hull, each being composed of contiguous empty cells and having a corresponding void boundary. A separation line is defined based on a first separation line endpoint along the void boundary of the first void and a second separation line endpoint along the void boundary of the second void, to separate two of the objects in the image. An output may be produced that includes indicia of at least portions of distinct boundaries of the objects in the image based on the separation line.