Object-Background Classification Noise Removal
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current background filter technologies in computer vision struggle to accurately distinguish between object and background regions in images, especially when noise is present, leading to inaccurate classification.
Innovation Solution
An electronic apparatus and method that captures an input image, classifies it into object and background regions, preprocesses the classification map to remove noise, and uses correction coefficients based on distance and noise ratios to refine the classification, resulting in a more accurate object image by applying a final classification map to the input image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If background filter technology is used to classify object and background regions, then background replacement function is achieved, but classification accuracy deteriorates due to noise interference
Solution Approach 1:
The patent applies preliminary action by performing noise removal on the classification map before using it for background replacement. The processor removes noise regions from the classification map generated by the background filter technology, thereby improving classification accuracy while maintaining the background replacement function.
Solution Approach 2:
The patent converts the harmful noise interference into a beneficial process by identifying and removing noise regions from the classification map. The noise removal process transforms the previously harmful noise into a controlled parameter that can be corrected, thereby improving overall classification accuracy.
2Productivity
If classification map is generated without noise removal, then processing speed is maintained, but classification accuracy deteriorates
Solution Approach 1:
The patent performs noise removal as a preliminary action on the classification map before final processing. This preliminary noise removal step ensures that accurate classification is achieved without significantly impacting overall processing speed, as the noise removal is integrated into the existing processing pipeline.
3Measurement precision
If noise region is removed from classification map, then classification accuracy is improved, but device complexity increases
Solution Approach 1:
The patent applies self-service by using the background filter technology's own generated classification map as the basis for noise removal. The noise removal process operates on the existing classification map without requiring entirely new complex processing systems, thereby improving accuracy while limiting the increase in device complexity.
Data Source
AI summary
An electronic apparatus includes: a memory storing at least one instruction; and at least one processor configured to execute the at least one instruction to: obtain an input image by capturing an object and a background of the object through a camera; obtain a first classification map by classifying a first part of the obtained input image as an object region corresponding to the object and a second part of the obtained input image as a background region corresponding to the background of the object; pre-process the first classification map to obtain a second classification map in which a noise region in the first classification map is removed; and obtain an object image corresponding to the object, based on the first classification map and the second classification map, by using the noise region in the first classification map and information about a distance between the camera and the object.