Machine Learning Model for Image Processing Area Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing technologies face challenges in accurately identifying areas within an image where specific processing, such as sharpening, should be applied, leading to inadequate processing in certain regions.
Innovation Solution
A machine learning model is trained to differentiate between areas in an image where edge enhancement and smoothing processes should be performed, using input image data and teacher data to adjust parameters, enabling the image processing apparatus to perform these processes appropriately in identified areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional edge detection methods are used to identify processing areas, then the processing speed is fast, but the accuracy of identifying areas requiring specific image processing is insufficient
Solution Approach 1:
The patent replaces traditional mechanical edge detection algorithms with a machine learning model (neural network) that automatically learns and identifies regions requiring specific image processing. The model processes input images to generate output images indicating first areas (requiring first image processing) and second areas (requiring second image processing), achieving higher accuracy without manually designing detection rules.
Solution Approach 2:
The machine learning model is trained using teaching data that includes input images and corresponding output images indicating processing areas. Through this self-learning process, the model automatically acquires the ability to identify regions requiring specific processing, eliminating the need for manual programming of detection logic and continuously improving its accuracy.
2Manufacturing precision
If different sharpening processes are executed for edge and non-edge portions, then the image quality is improved, but the processing time increases
Solution Approach 1:
The patent segments the image into different processing areas (first areas and second areas) based on the machine learning model's output. By dividing the image into distinct regions that require different processing approaches, the system can apply optimized processing to each segment, improving overall quality while managing processing time through efficient area classification.
Solution Approach 2:
The patent applies different image processing techniques to different local areas of the image based on their specific characteristics. First image processing is applied to first areas identified by the model, and second image processing is applied to second areas, allowing each region to receive the most appropriate processing for its content and requirements.
Data Source
AI summary
A non-transitory computer-readable storage medium storing a set of program instructions for an image processing apparatus is disclosed. The set of program instructions, when executed by a controller of the image processing apparatus, causes the image processing apparatus to: acquire input image data indicating an input image; and input the input image data to a trained machine learning model configured to perform calculation processing on the input image data and to generate output image data corresponding to the input image data. The machine learning model is trained to generate the output image data indicating a first area and a second area. The first area is an area in the input image in which it is preferable to perform first image processing. The second area is an area in the input image in which it is preferable to perform second image processing different from the first image processing.