Stereo Mode Detection Using Image-Half Similarity and Histograms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video and image viewers struggle to accurately determine the stereo mode of images, particularly mono or stereo types, without relying on metadata, which is often incomplete, and machine learning solutions are computationally expensive.
Innovation Solution
The method involves dividing images vertically and horizontally to calculate similarity and histogram scores between image halves, using pixel differences and histogram analysis to identify whether an image is a left-right stereo, top-bottom stereo, or mono image type.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning methods are used to determine stereo mode, then classification accuracy is improved, but computational cost increases
Solution Approach 1:
The image is divided into two vertical halves and two horizontal halves, allowing the system to analyze smaller image segments separately. This segmentation enables the calculation of similarity scores and histogram scores for each half, reducing the overall computational burden compared to analyzing the entire image with complex machine learning models while maintaining sufficient accuracy for stereo mode detection.
2Productivity
If metadata is used to determine image type, then processing speed is improved, but reliability deteriorates due to incomplete metadata
Solution Approach 1:
The system performs self-service by automatically analyzing the image content itself to determine stereo mode, rather than relying on external metadata that may be incomplete or incorrect. The image data serves its own classification purpose through histogram analysis and similarity scoring, ensuring both speed and reliability.
3Measurement precision
If complex analysis methods are used to classify images, then classification accuracy is improved, but device complexity increases
Solution Approach 1:
The system changes parameters by computing similarity scores and histogram scores between image halves, then uses these parameter transformations to classify stereo modes. This approach achieves accurate classification through mathematical parameter comparisons rather than complex structural analysis, reducing device complexity while maintaining precision.
Data Source
AI summary
A method includes obtaining an image, dividing the image vertically into first and second vertical halves, determining a first similarity score representing a similarity between the first and second vertical halves, and determining a first histogram score representing a resemblance between histograms of the first and second vertical halves. The method also includes dividing the image horizontally into first and second horizontal halves, determining a second similarity score representing a similarity between the first and second horizontal halves, and determining a second histogram score representing a resemblance between histograms of the first and second horizontal halves. The method further includes identifying whether the image is a left-right (LR) stereo image, a top-bottom (TB) stereo image, or a mono image using the first and second similarity scores and the first and second histogram scores.