Focused Preview Image Generation Using Saliency Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image management systems fail to accurately depict the subjects of interest in digital images, as they typically crop images from the center, which can exclude important subjects, making it difficult for users to browse and manage their digital repositories effectively.
Innovation Solution
The system generates intelligent personalized preview images by using a saliency map and focus information to identify and center on the subject of interest, ensuring that the subject is prominently displayed in the preview image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If conventional systems crop digital images to create preview images of predetermined sizes, then the visual space is saved and the number of thumbnails shown per page is maximized, but the subjects of interest are frequently excluded from the thumbnails
Solution Approach 1:
The system performs preliminary analysis of the digital image to identify the subject of interest before generating the preview image. By using focus information captured by the camera device and generating a saliency map, the system determines the subject of interest in advance, allowing the preview image to be cropped and positioned to include this subject while still maximizing the number of thumbnails displayed per page.
2Ease of operation
If conventional systems generate thumbnails by cropping to the centers of digital images, then the layout is aesthetically pleasing and easily reviewable, but the subjects of interest are excluded from view
Solution Approach 1:
The system applies different quality standards to different regions of the digital image. Instead of uniformly cropping to the center, the system identifies the specific region containing the subject of interest using focus information and saliency map analysis, then applies selective cropping and positioning that prioritizes including this important region while maintaining an aesthetically pleasing layout.
3Measurement precision
If the system generates focused preview images by identifying subjects of interest using saliency maps and focus information, then the subjects of interest are prominently displayed, but the computational resources required for image processing increase
Solution Approach 1:
The system performs preliminary analysis by generating a saliency map and identifying focus information from the captured digital image. By conducting this subject identification analysis before preview image generation, the system avoids redundant computational operations during the actual preview creation process, thereby improving subject identification accuracy while managing computational resource usage efficiently.
Data Source
AI summary
Methods, systems, and non-transitory computer readable storage media are disclosed for generating focused preview images that include the subjects of interest of digital images. For example, in one or more embodiments, the disclosed system utilizes a machine-learning model to generate a saliency map for a digital image to indicate one or more salient objects portrayed within the digital image. Additionally, in one or more embodiments, the system identifies a focus region based on focus information captured by a camera device at the time of capturing the digital image. Furthermore, the system can then utilize the saliency map and the focus region to generate a focused preview image. For instance, in one or more embodiments, the system crops the digital image based on an overlapping portion of the saliency map and the focus region to generate a focused preview image.