17960603. GENERATION OF EMPHASIS IMAGE WITH EMPHASIS BOUNDARY simplified abstract (Microsoft Technology Licensing, LLC)
Contents
- 1 GENERATION OF EMPHASIS IMAGE WITH EMPHASIS BOUNDARY
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 GENERATION OF EMPHASIS IMAGE WITH EMPHASIS BOUNDARY - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
GENERATION OF EMPHASIS IMAGE WITH EMPHASIS BOUNDARY
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Salman Muin Kayser Chishti of Tallinn (EE)
GENERATION OF EMPHASIS IMAGE WITH EMPHASIS BOUNDARY - A simplified explanation of the abstract
This abstract first appeared for US patent application 17960603 titled 'GENERATION OF EMPHASIS IMAGE WITH EMPHASIS BOUNDARY
Simplified Explanation
The automated generation of an emphasis image based on an input image is achieved through a machine-learned model trained to label portions of images, which then outputs identifications and labels for each portion. The generated label is used to determine an emphasis bounding box, which is applied to the input image to create the emphasis image, such as a cropped image.
- Machine-learned model trained to label portions of images
- Output includes identifications and labels for each portion
- Generated label used to determine emphasis bounding box
- Emphasis bounding box applied to input image to create emphasis image
Potential Applications
This technology could be applied in various fields such as image editing software, content analysis tools, and automated image cropping services.
Problems Solved
This technology solves the problem of manually cropping images for emphasis, saving time and effort for users who need to highlight specific portions of an image.
Benefits
The benefits of this technology include improved efficiency in image editing tasks, enhanced visual communication through emphasized images, and increased automation in content analysis processes.
Potential Commercial Applications
A potential commercial application of this technology could be in the development of image editing software with automated emphasis cropping features, catering to professionals in the design and photography industries.
Possible Prior Art
One possible prior art could be the use of machine learning models for image recognition and labeling, which has been applied in various fields such as object detection and image classification tasks.
Unanswered Questions
How does the machine-learned model differentiate between different portions of an image?
The machine-learned model likely uses features such as color, texture, and shape to differentiate between different portions of an image and assign appropriate labels.
What is the accuracy rate of the machine-learned model in identifying and labeling portions of images?
The accuracy rate of the machine-learned model would depend on the quality of the training data, the complexity of the images, and the effectiveness of the model architecture in capturing relevant features for labeling.
Original Abstract Submitted
The automated generation of an emphasis image (such as a cropped image) that is based on an input image. The input image is fed to a machine-learned model that is trained to label portions of images. That machine-learned model then outputs an identification of multiple portions of images, along with potentially labels of each of those identified portions. The label identifies a property of the corresponding identified portion. As an example, one portion might be labelled as irrelevant, another might be labelled as a name, another might be labelled as a comment, and so forth. That output is accessed and the generated label is used to determine an emphasis bounding box. The emphasis bounding box is then applied to the input image to generate an emphasis image. As an example, the emphasis image may be a cropped image of the input image.
