View source for 18517809. METHOD AND ELECTRONIC DEVICE FOR RECOGNIZING OBJECT BASED ON MASK UPDATES simplified abstract (ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE)

=METHOD AND ELECTRONIC DEVICE FOR RECOGNIZING OBJECT BASED ON MASK UPDATES=


==Organization Name==

[[:Category:ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE|ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE]]


[[Category:ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE]]

==Inventor(s)==

[[:Category:Ye-Bin Moon of Daejeon (KR)|Ye-Bin Moon of Daejeon (KR)]][[Category:Ye-Bin Moon of Daejeon (KR)]]

[[:Category:Tae-Hyun Oh of Daejeon (KR)|Tae-Hyun Oh of Daejeon (KR)]][[Category:Tae-Hyun Oh of Daejeon (KR)]]

[[:Category:Yongjin Kwon of Daejeon (KR)|Yongjin Kwon of Daejeon (KR)]][[Category:Yongjin Kwon of Daejeon (KR)]]

==METHOD AND ELECTRONIC DEVICE FOR RECOGNIZING OBJECT BASED ON MASK UPDATES - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18517809 titled 'METHOD AND ELECTRONIC DEVICE FOR RECOGNIZING OBJECT BASED ON MASK UPDATES

==Simplified Explanation==

The abstract describes a method of recognizing an object based on mask updates in an input image. Here is a simplified explanation of the patent application:

* The method separates the foreground and background of an input image.
* It matches the results of object recognition within the input image and a boundary portion of the object.
* An objective function is calculated based on result information and parameter information.
* All mask heads are updated based on the objective function.
* Object recognition is performed based on the updated mask.

---

### Potential Applications
This technology could be applied in various fields such as computer vision, image processing, and object recognition systems.

### Problems Solved
This technology helps in accurately recognizing objects in images by updating mask heads based on objective functions, improving the overall performance of object recognition systems.

### Benefits
- Enhanced accuracy in object recognition
- Efficient separation of foreground and background in images
- Improved boundary matching of objects in images

### Potential Commercial Applications
- Security systems for identifying objects in surveillance footage
- Autonomous vehicles for detecting and recognizing objects on the road
- Medical imaging for identifying and analyzing specific areas of interest in scans

### Possible Prior Art
One possible prior art could be the use of convolutional neural networks (CNNs) for object recognition in images. These networks have been widely used in the field of computer vision for tasks such as image classification and object detection.

---

## Unanswered Questions

### How does this method handle complex backgrounds in images?
The abstract does not provide specific details on how the method deals with complex backgrounds that may affect object recognition accuracy.

### What is the computational cost of updating all mask heads based on the objective function?
The abstract does not mention the computational resources required to update all mask heads, which could be crucial for real-time applications or resource-constrained devices.


==Original Abstract Submitted==

A method of recognizing an object based on mask updates is provided. The method includes generating first result information in which a foreground and background of a predetermined input image have been separated from each other, generating second result information in which the results of the object recognition within the input image and a boundary portion of the object have been matched, calculating an objective function to be applied to each mask head based on the first and second result information and parameter information for the first and second result information, updating all of the mask heads based on the objective function, and performing object recognition based on the updated mask.



[[Category:G06V10/74]]
[[Category:G06V10/26]]
[[Category:G06V10/75]]
[[Category:G06V10/77]]