View source for 18471055. COMPUTER-READABLE RECORDING MEDIUM STORING OBJECT DETECTION PROGRAM, DEVICE, AND MACHINE LEARNING MODEL GENERATION METHOD simplified abstract (Fujitsu Limited)

=COMPUTER-READABLE RECORDING MEDIUM STORING OBJECT DETECTION PROGRAM, DEVICE, AND MACHINE LEARNING MODEL GENERATION METHOD=


==Organization Name==

[[:Category:Fujitsu Limited|Fujitsu Limited]]


[[Category:Fujitsu Limited]]

==Inventor(s)==

[[:Category:Moyuru Yamada of Bangalore (IN)|Moyuru Yamada of Bangalore (IN)]][[Category:Moyuru Yamada of Bangalore (IN)]]

==COMPUTER-READABLE RECORDING MEDIUM STORING OBJECT DETECTION PROGRAM, DEVICE, AND MACHINE LEARNING MODEL GENERATION METHOD - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18471055 titled 'COMPUTER-READABLE RECORDING MEDIUM STORING OBJECT DETECTION PROGRAM, DEVICE, AND MACHINE LEARNING MODEL GENERATION METHOD

==Simplified Explanation==

The patent application describes a program stored on a recording medium that enables a computer to detect objects in images by combining information from two different models.

* Acquiring a first portion specifying a region in an image that includes a first object from a model trained on labeled training data.
* Generating a third model by combining the first portion with a third portion of a second model trained on training data with position information labeled for a second object.
* Outputting a detection result of an object by inputting an image to the third model.

== Potential Applications ==
This technology could be applied in various fields such as autonomous vehicles, surveillance systems, medical imaging, and robotics for object detection and recognition tasks.

== Problems Solved ==
This technology solves the problem of accurately detecting and recognizing objects in images by combining information from different models trained on labeled data.

== Benefits ==
The benefits of this technology include improved accuracy in object detection, enhanced performance in image analysis tasks, and the ability to handle complex scenes with multiple objects.

== Potential Commercial Applications ==
Potential commercial applications of this technology include developing advanced security systems, enhancing medical diagnostic tools, improving autonomous driving systems, and optimizing industrial automation processes.

== Possible Prior Art ==
One possible prior art for this technology could be the use of deep learning models for object detection and recognition in images, but the specific method of combining information from different models may be a novel aspect of this patent application.

=== What is the accuracy rate of object detection using this technology? ===

The patent application does not provide specific information on the accuracy rate of object detection using this technology.

=== How does this technology compare to existing object detection methods? ===

The patent application does not compare this technology to existing object detection methods.


==Original Abstract Submitted==

A recording medium storing a program for causing a computer to execute processing including: acquiring, from a first model trained based on training data in which the first object is labeled in an image, a first portion specifying a region in an image that includes a first object; generating a third model by combining the first portion and a third portion of a second model being a model that includes a second portion and the third portion and that is trained based on training data in which position information regarding the second object is labeled in an image, the second portion being a portion that specifies a region in an image including a second object, the third portion being a portion that determines a position in an image of a specified region; and outputting a detection result of an object by inputting an image to the third model.



[[Category:G06T7/73]]
[[Category:G06V10/22]]
[[Category:G06V10/44]]
[[Category:G06V10/74]]
[[Category:G06V10/774]]