18518787. ELECTRONIC DEVICE PERFORMING SCALING USING ARTIFICIAL INTELLIGENCE MODEL AND METHOD FOR OPERATING THE SAME simplified abstract (Samsung Electronics Co., Ltd.)

From WikiPatents
Jump to navigation Jump to search

ELECTRONIC DEVICE PERFORMING SCALING USING ARTIFICIAL INTELLIGENCE MODEL AND METHOD FOR OPERATING THE SAME

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Taewon Do of Suwon-si (KR)

Yongtae Kim of Suwon-si (KR)

Hoonjae Lee of Suwon-si (KR)

Gautam Tushar of Suwon-si (KR)

Hyeyoung Jun of Suwon-si (KR)

ELECTRONIC DEVICE PERFORMING SCALING USING ARTIFICIAL INTELLIGENCE MODEL AND METHOD FOR OPERATING THE SAME - A simplified explanation of the abstract

This abstract first appeared for US patent application 18518787 titled 'ELECTRONIC DEVICE PERFORMING SCALING USING ARTIFICIAL INTELLIGENCE MODEL AND METHOD FOR OPERATING THE SAME

Simplified Explanation

The electronic device described in the patent application utilizes artificial intelligence to down-scale images based on communication environment and bitrate information.

  • The electronic device includes memory, a camera module, a communication module, and at least one processor.
  • The memory, when executed by the processor, allows the device to establish a call connection with a network.
  • The device identifies a first image captured by the camera module and associated information on bitrate.
  • Based on the communication environment, the device identifies a second image output from an artificial intelligence model for down-scaling.
  • The artificial intelligence model is trained to receive high-resolution image information and bitrate as input to output a low-resolution image.
  • The second image is transmitted through the call connection.

---

      1. Potential Applications

This technology could be applied in video conferencing systems, surveillance cameras, and remote monitoring devices.

      1. Problems Solved

This technology addresses the challenge of optimizing image quality based on communication environment and bitrate constraints.

      1. Benefits

The benefits of this technology include improved image transmission efficiency, reduced bandwidth usage, and enhanced user experience in visual communication.

      1. Potential Commercial Applications

Potential commercial applications of this technology include video streaming services, telemedicine platforms, and online gaming networks.

      1. Possible Prior Art

One possible prior art for this technology could be image compression algorithms used in video streaming services.

---

    1. Unanswered Questions
      1. How does the artificial intelligence model determine the optimal resolution for down-scaling images?

The patent application does not provide specific details on the decision-making process of the artificial intelligence model in determining the optimal resolution for down-scaling images.

      1. What are the potential limitations of using artificial intelligence for down-scaling images in real-time communication applications?

The patent application does not address the potential limitations or challenges that may arise when implementing artificial intelligence for down-scaling images in real-time communication applications.


Original Abstract Submitted

An electronic device is provided. The electronic device includes memory, a camera module, a communication module, and at least one processor operatively connected to the memory, the camera module, and the communication module. The memory, when executed by the at least one processor, cause the electronic device to establish a call connection with a network based on the communication module, identify a first image captured based on the camera module, identify first information associated with a first bitrate corresponding to the first image, based on a communication environment between the network and the electronic device, identify a second image corresponding to the first image output from an artificial intelligence model for down-scaling, trained to receive information associated with a high-resolution image and a bitrate as an input value to output a low-resolution image, by inputting the first image and the first information to the artificial intelligence model, and transmit the second image through the call connection.