Ai encoding apparatus and operation method of the same, and ai decoding apparatus and operation method of the same

a technology of encoding apparatus and operation method, applied in the field of artificial intelligence (ai) encoding apparatus, can solve problems such as transformation error, and achieve the effect of minimizing the transformation error

Inactive Publication Date: 2020-04-23
SAMSUNG ELECTRONICS CO LTD
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The patent describes an AI decoding system that can reduce errors when expressing intermediate results from a second DNN. The system minimizes these errors by using a low precision approach. The technical effect of this invention is to improve the accuracy and efficiency of AI decoding.

Problems solved by technology

When low-precision transformation is performed, a transformation error may occur, and thus, a method of minimizing this transformation error is needed.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Ai encoding apparatus and operation method of the same, and ai decoding apparatus and operation method of the same
  • Ai encoding apparatus and operation method of the same, and ai decoding apparatus and operation method of the same
  • Ai encoding apparatus and operation method of the same, and ai decoding apparatus and operation method of the same

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053]Embodiments of the disclosure provide apparatuses and methods for performing artificial intelligence (AI) encoding and AI decoding on an image, wherein an image is encoded and decoded based on AI to achieve a low bitrate and minimize a low-precision transformation error.

[0054]As the disclosure allows for various changes and numerous examples, embodiments will be illustrated in the drawings and described in detail in the written description. However, this is not intended to limit the disclosure to modes of practice, and it will be understood that all changes, equivalents, and substitutes that do not depart from the spirit and technical scope of the disclosure are encompassed in the disclosure.

[0055]In the description of embodiments, detailed explanations of related art are omitted when it is deemed that they may unnecessarily obscure the essence of the disclosure. Also, numbers (for example, a first, a second, and the like) used in the description of the specification are ident...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Provided is an artificial intelligence (AI) decoding apparatus including a memory storing one or more instructions; and a processor configured to execute the one or more instructions to, when an image is input to a second DNN including a plurality of layers, obtain first result values based on an operation between the image and a first filter kernel and obtain second result values based on an operation between the image and a second filter kernel, from a first layer including the first and second filter kernels from among the plurality of layers, perform normalization by transforming the first result values into first values by using a first scale factor, and, perform normalization by transforming the second result values into second values by using a second scale factor, transform the first values and the second values into integer values included in a preset range.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]This application is based on and claims priority under 35 U.S.C. ยง 119 to Korean Patent Application No. 10-2018-0125406, filed on Oct. 19, 2018, Korean Patent Application No. 10-2018-0148905, filed on Nov. 27, 2018, Korean Patent Application No. 10-2019-0041100, filed on Apr. 8, 2019, and Korean Patent Application No. 10-2019-0078344, filed on Jun. 28, 2019, in the Korean Intellectual Property Office, the disclosures of which are incorporated by reference herein in their entireties.BACKGROUND1. Field[0002]The disclosure relates to an artificial intelligence (AI) encoding apparatus including a deep neural network (DNN) for AI-downscaling an image and an operation method of the AI encoding apparatus and an AI decoding apparatus including a DNN for AI-upscaling an image and an operation method of the AI decoding apparatus, and more particularly, to an AI encoding apparatus for reducing the amounts of memory and calculation necessary for perf...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityApplications(United States)
IPC IPC(8): G06T9/00G06T3/40G06K9/62
CPCG06T2207/20081G06K9/6256G06T3/4046G06T9/002G06T2207/20084G06K9/6232H04N19/59G06N3/084G06N3/063H04N19/102H04N19/117H04N19/136H04N19/157H04N19/154H04N19/192H04N19/85H04N19/80G06V10/454G06V10/82G06V10/7715G06N3/048G06N3/044G06N3/045G06N3/02G06F18/214
InventorDINH, QUOCKHANHCHOI, MINSEOKCHOI, KWANGPYO
OwnerSAMSUNG ELECTRONICS CO LTD