WO2023024660A1 - Procédé et appareil d'optimisation d'image - Google Patents

Procédé et appareil d'optimisation d'image Download PDF

Info

Publication number
WO2023024660A1
WO2023024660A1 PCT/CN2022/098754 CN2022098754W WO2023024660A1 WO 2023024660 A1 WO2023024660 A1 WO 2023024660A1 CN 2022098754 W CN2022098754 W CN 2022098754W WO 2023024660 A1 WO2023024660 A1 WO 2023024660A1
Authority
WO
WIPO (PCT)
Prior art keywords
value
pixel
processed
comparison
image
Prior art date
Application number
PCT/CN2022/098754
Other languages
English (en)
Chinese (zh)
Inventor
刘俊
Original Assignee
深圳前海微众银行股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳前海微众银行股份有限公司 filed Critical 深圳前海微众银行股份有限公司
Publication of WO2023024660A1 publication Critical patent/WO2023024660A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Definitions

  • FIG. 10 is a schematic diagram of a target enhanced image provided by an embodiment of the present invention.
  • the brightness values corresponding to the pixels in the first comparison group are M1, M2, and M3 respectively, the brightness value of the first pixel is L0, the first preset weight is A1, and the second preset weight is 1- A1, then it can be determined that the first mean value is: (M1+M2+M3), the first product value is: (M1+M2+M3)*A1, and the second product value is L0*(1-A1), so that it can be determined The sum value is: (M1+M2+M3)*A1+L0*(1-A1).
  • the computer device may adopt but not limited to the following steps to determine the target enhanced image, as shown in FIG. 8 .
  • the second processing unit 1103 is specifically configured to: determine the transparency value, red color value, green color value, and blue color value corresponding to the first comparison pixel group; performing weighted average processing on the transparency value, red color value, green color value and blue color value corresponding to the pixel group, to obtain the transparency adjustment value, red color adjustment value, green color adjustment value and Blue color adjustment value; the transparency adjustment value, red color adjustment value, green color adjustment value and blue color adjustment value corresponding to the first pixel to be processed are spliced into a binary number of the target value type, and the binary number as the first color value of the first pixel to be processed.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Processing (AREA)

Abstract

Sont divulgués un procédé et un appareil d'optimisation d'image. Le procédé consiste à : effectuer un traitement d'agrandissement sur une image de trame à traiter pour obtenir une image de trame agrandie ; déterminer une image de trame en niveaux de gris correspondant à l'image de trame agrandie ; effectuer un traitement d'affinement sur l'image de trame en niveaux de gris pour obtenir une première image traitée, une nouvelle valeur de luminance de chaque premier pixel dans la première image traitée, et des premiers groupes de pixels de référence utilisés pour déterminer la nouvelle valeur de luminance de chaque premier pixel ; sélectionner à partir de l'image de trame agrandie un premier groupe de pixels de comparaison au niveau de la même position que n'importe quel premier groupe de pixels de référence, et un premier pixel à traiter au niveau de la même position qu'un premier pixel correspondant ; sur la base d'une valeur de couleur correspondant au premier groupe de pixels de comparaison, effectuer un traitement d'ajustement de luminance sur une valeur de couleur du premier pixel à traiter, pour obtenir une première valeur de couleur du premier pixel à traiter ; et, sur la base d'une première valeur de couleur de chaque premier pixel à traiter, obtenir une première image optimisée correspondant à l'image de trame à traiter.
PCT/CN2022/098754 2021-08-23 2022-06-14 Procédé et appareil d'optimisation d'image WO2023024660A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110969933.1A CN113689333A (zh) 2021-08-23 2021-08-23 一种图像增强的方法及装置
CN202110969933.1 2021-08-23

Publications (1)

Publication Number Publication Date
WO2023024660A1 true WO2023024660A1 (fr) 2023-03-02

Family

ID=78581524

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/098754 WO2023024660A1 (fr) 2021-08-23 2022-06-14 Procédé et appareil d'optimisation d'image

Country Status (2)

Country Link
CN (1) CN113689333A (fr)
WO (1) WO2023024660A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113689333A (zh) * 2021-08-23 2021-11-23 深圳前海微众银行股份有限公司 一种图像增强的方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6674903B1 (en) * 1998-10-05 2004-01-06 Agfa-Gevaert Method for smoothing staircase effect in enlarged low resolution images
CN102063703A (zh) * 2009-11-18 2011-05-18 夏普株式会社 用于增强输入图像的系统、图像显示系统和用于图像增强的方法
WO2012168985A1 (fr) * 2011-06-10 2012-12-13 株式会社島津製作所 Procédé de traitement d'images et appareil associé
CN109035166A (zh) * 2018-07-16 2018-12-18 国网四川省电力公司巴中供电公司 基于非下采样剪切波变换的电气设备红外图像增强方法
CN113689333A (zh) * 2021-08-23 2021-11-23 深圳前海微众银行股份有限公司 一种图像增强的方法及装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100306756B1 (ko) * 1999-11-02 2001-11-02 윤종용 명도 성분에 기반한 칼라 화상의 윤곽선 강조 방법
CN109785240B (zh) * 2017-11-13 2021-05-25 中国移动通信有限公司研究院 一种低照度图像增强方法、装置及图像处理设备
KR102215607B1 (ko) * 2019-12-17 2021-02-15 주식회사 한글과컴퓨터 어두운 이미지의 밝기를 개선하기 위한 보정 처리가 가능한 전자 장치 및 그 동작 방법
CN113018856A (zh) * 2021-03-30 2021-06-25 网易（杭州）网络有限公司 图像处理方法、装置、电子设备及存储介质
CN113096014B (zh) * 2021-03-31 2023-12-08 咪咕视讯科技有限公司 视频超分处理方法、电子设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6674903B1 (en) * 1998-10-05 2004-01-06 Agfa-Gevaert Method for smoothing staircase effect in enlarged low resolution images
CN102063703A (zh) * 2009-11-18 2011-05-18 夏普株式会社 用于增强输入图像的系统、图像显示系统和用于图像增强的方法
WO2012168985A1 (fr) * 2011-06-10 2012-12-13 株式会社島津製作所 Procédé de traitement d'images et appareil associé
CN109035166A (zh) * 2018-07-16 2018-12-18 国网四川省电力公司巴中供电公司 基于非下采样剪切波变换的电气设备红外图像增强方法
CN113689333A (zh) * 2021-08-23 2021-11-23 深圳前海微众银行股份有限公司 一种图像增强的方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ANONYMOUS: "GitHub - h5mcbox/anime4k: A High-Quality Real Time Upscaler for Anime Video", XP093040002, Retrieved from the Internet <URL:https://github.com/h5mcbox/anime4k> [retrieved on 20230418] *

Also Published As

Publication number Publication date
CN113689333A (zh) 2021-11-23

Similar Documents

Publication Publication Date Title
US11537873B2 (en) Processing method and system for convolutional neural network, and storage medium
JP2020113301A (ja) 非正規直交グリッドへのテクスチャマッピングのためのグラデーションの調整
JP6639877B2 (ja) 映像処理装置及び方法
CN105023234B (zh) 基于嵌入式系统存储优化的图形加速方法
CN108022223B (zh) 一种基于对数映射函数分块处理融合的色调映射方法
CN103778900B (zh) 一种图像处理方法及系统
US9565414B2 (en) Efficient stereo to multiview rendering using interleaved rendering
JPH03212685A (ja) 表示の解像度を高める装置と方法
US11544818B2 (en) Enhancing high-resolution images with data from low-resolution images
JP2002537615A (ja) スーパサンプリング・サンプル・バッファを有し、アーチファクトを縮小するため選択的フィルタリング調節を使用して出力ピクセルを生成するグラフィックス・システム。
WO2023024660A1 (fr) Procédé et appareil d&#39;optimisation d&#39;image
KR20120015980A (ko) 오브젝트 색상 보정 방법, 시스템 및 컴퓨터 프로그램 제품
US20170274285A1 (en) Method and apparatus for automating the creation of a puzzle pix playable on a computational device from a photograph or drawing
CN108122216A (zh) 用于数字图像的动态范围扩展的系统和方法
CN116703777A (zh) 一种图像处理方法、系统、存储介质及电子设备
CN111724313A (zh) 一种阴影贴图生成方法与装置
CN113837945B (zh) 一种基于超分辨率重建的显示画质优化方法及系统
CN105469367B (zh) 动态视频图像清晰度强化方法及装置
WO2020241337A1 (fr) Dispositif de traitement d&#39;image
CN111798393A (zh) 图像处理方法及装置、电子设备及存储介质
US8698832B1 (en) Perceptual detail and acutance enhancement for digital images
Pang et al. Subpixel-based image scaling for grid-like subpixel arrangements: A generalized continuous-domain analysis model
CN111815547A (zh) 图像处理方法及装置、电子设备及存储介质
WO2023044653A1 (fr) Système de dispositif d&#39;affichage et procédé d&#39;amélioration adaptative de qualité d&#39;image
CN106847149B (zh) 一种高动态对比度图像的色调映射与显示方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22860007

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE