JP2023109570A - 情報処理装置、学習装置、画像認識装置、情報処理方法、学習方法、画像認識方法 - Google Patents

情報処理装置、学習装置、画像認識装置、情報処理方法、学習方法、画像認識方法 Download PDF

Info

Publication number
JP2023109570A
JP2023109570A JP2022011140A JP2022011140A JP2023109570A JP 2023109570 A JP2023109570 A JP 2023109570A JP 2022011140 A JP2022011140 A JP 2022011140A JP 2022011140 A JP2022011140 A JP 2022011140A JP 2023109570 A JP2023109570 A JP 2023109570A
Authority
JP
Japan
Prior art keywords
image
learning
texture
information processing
region
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
JP2022011140A
Other languages
English (en)
Japanese (ja)
Other versions
JP2023109570A5 (https=
Inventor
建志 齋藤
Kenshi Saito
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Canon Inc
Original Assignee
Canon Inc
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 Canon Inc filed Critical Canon Inc
Priority to JP2022011140A priority Critical patent/JP2023109570A/ja
Priority to US18/157,100 priority patent/US20230237777A1/en
Publication of JP2023109570A publication Critical patent/JP2023109570A/ja
Publication of JP2023109570A5 publication Critical patent/JP2023109570A5/ja
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/54—Extraction of image or video features relating to texture
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/772—Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Image Analysis (AREA)
JP2022011140A 2022-01-27 2022-01-27 情報処理装置、学習装置、画像認識装置、情報処理方法、学習方法、画像認識方法 Pending JP2023109570A (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022011140A JP2023109570A (ja) 2022-01-27 2022-01-27 情報処理装置、学習装置、画像認識装置、情報処理方法、学習方法、画像認識方法
US18/157,100 US20230237777A1 (en) 2022-01-27 2023-01-20 Information processing apparatus, learning apparatus, image recognition apparatus, information processing method, learning method, image recognition method, and non-transitory-computer-readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2022011140A JP2023109570A (ja) 2022-01-27 2022-01-27 情報処理装置、学習装置、画像認識装置、情報処理方法、学習方法、画像認識方法

Publications (2)

Publication Number Publication Date
JP2023109570A true JP2023109570A (ja) 2023-08-08
JP2023109570A5 JP2023109570A5 (https=) 2025-01-23

Family

ID=87314294

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2022011140A Pending JP2023109570A (ja) 2022-01-27 2022-01-27 情報処理装置、学習装置、画像認識装置、情報処理方法、学習方法、画像認識方法

Country Status (2)

Country Link
US (1) US20230237777A1 (https=)
JP (1) JP2023109570A (https=)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220237902A1 (en) * 2019-06-17 2022-07-28 Nippon Telegraph And Telephone Corporation Conversion device, conversion learning device, conversion method, conversion learning method, conversion program, and conversion learning program
JP7565986B2 (ja) 2022-08-31 2024-10-11 キヤノン株式会社 画像処理装置およびその制御方法
CN117611600B (zh) * 2024-01-22 2024-03-29 南京信息工程大学 一种图像分割方法、系统、存储介质及设备
IL314858B2 (en) * 2024-08-08 2026-02-01 Geox Gis Innovations Ltd System and method for using semantic segmentation for object delineation

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017058930A (ja) * 2015-09-16 2017-03-23 日本電信電話株式会社 学習データ生成装置、学習装置、画像評価装置、学習データ生成方法、学習方法、画像評価方法及び画像処理プログラム
JP2020119127A (ja) * 2019-01-22 2020-08-06 日本金銭機械株式会社 学習用データ生成方法、プログラム、学習用データ生成装置、および、推論処理方法
JP2020197833A (ja) * 2019-05-31 2020-12-10 楽天株式会社 データ拡張システム、データ拡張方法、及びプログラム
KR102204041B1 (ko) * 2020-09-22 2021-01-18 주식회사 동신지티아이 지물이미지의 매핑을 위한 경계라인 수정 기능의 영상처리 오류보정 시스템
US20210279952A1 (en) * 2020-03-06 2021-09-09 Nvidia Corporation Neural rendering for inverse graphics generation

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017058930A (ja) * 2015-09-16 2017-03-23 日本電信電話株式会社 学習データ生成装置、学習装置、画像評価装置、学習データ生成方法、学習方法、画像評価方法及び画像処理プログラム
JP2020119127A (ja) * 2019-01-22 2020-08-06 日本金銭機械株式会社 学習用データ生成方法、プログラム、学習用データ生成装置、および、推論処理方法
JP2020197833A (ja) * 2019-05-31 2020-12-10 楽天株式会社 データ拡張システム、データ拡張方法、及びプログラム
US20210279952A1 (en) * 2020-03-06 2021-09-09 Nvidia Corporation Neural rendering for inverse graphics generation
KR102204041B1 (ko) * 2020-09-22 2021-01-18 주식회사 동신지티아이 지물이미지의 매핑을 위한 경계라인 수정 기능의 영상처리 오류보정 시스템

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
YUTA FUKATSU; MASAKI AONO: "3D Mesh Generation by Introducing Extended Attentive Normalization", 2021 8TH INTERNATIONAL CONFERENCE ON ADVANCED INFORMATICS: CONCEPTS, THEORY AND APPLICATIONS (ICAICT, JPN7025004178, 29 September 2021 (2021-09-29), ISSN: 0005801557 *
吉田 英史 HIDEFUMI YOSHIDA: "生成型学習法を用いた姿勢変化に頑健な歩行者検出の検討 A study on a method for stable pedestrian dete", 電子情報通信学会技術研究報告 ＶＯＬ．１１１ ＮＯ．４９ IEICE TECHNICAL REPORT, vol. 第111巻 第49号, JPN6025038977, 12 May 2011 (2011-05-12), pages 127 - 132, ISSN: 0005801556 *

Also Published As

Publication number Publication date
US20230237777A1 (en) 2023-07-27

Similar Documents

Publication Publication Date Title
US11748934B2 (en) Three-dimensional expression base generation method and apparatus, speech interaction method and apparatus, and medium
JP2023109570A (ja) 情報処理装置、学習装置、画像認識装置、情報処理方法、学習方法、画像認識方法
US12561956B2 (en) Affordance-based reposing of an object in a scene
CN107615310A (zh) 信息处理设备
EP3533218B1 (en) Simulating depth of field
US20240153188A1 (en) Physics-based simulation of dynamic character motion using generative artificial intelligence
EP4172862A1 (en) Object recognition neural network for amodal center prediction
CN113822965B (zh) 图像渲染处理方法、装置和设备及计算机存储介质
US20230290132A1 (en) Object recognition neural network training using multiple data sources
US20220292690A1 (en) Data generation method, data generation apparatus, model generation method, model generation apparatus, and program
US10893252B2 (en) Image processing apparatus and 2D image generation program
CN115023742A (zh) 具有详细褶皱的面部网格变形
CN110910478B (zh) Gif图生成方法、装置、电子设备及存储介质
JP2019016164A (ja) 学習データ生成装置、推定装置、推定方法及びコンピュータプログラム
CN111079535B (zh) 一种人体骨架动作识别方法、装置及终端
CN117218246A (zh) 图像生成模型的训练方法、装置、电子设备及存储介质
CN114445676B (zh) 一种手势图像处理方法、存储介质及设备
CN111382618A (zh) 一种人脸图像的光照检测方法、装置、设备和存储介质
Zhao et al. End-to-end image colorization with multiscale pyramid transformer
US10791321B2 (en) Constructing a user's face model using particle filters
JP7267068B2 (ja) 学習済みモデル生成装置、プログラム及び学習済みモデル生成システム
CN115018979B (zh) 图像重建方法、装置、电子设备、存储介质和程序产品
JP6967150B2 (ja) 学習装置、画像生成装置、学習方法、画像生成方法及びプログラム
JP7662984B2 (ja) 三次元形状モデル生成装置、三次元形状モデル生成方法、及びプログラム
CN112991179B (zh) 用于输出信息的方法、装置、设备以及存储介质

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20250115

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20250115

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20250916

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20250926

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20251125

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20260224

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20260427