WO2023033469A1 - Procédé de rognage 3d d'image médicale et dispositif associé - Google Patents

Procédé de rognage 3d d'image médicale et dispositif associé Download PDF

Info

Publication number
WO2023033469A1
WO2023033469A1 PCT/KR2022/012852 KR2022012852W WO2023033469A1 WO 2023033469 A1 WO2023033469 A1 WO 2023033469A1 KR 2022012852 W KR2022012852 W KR 2022012852W WO 2023033469 A1 WO2023033469 A1 WO 2023033469A1
Authority
WO
WIPO (PCT)
Prior art keywords
cropping
cross
input
sectional
cropped
Prior art date
Application number
PCT/KR2022/012852
Other languages
English (en)
Korean (ko)
Inventor
이준호
Original Assignee
인그래디언트 주식회사
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 인그래디언트 주식회사 filed Critical 인그래디언트 주식회사
Publication of WO2023033469A1 publication Critical patent/WO2023033469A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing

Definitions

  • the present invention relates to a method and an apparatus for 3D cropping of a medical imaging image. More specifically, it relates to a method and apparatus capable of easily and quickly implementing 3D cropping of an image only by setting a bounding box in two stages.
  • image cropping of the region is required.
  • 3D cropping based on 3D image images three It is necessary to operate to set the area on each side. At this time, assuming that it is necessary to set the area twice horizontally and vertically to set the area of each side, 3D cropping is possible through at least six mouse operations.
  • An object of the present invention is to provide a more efficient and rapid 3D cropping method and apparatus capable of quickly completing a 3D cropping operation with only two steps.
  • an object of the present invention is to provide a 3D cropping method and apparatus capable of obtaining a 3D cropped image in accordance with the input size limit of an artificial intelligence model.
  • an object of the present invention is to provide a UX/UI of a cropping tool capable of more quickly completing a 3D cropping operation of a medical imaging image in accordance with a user's intention.
  • a method for 3D cropping a medical imaging image includes receiving a medical imaging image; displaying at least three cross-sectional views related to the medical imaging image; receiving a first cropping input for a first cross-section of the three cross-sections; receiving a second cropping input for a second cross-section of the three cross-sections; and determining a 3D cropping area based on the first cropping input and the second cropping input, wherein the three cross-sectional views include a transverse cross-sectional view, a sagittal cross-sectional view, and a coronal cross-sectional view.
  • a ping method can be provided.
  • first cropping input and the second cropping input may be inputs for setting a bounding box by a user.
  • an area other than the first cropped area may be displayed translucently.
  • the size of the first cropped region may be displayed, and the first cropping input may be configurable within a limit of a predetermined image size.
  • the first cropped area is reset based on the second cropped area.
  • a computer readable recording medium storing a program for implementing the method described above may be provided.
  • an apparatus for 3D cropping a medical imaging image includes an image receiving unit configured to receive a medical imaging image; and displaying at least three cross-sectional views related to the medical imaging image, receiving a first cropping input for a first cross-sectional view among the three cross-sectional views, and receiving a second cropping input for a second cross-sectional view among the three cross-sectional views. and a 3D cropping processing unit configured to receive and determine a 3D cropping area based on the first cropping input and the second cropping input, wherein the three cross-sectional views include a transverse cross-sectional view, a sagittal cross-sectional view, and a coronal cross-sectional view.
  • the three cross-sectional views include a transverse cross-sectional view, a sagittal cross-sectional view, and a coronal cross-sectional view.
  • first cropping input and the second cropping input may be inputs for setting a bounding box by a user.
  • the 3D cropping processing unit divides and displays the first cropped area in the first cross-section according to the first cropping input, and displays the first cropped area in the second and third cross-sectional views, respectively. It may be configured to automatically distinguish and display the first cropped region to correspond to the region.
  • the 3D cropping processing unit may be configured to display an area other than the first cropped area translucently.
  • the size of the first cropped region may be displayed, and the first cropping input may be configurable within a limit of a predetermined image size.
  • the 3D cropping processing unit divides and displays a second cropped area in the second cross-sectional view according to a second cropping input for the second cross-sectional view, and respectively displays the first cropped area in the first cross-sectional view and the third cross-sectional view. It may be configured to automatically distinguish and display the second cropped area to correspond to the second cropped area.
  • the 3D cropping processing unit when the size of the second cropped area is set to be different from the size corresponding to the first cropped area, based on the second cropped area, the first cropped area You can reset the cropped area.
  • the 3D cropping processor may perform a third cropping operation in the first or third cross-sectional view when the second cropped area and the first cropped area overlap less than a predetermined criterion.
  • an object of the present invention is to provide a 3D cropping method and apparatus capable of obtaining a 3D cropped image in accordance with the input size limit of an artificial intelligence model.
  • an object of the present invention is to provide a UX/UI of a cropping tool capable of more quickly completing a 3D cropping operation of a medical imaging image in accordance with a user's intention.
  • 1 is an exemplary diagram for explaining 3D cropping of a medical imaging image.
  • FIG. 2 is a block diagram for explaining the configuration of a medical image 3D cropping device according to an embodiment of the present invention.
  • 3A to 3D are screen views illustrating a 3D cropping method of a medical imaging image according to an embodiment of the present invention.
  • FIG. 4 is a flowchart illustrating a method of 3D cropping a medical imaging image according to an embodiment of the present invention.
  • each component is listed and described as each component for convenience of description, and at least two components of each component may be combined to form one component, or one component may be divided into a plurality of components to perform a function.
  • An integrated embodiment and a separate embodiment of each of these components are also included in the scope of the present invention unless departing from the essence of the present invention.
  • 1 is an exemplary diagram for explaining 3D cropping of a medical imaging image.
  • a three-dimensional (3D) medical imaging image is shown, and a cropped image obtained by selecting and cropping only a region of interest from an image on the left is shown on the right.
  • the size of the image may be reduced by cropping the image.
  • the cropping area is set by setting the vertical and horizontal lengths in three planes, such as a transverse cross section, a sagittal cross section, and a coronal cross section, respectively. Since 3D cropping is completed through six size setting operations, there are problems in that it takes a long time and requires a lot of user's manual operation. In addition, when the cropping setting is wrong on one side, there is a hassle of having to reset the cropping setting on the entire side.
  • FIG. 2 is a block diagram for explaining the configuration of a medical image 3D cropping device according to an embodiment of the present invention.
  • the apparatus for 3D cropping medical images may be composed of a terminal capable of receiving, processing, and displaying various data via a wired/wireless communication network according to input/output operations of a user.
  • a desktop computer Laptop computers, notebooks, smart phones, tablet computers, workstations, personal digital assistants (PDAs), portable computers, wireless phones, mobile phones ( mobile phone), e-book, portable multimedia player (PMP), portable game machine, navigation device, black box, digital camera, television, wearable device (wearable device), a voice recognition speaker, a smart speaker, and an artificial intelligence (AI) speaker, but is not limited thereto.
  • the medical image 3D cropping apparatus may include a program or program module that can be executed by one or more processors, and may receive a user input in conjunction with the user input unit 230, and display unit In conjunction with (240), the processed result can be output.
  • the programs or program modules included in the 3D cropping processing unit 220 may be configured in the form of an operating system, application program, or program, and may be stored on various types of widely used storage devices. can be physically stored in Such a program or program module includes one or more routines, subroutines, programs, objects, components, instructions, data structures, and specific tasks ( It may include various forms for performing tasks) or executing specific data types, but is not limited to these forms.
  • the image receiver 210 is configured to receive a medical imaging image.
  • the image receiving unit 210 may receive a plurality of medical imaging images by directly or indirectly communicating with an external device through the communication unit.
  • the medical imaging image received by the image receiver 210 may be transferred to the 3D cropping processor 220, and the medical imaging image may include 3D images and 2D images.
  • the 3D cropping processing unit 220 displays at least three cross-sectional views related to the medical imaging image through the display unit 240, and displays a first cross-sectional view among the three cross-sectional views (including the first cross-sectional view, the second cross-sectional view, and the third cross-sectional view).
  • Receives a first cropping input for a second cross-section of three cross-sections receives a second cropping input for a second cross-sectional view, and generates a 3D cropping area based on the first cropping input and the second cropping input through two steps. It can be configured to determine.
  • the three sectional views may include a transverse sectional view, a sagittal sectional view, and a coronal sectional view.
  • first cropping input and the second cropping input received from the user through the user input unit 230 may be inputs for setting a rectangular bounding box having a horizontal length and a vertical length, but are not limited thereto. don't
  • the 3D cropping processing unit 220 may divide and display the first cropped region in the first cross-sectional view according to the first cropping input.
  • the cropping area may be displayed to be distinguished by displaying an area other than the first cropped area selected by the user in a translucent color or a different color.
  • cropping is automatically performed to correspond to the first cropped region in the second and third cross-sectional views, and the regions corresponding to the first cropped region are separately displayed in the second and third cross-sectional views. can do.
  • regions other than the first cropped region may be marked translucently or displayed in a different color to distinguish the cropped region.
  • the 3D cropping processing unit 220 may inform the user of the cropping size in advance by displaying the size of the first cropped region, for example, the horizontal length and the vertical length, as pixel sizes through the display unit 240 .
  • the user may proceed with cropping to a desired size on a desired region of interest while checking the size of the cropping size while adjusting the bounding box.
  • the 3D cropping processing unit 220 may set a bounding box for cropping within a limit of a predetermined image size. Since an input size limit may exist in an artificial intelligence model, the limit on the setting size of the bounding box may be set in advance according to the input size limit of the artificial intelligence model to be suitable for use as a training dataset of the artificial intelligence model. For example, if the input size limit of the artificial intelligence model is 128 pixels, the user input may be limited so that the length of the bounding box does not exceed 128 pixels.
  • the 3D cropping processing unit 220 divides and displays the second cropped area in the second cross-sectional view according to the second cropping input for the second cross-sectional view after the first cropping input, and displays the second cropped area in the first cropping operation.
  • the second cropped area may be automatically distinguished and displayed to correspond to the second cropped area in the remaining cross-sectional views, that is, the first cross-sectional view and the third cross-sectional view, respectively.
  • the size of the second cropped area is set to be different from the size corresponding to the first cropped area
  • the first cropped area is determined based on the second cropped area through the second user input. can be reset.
  • the corresponding horizontal size of the first cropped region may be reset to be equally wide. .
  • the most recent cropping setting value is reset by resetting the previous cropping area based on the last cropping input value. can be given priority.
  • the second cropped region and the first cropped region overlap by less than a predetermined criterion, for example, the second cropped region and the first cropped region are completely out of alignment and overlap each other.
  • the first cropped area is ignored, and the third cropping input is applied again in the first or third cross-section based on the second cropped area performed in the second cross-section. received, and a 3D cropping area may be determined based on the second cropping input and the third cropping input.
  • the present invention can efficiently and quickly complete 3D cropping through only two-step cropping, and only when the two cropped areas and the first cropped area completely deviate, the user's intention is changed to the first cropped area. It is determined that the region is ignored, and a third cropping input is performed again based on the second cropped region to complete 3D cropping.
  • the user input unit 230 uses a touch pad, a touch panel, a key pad, a mouse, a keyboard, and a dome switch to receive various inputs for user manipulation and selection.
  • a touch pad a touch panel
  • a key pad a mouse
  • a keyboard a keyboard
  • a dome switch to receive various inputs for user manipulation and selection.
  • (dome switch), a physical button, a jog shuttle (jog shuttle) and a sensor (sensor) may include an input unit composed of at least one, but is not limited thereto.
  • the display unit 240 serves to show output results to a user, and the display unit 221 may be, for example, a liquid crystal display (LCD), a light emitting diode (LED) display, or an organic light emitting diode (OLED) display.
  • LCD liquid crystal display
  • LED light emitting diode
  • OLED organic light emitting diode
  • organic LED displays
  • micro LEDs micro electro mechanical systems
  • electronic paper displays but is not limited thereto.
  • such a display unit 240 may be combined with the user input unit 230 and implemented in the form of a touch screen.
  • 3A to 3D are screen views illustrating a 3D cropping method of a medical imaging image according to an embodiment of the present invention.
  • three cross-sectional views may be displayed through the display unit 240, and for example, three cross-sectional views may be displayed as a horizontal cross-sectional view 301, a sagittal cross-sectional view 302, and a coronal cross-sectional view 303.
  • the user may perform cropping input such as a bounding box through the user input unit 230, and, for example, as shown in FIG. A first cropping input may be performed.
  • an area other than the bounding box may be displayed separately, for example, an area other than the cropping area, that is, the bounding Areas other than the box area can be displayed by distinguishing the cropped area from the entire image by displaying them in translucency or a different color.
  • cropping is automatically performed in each of the sagittal cross section 302 and the coronal cross section 303 in response to the cropping input set as the horizontal length a and the vertical length b in the transverse cross section 310, respectively.
  • the first cropped regions 320 and 330 may be displayed. Referring to FIG.
  • the horizontal length of the first cropped region 320 of the sagittal cross section 302 corresponds to the vertical length of the transverse cross section 310, it is set to b, and the first cropped area of the coronal cross section 303 corresponds to the vertical length. It can be seen that the horizontal length of the cropped region 330 is set to a because it corresponds to the horizontal length of the cross-sectional view 310 .
  • the user may check a screen in which 3D cropping is completed by setting a second bounding box for the second cropping.
  • the bounding box of the first cropping input is based on the last cropping input.
  • the horizontal length of (the bounding box of the transverse cross section 310) can be reset to a' greater than a, and the vertical length of the sagittal cross section 302 is automatically set to c corresponding to the vertical length c of the coronal cross section 303.
  • the second cropping may be performed with In this way, 3D cropping can be completed quickly through only two-step bounding box setting input through the first cropping and the second cropping.
  • the second cropped region and the first cropped region overlap by a predetermined criterion or less, for example, the second cropped region and the first cropped region
  • the first cropped area is ignored and the transverse cross section 301 is again based on the second cropped area performed in the coronal section 303.
  • a third cropping input may be received from the sagittal cross-sectional view 302 , and a 3D cropping area may be finally determined based on the second cropping input and the third cropping input.
  • the size of the bounding box 310 may be previously informed of the horizontal length 341 and the vertical length 342 as numerical values equal to the pixel size. .
  • the user can check the size of the bounding box in advance while adjusting the setting area of the bounding box. For example, when the image input size of an artificial intelligence model is limited to 128 x 96 pixels in width, the size setting of the bounding box 310 for cropping is set to 128 x 96 pixels in order to generate the input data of the corresponding artificial intelligence model. You can set a limit value so that the vertical size does not exceed 96 pixels.
  • FIG. 4 is a flowchart illustrating a method of 3D cropping a medical imaging image according to an embodiment of the present invention.
  • a medical imaging image may be received through the image receiver 210 (S410).
  • the received image includes not only a 3D image but also a transverse cross-sectional view, a sagittal cross-sectional view, and a coronal cross-sectional view corresponding to the corresponding 3D image. can do.
  • three cross-sectional views for example, a transverse cross-sectional view, a sagittal cross-sectional view, and a coronal cross-sectional view, may be displayed through the display unit 240 (S420).
  • the 3D grouping processing unit 220 may receive the first cropping input.
  • the first cropping may be applied to all three cross-sections by applying the first cropping to the second and third cross-sections to correspond thereto (S440).
  • the 3D grouping processing unit 220 may receive the second cropping input.
  • step S440 based on the second cropping input for the second cross-section, the second cropping is applied to all three cross-sections by applying the second cropping to the remaining first and third cross-sections to correspond thereto.
  • step S460 At this time, by resetting the setting value of the first cropping input based on the last cropping input, the value changed through the second cropping is determined as the final setting value intended by the user and applied. An error in the first cropping input may be corrected in the second cropping input.
  • the user's intention sets the cropping area differently than before. Recognize that, it may receive a third cropping input again, apply 3D cropping based on the second cropping input and the third cropping input, and complete it.
  • various embodiments described in this specification may be implemented by hardware, middleware, microcode, software, and/or combinations thereof.
  • various embodiments may include one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), ), processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions presented herein, or combinations thereof.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGAs field programmable gate arrays
  • processors controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions presented herein, or combinations thereof.
  • various embodiments may be embodied or encoded in a computer-readable medium containing instructions. Instructions embodied or encoded on a computer-readable medium can cause a programmable processor or other processor to perform a method, for example when the instructions are executed.
  • Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another.
  • a storage medium may be any available medium that can be accessed by a computer.
  • such computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage medium, magnetic disk storage medium or other magnetic storage device, or instructions or data accessible by a computer that contains desired program code. any other medium that can be used for transport or storage in the form of structures.
  • Such hardware, software, firmware, etc. may be implemented within the same device or within separate devices to support the various operations and functions described herein. Additionally, components, units, modules, components, etc., described as "-units" in the present invention may be implemented together or separately as separate but interoperable logic devices. Depiction of different features for modules, units, etc. is intended to highlight different functional embodiments and does not necessarily mean that they must be realized by separate hardware or software components. Rather, functionality associated with one or more modules or units may be performed by separate hardware or software components or integrated within common or separate hardware or software components.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

La présente invention concerne un procédé de rognage 3D d'une image médicale, comportant des étapes consistant à: recevoir une image médicale; afficher au moins trois vues en coupe liées à l'image médicale; recevoir une première entrée de rognage pour une première vue en coupe parmi les trois vues en coupe; recevoir une seconde entrée de rognage pour une seconde vue en coupe parmi les trois vues en coupe; et déterminer une zone de rognage 3D sur la base de la première entrée de rognage et de la seconde entrée de rognage, les trois vues en coupe incluant une vue en coupe, une vue en coupe superficielle, et une vue en coupe tubulaire.
PCT/KR2022/012852 2021-08-30 2022-08-29 Procédé de rognage 3d d'image médicale et dispositif associé WO2023033469A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2021-0114623 2021-08-30
KR1020210114623A KR102385689B1 (ko) 2021-08-30 2021-08-30 의료 영상 이미지의 3d 크롭핑 방법 및 이를 위한 장치

Publications (1)

Publication Number Publication Date
WO2023033469A1 true WO2023033469A1 (fr) 2023-03-09

Family

ID=81211198

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/012852 WO2023033469A1 (fr) 2021-08-30 2022-08-29 Procédé de rognage 3d d'image médicale et dispositif associé

Country Status (2)

Country Link
KR (1) KR102385689B1 (fr)
WO (1) WO2023033469A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102385689B1 (ko) * 2021-08-30 2022-04-14 인그래디언트 주식회사 의료 영상 이미지의 3d 크롭핑 방법 및 이를 위한 장치

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080031505A1 (en) * 2006-08-04 2008-02-07 Eastman Kodak Company Method for producing a cropped medical image
US20080123895A1 (en) * 2006-11-27 2008-05-29 Todd Gable Method and system for fast volume cropping of three-dimensional image data
JP2019195609A (ja) * 2017-11-26 2019-11-14 キヤノン ユーエスエイ, インコーポレイテッドCanon U.S.A., Inc 高度な自動デバイス画像間の位置合わせのための自動画像クロップ
US20210065360A1 (en) * 2019-08-29 2021-03-04 Varian Medical Systems International Ag Systems and methods for image cropping and anatomical structure segmentation in medical imaging
KR102385689B1 (ko) * 2021-08-30 2022-04-14 인그래디언트 주식회사 의료 영상 이미지의 3d 크롭핑 방법 및 이를 위한 장치

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102378746B1 (ko) 2019-08-16 2022-03-25 서울여자대학교 산학협력단 의료 영상에서 딥러닝에 기반한 복부 장기 자동분할 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080031505A1 (en) * 2006-08-04 2008-02-07 Eastman Kodak Company Method for producing a cropped medical image
US20080123895A1 (en) * 2006-11-27 2008-05-29 Todd Gable Method and system for fast volume cropping of three-dimensional image data
JP2019195609A (ja) * 2017-11-26 2019-11-14 キヤノン ユーエスエイ, インコーポレイテッドCanon U.S.A., Inc 高度な自動デバイス画像間の位置合わせのための自動画像クロップ
US20210065360A1 (en) * 2019-08-29 2021-03-04 Varian Medical Systems International Ag Systems and methods for image cropping and anatomical structure segmentation in medical imaging
KR102385689B1 (ko) * 2021-08-30 2022-04-14 인그래디언트 주식회사 의료 영상 이미지의 3d 크롭핑 방법 및 이를 위한 장치

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ANONYMOUS: "MIPAV User Guide", MIPAV USER GUIDE, NATIONAL INSTITUTES OF HEALTH CENTER FOR INFORMATION TECHNOLOGY, US, vol. 1, US, pages 1 - 718, XP009544114, Retrieved from the Internet <URL:https://mipav.cit.nih.gov/documentation/userguide/MIPAVUsersGuideVolume1.pdf> [retrieved on 20221114] *

Also Published As

Publication number Publication date
KR102385689B1 (ko) 2022-04-14
KR102385689B9 (ko) 2022-09-30

Similar Documents

Publication Publication Date Title
WO2012077906A1 (fr) Procédé et appareil pour afficher des listes
WO2012102519A2 (fr) Terminal à écran tactile et procédé d&#39;identification d&#39;un événement tactile sur celui-ci
WO2015030303A1 (fr) Dispositif portatif affichant une image de réalité augmentée et son procédé de commande
EP2649511A2 (fr) Système d&#39;affichage tridimensionnel (3d) répondant au mouvement d&#39;un utilisateur, et interface utilisateur pour le système d&#39;affichage 3d
WO2015099293A1 (fr) Dispositif et procédé permettant d&#39;afficher l&#39;interface utilisateur d&#39;un dispositif d&#39;entrée virtuel d&#39;après une reconnaissance de mouvements
WO2014051246A1 (fr) Procédé et appareil pour déduire un composite facial
EP2678756A1 (fr) Appareil et procédé d&#39;entrée d&#39;instruction à l&#39;aide de geste
WO2023033469A1 (fr) Procédé de rognage 3d d&#39;image médicale et dispositif associé
WO2016013885A1 (fr) Procédé d&#39;extraction d&#39;image et dispositif électronique associé
WO2022019654A1 (fr) Appareil et procédé de recommandation de schéma de couleurs basée sur une analyse d&#39;image spatiale
WO2011053036A2 (fr) Procédé, terminal, et support d&#39;enregistrement lisible par ordinateur destinés à découper une partie de contenu d&#39;image
WO2012011644A1 (fr) Unité centrale de traitement, son procédé de simulation de gpu et système informatique l&#39;incluant
WO2016099186A1 (fr) Appareil d&#39;affichage et procédé de commande
WO2020017890A1 (fr) Système et procédé d&#39;association 3d d&#39;objets détectés
WO2020222378A1 (fr) Moteur de transmission en continu à convolution pour réseaux neuronaux profonds
WO2014003520A1 (fr) Afficheur à del de publicité en extérieur, et procédé d&#39;interaction
WO2020166849A1 (fr) Système d&#39;affichage permettant de détecter un défaut sur un écran large
WO2011078430A1 (fr) Procédé de recherche séquentielle pour reconnaître une pluralité de marqueurs à base de points de caractéristique et procédé de mise d&#39;oeuvre de réalité augmentée utilisant ce procédé
WO2014116040A1 (fr) Dispositif et procédé permettant de modifier la couleur d&#39;un texte affiché sur un dispositif d&#39;affichage
WO2015023057A1 (fr) Appareil et procédé de traitement d&#39;éléments graphiques
EP3186956A1 (fr) Dispositif d&#39;affichage et procédé de commande pour celui-ci
WO2023167391A1 (fr) Procédé de commande pour un dispositif électronique convertissant une carte normale en une carte de hauteur
WO2017003240A1 (fr) Dispositif de conversion d&#39;image et procédé de conversion d&#39;image associé
WO2014058230A1 (fr) Dispositif portable et son procédé d&#39;affichage d&#39;images
WO2019231119A1 (fr) Appareil et procédé de visualisation d&#39;encombrement

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: 22864971

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE