WO2017208423A1 - Dispositif, procédé et programme de traitement d'images - Google Patents

Dispositif, procédé et programme de traitement d'images Download PDF

Info

Publication number
WO2017208423A1
WO2017208423A1 PCT/JP2016/066443 JP2016066443W WO2017208423A1 WO 2017208423 A1 WO2017208423 A1 WO 2017208423A1 JP 2016066443 W JP2016066443 W JP 2016066443W WO 2017208423 A1 WO2017208423 A1 WO 2017208423A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
candidate
shooting
acquired
priority
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.)
Ceased
Application number
PCT/JP2016/066443
Other languages
English (en)
Japanese (ja)
Inventor
康祐 梶村
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.)
Olympus Corp
Original Assignee
Olympus Corp
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 Olympus Corp filed Critical Olympus Corp
Priority to PCT/JP2016/066443 priority Critical patent/WO2017208423A1/fr
Publication of WO2017208423A1 publication Critical patent/WO2017208423A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—Two-dimensional [2D] image generation
    • G06T11/60—Creating or editing images; Combining images with text

Definitions

  • the present invention relates to an image processing apparatus, an image processing method, and an image processing program.
  • a technique is known in which a single combined image is generated by combining a plurality of images acquired using a photographing apparatus such as a digital camera (see, for example, Patent Document 1).
  • a photographing apparatus such as a digital camera
  • similar images having similar feature quantities of acquired images are extracted and combined.
  • a set image is automatically generated. Since the generated set image is a collection of similar images having similar feature amounts, a set in which only similar images are combined. There is an inconvenience that it becomes an image and the range of expression of the user cannot be expanded.
  • the present invention has been made in view of the above-described circumstances, and a new discovery of an expression method by generating a combined image without a user performing a shooting action with the intention of generating the combined image.
  • An object of the present invention is to provide an image processing apparatus, an image processing method, and an image processing program capable of providing a user with learning.
  • One aspect of the present invention is an image storage unit that stores an image in association with shooting time information, an image analysis unit that analyzes at least one of a main subject and a scene of the acquired image when the image is acquired, Based on the analysis result of the main subject or scene of the acquired image analyzed by the image analysis unit and the shooting time information of the acquired image, a plurality of candidate images that are candidates for a group image are stored from the image storage unit.
  • An image processing apparatus comprising: an image generation unit configured to generate a combined image by combining a predetermined number of candidate images having a high degree with the acquired image.
  • the image acquired in the past is stored in the image storage unit in association with the shooting time information, and when the image is acquired by shooting, the image analysis unit stores the main subject and the scene in the acquired image. At least one is analyzed, and a candidate image is extracted based on the analysis result and the shooting time information. In each of the extracted candidate images, the priority setting unit sets a priority according to the shooting time information. Therefore, by combining a predetermined number of candidate images having a high priority in the image generation unit, a certain relationship is obtained. A combined image is generated in which not only similar but similar images are combined. Accordingly, it is possible to generate a combined image without performing shooting action with the user's intention to generate the combined image, and to provide the user with new discoveries and learning about the expression method.
  • the shooting time information may include at least one of a shooting date and time, a shooting position, and a shooting condition.
  • the said priority setting part may set a high priority, so that the said imaging
  • the said priority setting part may set a high priority, so that the said imaging conditions differ.
  • the photographing conditions include the posture and angle of the photographing apparatus at the time of photographing, in addition to the shutter speed, aperture, ISO sensitivity, and the like.
  • the image generation unit when the image generation unit determines the candidate image for generating the combined image, the image generation unit adds a flag to the determined candidate image and stores the flag in the image storage unit.
  • the setting unit may lower the priority when the flag is attached to the extracted candidate image. By doing so, it is possible to prevent only the same image from being selected.
  • a storage step for storing an image in association with shooting time information, and an analysis step for analyzing at least one of a main subject and a scene of the acquired image when the image is acquired,
  • a candidate extracting step of extracting a plurality of candidate images that are candidates for the group image based on the analysis result of the main subject or scene of the acquired image analyzed by the analyzing step and the shooting time information of the acquired image
  • a priority setting step for setting priority according to the shooting time information to the plurality of candidate images extracted by the candidate extraction step, and a predetermined number of high priority set by the priority setting step
  • an image generation step of generating the combined image by combining the candidate image with the acquired image.
  • a storage step for storing an image in association with shooting time information, and an analysis step for analyzing at least one of a main subject and a scene of the acquired image when the image is acquired,
  • a candidate extracting step of extracting a plurality of candidate images that are candidates for the group image based on the analysis result of the main subject or scene of the acquired image analyzed by the analyzing step and the shooting time information of the acquired image
  • a priority setting step for setting priority according to the shooting time information to the plurality of candidate images extracted by the candidate extraction step, and a predetermined number of high priority set by the priority setting step
  • An image processing program for causing a computer to execute an image generation step of generating the combined image by combining the candidate image of the image and the acquired image.
  • FIG. 1 is a block diagram illustrating a photographing apparatus including an image processing apparatus according to an embodiment of the present invention. It is a figure which shows the example of an image memorize
  • FIG. 4 is a diagram showing a list of candidate images, subjects / scenes, and shooting conditions extracted by the image processing apparatus of FIG. 1 for the acquired image of FIG. 3.
  • FIG. 5 is a diagram illustrating a list of candidate images in FIG. 4 in which priorities are set by the image processing apparatus in FIG. 1.
  • 3 is a flowchart illustrating an image processing method according to an embodiment of the present invention using the image processing apparatus of FIG. 1.
  • FIG. 7 is a flowchart for explaining subject / scene extraction processing in the flowchart of FIG. 6; It is a flowchart explaining the extraction process of the candidate image in the flowchart of FIG. 7 is a flowchart illustrating priority setting processing in the flowchart of FIG. 6. It is a figure which shows an example of the group image produced
  • FIG. 13 is a diagram showing a list of candidate images, subjects / scenes, shooting conditions, and priorities extracted by the image processing apparatus of FIG. 1 for the acquired image of FIG. It is a figure which shows the other example of the group image produced
  • FIG. 1 shows a camera (photographing apparatus) 100 including an image processing apparatus 1 according to the present embodiment.
  • the camera 100 includes an imaging unit 110 that captures light from a subject, the image processing apparatus 1 according to the present embodiment, and a display unit 120.
  • the imaging unit 110 includes an imaging lens 130 that collects light from a subject, an imaging element 140 that captures light collected by the imaging lens 130, and an image based on an image signal acquired by the imaging element 140.
  • an image generation unit 150 for generating.
  • the image processing apparatus 1 includes an image storage unit 2 that stores an image generated by the image generation unit 150 in association with shooting time information and an analysis result described below, and the image generation unit 150 generates the image storage unit 2.
  • An image analysis unit 3 that analyzes the acquired image
  • a candidate image extraction unit (candidate extraction unit) 4 that extracts a candidate image that is a candidate for a combined image based on an analysis result by the image analysis unit 3 and shooting time information
  • extraction A priority setting unit 5 for setting a priority to the candidate image
  • a group image generation unit (image generation unit) 6 for generating a group image by combining candidate images with high priority.
  • the shooting time information stored in association with the acquired image in the image storage unit 2 includes shooting conditions (focal length, F value, etc.) including the shooting date and time, the shooting position, and the posture of the camera 100 (camera angle). Yes.
  • the image analysis unit 3 analyzes an acquired image newly acquired by the imaging unit 110 and detects at least one of a main subject and a scene.
  • the candidate image extraction unit 4 searches all the images in the image storage unit 2 as to whether or not the main subject or scene detected by the image analysis unit 3 is similar, and selects an image having the main subject or scene similar as the candidate image. Is supposed to be extracted as Further, the candidate image extraction unit 4 searches all the images in the image storage unit 2 based on the shooting time information associated with the acquired image.
  • the shooting date and time or the shooting position is used as the shooting time information
  • an image with a similar shooting date and time or shooting position is extracted as a candidate image.
  • shooting conditions are used as shooting time information
  • images with different shooting conditions are extracted as candidate images.
  • the priority setting unit 5 sets priorities for a plurality of images extracted by the candidate image extraction unit 4 according to a predetermined rule. In the present embodiment, the priority setting unit 5 sets higher priorities in the order in which the shooting date and time are close, the shooting position is close, the shooting conditions are different, and the subject or scene is common.
  • the combined image generation unit 6 generates a combined image by selecting and combining a predetermined number of candidate images in descending order of priority from the candidate images extracted by the candidate image extracting unit 4. ing.
  • the acquired image is analyzed in the image analysis unit 3 to detect at least one of the main subject and the scene.
  • Shooting time information associated with the main subject or scene detected by the image analysis unit 3 and the acquired image is sent to the candidate image extraction unit 4 and compared with the five images stored in the image storage unit 2.
  • a candidate image is extracted.
  • FIG. 4 shows an example of a candidate image list.
  • Candidate image NO. 1 is an acquired image
  • NO. Nos. 2 and 3 are candidate images whose shooting date and time and shooting positions are very close.
  • No. 4 is a candidate image having a relatively low correlation between the shooting date and time and the shooting position.
  • Reference numeral 5 denotes a candidate image having a high correlation between the shooting date and time and the shooting position and different shooting conditions.
  • priority setting unit 5 sets priority.
  • the priority is set as follows. First, a high priority is set when the main subject or scene is similar. A high priority is set when the shooting date and / or shooting position is close.
  • the priority is lowered if the shooting conditions are similar even if the shooting date and / or shooting position is close. Furthermore, high priority is raised when shooting conditions are different.
  • the candidate image NO. 2 is a candidate image NO. 1 and subject determination are the same, and the correlation with respect to the shooting date and the shooting position is high. Furthermore, since the photographing conditions such as the focal length and the F value are different, the priority is set high.
  • candidate image NO. 3 is a candidate image NO. 2 and the subject determination are the same, and the correlation with respect to the shooting date and position and the shooting position is high. 2 and the shooting conditions are the same, the priority is set relatively low.
  • candidate image NO. 4 is a candidate image NO. 1 and the subject determination are the same, but since the correlation between the shooting date and the shooting position is relatively low compared to other candidate images, a low priority is set.
  • candidate image NO. 5 the subject or scene is not similar, but the correlation between the shooting date and the shooting position is high, and the correlation between the shooting date and the shooting position is relatively high compared to other images. As a result, the priority is set as shown in FIG.
  • the group image generation unit 6 it is determined whether or not the number of candidate images for which the priority is set in the priority setting unit 5 is necessary for the group image, for example, three, is present. A set image is generated. If it does not exist, no combined image is generated.
  • the group image generation unit 6 selects a necessary number of candidate images in descending order of priority, suitably trims the main subject of each candidate image, and applies it to each frame of the group image. As a result, a combined image as shown in FIG. 10 is automatically generated.
  • step S1 when an image is acquired and the acquired image is generated by the image generation unit 150 (step S1), the image analysis unit 3 Main subjects or scenes are extracted (step S2).
  • the analysis by the image analysis unit 3 is performed by extracting an image feature amount from the acquired image (step S21) and searching a subject / scene database based on the extracted image feature amount (Ste S22) is performed by detecting a subject or scene corresponding to the image feature amount.
  • Step S21 the analysis by the image analysis unit 3 is performed by extracting an image feature amount from the acquired image
  • Step S22 searching a subject / scene database based on the extracted image feature amount
  • Step S22 is performed by detecting a subject or scene corresponding to the image feature amount.
  • the extracted main subject or scene information is stored in the image storage unit 2 in association with the acquired image and shooting time information (storage step S3).
  • the candidate image extraction unit 4 extracts candidate images (step S4).
  • candidate images first, as shown in FIG. 8, the correlation between the main subject or scene of the acquired image and the main subject or scene of another image stored in the image storage unit 2 is calculated ( Analysis step S41), it is determined whether or not the calculated correlation is higher than a predetermined threshold (step S42), and an image having a correlation higher than the threshold is extracted as a candidate image (candidate extraction step S43).
  • the candidate image extraction unit 4 includes the shooting date and time and the shooting date and time of the image stored in the image storage unit 2 in the shooting time information of the acquired image. Is calculated (step S44), and it is determined whether or not the difference in shooting date and time is smaller than a predetermined threshold, for example, within 3 days (step S45), and an image having a small date and time difference is extracted as a candidate image (step S45).
  • a predetermined threshold for example, within 3 days
  • the candidate image extraction unit 4 includes the shooting position and the shooting position of the image stored in the image storage unit 2 in the shooting time information of the acquired image. Is calculated (step S46), and it is determined whether or not the difference in shooting position is smaller than a predetermined threshold (step S47), and an image with a small position difference is extracted as a candidate image (candidate extraction step S43). .
  • the process from step S41 is repeated until extraction processing is performed for all the images stored in the image storage unit 2 (step S48).
  • the priority setting unit 5 sets priorities for the plurality of candidate images extracted by the candidate image extraction unit 4 (priority setting step S5). As shown in FIG. 9, the priority is set to a high priority when the main subject or the scene is similar (steps S51, S52, S53). Next, a high priority is set when the shooting date and / or shooting position is close (steps S54 to S59).
  • step S60 it is determined whether or not the shooting conditions are similar to the plurality of candidate images extracted by the candidate image extraction unit 4 (step S60). The closer the shooting conditions are, the lower the priority is (step S61). The priority is increased as the conditions differ (step S62). It is determined whether or not priorities have been set for all candidate images (step S63). If not set, the processes from step S51 are repeated.
  • step S6 it is determined whether or not there are as many candidate images as are necessary for generating the combined image. As many candidate images as necessary are selected in descending order (step S7). If the required number of candidate images does not exist, the process ends. Then, as shown in FIG. 10, using the selected number of candidate images, a set image is generated (image generation step S8) and displayed on the display unit 120 (step S9).
  • the image processing device 1 and the image processing method according to the present embodiment the past image captured by the user himself / herself even if the user does not perform the photographing action with the intention of generating the combined image. Since the combined image is generated based on the above, there is an advantage that by displaying the generated combined image, it is possible to provide the user with new discovery and learning about the expression method.
  • the conditions extracted as candidate images may be arbitrarily changed by the user. Specifically, only images with the same shooting date and time may be extracted. Further, for example, the determination may be made simply by the difference in date and time, or as shown in FIG. 11, a correlation graph shape and a threshold value for extracting an image of exactly one year ago may be set. . Further, it may be set so that images of morning, noon and night can be easily extracted as candidate images even at the same date and time.
  • the shooting conditions for setting the priority include various settings that can be changed by the user during shooting, such as the type of lens used, exposure time, image finish setting (flat, vivid, etc.), tone curve setting, exposure correction level, etc. May be considered. Accordingly, there is an advantage that a combined image is automatically generated with a combination that the user himself / herself has not noticed, and the user can obtain new discoveries and learning.
  • condition for setting the priority may be specified according to the user's preference. For example, prioritize the same subject judgment so that it does not become a combined image, or prioritize the same subject determination as a combined image even if the correlation of shooting date and time and shooting position is low You can do it. By doing so, there is an advantage that the user's preference can be added to the automatically generated combined image, and new discoveries and learning can be obtained while reflecting the user's preference.
  • the user may set the number of images necessary for generating the combined image.
  • the apparatus may prepare a plurality of patterns as the required number of patterns and set them randomly. Further, it may be determined adaptively according to the number of extracted candidate images.
  • the set image generation unit 6 selects a candidate image for generating the set image
  • the set image generation is performed in association with the corresponding image in the image storage unit 2 as indicated by a chain line in FIG.
  • a flag indicating that the flag is used may be stored.
  • the acquired image has a plurality of main subject areas as shown in FIG. 12, two people are recognized by subject determination, and a candidate list and priority are set as shown in FIG.
  • the combined image generation unit 6 an image obtained by cutting out each of the two main subjects of the acquired image and the No. with the highest priority.
  • a combination image as shown in FIG. 14 may be generated by combining the three images.
  • the image processing method may be realized by an image processing program that can be executed by a computer.
  • the computer includes a main storage device such as a CPU and a RAM, and a computer-readable recording medium, and an image processing program for realizing the processing described above is recorded on the recording medium. Then, the CPU can read out the image processing program recorded on the recording medium, and can realize the same processing as that of the image processing apparatus 1.
  • the image processing apparatus 1 may be applied to any photographing apparatus such as a microscope and an endoscope. .

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Studio Devices (AREA)

Abstract

La présente invention a pour objet de générer une image composite et d'offrir à un utilisateur des découvertes et des connaissances nouvelles en ce qui concerne les procédés d'expression. Un dispositif (1) de traitement d'images selon la présente invention comporte: une unité (2) de stockage d'images qui stocke une image en association avec des informations d'instant de photographie; une unité (3) d'analyse d'images qui, lorsqu'une image a été acquise, analyse un sujet principal et/ou une scène de ladite image acquise; une unité (4) d'extraction de candidates qui extrait de l'unité de stockage d'images une pluralité d'images candidates qui sont des candidates pour une image composite sur la base du résultat de l'analyse du sujet principal ou de la scène de l'image acquise qui a été analysée par l'unité (3) d'analyse d'images et des informations d'instant de photographie de l'image acquise; une unité (5) de spécification de priorités qui spécifie des priorités d'après les informations d'instant de photographie pour la pluralité d'images candidates qui ont été extraites par l'unité (4) d'extraction de candidates; et une unité (6) de génération d'images qui combine l'image acquise avec un nombre prescrit d'images candidates présentant des priorités élevées telles que spécifiées par l'unité (5) de spécification de priorités, et génère l'image composite.
PCT/JP2016/066443 2016-06-02 2016-06-02 Dispositif, procédé et programme de traitement d'images Ceased WO2017208423A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2016/066443 WO2017208423A1 (fr) 2016-06-02 2016-06-02 Dispositif, procédé et programme de traitement d'images

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2016/066443 WO2017208423A1 (fr) 2016-06-02 2016-06-02 Dispositif, procédé et programme de traitement d'images

Publications (1)

Publication Number Publication Date
WO2017208423A1 true WO2017208423A1 (fr) 2017-12-07

Family

ID=60478123

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2016/066443 Ceased WO2017208423A1 (fr) 2016-06-02 2016-06-02 Dispositif, procédé et programme de traitement d'images

Country Status (1)

Country Link
WO (1) WO2017208423A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113553144A (zh) * 2020-04-24 2021-10-26 杭州海康威视数字技术股份有限公司 数据分发方法、装置及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000215212A (ja) * 1998-11-25 2000-08-04 Eastman Kodak Co フォトコラ―ジュの作成方法及びそれを用いたシステム
JP2006293986A (ja) * 2005-03-15 2006-10-26 Fuji Photo Film Co Ltd アルバム作成装置、アルバム作成方法、及びプログラム
JP2007172344A (ja) * 2005-12-22 2007-07-05 Canon Inc 画像編集プログラム及び画像編集装置
JP2016058923A (ja) * 2014-09-10 2016-04-21 カシオ計算機株式会社 画像処理装置、画像処理方法及びプログラム
JP2016066343A (ja) * 2014-06-30 2016-04-28 カシオ計算機株式会社 画像生成装置、画像生成方法及びプログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000215212A (ja) * 1998-11-25 2000-08-04 Eastman Kodak Co フォトコラ―ジュの作成方法及びそれを用いたシステム
JP2006293986A (ja) * 2005-03-15 2006-10-26 Fuji Photo Film Co Ltd アルバム作成装置、アルバム作成方法、及びプログラム
JP2007172344A (ja) * 2005-12-22 2007-07-05 Canon Inc 画像編集プログラム及び画像編集装置
JP2016066343A (ja) * 2014-06-30 2016-04-28 カシオ計算機株式会社 画像生成装置、画像生成方法及びプログラム
JP2016058923A (ja) * 2014-09-10 2016-04-21 カシオ計算機株式会社 画像処理装置、画像処理方法及びプログラム

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113553144A (zh) * 2020-04-24 2021-10-26 杭州海康威视数字技术股份有限公司 数据分发方法、装置及系统
CN113553144B (zh) * 2020-04-24 2023-09-26 杭州海康威视数字技术股份有限公司 数据分发方法、装置及系统

Similar Documents

Publication Publication Date Title
JP6076168B2 (ja) 撮像装置、構図アシスト装置、構図アシスト方法、及び構図アシストプログラム
JP4232774B2 (ja) 情報処理装置および方法、並びにプログラム
JP5631106B2 (ja) 画像処理装置、その制御方法、及びプログラム、並びに撮像装置
JP5128880B2 (ja) 画像取扱装置
KR20110006878A (ko) 복수의 인물에 대한 이미지 생성 장치 및 방법
JP5652886B2 (ja) 顔認証装置、認証方法とそのプログラム、情報機器
KR20090087670A (ko) 촬영 정보 자동 추출 시스템 및 방법
JP4624947B2 (ja) 画像のトリミング方法および装置並びにプログラム
JP5699432B2 (ja) 画像処理装置
JP2010211261A (ja) 画像検索装置及び画像検索方法
JP5710940B2 (ja) 画像処理装置、画像処理方法及び画像処理プログラム
CN110581950B (zh) 相机、选择相机设置的系统和方法
JP2010081453A (ja) 付帯情報付加装置及び方法
JP2015198300A (ja) 情報処理装置、撮像装置、画像管理システム
JP2005065048A (ja) 画像処理方法および装置、並びに画像処理プログラム
JP6594666B2 (ja) 撮像補助装置、撮像装置および撮像補助方法
JP5383308B2 (ja) 画像処理装置
WO2017208423A1 (fr) Dispositif, procédé et programme de traitement d'images
JP6614198B2 (ja) 画像処理装置、画像処理方法及びプログラム
JP2018124814A (ja) 画像処理装置、撮像装置、画像処理方法、画像処理プログラム、および、記憶媒体
JP7780879B2 (ja) 情報処理装置、情報処理方法、及びプログラム
JP5267136B2 (ja) 電子カメラ
JP2021061458A (ja) 情報処理装置、情報処理方法及びプログラム
JP2013157675A (ja) 撮像装置及びその制御方法、プログラム、並びに記憶媒体
US20210112191A1 (en) Imaging control device, imaging control method, and non-transitory computer-readable recording medium

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: 16904048

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16904048

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP