WO2017016146A1 - 图像显示方法及装置 - Google Patents

图像显示方法及装置 Download PDF

Info

Publication number
WO2017016146A1
WO2017016146A1 PCT/CN2015/097782 CN2015097782W WO2017016146A1 WO 2017016146 A1 WO2017016146 A1 WO 2017016146A1 CN 2015097782 W CN2015097782 W CN 2015097782W WO 2017016146 A1 WO2017016146 A1 WO 2017016146A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
images
image set
similar
representative
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/CN2015/097782
Other languages
English (en)
French (fr)
Inventor
张涛
龙飞
陈志军
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.)
Xiaomi Inc
Original Assignee
Xiaomi 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 Xiaomi Inc filed Critical Xiaomi Inc
Priority to JP2017530393A priority Critical patent/JP6357589B2/ja
Priority to KR1020167003923A priority patent/KR20170023742A/ko
Priority to MX2016003875A priority patent/MX359585B/es
Priority to RU2016112557A priority patent/RU2636668C2/ru
Publication of WO2017016146A1 publication Critical patent/WO2017016146A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G06V10/993—Evaluation of the quality of the acquired pattern
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/30—Scenes; Scene-specific elements in albums, collections or shared content, e.g. social network photos or video
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/00127—Connection or combination of a still picture apparatus with another apparatus, e.g. for storage, processing or transmission of still picture signals or of information associated with a still picture
    • H04N1/00129—Connection or combination of a still picture apparatus with another apparatus, e.g. for storage, processing or transmission of still picture signals or of information associated with a still picture with a display device, e.g. CRT or LCD monitor
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/00127—Connection or combination of a still picture apparatus with another apparatus, e.g. for storage, processing or transmission of still picture signals or of information associated with a still picture
    • H04N1/00132—Connection or combination of a still picture apparatus with another apparatus, e.g. for storage, processing or transmission of still picture signals or of information associated with a still picture in a digital photofinishing system, i.e. a system where digital photographic images undergo typical photofinishing processing, e.g. printing ordering
    • H04N1/00185—Image output
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/40—Picture signal circuits
    • H04N1/40012—Conversion of colour to monochrome

Definitions

  • the present disclosure relates to the field of terminal technologies, and in particular, to an image display method and apparatus.
  • the present disclosure provides an image display method and apparatus.
  • an image display method comprising:
  • a representative image of the plurality of similar image sets is displayed.
  • the image in the album is clustered by similar images to obtain a plurality of similar image sets, and multiple images in each similar image set are filtered to obtain
  • the representative image with better image quality in the similar image set displays the representative image with better image quality among the plurality of similar image sets, thereby enhancing the display effect of the representative images of the plurality of similar image sets.
  • performing screening on a plurality of images in each similar image set to obtain a representative image of the similar image set includes:
  • the terminal filters the multiple images in the similar image set based on the ray quality parameters of the multiple images in the similar image set, so that the images with better light quality in the multiple images can be obtained, thereby The problem that the image of the first image set is too dark or overexposed when the image is displayed is avoided, and the image display effect is enhanced.
  • the method further includes:
  • the terminal filters the plurality of images in the first image set based on the face angle of the plurality of images in the first image set, and obtains an image with a relatively positive face angle in the plurality of images. Therefore, the problem that the face image is not too positive when the image is displayed in the second image set is avoided, so that the selected image is closer to the visual requirement of the user, and the image display effect is enhanced.
  • the method further includes:
  • an image of the non-closed eyes is selected from the second image set to obtain a third image set.
  • the terminal filters the plurality of images in the second image set based on the eye features of the plurality of images in the second image set, so as to obtain an image of the non-closed eyes in the plurality of images, thereby avoiding
  • the third image set has a problem of closing eyes when the image is displayed, so that the display effect of the selected image is better.
  • the method further includes:
  • the terminal selects multiple images in the third image set based on the face sharpness of the plurality of images in the third image set, and obtains a better face resolution in the multiple images.
  • the image thus enhances the sharpness of the image when representing the image display.
  • the ray quality parameter of the multiple images in the similar image set is used from the similar image set before selecting the image whose light quality parameter is smaller than the light threshold, before obtaining the first image set, the method further includes:
  • a ray quality parameter of the image is determined based on the first ratio and the second ratio.
  • the terminal performs the face angle screening on the multiple images in the similar image set by determining the light quality parameter of the image, so that the image with better light quality in the multiple images can be obtained, thereby avoiding the first
  • An image collection has a problem that the image is too dark or overexposed when the image is displayed, and the image display effect is enhanced.
  • the method further includes:
  • a first feature point and a second feature point are selected, the first feature point and the second feature point being bilaterally symmetric about the nose Feature points;
  • a face angle of the image is determined based on the first distance and the second distance.
  • the terminal performs face angle screening on multiple images in the first image set by determining a face angle of the image, thereby obtaining an image with a relatively positive face angle in the multiple images, thereby avoiding the first
  • the two image collections have a problem that the face pose is not positive when the image is displayed, so that the selected image is closer to the user's visual needs and enhances the image display effect.
  • the third aspect of the image in the third image set is based on the In the image set, selecting an image whose face sharpness is greater than or equal to the specified sharpness, before obtaining the representative image of the similar image set, further includes:
  • the gradient cumulative value is determined as the face sharpness of the image.
  • the terminal performs face sharpness screening on multiple images in the third image set by determining the face sharpness of the image, and obtains an image with better face clarity in the multiple images. Thereby, the image sharpness at the time of representative image display is improved.
  • displaying the representative image of the multiple similar image sets includes:
  • the adjusted representative image is displayed in the specified dynamic display format.
  • the terminal rotates and adjusts the representative image of the plurality of similar image sets, and displays the adjusted representative image in a specified dynamic display form, thereby enriching the display form and enhancing the representative image. display effect.
  • the terminal when there are multiple representative images in the similar image set, the terminal randomly selects one Or two pictures are displayed, thereby avoiding the problem of monotonous when displaying a plurality of representative images.
  • an image display apparatus comprising:
  • a clustering module configured to perform similar image clustering on the images in the album when receiving the album opening instruction, to obtain a plurality of similar image sets
  • a screening module configured to perform screening on a plurality of images in each of the similar image sets to obtain a representative image of the similar image collection
  • a display module configured to display a representative image of the plurality of similar image sets.
  • the screening module includes:
  • a first selecting unit configured to: for each of the plurality of similar image sets, select a ray quality parameter from the similar image set based on a ray quality parameter of the plurality of images in the similar image set An image of the light threshold results in a first set of images.
  • the screening module further includes:
  • a second selecting unit configured to select, according to a face angle of the plurality of images in the first image set, an image with a face angle within a specified angle range from the first image set, to obtain a second image set.
  • the screening module further includes:
  • a third selecting unit configured to select an image of the non-closed eye from the second image set based on an eye feature of the plurality of images in the second image set to obtain a third image set.
  • the screening module further includes:
  • a fourth selecting unit configured to select an image whose face resolution is greater than or equal to a specified sharpness from the third image set based on a face sharpness of the plurality of images in the third image set, to obtain the A representative image of a similar image collection.
  • the screening module further includes:
  • a converting unit configured to convert multiple images in the similar image set into a grayscale image
  • a first determining unit configured to determine, from each of the plurality of images, a first number of pixels whose gray value is smaller than the first gray threshold from the gray image corresponding to the image, and determine a second number of pixels whose gray value is greater than the second gray threshold;
  • a second determining unit configured to determine a first ratio of the first number in the total number, and determine a second ratio of the second number in the total number,
  • the total number is the number of all pixels in the grayscale image
  • a third determining unit configured to determine a light quality parameter of the image based on the first ratio and the second ratio.
  • the screening module further includes:
  • a first acquiring unit configured to acquire a facial feature point of multiple images in the first image set
  • a fifth selecting unit configured to select, from the image, a first feature point and a second feature point for each of the plurality of images, wherein the first feature point and the second feature point are a bilaterally symmetrical feature point centered on the nose;
  • a fourth determining unit configured to determine a first distance between the first feature point and the specified feature point, and determine a second distance between the second feature point and the specified feature point;
  • a fifth determining unit configured to determine a face angle of the image based on the first distance and the second distance.
  • the screening module further includes:
  • a second acquiring unit configured to acquire, for each image of the plurality of images of the third image set, a pixel value of each pixel included in the face region of the image
  • a sixth determining unit configured to determine a gradient cumulative value of the face region based on the pixel value of each pixel point
  • a seventh determining unit configured to determine the gradient integrated value as the face sharpness of the image.
  • the display module includes:
  • a rotation unit configured to rotate and align the representative images of the plurality of similar image sets such that face directions in the representative images of the plurality of similar image sets are the same;
  • the adjusting unit is configured to adjust each representative image after the rotation alignment so that the size of the face region in each of the adjusted representative images is equal;
  • a display unit for displaying the adjusted representative image in a specified dynamic display form.
  • an image display apparatus comprising:
  • a memory for storing processor executable instructions
  • processor is configured to:
  • a representative image of the plurality of similar image sets is displayed.
  • the technical solution provided by the embodiment of the present disclosure may include the following beneficial effects: when the terminal receives the album opening instruction, performing similar image clustering on the image in the album to obtain a plurality of similar image sets, for each similar image set The plurality of images are filtered to obtain a representative image with better image quality in the similar image set, and the representative image with better image quality in the plurality of similar image sets is displayed, thereby enhancing the representative image of the plurality of similar image sets.
  • the display effect when the terminal receives the album opening instruction, performing similar image clustering on the image in the album to obtain a plurality of similar image sets, for each similar image set
  • the plurality of images are filtered to obtain a representative image with better image quality in the similar image set, and the representative image with better image quality in the plurality of similar image sets is displayed, thereby enhancing the representative image of the plurality of similar image sets.
  • FIG. 1 is a flow chart showing an image display method according to an exemplary embodiment.
  • FIG. 2 is a flowchart of another image display method according to an exemplary embodiment.
  • FIG. 3 is a schematic diagram showing a distribution of facial feature points according to an exemplary embodiment.
  • FIG. 4 is a block diagram of an image display apparatus according to an exemplary embodiment.
  • FIG. 5 is a block diagram of a first screening module, according to an exemplary embodiment.
  • FIG. 6 is a block diagram of a second screening module, according to an exemplary embodiment.
  • FIG. 7 is a block diagram of a third screening module, shown according to an exemplary embodiment.
  • FIG. 8 is a block diagram of a fourth screening module, according to an exemplary embodiment.
  • FIG. 9 is a block diagram of a fifth screening module, according to an exemplary embodiment.
  • FIG. 10 is a block diagram of a sixth screening module, according to an exemplary embodiment.
  • FIG. 11 is a block diagram of a seventh screening module, according to an exemplary embodiment.
  • FIG. 12 is a block diagram of a display module, according to an exemplary embodiment.
  • FIG. 13 is a block diagram of another image display device according to an exemplary embodiment.
  • FIG. 1 is a flowchart of an image display method according to an exemplary embodiment. As shown in FIG. 1 , the method is used in a terminal, and includes the following steps.
  • step 101 when an album open command is received, similar images are clustered on the images in the album to obtain a plurality of similar image sets.
  • step 102 a plurality of images in each similar image set are filtered to obtain a representative image of the similar image set.
  • step 103 the representative images of the plurality of similar image sets are displayed.
  • the image in the album is clustered by similar images to obtain a plurality of similar image sets, and multiple images in each similar image set are filtered to obtain
  • the representative image with better image quality in the similar image set displays the representative image with better image quality among the plurality of similar image sets, thereby enhancing the display effect of the representative images of the plurality of similar image sets.
  • screening a plurality of images in each similar image set to obtain a representative image of the similar image set includes:
  • an image with a ray quality parameter smaller than a ray threshold is selected from the similar image set to obtain a first image set.
  • the terminal filters the multiple images in the similar image set based on the ray quality parameters of the multiple images in the similar image set, so that the images with better light quality in the multiple images can be obtained, thereby The problem that the image of the first image set is too dark or overexposed when the image is displayed is avoided, and the image display effect is enhanced.
  • the method further includes:
  • an image of the face angle within a specified angle range is selected from the first image set to obtain a second image set.
  • the terminal filters the plurality of images in the first image set based on the face angle of the plurality of images in the first image set, and obtains an image with a relatively positive face angle in the plurality of images. Therefore, the problem that the face image is not too positive when the image is displayed in the second image set is avoided, so that the selected image is closer to the visual requirement of the user, and the image display effect is enhanced.
  • the method further includes:
  • an image of the non-closed eyes is selected from the second image set to obtain a third image set.
  • the terminal filters the plurality of images in the second image set based on the eye features of the plurality of images in the second image set, so as to obtain an image of the non-closed eyes in the plurality of images, thereby avoiding
  • the third image set has a problem of closing eyes when the image is displayed, so that the display effect of the selected image is better.
  • the method further includes:
  • the terminal selects multiple images in the third image set based on the face sharpness of the plurality of images in the third image set, and obtains a better face resolution in the multiple images.
  • the image thus enhances the sharpness of the image when representing the image display.
  • the method based on the ray quality parameter of the plurality of images in the similar image set, from the similar image set, selecting an image whose ray quality parameter is smaller than a ray threshold, before obtaining the first image set, the method also includes:
  • a light quality parameter of the image is determined based on the first ratio and the second ratio.
  • the terminal performs the face angle screening on the multiple images in the similar image set by determining the light quality parameter of the image, so that the image with better light quality in the multiple images can be obtained, thereby avoiding the first
  • An image collection has a problem that the image is too dark or overexposed when the image is displayed, and the image display effect is enhanced.
  • the method based on the face angle of the plurality of images in the first image set, from the first image set, selecting an image whose face angle is within a specified angle range, before obtaining the second image set, The method also includes:
  • first feature point and a second feature point For each image of the plurality of images, from the image, selecting a first feature point and a second feature point, wherein the first feature point and the second feature point are left and right symmetrical feature points centered on the nose;
  • a face angle of the image is determined based on the first distance and the second distance.
  • the terminal performs face angle screening on multiple images in the first image set by determining a face angle of the image, thereby obtaining an image with a relatively positive face angle in the multiple images, thereby avoiding the first
  • the two image collections have a problem that the face pose is not positive when the image is displayed, so that the selected image is closer to the user's visual needs and enhances the image display effect.
  • the method further includes:
  • the gradient cumulative value is determined as the face sharpness of the image.
  • the terminal performs face sharpness screening on multiple images in the third image set by determining the face sharpness of the image, and obtains an image with better face clarity in the multiple images. Thereby, the image sharpness at the time of representative image display is improved.
  • displaying the representative images of the plurality of similar image sets includes:
  • the adjusted representative image is displayed in the specified dynamic display format.
  • the terminal rotates and adjusts the representative image of the plurality of similar image sets, and displays the adjusted representative image in a specified dynamic display form, thereby enriching the display form and enhancing the representative image. display effect.
  • the terminal when there are multiple representative images in the similar image set, the terminal randomly selects one or two images for display, thereby avoiding monotonous when displaying similar multiple representative images. problem.
  • FIG. 2 is a flowchart of an image display method according to an exemplary embodiment. As shown in FIG. 2, the method is used in a terminal, and includes the following steps.
  • step 201 when an album open command is received, similar images are clustered on the images in the album to obtain a plurality of similar image sets.
  • the terminal When the terminal receives the album open instruction, the terminal performs similar image clustering on all the images in the album, that is, the terminal divides the similar or identical multiple images in the album into one set, thereby The album is divided into a plurality of sets, which are a plurality of similar image sets.
  • the album opening instruction is used to open the album, and the album opening instruction can be triggered by the user, and the user can be triggered by a specified operation, which can be a click operation, a sliding operation, a voice operation, and the like.
  • a specified operation which can be a click operation, a sliding operation, a voice operation, and the like.
  • the embodiment of the present disclosure does not specifically limit this.
  • the specific operation of the terminal to perform similar image clustering on the image in the album may refer to related technologies such as similar clustering, which is not elaborated in the embodiment of the present disclosure.
  • step 202 for a plurality of images in each similar image set, the terminal selects an image with a light quality parameter smaller than a light threshold from the similar image set based on a light quality parameter of the plurality of images in the similar image set. A first image set is obtained.
  • a plurality of images included in the similar image set may have an image with dark light or bright light, that is, in a plurality of images included in the similar image set, there may be an image that is too dark or overexposed, so
  • the terminal needs to select an image whose light quality parameter is smaller than a light threshold based on the light quality parameter of the plurality of images in the similar image set. Thereby a first image set is obtained.
  • the ray threshold may be set in advance, and the ray threshold is greater than 0 and less than 1.
  • the ray threshold may be 0.8, 0.9, or the like, which is not specifically limited in the embodiment of the present disclosure.
  • the similar image set includes five images, and the five images are image 1, image 2, image 3, image 4, and image 5, respectively, and the light quality parameter corresponding to image 1 is 0.26, and the light quality parameter corresponding to image 2 is
  • the ray quality parameter corresponding to image 3 is 0.7
  • the ray quality parameter corresponding to image 4 is 0.3
  • the ray quality parameter corresponding to image 5 is 0.9
  • the ray threshold is 0.8
  • the terminal is based on multiple images in the similar image set.
  • the ray quality parameter from the similar image set, the image whose ray quality parameter is less than the ray threshold of 0.8 has image 1, image 2, image 3 and image 4, so that the terminal determines the image of the similar image set that satisfies the ray quality parameter It is Image 1, Image 2, Image 3, and Image 4, thereby obtaining a first image set.
  • the terminal selects an image with a light quality parameter smaller than a light threshold from the similar image set based on a light quality parameter of the plurality of images in the similar image set, and the terminal may determine the similarity before obtaining the first image set.
  • the ray quality parameter of the plurality of images in the image set, and determining the ray quality parameter of the plurality of images in the similar image set may be: converting the plurality of images in the similar image set into a grayscale image; For each image in the image, the terminal determines a first number of pixels whose gray value is smaller than the first gray threshold from the gray image corresponding to the image, and determines a pixel whose gray value is greater than the second gray threshold The second number of points; the terminal determines the first proportion of the first number in the total number, and determines the second proportion of the second number in the total number, the total number is the gray The number of all pixels in the graph; the terminal determines the ray quality parameter of the image based on the first ratio and the second ratio.
  • the terminal determines, according to the first ratio and the second ratio, the ray quality parameter of the image, the terminal may determine at least one of the first ratio and the second ratio as a ray quality parameter of the image, of course, the terminal It is also possible to select a maximum value from the first ratio and the second ratio, and determine the selected maximum value as the ray quality parameter of the image, which is not specifically limited in the embodiment of the present disclosure.
  • first gray threshold and the second gray threshold may be set in advance, and the second gray threshold is greater than the first gray threshold.
  • the first gray threshold may be 30, and the second gray threshold may be The embodiment of the present disclosure does not specifically limit this.
  • the first grayscale threshold is 30, and the second grayscale threshold is 200.
  • the terminal converts multiple images in the similar image set into grayscale images. For the image 1 in the multiple images, the image 1 The total number of all the pixels in the grayscale image is 1000, and the terminal determines, from the grayscale image corresponding to the image 1, that the first number of pixels whose grayscale value is less than the first grayscale threshold 30 is 150, and Determining that the second number of pixels whose gray value is greater than the second gray threshold 200 is 260, the terminal determines that the first ratio of the first 150 in the total number 1000 is 0.15, and determines the second number The second ratio of 260 in the total number is 0.26; if the terminal determines the maximum value of the first ratio and the second ratio as the light quality parameter of the image, since the first ratio is smaller than the second ratio, Therefore, the terminal can determine the second ratio 0.26 as the light quality parameter of the image 1.
  • the terminal filters the multiple images in the similar image set based on the ray quality parameters of the multiple images in the similar image set, so that the images with better light quality in the multiple images can be obtained, thereby The problem that the image of the first image set is too dark or overexposed when the image is displayed is avoided, and the image display effect is enhanced.
  • step 203 based on the face angle of the plurality of images in the first image set, an image having a face angle within a specified angle range is selected from the first image set to obtain a second image set.
  • a plurality of images included in the first image set there may be an image in which the face pose is not positive, and when there are images in the plurality of images whose face pose is not positive, when the plurality of images are displayed, the influence is affected.
  • the display effect of the plurality of images, and determining whether the face pose in the image is positive may be based on a face angle in the image. Therefore, in order to select a face image from the first image set to compare the front image, the terminal needs to be based on the A face angle of a plurality of images in an image set, and an image in which the face angle is within a specified angle range is selected from the first image set, thereby obtaining a second image set.
  • the face angle of the image 1 is 5 degrees
  • the face angle of the image 2 is 30 degrees
  • the face angle of the image 3 is 20 degrees
  • the face angle of the image 4 is 60 degrees
  • the specified angle range is 0 to 45.
  • the terminal selects an image having a face angle within a range of 0 to 45 degrees within a specified angle range from the first image set based on a face angle of the plurality of images in the first image set, and has an image 1, an image 2, and an image 3, Thereby a second image set is obtained.
  • the terminal selects an image whose face angle is within a specified angle range from the first image set based on a face angle of the plurality of images in the first image set, and the terminal may determine the second image set before obtaining the second image set.
  • the face angle of the plurality of images in the image set, and the operation of determining the face angle of the plurality of images in the first image set may be: the terminal acquiring the face feature points of the plurality of images in the first image set; For each image in the plurality of images, from the image, the first feature point and the second feature point are selected, and the first feature point and the second feature point are left and right symmetrical feature points centered on the nose; determining the first feature point a first distance from the specified feature point, and a second distance between the second feature point and the specified feature point; determining a face angle of the image based on the first distance and the second distance.
  • the specified feature point may be a feature point or two feature points.
  • the specified feature point may be located on a left-right symmetry line of the face, that is, On the straight line where the nose is located, for example, the face feature point of the image is as shown in FIG. 3, and the designated feature point may be the feature point G14 corresponding to the tip of the nose, or the feature point B12, B15 at the middle position of the lip, or the center of the chin.
  • the first feature point and the second feature point are left and right symmetrical feature points centered on the nose, for convenience of calculation, the first feature point and the second feature point may be determined as a face contour point, for example, the first The feature point is the feature point A11 in FIG. 3, and the second feature point is the feature point A19 in FIG. 3, which is also not specifically limited in the embodiment of the present disclosure.
  • the terminal determining the first distance and the second distance may be: the terminal determines the distance between the first feature point and the specified feature point as the first distance, and the second feature The distance of the point from the specified feature point is determined to be the second distance.
  • the terminal can determine the first distance and the second distance.
  • the distance between the specified feature point on the left side of the nose and the first feature point is determined as the first distance
  • the distance between the designated feature point on the right side of the nose and the second feature point is determined as The second distance.
  • the terminal may divide the first distance by the second distance to obtain a third ratio, and the terminal is stored according to the third ratio.
  • the ratio and the face angle the corresponding face angle is obtained, and the acquired face angle is determined as the face angle of the image.
  • the specified feature point is a feature point
  • the designated feature point is a feature point G14 corresponding to the nose tip
  • the terminal acquires a face feature point of the image 1 in the first image set as shown in FIG. 3, from the image 1 In the face feature point, the selected first feature point is the feature point A11 of the left face contour, and the second feature point is the feature point A19 of the right face contour,
  • the first feature point A11 and the second feature point A19 are bilaterally symmetric about the nose.
  • the terminal determines that the first distance between the first feature point A11 and the designated feature point G14 is 36 mm, and determines the second feature point A19 point and the designation.
  • the second distance between the feature points G14 is 40 mm.
  • the terminal divides the first distance by 36 mm by the second distance by 40 mm, and obtains a third ratio of 0.9.
  • the terminal is based on the third ratio of 0.9, as shown in Table 1 below.
  • the corresponding face angle is 5 degrees, and the terminal determines the acquired face angle of 5 degrees as the face angle of the image.
  • the terminal when the terminal acquires facial feature points of multiple images in the first image set, the terminal can obtain not only the facial feature points of the multiple images by the SDM (Sparse Deforming Model) algorithm, of course.
  • the terminal may also obtain facial feature points of the plurality of images by using other algorithms, such as an ASM (Active Shape Model) algorithm, an AAM (Active Appearance Model) algorithm, and the like.
  • ASM Active Shape Model
  • AAM Active Appearance Model
  • the terminal filters the plurality of images in the first image set based on the face angle of the plurality of images in the first image set, and obtains an image with a relatively positive face angle in the plurality of images. Therefore, the problem that the face image is not too positive when the image is displayed in the second image set is avoided, so that the selected image is closer to the visual requirement of the user, and the image display effect is enhanced.
  • step 204 based on the eye features of the plurality of images in the second image set, an image of the non-closed eyes is selected from the second image set to obtain a third image set.
  • the terminal needs to select an image of the non-closed eye from the second image set based on the eye features of the plurality of images in the second image set to obtain a third image set.
  • the terminal is configured to select an image of the non-closed eye from the second image set based on the eye features of the plurality of images in the second image set, wherein the terminal acquires the image for each image of the multiple images.
  • Eye feature points and based on all eye feature points of the image, determine the classification result by specifying a classifier, when the classification result is the first number
  • the terminal determines that the image is an image with a closed eye, and when the classification result is a second value, the terminal determines that the image is an image that is not closed.
  • first value and the second value may be set in advance, and the first value and the second value are not equal.
  • first value may be 1, and the second value may be 0, etc. No specific restrictions.
  • the terminal uses the specified classifier to determine whether the image is a closed-eye image, or the specific operation of the non-closed-eye image may refer to related technologies, which is not described in detail in the embodiments of the present disclosure.
  • the first value is 1, and the second value is 0.
  • the terminal acquires the eye feature points of the image 1 and the image 2 in the second image set, and passes the specified classifier based on all the eye feature points of the image 1. Determining that the classification result of the image 1 is 0, the terminal determines that the image 1 is a non-closed eye image, and the terminal determines, according to all the eye feature points of the image 2, the classification result of the image 2 by using the designated classifier. 1.
  • the terminal determines that the image 2 is an image of a closed eye, and the terminal determines, according to all the eye feature points of the image 3, that the classification result of the image 3 is 0 by using the designated classifier, and the terminal determines that the image 3 is not In the image of the closed eye, the terminal selects the image of the non-closed eye as the image 1 and the image 3 from the second image set, thereby obtaining the third image set.
  • the terminal filters the plurality of images in the second image set based on the eye features of the plurality of images in the second image set, so as to obtain an image of the non-closed eyes in the plurality of images, thereby avoiding
  • the third image set has a problem of closing eyes when the image is displayed, so that the display effect of the selected image is better.
  • step 205 based on the face sharpness of the plurality of images in the third image set, an image whose face sharpness is greater than or equal to the specified sharpness is selected from the third image set, and a representative image of the similar image set is obtained.
  • the terminal needs to be based on the face sharpness of the plurality of images in the third image set, from the third image set, An image whose face definition is greater than or equal to the specified sharpness is selected to obtain a representative image of the similar image set.
  • the specified definition is used to determine whether the face of the plurality of images is clear, and the specified definition may be set in advance.
  • the specified definition may be 180, 200, etc., and the embodiment of the present disclosure is This is not specifically limited.
  • the face resolution of the image 1 is 80
  • the face resolution of the image 2 is 200
  • the specified definition is 180
  • the terminal is based on the face sharpness of the plurality of images in the third image set, from the third image.
  • the image whose face resolution is greater than or equal to the specified sharpness 180 is selected to have the image 1, so that the representative image of the similar image set is the image 1.
  • the terminal selects an image whose face sharpness is greater than or equal to a specified sharpness from the third image set based on the face sharpness of the plurality of images in the third image set, and obtains a representative image of the similar image set.
  • the terminal may also determine the face sharpness of the plurality of images in the third image set, and the operation of determining the face sharpness of the plurality of images in the third image set may be: for each of the plurality of images of the third image set An image obtained by acquiring a pixel value of each pixel included in the face region of the image; determining a gradient cumulative of the face region based on the pixel value of each pixel Value; the gradient cumulative value is determined as the face sharpness of the image.
  • the operation of acquiring, by the terminal, the pixel value of each pixel point included in the face region of the image may be: for each of the plurality of images of the third image set a picture, the terminal performs face detection on the image, and determines the detected face area as a face area of the image, and the terminal acquires each pixel point included in the face area based on the determined face area Pixel values.
  • the specific operation of the terminal for performing face detection on the image may refer to related technologies such as face detection, which are not elaborated in this embodiment of the present disclosure.
  • the determining, by the terminal, the gradient integrated value of the face region based on the pixel value of each pixel point may be: the terminal subtracts the pixel values of the two adjacent pixel points in the horizontal direction of the face region. Obtaining a plurality of pixel difference values in the horizontal direction, and determining a sum of the plurality of pixel difference values in the horizontal direction as the first gradient value. Similarly, the terminal sequentially adjacent the face region in the vertical direction.
  • the pixel values of the two pixels are subtracted to obtain a plurality of pixel difference values in the vertical direction, and the sum of the plurality of pixel difference values in the vertical direction is determined as the second gradient value, and the terminal sets the first gradient value And the sum of the second gradient values is determined as the gradient cumulative value of the face region.
  • the terminal selects multiple images in the third image set based on the face sharpness of the plurality of images in the third image set, and obtains a better face resolution in the multiple images.
  • the image thus enhances the sharpness of the image when representing the image display.
  • the terminal may not only perform screening by using the above steps 202-205 to obtain a representative image of the similar image set, but the terminal may also pass the above step 202. Performing the screening, or performing the screening by the above steps 202-203, or by performing the above-mentioned steps 202-204 to obtain a representative image of the similar image set. Of course, in practical applications, the terminal may also pass the above steps 202-205. Any one of the steps, or any combination of any of the plurality of steps, is performed to obtain a representative image of the similar image set, which is not specifically limited in the embodiment of the present disclosure.
  • the terminal when the terminal filters a plurality of images in each similar image set, the terminal can pass not only the light quality parameters, the face angle, the eye features, and the face of the image mentioned in the above steps 202-205.
  • the screening may be performed according to the resolution, the contrast, the color saturation, and the like. The embodiment of the present disclosure does not specifically limit this.
  • step 206 the representative images of the plurality of similar image sets are displayed.
  • the operation of the terminal to display the representative image of the plurality of similar image sets may be: the terminal rotationally aligns the representative images of the plurality of similar image sets, so that the face orientation in the representative image of the plurality of similar image sets The same is true; each representative image after the rotation alignment is adjusted so that the size of the face region in each of the adjusted representative images is equal; and the adjusted representative image is displayed in the designated dynamic display form.
  • the terminal When the terminal rotates and aligns the representative images of the plurality of similar image sets such that the face directions in the representative images of the plurality of similar image sets are the same, the terminal can not only rotate the representative image to the left, but also The embodiment of the present disclosure does not specifically limit the rotation to the right, the horizontal flip, the vertical flip, or the rotation at any angle.
  • the terminal when the terminal adjusts each of the representative images after the rotation alignment so that the size of the face region in each of the adjusted representative images is equal, the terminal can represent the faces in the plurality of representative images based on the specified size.
  • the representative image of the smaller area is enlarged, and the representative image having a larger face area is reduced so that the size of the face area of each of the adjusted representative images is equal.
  • the specified size may be set in advance, and when the specified size is set, it may be set based on the screen size of the terminal, or may be set based on any representative image in the plurality of representative images, for example, the terminal.
  • the screen size is 4.5 inches, and the specified size can be set to 2.5 inches, 3 inches, and the like, which is not specifically limited in the embodiment of the present disclosure.
  • the terminal when the terminal displays the adjusted representative image in a designated dynamic display form, the terminal can not only display the representative image of the plurality of similar image sets in a specified dynamic display form according to the storage time of the image, The terminal can also randomly display the representative images of the plurality of similar image sets in a specified dynamic display form, thereby forming a time-dynamic dynamic photo album centered on the user corresponding to the representative image, so as to give the user a strong shock force and
  • the specific embodiments of the present disclosure do not specifically limit the specific dynamic display form.
  • the specified dynamic display form may be not only a form of a slideshow, but also a display form of other dynamics, and the like.
  • the terminal may In the plurality of representative images in the similar image set, one or two images are randomly selected for display.
  • the terminal may display multiple browsing modes, so that the user selects a dynamic display form, and the terminal receives the multiple browsing modes.
  • the terminal can display the image of the album in a dynamic display form based on the method provided in the above steps 201-206.
  • the terminal can also set the image display method of the above steps 201-206 as the default display method.
  • the terminal can automatically display the image in the specified dynamic display format to enhance the image display effect. , giving people a strong shock and attraction.
  • the terminal displays the image of the album in the specified dynamic display form, or after the terminal finishes displaying the image of the album, if the terminal receives the display end instruction, the terminal may exit the representative image display of the album.
  • the terminal may display the multiple browsing modes directly when receiving the album opening instruction, so that the user selects from the multiple browsing modes, and of course, the terminal further By designating a button, when the user clicks the designated button, the terminal displays a drop-down menu, and the pull-down menu includes the plurality of browsing modes, so that the user can select from the plurality of browsing modes, so that the user does not need to select to browse. In the case of the mode, it is avoided to directly display the multiple browsing modes to bring unnecessary interference to the user.
  • the display instruction of the dynamic image is used to display an image of the album in a dynamic display format, and the display instruction of the dynamic image is triggered by a user, and the user can trigger by clicking an operation such as a designated button, and the embodiment of the present disclosure
  • the display end instruction is used to end the display of the representative image, and the display end instruction can be triggered by the user, and the user can trigger by clicking, sliding, shaking, etc.
  • the disclosed embodiments do not specifically limit this.
  • the terminal may not only select a representative image from the album for display according to the manner of the above steps 201-206, of course, the terminal may first perform an image on the album before receiving the album open command. Similar image clustering, obtaining a plurality of similar image sets, screening a plurality of images in each similar image set to obtain a representative image of the similar image set, and then, when the terminal receives an album open command, the terminal will The representative images of the plurality of similar image sets are displayed, which saves image display time and improves image display efficiency.
  • the terminal when the terminal displays the representative image of the plurality of similar image sets, the terminal can not only display the representative image of the plurality of similar image sets in the specified dynamic display form when receiving the album opening instruction. And of course, the terminal may further select a dynamic image display template from the dynamic image display template library before receiving the album open command, and fill the representative image of the plurality of similar image sets into the dynamic image display template. Thus, a dynamic image album is formed. When the terminal receives the album opening instruction, the terminal directly displays the dynamic image album, thereby enhancing the display effect of the image, giving a strong shock and attraction.
  • the dynamic image display template library may be stored in the terminal in advance, or may be a dynamic image display template library acquired by the terminal from the server, which is not specifically limited in the embodiment of the present disclosure.
  • the terminal when the terminal performs similar image clustering on the album before receiving the album opening instruction, and screening each similar image collection, since the image in the album can be updated at any time, that is, The user can delete, add, and the like in the album at any time. Therefore, in order to update the representative image selected from the album in time, the terminal can periodically perform similar image clustering on the album, and A similar image collection is screened to update the filtered representative image and improve the display accuracy of the image.
  • the length of the period in which the terminal updates the representative image selected in the album may be a specified duration.
  • the specified duration may be 1 week, 2 weeks, 1 month, etc.
  • the terminal also It can be determined that the number of image updates in the album is updated once when it is a specified value.
  • the specified value may be 10, 20, etc., which is not specifically limited in the embodiment of the present disclosure.
  • the terminal when the terminal receives the album opening instruction, the terminal performs similar image clustering on the image in the album to obtain a plurality of similar image sets, for each similar image set in the plurality of similar image sets. And filtering multiple images in the similar image set based on the light quality parameter, the face angle, the eye feature, and the face sharpness respectively, thereby obtaining a representative image with better image quality in the similar image set, which is more
  • a representative image with better image quality in a similar image collection is displayed in a specified dynamic display form, thereby enriching the display form of the album, and enhancing the display effect of the representative image, giving a strong shock and attraction.
  • FIG. 4 is a block diagram of an image display device according to an exemplary embodiment.
  • the apparatus includes a clustering module 401, a screening module 402, and a display module 403.
  • the clustering module 401 is configured to perform similar image clustering on the images in the album when the album opening instruction is received, to obtain a plurality of similar image sets;
  • the screening module 402 is configured to perform screening on multiple images in each similar image set to obtain the similar image collection. Representative image
  • the display module 403 is configured to display the representative images of the plurality of similar image sets.
  • the screening module 402 includes a first selection unit 4021.
  • a first selecting unit 4021 configured to: for each similar image set in the plurality of similar image sets, select a ray quality parameter from the similar image set to be smaller than a ray threshold based on ray quality parameters of the plurality of images in the similar image set The image gets the first image collection.
  • the screening module 402 further includes a second selection unit 4022.
  • the second selecting unit 4022 is configured to select an image with a face angle within a specified angle range from the first image set based on a face angle of the plurality of images in the first image set to obtain a second image set.
  • the screening module 402 further includes a third selecting unit 4023.
  • the third selecting unit 4023 is configured to select an image of the non-closed eye from the second image set based on the eye features of the plurality of images in the second image set to obtain a third image set.
  • the screening module 402 further includes a fourth selection unit 4024.
  • the fourth selecting unit 4024 is configured to select, according to the face sharpness of the plurality of images in the third image set, an image whose face sharpness is greater than or equal to the specified sharpness from the third image set, to obtain the similar image set. Represents an image.
  • the screening module 402 further includes a converting unit 4025, a first determining unit 4026, a second determining unit 4027, and a third determining unit 4028.
  • the converting unit 4025 is configured to convert the plurality of images in the similar image set into a grayscale image
  • a first determining unit 4026 configured to determine, for each image in the plurality of images, a first number of pixels whose gray value is smaller than the first gray threshold from the grayscale image corresponding to the image, and determine gray a second number of pixels having a degree greater than the second gray threshold;
  • a second determining unit 4027 configured to determine a first ratio of the first number in the total number, and determine a second ratio of the second number in the total number, the total number is the gray The number of all pixels in the graph;
  • the third determining unit 4028 is configured to determine a light quality parameter of the image based on the first ratio and the second ratio.
  • the screening module 402 further includes a first obtaining unit 4029, a fifth selecting unit 40210, a fourth determining unit 40211, and a fifth determining unit 40212.
  • a first acquiring unit 4029 configured to acquire a facial feature point of multiple images in the first image set
  • a fifth selecting unit 40210 configured to select, from each of the plurality of images, a first feature point and a second feature point, wherein the first feature point and the second feature point are around the nose Symmetrical feature points;
  • a fourth determining unit 40211 configured to determine a first distance between the first feature point and the specified feature point, and determine a second distance between the second feature point and the specified feature point;
  • the fifth determining unit 40212 is configured to determine a face angle of the image based on the first distance and the second distance.
  • the screening module 402 further includes a second obtaining unit 40213, a sixth determining unit 40214, and a seventh determining unit 40215.
  • a second obtaining unit 40213, configured to acquire, for each image of the multiple images of the third image set The pixel value of each pixel included in the face region;
  • a sixth determining unit 40214 configured to determine a gradient cumulative value of the face region based on a pixel value of each pixel point
  • the seventh determining unit 40215 is configured to determine the gradient integrated value as the face sharpness of the image.
  • the display module 403 includes a rotation unit 4031, an adjustment unit 4032, and a display unit 4033.
  • a rotating unit 4031 configured to rotate and align the representative images of the plurality of similar image sets, so that the face directions in the representative images of the plurality of similar image sets are the same;
  • the adjusting unit 4032 is configured to adjust each representative image after the rotation alignment so that the size of the face region in each of the adjusted representative images is equal;
  • the display unit 4033 is configured to display the adjusted representative image in a specified dynamic display form.
  • one or two sheets are randomly selected for display.
  • the image in the album is clustered by similar images to obtain a plurality of similar image sets, and multiple images in each similar image set are filtered to obtain
  • the representative image with better image quality in the similar image set displays the representative image with better image quality among the plurality of similar image sets, thereby enhancing the display effect of the representative images of the plurality of similar image sets.
  • FIG. 13 is a block diagram of an apparatus 1300 for image display, according to an exemplary embodiment.
  • device 1300 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a gaming console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.
  • device 1300 can include one or more of the following components: processing component 1302, memory 1304, power component 1306, multimedia component 1308, audio component 1310, input/output (I/O) interface 1312, sensor component 1314, And a communication component 1316.
  • Processing component 1302 typically controls the overall operation of device 1300, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • Processing component 1302 can include one or more processors 1320 to execute instructions to perform all or part of the steps of the above described methods.
  • processing component 1302 can include one or more modules to facilitate interaction between component 1302 and other components.
  • processing component 1302 can include a multimedia module to facilitate interaction between multimedia component 1308 and processing component 1302.
  • Memory 1304 is configured to store various types of data to support operation at device 1300. Examples of such data include instructions for any application or method operating on device 1300, contact data, phone book data, messages, pictures, videos, and the like.
  • Memory 1304 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), Magnetic memory, flash memory, disk or optical disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM erasable Programmable read only memory
  • PROM programmable read only memory
  • ROM read only memory
  • Magnetic memory flash memory, disk or optical disk.
  • Power component 1306 provides power to various components of device 1300.
  • Power component 1306 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for device 1300.
  • the multimedia component 1308 includes a screen between the device 1300 and the user that provides an output interface.
  • the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may sense not only the boundary of the touch or sliding action, but also the duration and pressure associated with the touch or slide operation.
  • the multimedia component 1308 includes a front camera and/or a rear camera. When the device 1300 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 1310 is configured to output and/or input an audio signal.
  • the audio component 1310 includes a microphone (MIC) that is configured to receive an external audio signal when the device 1300 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode.
  • the received audio signal may be further stored in memory 1304 or transmitted via communication component 1316.
  • the audio component 1310 also includes a speaker for outputting an audio signal.
  • the I/O interface 1312 provides an interface between the processing component 1302 and the peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to, a home button, a volume button, a start button, and a lock button.
  • Sensor assembly 1314 includes one or more sensors for providing device 1300 with a status assessment of various aspects.
  • sensor assembly 1314 can detect an open/closed state of device 1300, a relative positioning of components, such as the display and keypad of device 1300, and sensor component 1314 can also detect a change in position of one component of device 1300 or device 1300. The presence or absence of contact by the user with the device 1300, the orientation or acceleration/deceleration of the device 1300 and the temperature change of the device 1300.
  • Sensor assembly 1314 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • Sensor assembly 1314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor component 1314 can also include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • Communication component 1316 is configured to facilitate wired or wireless communication between device 1300 and other devices.
  • the device 1300 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof.
  • the communication component 1316 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel.
  • the communication component 1316 also includes a near field communication (NFC) module to facilitate short range communication.
  • NFC near field communication
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • apparatus 1300 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), A gated array (FPGA), controller, microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA gated array
  • controller microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
  • non-transitory computer readable storage medium comprising instructions, such as a memory 1304 comprising instructions executable by processor 1320 of apparatus 1300 to perform the above method.
  • the non-transitory computer readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.
  • a non-transitory computer readable storage medium when instructions in the storage medium are executed by a processor of a mobile terminal, to enable the mobile terminal to perform an image display method, the method comprising:
  • a plurality of images in each similar image set are filtered to obtain a representative image of the similar image set.
  • a representative image of the plurality of similar image sets is displayed.
  • screening a plurality of images in each similar image set to obtain a representative image of the similar image set includes:
  • an image with a ray quality parameter smaller than a ray threshold is selected from the similar image set to obtain a first image set.
  • the method further includes:
  • an image of the face angle within a specified angle range is selected from the first image set to obtain a second image set.
  • the method further includes:
  • an image of the non-closed eyes is selected from the second image set to obtain a third image set.
  • the method further includes:
  • the method based on the ray quality parameter of the plurality of images in the similar image set, from the similar image set, selecting an image whose ray quality parameter is smaller than a ray threshold, before obtaining the first image set, the method also includes:
  • a light quality parameter of the image is determined based on the first ratio and the second ratio.
  • the method based on the face angle of the plurality of images in the first image set, from the first image set, selecting an image whose face angle is within a specified angle range, before obtaining the second image set, The method also includes:
  • first feature point and a second feature point For each image of the plurality of images, from the image, selecting a first feature point and a second feature point, wherein the first feature point and the second feature point are left and right symmetrical feature points centered on the nose;
  • a face angle of the image is determined based on the first distance and the second distance.
  • the method further includes:
  • the gradient cumulative value is determined as the face sharpness of the image.
  • displaying the representative images of the plurality of similar image sets includes:
  • the adjusted representative image is displayed in the specified dynamic display format.
  • one or two sheets are randomly selected for display.
  • the image in the album is clustered by similar images to obtain a plurality of similar image sets, and multiple images in each similar image set are filtered to obtain
  • the representative image with better image quality in the similar image set displays the representative image with better image quality among the plurality of similar image sets, thereby enhancing the display effect of the representative images of the plurality of similar image sets.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Signal Processing (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Library & Information Science (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Geometry (AREA)
  • Databases & Information Systems (AREA)
  • Image Processing (AREA)
  • Processing Or Creating Images (AREA)
  • Image Analysis (AREA)
  • User Interface Of Digital Computer (AREA)
  • Editing Of Facsimile Originals (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

一种图像显示方法及装置，属于终端技术领域。所述方法包括：当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合（101）；对于每个所述相似图像集合中的多张图像进行筛选，得到所述相似图像集合的代表图像（102）；将所述多个相似图像集合的代表图像进行显示（103）。所述方法通过对相册中的图像进行相似图像聚类，得到多个相似图像集合，从得到的多个相似图像集合中筛选出图像质量较好的代表图像，并将该代表图像进行显示，从而增强了该多个相似图像集合的代表图像的显示效果。

Description

图像显示方法及装置
本申请基于申请号为201510452003.3、申请日为2015年7月28日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及终端技术领域，尤其涉及一种图像显示方法及装置。
背景技术
随着终端技术的快速发展，出现了越来越多具有图像显示功能的终端，比如，手机、平板电脑、计算机等，这些终端可以将存储的多张图像进行显示。而相关技术中，当终端将存储的多张图像进行显示时，该终端按照该多张图像的图像存储时间，将该多张图像以缩略图的形式进行显示，而一旦该多张图像中存在相似或者拍摄质量较差的图像，会导致图像显示效果比较差，因此，亟需一种增强显示效果的图像显示方法。
发明内容
为克服相关技术中存在的问题，本公开提供一种图像显示方法及装置。
根据本公开实施例的第一方面，提供一种图像显示方法，所述方法包括：
当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合；
对于每个所述相似图像集合中的多张图像进行筛选，得到所述相似图像集合的代表图像；
将所述多个相似图像集合的代表图像进行显示。
在本公开实施例中，当该终端接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合，对于每个相似图像集合中的多张图像进行筛选，从而得到该相似图像集合中图像质量较好的代表图像，将该多个相似图像集合中图像质量较好的代表图像进行显示，从而增强该多个相似图像集合的代表图像的显示效果。
结合第一方面，在上述第一方面的第一种可能的实现方式中，对于每个相似图像集合中的多张图像进行筛选，得到所述相似图像集合的代表图像，包括：
基于所述相似图像集合中多张图像的光线质量参数，从所述相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合。
在本公开实施例中，该终端基于该相似图像集合中多张图像的光线质量参数，对该相似图像集合中多张图像进行筛选，可以得到该多张图像中光线质量较好的图像，从而避免了第一图像集合在图像显示时出现图像太黑或曝光过度的问题，增强图像显示效果。
结合第一方面的第一种可能的实现方式，在上述第一方面的第二种可能的实现方式中，所述方法还包括：
基于所述第一图像集合中多张图像的人脸角度，从所述第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合。
在本公开实施例中，该终端基于第一图像集合中多张图像的人脸角度，对第一图像集合中多张图像进行筛选，可以得到该多张图像中人脸角度比较正面的图像，从而避免了第二图像集合在图像显示时出现人脸姿态不太正面的问题，使选择的图像更贴近于用户的视觉需求，增强图像显示效果。
结合第一方面的第二种可能的实现方式，在上述第一方面的第三种可能的实现方式中，所述方法还包括：
基于所述第二图像集合中多张图像的眼部特征，从所述第二图像集合中，选择非闭眼的图像，得到第三图像集合。
在本公开实施例中，该终端基于第二图像集合中多张图像的眼部特征，对第二图像集合中多张图像进行筛选，可以得到该多张图像中非闭眼的图像，从而避免了第三图像集合在图像显示时出现闭眼的问题，使选择的图像的显示效果较好。
结合第一方面的第三种可能的实现方式，在上述第一方面的第四种可能的实现方式中，所述方法还包括：
基于所述第三图像集合中多张图像的人脸清晰度，从所述第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到所述相似图像集合的代表图像。
在本公开实施例中，该终端基于第三图像集合中多张图像的人脸清晰度，对第三图像集合中多张图像进行筛选，可以得到该多张图像中人脸清晰度较好的图像，从而提高了代表图像显示时的图像清晰度。
结合第一方面的第一种可能的实现方式，在上述第一方面的第五种可能的实现方式中，基于所述相似图像集合中多张图像的光线质量参数，从所述相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合之前，还包括：
将所述相似图像集合中多张图像转换为灰度图；
对于所述多张图像中每张图像，从所述图像对应的灰度图中，确定灰度值小于第一灰度阈值的像素点的第一个数，以及确定灰度值大于第二灰度阈值的像素点的第二个数；
确定所述第一个数在总个数中所占的第一比例，以及确定所述第二个数在所述总个数中所占的第二比例，所述总个数为所述灰度图中所有像素点的个数；
基于所述第一比例和所述第二比例，确定所述图像的光线质量参数。
在本公开实施例中，该终端通过确定图像的光线质量参数，对该相似图像集合中多张图像进行人脸角度筛选，可以得到该多张图像中光线质量较好的图像，从而避免了第一图像集合在图像显示时出现图像太黑或曝光过度的问题，增强图像显示效果。
结合第一方面的第二种可能的实现方式，在上述第一方面的第六种可能的实现方式 中，基于所述第一图像集合中多张图像的人脸角度，从所述第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合之前，还包括：
获取所述第一图像集合中多张图像的人脸特征点；
对于所述多张图像中每张图像，从所述图像中，选择第一特征点和第二特征点，所述第一特征点和所述第二特征点为以鼻子为中心的左右对称的特征点；
确定所述第一特征点与指定特征点之间的第一距离，以及确定所述第二特征点与所述指定特征点之间的第二距离；
基于所述第一距离和所述第二距离，确定所述图像的人脸角度。
在本公开实施例中，该终端通过确定图像的人脸角度，对第一图像集合中多张图像进行人脸角度筛选，得到该多张图像中人脸角度比较正面的图像，从而避免了第二图像集合在图像显示时出现人脸姿态不正面的问题，使选择的图像更贴近于用户的视觉需求，增强图像显示效果。
结合第一方面的第四种可能的实现方式，在上述第一方面的第七种可能的实现方式中，基于所述第三图像集合中多张图像的人脸清晰度，从所述第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到所述相似图像集合的代表图像之前，还包括：
对于所述第三图像集合的多张图像中每张图像，获取所述图像的人脸区域包括的每个像素点的像素值；
基于所述每个像素点的像素值，确定所述人脸区域的梯度累计值；
将所述梯度累计值确定为所述图像的人脸清晰度。
在本公开实施例中，该终端通过确定图像的人脸清晰度，从而对第三图像集合中多张图像进行人脸清晰度筛选，得到该多张图像中人脸清晰度较好的图像，从而提高了代表图像显示时的图像清晰度。
结合第一方面，在上述第一方面的第八种可能的实现方式中，将所述多个相似图像集合的代表图像进行显示包括：
将所述多个相似图像集合的代表图像进行旋转对齐，使所述多个相似图像集合的代表图像中的人脸方向相同；
将旋转对齐后的每张代表图像进行调整，使调整后的每张代表图像中人脸区域的尺寸相等；
将调整后的代表图像，以指定动态显示形式进行显示。
在本公开实施例中，该终端通过对该多个相似图像集合的代表图像进行旋转和调整，并将调整后的代表图像，以指定动态显示形式进行显示，从而丰富显示形式，增强代表图像的显示效果。
结合第一方面的第八种可能的实现方式，在上述第一方面的第九种可能的实现方式中，当所述相似图像集合中有多个代表图像时，随机选取1张或者2张进行显示。
在本公开的实施例中，当该相似图像集合中有多个代表图像时，该终端随机选取1张 或者2张进行显示，从而避免了将相似的多张代表图像进行显示时会显得单调的问题。
根据本公开实施例的第二方面，提供一种图像显示装置，所述装置包括：
聚类模块，用于当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合；
筛选模块，用于对于每个所述相似图像集合中的多张图像进行筛选，得到所述相似图像集合的代表图像；
显示模块，用于将所述多个相似图像集合的代表图像进行显示。
结合第二方面，在上述第二方面的第一种可能的实现方式中，所述筛选模块包括：
第一选择单元，用于对于所述多个相似图像集合中每个相似图像集合，基于所述相似图像集合中多张图像的光线质量参数，从所述相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合。
结合第二方面的第一种可能的实现方式，在上述第二方面的第二种可能的实现方式中，所述筛选模块还包括：
第二选择单元，用于基于所述第一图像集合中多张图像的人脸角度，从所述第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合。
结合第二方面的第二种可能的实现方式，在上述第二方面的第三种可能的实现方式中，所述筛选模块还包括：
第三选择单元，用于基于所述第二图像集合中多张图像的眼部特征，从所述第二图像集合中，选择非闭眼的图像，得到第三图像集合。
结合第二方面的第三种可能的实现方式，在上述第二方面的第四种可能的实现方式中，所述筛选模块还包括：
第四选择单元，用于基于所述第三图像集合中多张图像的人脸清晰度，从所述第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到所述相似图像集合的代表图像。
结合第二方面的第一种可能的实现方式，在上述第二方面的第五种可能的实现方式中，所述筛选模块还包括：
转换单元，用于将所述相似图像集合中多张图像转换为灰度图；
第一确定单元，用于对于所述多张图像中每张图像，从所述图像对应的灰度图中，确定灰度值小于第一灰度阈值的像素点的第一个数，以及确定灰度值大于第二灰度阈值的像素点的第二个数；
第二确定单元，用于确定所述第一个数在总个数中所占的第一比例，以及确定所述第二个数在所述总个数中所占的第二比例，所述总个数为所述灰度图中所有像素点的个数；
第三确定单元，用于基于所述第一比例和所述第二比例，确定所述图像的光线质量参数。
结合第二方面的第二种可能的实现方式，在上述第二方面的第六种可能的实现方式 中，所述筛选模块还包括：
第一获取单元，用于获取所述第一图像集合中多张图像的人脸特征点；
第五选择单元，用于对于所述多张图像中每张图像，从所述图像中，选择第一特征点和第二特征点，所述第一特征点和所述第二特征点为以鼻子为中心的左右对称的特征点；
第四确定单元，用于确定所述第一特征点与指定特征点之间的第一距离，以及确定所述第二特征点与所述指定特征点之间的第二距离；
第五确定单元，用于基于所述第一距离和所述第二距离，确定所述图像的人脸角度。
结合第二方面的第四种可能的实现方式，在上述第二方面的第七种可能的实现方式中，所述筛选模块还包括：
第二获取单元，用于对于所述第三图像集合的多张图像中每张图像，获取所述图像的人脸区域包括的每个像素点的像素值；
第六确定单元，用于基于所述每个像素点的像素值，确定所述人脸区域的梯度累计值；
第七确定单元，用于将所述梯度累计值确定为所述图像的人脸清晰度。
结合第二方面，在上述第二方面的第八种可能的实现方式中，所述显示模块包括：
旋转单元，用于将所述多个相似图像集合的代表图像进行旋转对齐，使所述多个相似图像集合的代表图像中的人脸方向相同；
调整单元，用于将旋转对齐后的每张代表图像进行调整，使调整后的每张代表图像中人脸区域的尺寸相等；
显示单元，用于将调整后的代表图像，以指定动态显示形式进行显示。
结合第二方面的第八种可能的实现方式，在上述第二方面的第九种可能的实现方式中，当所述相似图像集合中有多个代表图像时，随机选取1张或者2张进行显示。
根据本公开实施例的第三方面，提供一种图像显示装置，所述装置包括：
处理器；
用于存储处理器可执行指令的存储器；
其中，所述处理器被配置为：
当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合；
对于每个所述相似图像集合中的多张图像进行筛选，得到所述相似图像集合的代表图像；
将所述多个相似图像集合的代表图像进行显示。
本公开的实施例提供的技术方案可以包括以下有益效果：当该终端接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合，对于每个相似图像集合中的多张图像进行筛选，从而得到该相似图像集合中图像质量较好的代表图像，将该多个相似图像集合中图像质量较好的代表图像进行显示，从而增强该多个相似图像集合的代表图像的显示效果。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限 制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本发明的实施例，并与说明书一起用于解释本发明的原理。
图1是根据一示例性实施例示出的一种图像显示方法的流程图。
图2是根据一示例性实施例示出的另一种图像显示方法的流程图。
图3是根据一示例性实施例示出的一种人脸特征点的分布示意图。
图4是根据一示例性实施例示出的一种图像显示装置的框图。
图5是根据一示例性实施例示出的第一种筛选模块的框图。
图6是根据一示例性实施例示出的第二种筛选模块的框图。
图7是根据一示例性实施例示出的第三种筛选模块的框图。
图8是根据一示例性实施例示出的第四种筛选模块的框图。
图9是根据一示例性实施例示出的第五种筛选模块的框图。
图10是根据一示例性实施例示出的第六种筛选模块的框图。
图11是根据一示例性实施例示出的第七种筛选模块的框图。
图12是根据一示例性实施例示出的一种显示模块的框图。
图13是根据一示例性实施例示出的另一种图像显示装置的框图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本发明相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本发明的一些方面相一致的装置和方法的例子。
图1是根据一示例性实施例示出的一种图像显示方法的流程图，如图1所示，该方法用于终端中，包括以下步骤。
在步骤101中，当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合。
在步骤102中，对于每个相似图像集合中的多张图像进行筛选，得到该相似图像集合的代表图像。
在步骤103中，将该多个相似图像集合的代表图像进行显示。
在本公开实施例中，当该终端接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合，对于每个相似图像集合中的多张图像进行筛选，从而得到该相似图像集合中图像质量较好的代表图像，将该多个相似图像集合中图像质量较好的代表图像进行显示，从而增强该多个相似图像集合的代表图像的显示效果。
在本公开的另一实施例中，对每个相似图像集合中的多张图像进行筛选，得到该相似图像集合的代表图像包括：
基于该相似图像集合中多张图像的光线质量参数，从该相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合。
在本公开实施例中，该终端基于该相似图像集合中多张图像的光线质量参数，对该相似图像集合中多张图像进行筛选，可以得到该多张图像中光线质量较好的图像，从而避免了第一图像集合在图像显示时出现图像太黑或曝光过度的问题，增强图像显示效果。
在本公开的另一实施例中，该方法还包括：
基于第一图像集合中多张图像的人脸角度，从第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合。
在本公开实施例中，该终端基于第一图像集合中多张图像的人脸角度，对第一图像集合中多张图像进行筛选，可以得到该多张图像中人脸角度比较正面的图像，从而避免了第二图像集合在图像显示时出现人脸姿态不太正面的问题，使选择的图像更贴近于用户的视觉需求，增强图像显示效果。
在本公开的另一实施例中，该方法还包括：
基于第二图像集合中多张图像的眼部特征，从第二图像集合中，选择非闭眼的图像，得到第三图像集合。
在本公开实施例中，该终端基于第二图像集合中多张图像的眼部特征，对第二图像集合中多张图像进行筛选，可以得到该多张图像中非闭眼的图像，从而避免了第三图像集合在图像显示时出现闭眼的问题，使选择的图像的显示效果较好。
在本公开的另一实施例中，该方法还包括：
基于第三图像集合中多张图像的人脸清晰度，从第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到该相似图像集合的代表图像。
在本公开实施例中，该终端基于第三图像集合中多张图像的人脸清晰度，对第三图像集合中多张图像进行筛选，可以得到该多张图像中人脸清晰度较好的图像，从而提高了代表图像显示时的图像清晰度。
在本公开的另一实施例中，基于该相似图像集合中多张图像的光线质量参数，从该相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合之前，该方法还包括：
将该相似图像集合中多张图像转换为灰度图；
对于该多张图像中每张图像，从该图像对应的灰度图中，确定灰度值小于第一灰度阈值的像素点的第一个数，以及确定灰度值大于第二灰度阈值的像素点的第二个数；
确定第一个数在总个数中所占的第一比例，以及确定第二个数在总个数中所占的第二比例，该总个数为该灰度图中所有像素点的个数；
基于第一比例和第二比例，确定该图像的光线质量参数。
在本公开实施例中，该终端通过确定图像的光线质量参数，对该相似图像集合中多张图像进行人脸角度筛选，可以得到该多张图像中光线质量较好的图像，从而避免了第一图像集合在图像显示时出现图像太黑或曝光过度的问题，增强图像显示效果。
在本公开的另一实施例中，基于第一图像集合中多张图像的人脸角度，从第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合之前，该方法还包括：
获取第一图像集合中多张图像的人脸特征点；
对于该多张图像中每张图像，从该图像中，选择第一特征点和第二特征点，第一特征点和第二特征点为以鼻子为中心的左右对称的特征点；
确定第一特征点与该指定特征点之间的第一距离，以及确定第二特征点与该指定特征点之间的第二距离；
基于第一距离和第二距离，确定该图像的人脸角度。
在本公开实施例中，该终端通过确定图像的人脸角度，对第一图像集合中多张图像进行人脸角度筛选，得到该多张图像中人脸角度比较正面的图像，从而避免了第二图像集合在图像显示时出现人脸姿态不正面的问题，使选择的图像更贴近于用户的视觉需求，增强图像显示效果。
在本公开的另一实施例中，基于第三图像集合中多张图像的人脸清晰度，从第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到该相似图像集合的代表图像之前，该方法还包括：
对于第三图像集合的多张图像中每张图像，获取该图像的人脸区域包括的每个像素点的像素值；
基于每个像素点的像素值，确定该人脸区域的梯度累计值；
将该梯度累计值确定为该图像的人脸清晰度。
在本公开实施例中，该终端通过确定图像的人脸清晰度，从而对第三图像集合中多张图像进行人脸清晰度筛选，得到该多张图像中人脸清晰度较好的图像，从而提高了代表图像显示时的图像清晰度。
在本公开的另一实施例中，将该多个相似图像集合的代表图像进行显示包括：
将该多个相似图像集合的代表图像进行旋转对齐，使该多个相似图像集合的代表图像中的人脸方向相同；
将旋转对齐后的每张代表图像进行调整，使调整后的每张代表图像中人脸区域的尺寸相等；
将调整后的代表图像，以指定动态显示形式进行显示。
在本公开实施例中，该终端通过对该多个相似图像集合的代表图像进行旋转和调整，并将调整后的代表图像，以指定动态显示形式进行显示，从而丰富显示形式，增强代表图像的显示效果。
在本公开的另一实施例中，当该相似图像集合中有多个代表图像时，随机选取1张或 者2张进行显示。
在本公开的实施例中，当该相似图像集合中有多个代表图像时，该终端随机选取1张或者2张进行显示，从而避免了将相似的多张代表图像进行显示时会显得单调的问题。
上述所有可选技术方案，均可按照任意结合形成本公开的可选实施例，本公开实施例对此不再一一赘述。
图2是根据一示例性实施例示出的一种图像显示方法的流程图，如图2所示，该方法用于终端中，包括以下步骤。
在步骤201中，当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合。
当该终端接收到相册打开指令时，该终端对该相册中的所有图像进行相似图像聚类，也即是，该终端将该相册中相似或者相同的多张图像划分为一个集合，从而将该相册划分为多个集合，该多个集合即为多个相似图像集合。
需要说明的是，该相册打开指令用于打开该相册，且该相册打开指令可以由用户触发，该用户可以通过指定操作来触发，该指定操作可以是点击操作、滑动操作、语音操作等等，本公开实施例对此不做具体限定。
另外，该终端对该相册中图像进行相似图像聚类的具体操作可以参考相似聚类等相关技术，本公开实施例对此不做详细阐述。
在步骤202中，对每个相似图像集合中的多张图像，该终端基于该相似图像集合中多张图像的光线质量参数，从该相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合。
由于该相似图像集合包括的多张图像中，可能存在光线较暗或者光线较亮的图像，也即是，该相似图像集合包括的多张图像中，可能存在太黑或者曝光过度的图像，因此，为了从该相似图像集合中选择光线质量较好的图像，该终端需要基于该相似图像集合中多张图像的光线质量参数，从该相似图像集合中，选择光线质量参数小于光线阈值的图像，从而得到第一图像集合。
需要说明的是，该光线阈值可以事先设置，且该光线阈值大于0且小于1，比如，该光线阈值可以为0.8、0.9等等，本公开实施例对此不做具体限定。
比如，该相似图像集合包括5张图像，且该5张图像分别为图像1、图像2、图像3、图像4和图像5，图像1对应的光线质量参数为0.26，图像2对应的光线质量参数为0.4，图像3对应的光线质量参数为0.7，图像4对应的光线质量参数为0.3，图像5对应的光线质量参数为0.9，该光线阈值为0.8，该终端基于该相似图像集合中多张图像的光线质量参数，从该相似图像集合中，选择光线质量参数小于光线阈值0.8的图像有图像1、图像2、图像3和图像4，从而该终端确定该相似图像集合中满足光线质量参数的图像为图像1、图像2、图像3和图像4，从而得到第一图像集合。
进一步地，该终端基于该相似图像集合中多张图像的光线质量参数，从该相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合之前，该终端还可以确定该相似图像集合中多张图像的光线质量参数，而确定该相似图像集合中多张图像的光线质量参数的操作可以为：将该相似图像集合中的多张图像转换为灰度图；对于该多张图像中每张图像，该终端从该图像对应的灰度图中，确定灰度值小于第一灰度阈值的像素点的第一个数，以及确定灰度值大于第二灰度阈值的像素点的第二个数；该终端确定第一个数在总个数中所占的第一比例，以及确定第二个数在总个数中所占的第二比例，总个数为该灰度图中所有像素点的个数；该终端基于第一比例和第二比例，确定该图像的光线质量参数。
其中，该终端基于第一比例和第二比例，确定该图像的光线质量参数时，该终端可以将第一比例和第二比例中的至少一个确定为该图像的光线质量参数，当然，该终端还可以从第一比例和第二比例中，选择一个最大值，将选择的最大值确定为该图像的光线质量参数，本公开实施例对此不做具体限定。
需要说明的是，第一灰度阈值和第二灰度阈值可以事先设置，且第二灰度阈值大于第一灰度阈值，比如，第一灰度阈值可以为30，第二灰度阈值可以为200，本公开实施例对此不做具体限定。
比如，第一灰度阈值为30，第二灰度阈值为200，该终端将该相似图像集合中的多张图像转换为灰度图，对于该多张图像中的图像1，该图像1的灰度图中所有像素点的总个数为1000，该终端从该图像1对应的灰度图中，确定灰度值小于第一灰度阈值30的像素点的第一个数为150，以及确定灰度值大于第二灰度阈值200的像素点的第二个数为260，该终端确定第一个150在总个数1000中所占的第一比例为0.15，以及确定第二个数260在总个数中所占的第二比例为0.26；假如，该终端将第一比例和第二比例中的最大值确定为该图像的光线质量参数时，由于第一比例小于第二比例，因此，该终端可以将第二比例0.26确定为该图像1的光线质量参数。
在本公开实施例中，该终端基于该相似图像集合中多张图像的光线质量参数，对该相似图像集合中多张图像进行筛选，可以得到该多张图像中光线质量较好的图像，从而避免了第一图像集合在图像显示时出现图像太黑或曝光过度的问题，增强图像显示效果。
在步骤203中，基于第一图像集合中多张图像的人脸角度，从第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合。
由于第一图像集合包括的多张图像中，可能存在人脸姿态不正面的图像，而当该多张图像中存在人脸姿态不正面的图像时，对该多张图像进行显示时，会影响该多张图像的显示效果，而判断图像中人脸姿态是否正面可以基于该图像中的人脸角度，因此，为了从第一图像集合中选择人脸姿态比较正面的图像，该终端需要基于第一图像集合中多张图像的人脸角度，从第一图像集合中，选择人脸角度在指定角度范围内的图像，从而得到第二图像集合。
比如，图像1的人脸角度为5度、图像2的人脸角度为30度、图像3的人脸角度为20度、图像4的人脸角度为60度，该指定角度范围为0～45度，该终端基于第一图像集合中多张图像的人脸角度，从第一图像集合中，选择人脸角度在指定角度范围0～45度内的图像有图像1、图像2和图像3，从而得到第二图像集合。
进一步地，该终端基于第一图像集合中多张图像的人脸角度，从第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合之前，该终端可以确定第一图像集合中多张图像的人脸角度，而确定第一图像集合中多张图像的人脸角度的操作可以为：该终端获取第一图像集合中多张图像的人脸特征点；对于该多张图像中每张图像，从该图像中，选择第一特征点和第二特征点，第一特征点和第二特征点为以鼻子为中心的左右对称的特征点；确定第一特征点与指定特征点之间的第一距离，以及确定第二特征点与该指定特征点之间的第二距离；基于第一距离和第二距离，确定该图像的人脸角度。
其中，该指定特征点可以为一个特征点，也可以为两个特征点，当该指定特征点为一个特征点时，该指定特征点可以位于该人脸的左右对称线上，也即是，鼻子所在的直线上，比如，该图像的人脸特征点如图3所示，该指定特征点可以为鼻尖对应的特征点G14，或者嘴唇中间位置的特征点B12、B15，又或者是下巴中心位置的特征点A15等；当该指定特征点为两个特征点时，该两个特征点是以鼻子为中心左右对称的特征点，比如，该指定特征点可以为左眼下半部分的中心位置的特征点C12和右眼下半部分的中心位置的特征点D12，或者为左眼上半部分的中心位置的特征点C15和右眼上半部分的中心位置的特征点D15等，本公开实施例对此不做具体限定。另外，由于第一特征点和第二特征点为以鼻子为中心的左右对称的特征点，而为了便于计算，可以确定第一特征点和第二特征点为脸部轮廓点，比如，第一特征点为图3中的特征点A11，第二特征点为图3中的特征点A19，本公开实施例同样对此不做具体限定。
当该指定特征点为一个特征点时，该终端确定第一距离和第二距离的操作可以为：该终端将第一特征点与该指定特征点的距离确定为第一距离，将第二特征点与该指定特征点的距离确定为第二距离。
当该指定特征点为两个特征点时，为便于描述，假设第一特征点处于鼻子左侧，第二特征点处于鼻子的右侧，从而该终端确定第一距离和第二距离的操作可以为：该终端将处于鼻子左侧的指定特征点与第一特征点之间的距离，确定为第一距离，将处于鼻子右侧的指定特征点与第二特征点之间的距离，确定为第二距离。
另外，当该终端基于第一距离和第二距离，确定该图像的人脸角度时，该终端可以用第一距离除以第二距离，得到第三比例，该终端基于第三比例，从存储的比例与人脸角度之间的对应关系中，获取对应的人脸角度，将获取的人脸角度确定为该图像的人脸角度。
比如，该指定特征点为一个特征点，且该指定特征点为鼻尖对应的特征点G14，该终端获取第一图像集合中图像1的人脸特征点如图3所示，从该图像1的人脸特征点中，选择的第一特征点为左边脸部轮廓的特征点A11，第二特征点为右边脸部轮廓的特征点A19， 第一特征点A11和第二特征点A19以鼻子为中心左右对称，该终端确定第一特征点A11与指定特征点G14之间的第一距离为36mm，确定第二特征点A19点与该指定特征点G14之间的第二距离为40mm，之后，该终端用第一距离36mm除以第二距离40mm，得到第三比例为0.9，该终端基于第三比例0.9，从如下表1所示的比例与人脸角度之间的对应关系中，获取对应的人脸角度为5度，该终端将获取的人脸角度5度确定为该图像的人脸角度。
表1
比例 人脸角度
0.9 5度
0.8 10度
0.7 20度
…… ……
需要说明的是，在本公开实施例中，仅以上述表1所示的比例与人脸角度之间的对应关系为例进行说明，上述表1并不对本公开实施例构成限定。
另外，当该终端获取第一图像集合中多张图像的人脸特征点时，该终端不仅可以通过SDM(Sparse Deforming Model，稀疏的形变模型)算法获取该多张图像的人脸特征点，当然，实际应用中，该终端还可以通过其它算法获取该多张图像的人脸特征点，比如，ASM(Active Shape Model，主动形状模块)算法、AAM(Active Appearance Model，主动外观模型)算法等等，而通过上述算法获取该多张图像的人脸特征点的具体操作可以参考人脸特征点识别等相关技术，本公开实施例对此不做详细阐述。
在本公开实施例中，该终端基于第一图像集合中多张图像的人脸角度，对第一图像集合中多张图像进行筛选，可以得到该多张图像中人脸角度比较正面的图像，从而避免了第二图像集合在图像显示时出现人脸姿态不太正面的问题，使选择的图像更贴近于用户的视觉需求，增强图像显示效果。
在步骤204中，基于第二图像集合中多张图像的眼部特征，从第二图像集合中，选择非闭眼的图像，得到第三图像集合。
由于该第二图像集合中多张图像的眼部特征可能为闭眼，也可能为非闭眼，而当该多张图像中存在闭眼的图像时，对该多张图像进行显示时，会影响该多张图像的显示效果，因此，该终端需要基于第二图像集合中多张图像的眼部特征，从第二图像集合中，选择非闭眼的图像，得到第三图像集合。
而该终端基于第二图像集合中多张图像的眼部特征，从第二图像集合中，选择非闭眼的图像的操作可以为：对于该多张图像的每张图像，该终端获取该图像的眼部特征点，并基于该图像的所有眼部特征点，通过指定分类器，确定分类结果，当该分类结果为第一数 值时，该终端确定该图像为闭眼的图像，当该分类结果为第二数值时，该终端确定该图像为非闭眼的图像。
需要说明的是，第一数值和第二数值可以事先设置，且第一数值和第二数值不相等，比如，第一数值可以为1，第二数值可以为0等，本公开实施例对此不做具体限定。
另外，该终端使用该指定分类器判断该图像为闭眼的图像，或者非闭眼的图像的具体操作可以参考相关技术，本公开实施例对此不做详细阐述。
比如，第一数值为1，第二数值为0，该终端获取第二图像集合中图像1和图像2的眼部特征点，并基于该图像1的所有眼部特征点，通过该指定分类器，确定该图像1的分类结果为0，该终端确定该图像1为非闭眼的图像，该终端基于图像2的所有眼部特征点，通过该指定分类器，确定该图像2的分类结果为1，该终端确定该图像2为闭眼的图像，该终端基于图像3的所有眼部特征点，通过该指定分类器，确定该图像3的分类结果为0，该终端确定该图像3为非闭眼的图像，该终端从第二图像集合中，选择非闭眼的图像为图像1和图像3，从而得到第三图像集合。
在本公开实施例中，该终端基于第二图像集合中多张图像的眼部特征，对第二图像集合中多张图像进行筛选，可以得到该多张图像中非闭眼的图像，从而避免了第三图像集合在图像显示时出现闭眼的问题，使选择的图像的显示效果较好。
在步骤205中，基于第三图像集合中多张图像的人脸清晰度，从第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到相似图像集合的代表图像。
由于第三图像集合中的多张图像，可能会存在人脸模糊不清的图像，而当该多张图像中存在人脸模糊不清的图像时，对该多张图像进行显示时，会影响该多张图像的显示效果，因此，为了从第三图像集合中选择人脸比较清晰的图像，该终端需要基于第三图像集合中多张图像的人脸清晰度，从第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到该相似图像集合的代表图像。
需要说明的是，该指定清晰度用于判断该多张图像的人脸是否清晰，且该指定清晰度可以事先设置，比如，该指定清晰度可以为180、200等等，本公开实施例对此不做具体限定。
比如，图像1的人脸清晰度为80，图像2的人脸清晰度为200，该指定清晰度为180，该终端基于第三图像集合中多张图像的人脸清晰度，从第三图像集合中，选择人脸清晰度大于或等于指定清晰度180的图像有图像1，从而得到该相似图像集合的代表图像为图像1。
进一步地，该终端基于第三图像集合中多张图像的人脸清晰度，从第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到相似图像集合的代表图像之前，该终端还可以确定第三图像集合中多张图像的人脸清晰度，而确定第三图像集合中多张图像的人脸清晰度的操作可以为：对于第三图像集合的多张图像中每张图像，获取该图像的人脸区域包括的每个像素点的像素值；基于每个像素点的像素值，确定该人脸区域的梯度累计 值；将该梯度累计值确定为该图像的人脸清晰度。
其中，对于第三图像集合的多张图像中每张图像，该终端获取该图像的人脸区域包括的每个像素点的像素值的操作可以为：对于第三图像集合的多张图像中每张图像，该终端对该图像进行人脸检测，将检测到的人脸区域确定为该图像的人脸区域，该终端基于确定的人脸区域，获取该人脸区域包括的每个像素点的像素值。
需要说明的是，该终端对该图像进行人脸检测的具体操作可以参考人脸检测等相关技术，本公开实施例对此不做详细阐述。
另外，该终端基于每个像素点的像素值，确定该人脸区域的梯度累计值的操作可以为：该终端将该人脸区域水平方向上依次相邻的两个像素点的像素值相减，得到水平方向上的多个像素差值，将该水平方向上的多个像素差值之和确定为第一梯度值，同理，该终端将该人脸区域竖直方向上依次相邻的两个像素点的像素值相减，得到竖直方向上的多个像素差值，将该竖直方向上的多个像素差值之和确定为第二梯度值，该终端将第一梯度值和第二梯度值之和，确定为该人脸区域的梯度累计值。
在本公开实施例中，该终端基于第三图像集合中多张图像的人脸清晰度，对第三图像集合中多张图像进行筛选，可以得到该多张图像中人脸清晰度较好的图像，从而提高了代表图像显示时的图像清晰度。
进一步地，当该终端对于每个相似图像集合中多张图像进行筛选时，该终端不仅可以通过上述步骤202-205进行筛选，得到该相似图像集合的代表图像，该终端还可以通过上述步骤202进行筛选，或者通过上述步骤202-203进行筛选，又或者通过上述步骤202-204进行筛选，得到该相似图像集合的代表图像，当然，在实际应用中，该终端还可以通过上述步骤202-205中的任一步骤，或者其中任意多个步骤的任一组合进行筛选，得到该相似图像集合的代表图像，本公开实施例对此不做具体限定。
另外，当该终端对于每个相似图像集合中的多张图像进行筛选时，该终端不仅可以通过上述步骤202-205中提到的图像的光线质量参数、人脸角度、眼部特征以及人脸清晰度等进行筛选，还可以根据图像的分辨率、对比度、色饱和度等其它参数进行筛选，本公开实施例对此不做具体限定。
在步骤206中，将该多个相似图像集合的代表图像进行显示。
该终端将该多个相似图像集合的代表图像进行显示的操作可以为：该终端将该多个相似图像集合的代表图像进行旋转对齐，使该多个相似图像集合的代表图像中的人脸方向相同；将旋转对齐后的每张代表图像进行调整，使调整后的每张代表图像中人脸区域的尺寸相等；将调整后的代表图像，以指定动态显示形式进行显示。
其中，当该终端将该多个相似图像集合的代表图像进行旋转对齐，使该多个相似图像集合的代表图像中的人脸方向相同时，该终端不仅可以将该代表图像向左旋转，也可以向右旋转、水平翻转、垂直翻转，或者以任意角度进行旋转等，本公开实施例对此不做具体限定。
另外，当该终端将旋转对齐后的每张代表图像进行调整，使调整后的每张代表图像中人脸区域的尺寸相等时，该终端可以基于指定尺寸，将该多张代表图像中人脸区域较小的代表图像进行放大，将人脸区域较大的代表图像进行缩小，以使调整后的每张代表图像的人脸区域的尺寸相等。
需要说明的是，该指定尺寸可以事先设置，且设置该指定尺寸时，可以基于该终端的屏幕尺寸进行设置，也可以基于该多张代表图像中的任一代表图像进行设置，比如，该终端的屏幕尺寸为4.5寸，该指定尺寸可以设置为2.5寸、3寸等等，本公开实施例对此不做具体限定。
再者，该终端将调整后的代表图像，以指定动态显示形式进行显示时，该终端不仅可以按照图像的存储时间，将该多个相似图像集合的代表图像以指定动态显示形式进行显示，该终端还可以随机的将该多个相似图像集合的代表图像，以指定动态显示形式进行显示，从而形成以该代表图像对应的用户为中心的时光动态影册，给用户以极强的震撼力和吸引力，本公开实施例对具体的动态显示形式不做具体限定。比如，该指定动态显示形式不仅可以为幻灯片的形式，也可以为其他动态的显示形式等等，本公开实施例对此不做具体限定。
进一步地，当该相似图像集合中有多个代表图像时，为了使相似的该多个代表图像不多次出现，以避免将相似的多张代表图像进行显示时的单调性，该终端可以从该相似图像集合中的多张代表图像中，随机选取1张或者2张进行显示。
更进一步地，当该终端接收到相册打开指令，打开该相册进行图像显示时，该终端可以显示多种浏览方式，以便用户从中选择一种动态显示形式，当该终端接收到该多种浏览方式中的动态图像的显示指令时，该终端可以基于上述步骤201-206提供的方法，以指定动态显示形式，将该相册的图像进行显示。当然，该终端还可以将上述步骤201-206的图像显示方法设置为默认显示方法，当下次打开该相册时，该终端就可以自动的以指定动态显示形式进行图像显示，以增强图像显示的效果，给人以极强的震撼力和吸引力。当该终端以指定动态显示形式显示该相册的图像的过程中，或者在该终端完成该相册的图像显示之后，若该终端接收到显示结束指令，该终端可以退出该相册的代表图像显示。
其中，该终端显示该多种浏览方式时，该终端可以在接收到相册打开指令时，直接将该多种浏览方式进行显示，以便用户从该多种浏览方式中进行选择，当然，该终端还可以通过指定按钮，当用户点击该指定按钮时，该终端显示一个下拉菜单，该下拉菜单中包括该多种浏览方式，以便于用户从该多种浏览方式中进行选择，从而在不需要选择浏览方式的情况下，避免了直接显示该多种浏览方式给用户带来不必要的干扰。
需要说明的是，该动态图像的显示指令用于以动态显示形式显示该相册的图像，且该动态图像的显示指令由用户触发，该用户可以通过点击指定按钮等操作来触发，本公开实施例对此不做具体限定。另外，该显示结束指令用于结束该代表图像的显示，且该显示结束指令可以由用户触发，用户可以通过点击操作、滑动操作、甩动操作等操作来触发，本 公开实施例对此不做具体限定。
进一步地，该终端不仅可以基于上述步骤201-206的方式，从该相册中选择代表图像以进行显示，当然，该终端还可以在接收到该相册打开指令之前，首先对该相册中的图像进行相似图像聚类，得到多个相似图像集合，对于每个相似图像集合中的多张图像进行筛选，得到该相似图像集合的代表图像，然后，当该终端接收到相册打开指令时，该终端将该多个相似图像集合的代表图像进行显示，节省了图像显示时间，提高了图像显示效率。
另外，当该终端将该多个相似图像集合的代表图像进行显示时，该终端不仅可以在接收到该相册打开指令时，将该多个相似图像集合的代表图像，以指定动态显示形式进行显示，当然，该终端还可以在接收到该相册打开指令之前，从动态图像显示模板库中，选择一个动态图像显示模板，并将该多个相似图像集合的代表图像填充到该动态图像显示模板中，从而形成一个动态图像影册，当该终端接收到相册打开指令时，该终端直接将该动态图像影册进行显示，从而增强图像的显示效果，给人以极强的震撼力和吸引力。
需要说明的是，该动态图像显示模板库可以事先存储在该终端上，也可以是该终端从服务器中，获取的动态图像显示模板库，本公开实施例对此不做具体限定。
进一步，当该终端在接收到该相册打开指令之前，对该相册进行相似图像聚类，并对每个相似图像集合进行筛选时，由于该相册中的图像是可以随时更新的，也即是，用户可以随时对该相册中的图像进行删除、添加等等，因此，为了及时地更新从该相册中筛选出的代表图像，该终端可以周期性地对该相册进行相似图像聚类，以及对每个相似图像集合进行筛选，以实现对筛选出的代表图像进行更新，提高图像的显示准确率。
需要说明的是，该终端对该相册中筛选出的代表图像进行更新的周期长度可以是指定时长，比如，该指定时长可以是1周、2周、1个月等等，当然，该终端也可以确定相册中图像更新的数量为指定数值时更新一次，比如，该指定数值可以是10、20等等，本公开实施例对此不做具体限定。
在本公开实施例中，当该终端接收到相册打开指令时，该终端对该相册中图像进行相似图像聚类，得到多个相似图像集合，对于该多个相似图像集合中每个相似图像集合，分别基于光线质量参数、人脸角度、眼部特征、以及人脸清晰度对该相似图像集合中多张图像进行筛选，从而得到该相似图像集合中图像质量较好的代表图像，将该多个相似图像集合中图像质量较好的代表图像，以指定动态显示形式进行显示，从而丰富了该相册的显示形式，同时增强该代表图像的显示效果，给人以极强的震撼力和吸引力。
图4是根据一示例性实施例示出的一种图像显示装置框图。参照图4，该装置包括聚类模块401，筛选模块402，显示模块403。
聚类模块401，用于当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合；
筛选模块402，用于每个相似图像集合中的多张图像进行筛选，得到该相似图像集合 的代表图像；
显示模块403，用于将该多个相似图像集合的代表图像进行显示。
在本公开的另一实施例中，参照图5，该筛选模块402包括第一选择单元4021。
第一选择单元4021，用于对于该多个相似图像集合中每个相似图像集合，基于该相似图像集合中多张图像的光线质量参数，从该相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合。
在本公开的另一实施例中，参照图6，该筛选模块402还包括第二选择单元4022。
第二选择单元4022，用于基于第一图像集合中多张图像的人脸角度，从第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合。
在本公开的另一实施例中，参照图7，该筛选模块402还包括第三选择单元4023。
第三选择单元4023，用于基于第二图像集合中多张图像的眼部特征，从第二图像集合中，选择非闭眼的图像，得到第三图像集合。
在本公开的另一实施例中，参考图8，该筛选模块402还包括第四选择单元4024。
第四选择单元4024，用于基于第三图像集合中多张图像的人脸清晰度，从第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到该相似图像集合的代表图像。
在本公开的另一实施例中，参照图9，该筛选模块402还包括转换单元4025，第一确定单元4026，第二确定单元4027，第三确定单元4028。
转换单元4025，用于将该相似图像集合中多张图像转换为灰度图；
第一确定单元4026，用于对于该多张图像中每张图像，从该图像对应的灰度图中，确定灰度值小于第一灰度阈值的像素点的第一个数，以及确定灰度值大于第二灰度阈值的像素点的第二个数；
第二确定单元4027，用于确定第一个数在总个数中所占的第一比例，以及确定第二个数在总个数中所占的第二比例，该总个数为该灰度图中所有像素点的个数；
第三确定单元4028，用于基于第一比例和第二比例，确定该图像的光线质量参数。
在本公开的另一实施例中，参照图10，该筛选模块402还包括第一获取单元4029，第五选择单元40210，第四确定单元40211，第五确定单元40212。
第一获取单元4029，用于获取第一图像集合中多张图像的人脸特征点；
第五选择单元40210，用于对于该多张图像中每张图像，从该图像中，选择第一特征点和第二特征点，第一特征点和第二特征点为以鼻子为中心的左右对称的特征点；
第四确定单元40211，用于确定第一特征点与指定特征点之间的第一距离，以及确定第二特征点与指定特征点之间的第二距离；
第五确定单元40212，用于基于第一距离和第二距离，确定该图像的人脸角度。
在本公开的另一实施例中，参照图11，该筛选模块402还包括第二获取单元40213，第六确定单元40214，第七确定单元40215。
第二获取单元40213，用于对于第三图像集合的多张图像中每张图像，获取该图像的 人脸区域包括的每个像素点的像素值；
第六确定单元40214，用于基于每个像素点的像素值，确定该人脸区域的梯度累计值；
第七确定单元40215，用于将该梯度累计值确定为该图像的人脸清晰度。
在本公开的另一实施例中，参照图12，该显示模块403包括旋转单元4031，调整单元4032，显示单元4033。
旋转单元4031，用于将该多个相似图像集合的代表图像进行旋转对齐，使该多个相似图像集合的代表图像中的人脸方向相同；
调整单元4032，用于将旋转对齐后的每张代表图像进行调整，使调整后的每张代表图像中人脸区域的尺寸相等；
显示单元4033，用于将调整后的代表图像，以指定动态显示形式进行显示。
在本公开的另一实施例中，当该相似图像集合中有多个代表图像时，随机选取1张或者2张进行显示。
在本公开实施例中，当该终端接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合，对于每个相似图像集合中的多张图像进行筛选，从而得到该相似图像集合中图像质量较好的代表图像，将该多个相似图像集合中图像质量较好的代表图像进行显示，从而增强该多个相似图像集合的代表图像的显示效果。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
图13是根据一示例性实施例示出的一种用于图像显示的装置1300的框图。例如，装置1300可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
参照图13，装置1300可以包括以下一个或多个组件：处理组件1302，存储器1304，电源组件1306，多媒体组件1308，音频组件1310，输入/输出(I/O)的接口1312，传感器组件1314，以及通信组件1316。
处理组件1302通常控制装置1300的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理元件1302可以包括一个或多个处理器1320来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件1302可以包括一个或多个模块，便于处理组件1302和其他组件之间的交互。例如，处理部件1302可以包括多媒体模块，以方便多媒体组件1308和处理组件1302之间的交互。
存储器1304被配置为存储各种类型的数据以支持在设备1300的操作。这些数据的示例包括用于在装置1300上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器1304可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)， 磁存储器，快闪存储器，磁盘或光盘。
电力组件1306为装置1300的各种组件提供电力。电力组件1306可以包括电源管理系统，一个或多个电源，及其他与为装置1300生成、管理和分配电力相关联的组件。
多媒体组件1308包括在所述装置1300和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件1308包括一个前置摄像头和/或后置摄像头。当设备1300处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件1310被配置为输出和/或输入音频信号。例如，音频组件1310包括一个麦克风(MIC)，当装置1300处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器1304或经由通信组件1316发送。在一些实施例中，音频组件1310还包括一个扬声器，用于输出音频信号。
I/O接口1312为处理组件1302和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件1314包括一个或多个传感器，用于为装置1300提供各个方面的状态评估。例如，传感器组件1314可以检测到设备1300的打开/关闭状态，组件的相对定位，例如所述组件为装置1300的显示器和小键盘，传感器组件1314还可以检测装置1300或装置1300一个组件的位置改变，用户与装置1300接触的存在或不存在，装置1300方位或加速/减速和装置1300的温度变化。传感器组件1314可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件1314还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件1314还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件1316被配置为便于装置1300和其他设备之间有线或无线方式的通信。装置1300可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信部件1316经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信部件1316还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，装置1300可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可 编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器1304，上述指令可由装置1300的处理器1320执行以完成上述方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
一种非临时性计算机可读存储介质，当所述存储介质中的指令由移动终端的处理器执行时，使得移动终端能够执行一种图像显示方法，所述方法包括：
当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合。
对于每个相似图像集合中的多张图像进行筛选，得到该相似图像集合的代表图像。
将该多个相似图像集合的代表图像进行显示。
在本公开的另一实施例中，对每个相似图像集合中多张图像进行筛选，得到该相似图像集合的代表图像包括：
基于该相似图像集合中多张图像的光线质量参数，从该相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合。
在本公开的另一实施例中，该方法还包括：
基于第一图像集合中多张图像的人脸角度，从第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合。
在本公开的另一实施例中，该方法还包括：
基于第二图像集合中多张图像的眼部特征，从第二图像集合中，选择非闭眼的图像，得到第三图像集合。
在本公开的另一实施例中，该方法还包括：
基于第三图像集合中多张图像的人脸清晰度，从第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到该相似图像集合的代表图像。
在本公开的另一实施例中，基于该相似图像集合中多张图像的光线质量参数，从该相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合之前，该方法还包括：
将该相似图像集合中多张图像转换为灰度图；
对于该多张图像中每张图像，从该图像对应的灰度图中，确定灰度值小于第一灰度阈值的像素点的第一个数，以及确定灰度值大于第二灰度阈值的像素点的第二个数；
确定第一个数在总个数中所占的第一比例，以及确定第二个数在总个数中所占的第二比例，该总个数为该灰度图中所有像素点的个数；
基于第一比例和第二比例，确定该图像的光线质量参数。
在本公开的另一实施例中，基于第一图像集合中多张图像的人脸角度，从第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合之前，该方法还包括：
获取第一图像集合中多张图像的人脸特征点；
对于该多张图像中每张图像，从该图像中，选择第一特征点和第二特征点，第一特征点和第二特征点为以鼻子为中心的左右对称的特征点；
确定第一特征点与该指定特征点之间的第一距离，以及确定第二特征点与该指定特征点之间的第二距离；
基于第一距离和第二距离，确定该图像的人脸角度。
在本公开的另一实施例中，基于第三图像集合中多张图像的人脸清晰度，从第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到该相似图像集合的代表图像之前，该方法还包括：
对于第三图像集合的多张图像中每张图像，获取该图像的人脸区域包括的每个像素点的像素值；
基于每个像素点的像素值，确定该人脸区域的梯度累计值；
将该梯度累计值确定为该图像的人脸清晰度。
在本公开的另一实施例中，将该多个相似图像集合的代表图像进行显示包括：
将该多个相似图像集合的代表图像进行旋转对齐，使该多个相似图像集合的代表图像中的人脸方向相同；
将旋转对齐后的每张代表图像进行调整，使调整后的每张代表图像中人脸区域的尺寸相等；
将调整后的代表图像，以指定动态显示形式进行显示。
在本公开的另一实施例中，当该相似图像集合中有多个代表图像时，随机选取1张或者2张进行显示。
在本公开实施例中，当该终端接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合，对于每个相似图像集合中的多张图像进行筛选，从而得到该相似图像集合中图像质量较好的代表图像，将该多个相似图像集合中图像质量较好的代表图像进行显示，从而增强该多个相似图像集合的代表图像的显示效果。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本发明的其它实施方案。本申请旨在涵盖本发明的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本发明的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本发明的真正范围和精神由下面的权利要求指出。
应当理解的是，本发明并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本发明的范围仅由所附的权利要求来限制。

Claims (21)

  1. 一种图像显示方法，其特征在于，所述方法包括：
    当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合；
    对每个所述相似图像集合中的多张图像进行筛选，得到所述相似图像集合的代表图像；
    将所述多个相似图像集合的代表图像进行显示。
  2. 如权利要求1所述的方法，其特征在于，所述对每个所述相似图像集合中的多张图像进行筛选，得到所述相似图像集合的代表图像，包括：
    基于所述相似图像集合中多张图像的光线质量参数，从所述相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合。
  3. 如权利要求2所述的方法，其特征在于，所述方法还包括：
    基于所述第一图像集合中多张图像的人脸角度，从所述第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合。
  4. 如权利要求3所述的方法，其特征在于，所述方法还包括：
    基于所述第二图像集合中多张图像的眼部特征，从所述第二图像集合中，选择非闭眼的图像，得到第三图像集合。
  5. 如权利要求4所述的方法，其特征在于，所述方法还包括：
    基于所述第三图像集合中多张图像的人脸清晰度，从所述第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到所述相似图像集合的代表图像。
  6. 如权利要求2所述的方法，其特征在于，所述基于所述相似图像集合中多张图像的光线质量参数，从所述相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合之前，还包括：
    将所述相似图像集合中多张图像转换为灰度图；
    对于所述多张图像中每张图像，从所述图像对应的灰度图中，确定灰度值小于第一灰度阈值的像素点的第一个数，以及确定灰度值大于第二灰度阈值的像素点的第二个数；
    确定所述第一个数在总个数中所占的第一比例，以及确定所述第二个数在所述总个数中所占的第二比例，所述总个数为所述灰度图中所有像素点的个数；
    基于所述第一比例和所述第二比例，确定所述图像的光线质量参数。
  7. 如权利要求3所述的方法，其特征在于，所述基于所述第一图像集合中多张图像 的人脸角度，从所述第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合之前，还包括：
    获取所述第一图像集合中多张图像的人脸特征点；
    对于所述多张图像中每张图像，从所述图像中，选择第一特征点和第二特征点，所述第一特征点和所述第二特征点为以鼻子为中心的左右对称的特征点；
    确定所述第一特征点与指定特征点之间的第一距离，以及确定所述第二特征点与所述指定特征点之间的第二距离；
    基于所述第一距离和所述第二距离，确定所述图像的人脸角度。
  8. 如权利要求5所述的方法，其特征在于，所述基于所述第三图像集合中多张图像的人脸清晰度，从所述第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到所述相似图像集合的代表图像之前，还包括：
    对于所述第三图像集合的多张图像中每张图像，获取所述图像的人脸区域包括的每个像素点的像素值；
    基于所述每个像素点的像素值，确定所述人脸区域的梯度累计值；
    将所述梯度累计值确定为所述图像的人脸清晰度。
  9. 如权利要求1所述的方法，其特征在于，所述将所述多个相似图像集合的代表图像进行显示，包括：
    将所述多个相似图像集合的代表图像进行旋转对齐，使所述多个相似图像集合的代表图像中的人脸方向相同；
    将旋转对齐后的每张代表图像进行调整，使调整后的每张代表图像中人脸区域的尺寸相等；
    将调整后的代表图像，以指定动态显示形式进行显示。
  10. 如权利要求9所述的方法，其特征在于，当所述相似图像集合中有多张代表图像时，随机选取1张或者2张进行显示。
  11. 一种图像显示装置，其特征在于，所述装置包括：
    聚类模块，用于当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合；
    筛选模块，用于对于每个所述相似图像集合中的多张图像进行筛选，得到所述相似图像集合的代表图像；
    显示模块，用于将所述多个相似图像集合的代表图像显示。
  12. 如权利要求11所述的装置，其特征在于，所述筛选模块包括：
    第一选择单元，用于基于所述相似图像集合中多张图像的光线质量参数，从所述相似图像集合中，选择光线质量参数小于光线阈值的图像，得到第一图像集合。
  13. 如权利要求12所述的装置，其特征在于，所述筛选模块还包括：
    第二选择单元，用于基于所述第一图像集合中多张图像的人脸角度，从所述第一图像集合中，选择人脸角度在指定角度范围内的图像，得到第二图像集合。
  14. 如权利要求13所述的装置，其特征在于，所述筛选模块还包括：
    第三选择单元，用于基于所述第二图像集合中多张图像的眼部特征，从所述第二图像集合中，选择非闭眼的图像，得到第三图像集合。
  15. 如权利要求14所述的装置，其特征在于，所述筛选模块还包括：
    第四选择单元，用于基于所述第三图像集合中多张图像的人脸清晰度，从所述第三图像集合中，选择人脸清晰度大于或等于指定清晰度的图像，得到所述相似图像集合的代表图像。
  16. 如权利要求12所述的装置，其特征在于，所述筛选模块还包括：
    转换单元，用于将所述相似图像集合中多张图像转换为灰度图；
    第一确定单元，用于对于所述多张图像中每张图像，从所述图像对应的灰度图中，确定灰度值小于第一灰度阈值的像素点的第一个数，以及确定灰度值大于第二灰度阈值的像素点的第二个数；
    第二确定单元，用于确定所述第一个数在总个数中所占的第一比例，以及确定所述第二个数在所述总个数中所占的第二比例，所述总个数为所述灰度图中所有像素点的个数；
    第三确定单元，用于基于所述第一比例和所述第二比例，确定所述图像的光线质量参数。
  17. 如权利要求13所述的装置，其特征在于，所述筛选模块还包括：
    第一获取单元，用于获取所述第一图像集合中多张图像的人脸特征点；
    第五选择单元，用于对于所述多张图像中每张图像，从所述图像中，选择第一特征点和第二特征点，所述第一特征点和所述第二特征点为以鼻子为中心的左右对称的特征点；
    第四确定单元，用于确定所述第一特征点与指定特征点之间的第一距离，以及确定所述第二特征点与所述指定特征点之间的第二距离；
    第五确定单元，用于基于所述第一距离和所述第二距离，确定所述图像的人脸角度。
  18. 如权利要求15所述的装置，其特征在于，所述筛选模块还包括：
    第二获取单元，用于对于所述第三图像集合的多张图像中每张图像，获取所述图像的人脸区域包括的每个像素点的像素值；
    第六确定单元，用于基于所述每个像素点的像素值，确定所述人脸区域的梯度累计值；
    第七确定单元，用于将所述梯度累计值确定为所述图像的人脸清晰度。
  19. 如权利要求11所述的装置，其特征在于，所述显示模块包括：
    旋转单元，用于将所述多个相似图像集合的代表图像进行旋转对齐，使所述多个相似图像集合的代表图像中的人脸方向相同；
    调整单元，用于将旋转对齐后的每张代表图像进行调整，使调整后的每张代表图像中人脸区域的尺寸相等；
    显示单元，用于将调整后的代表图像，以指定动态显示形式进行显示。
  20. 如权利要求19所述的装置，其特征在于，当所述相似图像集合中有多个代表图像时，随机选取1张或者2张进行显示。
  21. 一种图像显示装置，其特征在于，所述装置包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为：
    当接收到相册打开指令时，对相册中图像进行相似图像聚类，得到多个相似图像集合；
    对于每个相似图像集合中的多张图像进行筛选，得到所述相似图像集合的代表图像；
    将所述多个相似图像集合的代表图像进行显示。
PCT/CN2015/097782 2015-07-28 2015-12-18 图像显示方法及装置 Ceased WO2017016146A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2017530393A JP6357589B2 (ja) 2015-07-28 2015-12-18 画像表示方法、装置、プログラムおよび記録媒体
KR1020167003923A KR20170023742A (ko) 2015-07-28 2015-12-18 이미지 표시 방법, 장치, 프로그램 및 컴퓨터가 판독가능한 기록매체
MX2016003875A MX359585B (es) 2015-07-28 2015-12-18 Metodo y dispositivo para desplegar una imagen.
RU2016112557A RU2636668C2 (ru) 2015-07-28 2015-12-18 Способ и устройство для отображения изображений

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510452003.3A CN105138962A (zh) 2015-07-28 2015-07-28 图像显示方法及装置
CN201510452003.3 2015-07-28

Publications (1)

Publication Number Publication Date
WO2017016146A1 true WO2017016146A1 (zh) 2017-02-02

Family

ID=54724306

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/097782 Ceased WO2017016146A1 (zh) 2015-07-28 2015-12-18 图像显示方法及装置

Country Status (8)

Country Link
US (1) US10032076B2 (zh)
EP (1) EP3125158B1 (zh)
JP (1) JP6357589B2 (zh)
KR (1) KR20170023742A (zh)
CN (1) CN105138962A (zh)
MX (1) MX359585B (zh)
RU (1) RU2636668C2 (zh)
WO (1) WO2017016146A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020516188A (ja) * 2017-07-21 2020-05-28 ベイジン センスタイム テクノロジー デベロップメント カンパニー， リミテッド 顔画像重複削除方法及び装置、電子機器、記憶媒体、プログラム

Families Citing this family (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102306538B1 (ko) * 2015-01-20 2021-09-29 삼성전자주식회사 콘텐트 편집 장치 및 방법
CN105138962A (zh) * 2015-07-28 2015-12-09 小米科技有限责任公司 图像显示方法及装置
CN107239473A (zh) * 2016-03-29 2017-10-10 阿里巴巴集团控股有限公司 一种展示图片选择方法及装置
CN106095876B (zh) * 2016-06-06 2021-11-09 北京小米移动软件有限公司 图像处理方法及装置
CN109389019B (zh) * 2017-08-14 2021-11-05 杭州海康威视数字技术股份有限公司 人脸图像选择方法、装置及计算机设备
CN107632759A (zh) * 2017-08-21 2018-01-26 珠海市魅族科技有限公司 图片展示方法、装置、计算机装置及计算机可读存储介质
CN107589963B (zh) * 2017-09-26 2019-05-17 维沃移动通信有限公司 一种图片处理方法、移动终端及计算机可读存储介质
CN109584198B (zh) * 2017-09-26 2022-12-23 浙江宇视科技有限公司 一种人脸图像质量评价方法、装置及计算机可读存储介质
CN107977674B (zh) * 2017-11-21 2020-02-18 Oppo广东移动通信有限公司 图像处理方法、装置、移动终端及计算机可读存储介质
CN108009277A (zh) * 2017-12-20 2018-05-08 珠海格力电器股份有限公司 一种图像删除方法及终端设备
CA3090779A1 (en) 2018-02-09 2019-08-15 The Board Of Trustees Of The University Of Illinois A system and method to fuse multiple sources of optical data to generate a high-resolution, frequent and cloud-/gap-free surface reflectance product
WO2019183347A1 (en) * 2018-03-21 2019-09-26 Walmart Apollo, Llc Product image evaluation system and method
CN108510446B (zh) * 2018-04-10 2023-03-14 四川和生视界医药技术开发有限公司 视网膜图像的叠加方法及视网膜图像的叠加装置
CN110971811B (zh) * 2018-09-30 2022-11-15 中兴通讯股份有限公司 图像筛选方法、系统、终端及计算机可读存储介质
CN110335237B (zh) * 2019-05-06 2022-08-09 北京字节跳动网络技术有限公司 用于生成模型的方法、装置和用于识别图像的方法、装置
CN110414424A (zh) * 2019-07-26 2019-11-05 广州云从信息科技有限公司 数据处理系统、方法、平台、机器可读介质及设备
USD934179S1 (en) 2019-09-04 2021-10-26 E. Mishan & Sons, Inc. Power strip tower
CN111061899B (zh) * 2019-12-18 2022-04-26 深圳云天励飞技术股份有限公司 一种档案代表图片生成方法、装置和电子设备
CN112651321A (zh) * 2020-12-21 2021-04-13 浙江商汤科技开发有限公司 档案处理方法、装置及服务器
US12470672B1 (en) 2021-10-08 2025-11-11 The Board Of Trustees Of The University Of Illinois Monitoring plant growth conditions by coupling near surface and remote sensing imageries
US20240194011A1 (en) * 2022-02-15 2024-06-13 Trinamix Gmbh Authentication of a user for access
CN114915730B (zh) * 2022-06-17 2023-10-27 维沃移动通信（深圳）有限公司 拍摄方法和拍摄装置
CN116129322B (zh) * 2023-02-07 2026-01-02 科大讯飞股份有限公司 视频检测方法、装置、电子设备和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101523412A (zh) * 2006-10-11 2009-09-02 惠普开发有限公司 基于人脸的图像聚类
US20110007975A1 (en) * 2009-07-10 2011-01-13 Kabushiki Kaisha Toshiba Image Display Apparatus and Image Display Method
CN103064963A (zh) * 2012-12-30 2013-04-24 浙江大学 一种基于流行自适应核的无障碍图片展示方法
CN103955481A (zh) * 2014-04-03 2014-07-30 小米科技有限责任公司 图片显示方法和装置
US20150071557A1 (en) * 2013-06-05 2015-03-12 Emotient Spatial organization of images based on emotion face clouds
CN105138962A (zh) * 2015-07-28 2015-12-09 小米科技有限责任公司 图像显示方法及装置

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006295890A (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
US8369570B2 (en) 2005-09-28 2013-02-05 Facedouble, Inc. Method and system for tagging an image of an individual in a plurality of photos
JP5034661B2 (ja) * 2007-05-07 2012-09-26 ソニー株式会社 画像管理装置、画像表示装置、撮像装置、および、これらにおける処理方法ならびに当該方法をコンピュータに実行させるプログラム
JP4577410B2 (ja) * 2008-06-18 2010-11-10 ソニー株式会社 画像処理装置、画像処理方法およびプログラム
JP2010118943A (ja) * 2008-11-13 2010-05-27 Noritsu Koki Co Ltd 画像処理装置、画像形成装置、画像処理方法及び画像処理プログラム
JP5180052B2 (ja) * 2008-12-23 2013-04-10 株式会社ニコンシステム 画像評価装置及び画像評価プログラム
WO2010146495A1 (en) * 2009-06-15 2010-12-23 Koninklijke Philips Electronics N.V. A method and apparatus for selecting a representative image
US8379939B1 (en) * 2009-09-08 2013-02-19 Adobe Systems Incorporated Efficient and scalable face recognition in photo albums
US8078623B2 (en) 2009-10-14 2011-12-13 Cyberlink Corp. Systems and methods for summarizing photos based on photo information and user preference
US8351661B2 (en) * 2009-12-02 2013-01-08 At&T Intellectual Property I, L.P. System and method to assign a digital image to a face cluster
CN101777059B (zh) 2009-12-16 2011-12-07 中国科学院自动化研究所 一种提取地标性场景摘要的方法
US8693789B1 (en) * 2010-08-09 2014-04-08 Google Inc. Face and expression aligned moves
US8724910B1 (en) * 2010-08-31 2014-05-13 Google Inc. Selection of representative images
KR101180471B1 (ko) * 2011-09-27 2012-09-07 (주)올라웍스 한정된 메모리 환경 하에서 얼굴 인식 성능 향상을 위한 참조 얼굴 데이터베이스 관리 방법, 장치 및 컴퓨터 판독 가능한 기록 매체
US20130100334A1 (en) * 2011-10-20 2013-04-25 Broadcom Corporation Method and System for an Adaptive Auto-Focus Algorithm
US8891883B2 (en) * 2012-05-15 2014-11-18 Google Inc. Summarizing a photo album in a social network system
WO2015107640A1 (ja) * 2014-01-15 2015-07-23 富士通株式会社 アルバム作成プログラム、アルバム作成方法およびアルバム作成装置
US20150317510A1 (en) 2014-04-30 2015-11-05 Microsoft Corporation Rating photos for tasks based on content and adjacent signals
US9922452B2 (en) * 2015-09-17 2018-03-20 Samsung Electronics Co., Ltd. Apparatus and method for adjusting brightness of image

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101523412A (zh) * 2006-10-11 2009-09-02 惠普开发有限公司 基于人脸的图像聚类
US20110007975A1 (en) * 2009-07-10 2011-01-13 Kabushiki Kaisha Toshiba Image Display Apparatus and Image Display Method
CN103064963A (zh) * 2012-12-30 2013-04-24 浙江大学 一种基于流行自适应核的无障碍图片展示方法
US20150071557A1 (en) * 2013-06-05 2015-03-12 Emotient Spatial organization of images based on emotion face clouds
CN103955481A (zh) * 2014-04-03 2014-07-30 小米科技有限责任公司 图片显示方法和装置
CN105138962A (zh) * 2015-07-28 2015-12-09 小米科技有限责任公司 图像显示方法及装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020516188A (ja) * 2017-07-21 2020-05-28 ベイジン センスタイム テクノロジー デベロップメント カンパニー， リミテッド 顔画像重複削除方法及び装置、電子機器、記憶媒体、プログラム
US11132581B2 (en) 2017-07-21 2021-09-28 Beijing Sensetime Technology Development Co., Ltd Method and apparatus for face image deduplication and storage medium
US11409983B2 (en) 2017-07-21 2022-08-09 Beijing Sensetime Technology Development Co., Ltd Methods and apparatuses for dynamically adding facial images into database, electronic devices and media

Also Published As

Publication number Publication date
CN105138962A (zh) 2015-12-09
RU2636668C2 (ru) 2017-11-27
EP3125158B1 (en) 2019-07-10
JP6357589B2 (ja) 2018-07-11
KR20170023742A (ko) 2017-03-06
US20170032185A1 (en) 2017-02-02
MX359585B (es) 2018-10-02
US10032076B2 (en) 2018-07-24
EP3125158A3 (en) 2017-03-08
JP2017527058A (ja) 2017-09-14
MX2016003875A (es) 2017-03-20
RU2016112557A (ru) 2017-10-09
EP3125158A2 (en) 2017-02-01

Similar Documents

Publication Publication Date Title
WO2017016146A1 (zh) 图像显示方法及装置
RU2634907C2 (ru) Метод и устройство для получения фотографии
CN106570110B (zh) 图像去重方法及装置
US9959484B2 (en) Method and apparatus for generating image filter
EP3179408A2 (en) Picture processing method and apparatus, computer program and recording medium
CN108289169A (zh) 拍摄方法、装置、电子设备及存储介质
WO2016011747A1 (zh) 肤色调整方法和装置
WO2017088470A1 (zh) 图像分类方法及装置
US11961278B2 (en) Method and apparatus for detecting occluded image and medium
CN105282441B (zh) 拍照方法及装置
CN113170049B (zh) 使用场景改变触发自动图像捕获
CN108668080A (zh) 提示镜头脏污程度的方法及装置、电子设备
WO2016192325A1 (zh) 视频文件的标识处理方法及装置
WO2020093798A1 (zh) 一种显示目标图像的方法、装置、终端及存储介质
CN106357804A (zh) 图像处理方法、电子设备及云端服务器
WO2018098860A1 (zh) 照片合成方法及装置
CN106339705B (zh) 图片获取方法及装置
CN107566878B (zh) 直播中显示图片的方法及装置
WO2016155227A1 (zh) 显示取景信息的方法及装置
WO2023077755A1 (zh) 行人信息确定方法、装置、车辆、电子设备及存储介质
EP3799415A2 (en) Method and device for processing videos, and medium
US11800041B2 (en) Image processing method and apparatus, electronic device, and storage medium
CN111726531A (zh) 图像拍摄方法、处理方法、装置、电子设备及存储介质
CN114827447B (zh) 图像抖动校正方法和装置
CN112752010B (zh) 一种拍摄方法、装置及介质

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2017530393

Country of ref document: JP

Kind code of ref document: A

Ref document number: 20167003923

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: MX/A/2016/003875

Country of ref document: MX

ENP Entry into the national phase

Ref document number: 2016112557

Country of ref document: RU

Kind code of ref document: A

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

Ref document number: 15899494

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: 15899494

Country of ref document: EP

Kind code of ref document: A1