CN116894008A - Photo album cleaning method, device, equipment and storage medium based on picture classification - Google Patents
Photo album cleaning method, device, equipment and storage medium based on picture classification Download PDFInfo
- Publication number
- CN116894008A CN116894008A CN202311160963.3A CN202311160963A CN116894008A CN 116894008 A CN116894008 A CN 116894008A CN 202311160963 A CN202311160963 A CN 202311160963A CN 116894008 A CN116894008 A CN 116894008A
- Authority
- CN
- China
- Prior art keywords
- cleaned
- album
- pictures
- picture
- subset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004140 cleaning Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003860 storage Methods 0.000 title claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000004220 aggregation Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009928 pasteurization Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
- G06F16/162—Delete operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/1737—Details of further file system functions for reducing power consumption or coping with limited storage space, e.g. in mobile devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/174—Redundancy elimination performed by the file system
- G06F16/1748—De-duplication implemented within the file system, e.g. based on file segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses an album cleaning method, device, equipment and storage medium based on picture classification, wherein the method comprises the following steps: acquiring an album picture, and adding a label to the album picture through a KNN algorithm; adding album pictures with the same label into a set to be cleaned; adding album pictures with the same downloading path in the collection to be cleaned into a first subset; adding album pictures which accord with a preset size range in the first subset into a second subset; taking a second subset with the number of the album pictures being more than or equal to 2 as a subset to be cleaned; calculating the difference value of gray level histograms of any two album pictures to be cleaned in the subset to be cleaned; clustering similar photo album pictures to be cleaned into a picture group; arranging the photo album pictures to be cleaned in the picture group according to a preset sequence so that a user side can clean similar photo album pictures to be cleaned in the picture group; the invention can clean the similar pictures in the album.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to an album cleaning method, apparatus, device and storage medium based on image classification.
Background
With the development of information technology, the importance of mobile devices in life is increasing, when users browse web pages or browse application software by using the mobile devices, pictures of interest are downloaded and added into an album, and as part of users possibly browse the same or similar pictures at different times, the users forget to save the pictures, so that the situation of repeatedly saving the same or similar pictures occurs. Because the storage space of the mobile device is limited, when the storage space of the mobile device reaches a peak value, in order to relieve the storage pressure of the storage space of the mobile device, a user is required to manually clean the downloaded and stored similar pictures or repeated pictures to release the storage space, but the number of the downloaded pictures in the album is large, the downloading time span is long, and the user is difficult to realize quick manual cleaning.
Therefore, how to assist the user to clean up the downloaded and saved similar pictures is a technical problem that needs to be solved by those skilled in the art.
Disclosure of Invention
The invention aims to provide an album cleaning method, device, equipment and storage medium based on picture classification, which can assist a user to quickly clean similar pictures in an album.
According to one aspect of the present invention, there is provided an album cleaning method based on picture classification, the method including:
acquiring an album picture, and adding a label to the album picture through a KNN algorithm; the photo album picture is a picture stored in the photo album through a preset downloading way;
adding album pictures with the same label into one set to be cleaned to obtain a set number of sets to be cleaned;
adding album pictures with the same downloading route in the collection to be cleaned into a first subset to obtain a set number of first subsets;
adding album pictures which accord with a preset size range in the first sub-set into a second sub-set to obtain a set number of second sub-sets;
taking a second subset with the number of album pictures being more than or equal to 2 as a subset to be cleaned, and taking the album pictures in the subset to be cleaned as album pictures to be cleaned;
acquiring gray histograms of the photo album pictures to be cleaned in the subset to be cleaned, and calculating difference values of the gray histograms of any two photo album pictures to be cleaned;
Determining a target album picture to be cleaned from the subset to be cleaned, and clustering the target album picture to be cleaned and similar album pictures to be cleaned, of which the difference value is smaller than or equal to a preset difference threshold value, into a picture group according to a preset clustering algorithm;
arranging the photo album pictures to be cleaned in the picture group according to a preset sequence so that a user side can clean similar photo album pictures to be cleaned in the picture group.
Optionally, the obtaining the album picture includes:
acquiring the adding and deleting states of the album to be processed in a set time period;
when the adding and deleting state is the adding and deleting state or the adding state, taking all pictures in the album to be processed as album pictures;
and when the adding and deleting states are adding and deleting states, taking the newly added pictures in the album to be processed as album pictures.
Optionally, the adding a label to the album picture through KNN algorithm includes:
acquiring a preset training set; wherein, each standard picture in the preset training set corresponds to a label;
extracting feature vectors of the album pictures, and sequentially calculating Euclidean distances between the feature vectors of the album pictures and the feature vectors of each standard picture in the preset training set;
Obtaining K standard pictures with minimum Euclidean distance with the album pictures through a KNN algorithm;
and counting the number of the labels of the same labels in the labels corresponding to the K standard pictures, and taking the label with the largest number of labels as the label of the album picture.
Optionally, the obtaining a gray level histogram of the album picture to be cleaned in the subset to be cleaned includes:
converting the photo album picture to be cleaned into a gray level image;
counting the occurrence frequency of each gray level pixel value in the converted gray level image;
and generating a gray level histogram H of the album picture to be cleaned according to the occurrence frequency of the gray level pixel value.
Optionally, the calculating a difference value of gray histograms of any two photo album pictures to be cleaned includes:
acquiring a gray level histogram H1 of a first album picture to be cleaned and a gray level histogram H2 of a second album picture to be cleaned in the subset to be cleaned, and calculating a difference value d between the gray level histogram H1 and the gray level histogram H2 according to the following formula:
；
wherein N represents a value range [0,255];
i represents the value range [0,255] of the gray histogram color channel of the photo album picture to be cleaned;
H1 (I) representing the distribution frequency of the gray level histogram of the first photo album picture to be cleaned at the I-th color point;
h2 (I) represents the distribution frequency of the gray level histogram of the second album picture to be cleaned under the I-th color point.
Optionally, the clustering, according to a preset clustering algorithm, the target album picture to be cleaned and similar album pictures to be cleaned with a difference value smaller than or equal to a preset difference threshold value are clustered into a picture group, including:
step 1: randomly selecting one album picture to be cleaned from the subset to be cleaned as a target album picture to be cleaned;
step 2: judging whether similar album pictures to be cleaned exist in the subset to be cleaned, wherein the difference value of the album pictures to be cleaned and the target album pictures to be cleaned is smaller than or equal to a preset difference threshold value, if so, clustering the album pictures to be cleaned and the similar album pictures to be cleaned, wherein the difference value of the album pictures to be cleaned and the target album pictures to be cleaned is smaller than or equal to the preset difference threshold value, and deleting the album pictures to be cleaned and the similar album pictures to be cleaned from the subset to be cleaned, if not, deleting the album pictures to be cleaned from the subset to be cleaned;
Step 3: and (2) selecting one photo album picture to be cleaned from the rest photo album pictures to be cleaned in the sub-set to be cleaned as a target photo album picture to be cleaned, and executing the step (2) until the photo album picture to be cleaned does not exist in the sub-set to be cleaned.
Optionally, the arranging the photo album pictures to be cleaned in the picture group according to a preset sequence for the user side to clean similar photo album pictures to be cleaned in the picture group includes:
acquiring picture quality information of each photo album picture to be cleaned in the picture group; wherein the picture quality information includes at least one of: pixel value, brightness value, picture integrity;
inputting the picture quality information of the photo album pictures to be cleaned into a preset scoring model to score so as to obtain a score value of each photo album picture to be cleaned;
arranging and displaying the photo album pictures to be cleaned in the picture group in a descending order according to the score value, and setting the photo album picture to be cleaned with the highest score value as a pre-estimated reserved picture in the picture group;
and receiving a cleaning request of a user side, deleting the photo album pictures to be cleaned selected by the user side when the cleaning request is manual cleaning, and reserving the estimated reserved pictures in the picture group and deleting the photo album pictures to be cleaned except the estimated reserved pictures in the picture group when the cleaning request is automatic cleaning.
In order to achieve the above object, the present invention further provides an album cleaning apparatus based on picture classification, the apparatus comprising:
the adding module is used for obtaining album pictures and adding labels to the album pictures through a KNN algorithm; the photo album picture is a picture stored in the photo album through a preset downloading way;
the first clustering module is used for adding album pictures with the same label into one set to be cleaned to obtain a set number of sets to be cleaned;
the second aggregation module is used for adding album pictures with the same downloading route in the collection to be cleaned into a first subset to obtain a set number of first subsets;
a third class module, configured to add album pictures in the first subset, which conform to a preset size range, to a second subset, so as to obtain a set number of second subsets;
the authentication module is used for taking a second subset with the number of album pictures being more than or equal to 2 as a subset to be cleaned, and taking the album pictures in the subset to be cleaned as album pictures to be cleaned;
the calculation module is used for acquiring the gray level histograms of the photo album pictures to be cleaned in the subset to be cleaned and calculating the difference value of the gray level histograms of any two photo album pictures to be cleaned;
The fourth clustering module is used for determining a target album picture to be cleaned from the subset to be cleaned, and clustering the target album picture to be cleaned and similar album pictures to be cleaned, of which the difference value is smaller than or equal to a preset difference threshold value, into a picture group according to a preset clustering algorithm;
the sorting module is used for arranging the photo album pictures to be cleaned in the picture group according to a preset sequence so that the user side can clean similar photo album pictures to be cleaned in the picture group.
In order to achieve the above object, the present invention further provides a computer device, which specifically includes: the photo album cleaning method comprises the steps of a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the steps of the photo album cleaning method based on the picture classification are realized when the processor executes the computer program.
In order to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above-described photo album cleaning method based on picture classification.
According to the album cleaning method, the album cleaning device, the album cleaning equipment and the storage medium based on the image classification, the label is added to album images through the KNN algorithm, so that an album image to be cleaned is obtained by first classifying the album images, then the album images in the album to be cleaned are classified for the second time according to a downloading way to obtain a first sub-set, album images in the first sub-set are classified for the third time according to a preset size range to obtain a second sub-set, the second sub-set with the number of album images being greater than or equal to 2 is used as the album image to be cleaned, a difference value is calculated on the album images to be cleaned in the sub-set, and finally similar album images to be cleaned in the album images are clustered into an album image group, and scoring sorting is carried out on the album images to be cleaned in the album group of the album images to be cleaned by a user side, so that the user can be effectively assisted in managing resource content in the album, and the user can conveniently and intuitively obtain media resources to be cleaned, or the similar images to be cleaned automatically, so that the image items in the album are released, and the storage space of the mobile equipment is saved, and better content is saved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 is a schematic flow chart of an alternative album cleaning method based on picture classification according to the first embodiment;
fig. 2 is a schematic diagram of a gray histogram of an album picture to be cleaned according to the first embodiment;
fig. 3 is a schematic diagram of an alternative composition structure of an album cleaning apparatus based on picture classification according to the second embodiment;
fig. 4 is a schematic diagram of an alternative hardware architecture of a computer device according to the third embodiment.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The embodiment of the invention provides an album cleaning method based on picture classification, which specifically comprises the following steps as shown in fig. 1:
step S101: acquiring an album picture, and adding a label to the album picture through a KNN algorithm; the photo album pictures are stored in the photo album through a preset downloading way.
When a user browses web pages or application software by using the mobile device, pictures which are interested in the user are stored in an album of the mobile device in a downloading mode, but when the user frequently browses the application software for a plurality of days, the same or similar pictures are stored, and when the storage space of the mobile device reaches a peak value, the same or similar album pictures in the album need to be cleaned in order to lighten the storage pressure of the storage space of the mobile device due to the limited storage space of the mobile device.
In this embodiment, the album picture to be processed is a picture obtained through a non-shooting way, for example, a picture downloaded through mobile device application software such as a web page, a WeChat, a mailbox, or a picture obtained by screen capturing, a first frame picture of a video obtained by screen recording, etc. The number of the photo album pictures of the type is large, and the similar pictures are difficult to acquire by directly calculating the similarity of any two pictures, because a large amount of calculation resources are consumed, and the calculation speed is low, the photo album pictures are classified step by step according to the label, the downloading way and the three-level picture size, gray histograms are calculated for the photo album pictures to be cleaned in a plurality of classified subsets to be cleaned, and the acquisition of similar picture groups is realized by calculating the difference value between the gray histograms, so that a user can clean the similar pictures conveniently and rapidly, and the storage space of mobile equipment is released. In addition, when the album cleaning process is started, the picture resources stored in the album through a preset downloading way are required to be acquired through a system interface, whether the pictures in the album to be processed belong to album pictures to be processed or not is analyzed in advance, then the album pictures are subjected to disk cache processing, and the purpose is to record and verify the state of the album resources, so that when the album cleaning process is carried out again later, the album pictures to be processed can be obtained more conveniently and rapidly, the processed album pictures are not required to be processed again, and only newly added pictures are processed, so that the album cleaning speed is increased, and the album cleaning efficiency is improved.
Further, the obtaining the album picture includes:
step A1: and acquiring the adding and deleting states of the album to be processed in a set time period.
The adding and deleting states can be divided into a non-adding and deleting state, an adding state, a deleting state and an adding and deleting state.
Step A2: and when the adding and deleting state is the no adding and deleting state or the adding state, taking all the pictures in the album to be processed as album pictures.
When the adding and deleting state is the non-adding and deleting state or the adding state, the user side is indicated that the album resource in the album is not subjected to the album cleaning process, so that all pictures in the album to be processed are taken as album pictures, and the subsequent album cleaning operation is executed.
Step A3: and when the adding and deleting states are adding and deleting states, taking the newly added pictures in the album to be processed as album pictures.
When the adding and deleting state is the adding and deleting state, the user side is indicated to clear the album resources, and only newly added pictures in the album to be processed are needed to be used as album pictures.
Particularly, when the adding and deleting state is the deleting state, judging that the album picture does not exist in the album to be processed.
When the adding and deleting state is the deleting state, the user is informed that the cleaning of the photo album pictures is completed, and no new pictures exist at the moment, so that photo album cleaning is not needed for the photo album to be processed in the state.
Still further, the adding a label to the album picture through the KNN algorithm includes:
step B1: acquiring a preset training set; wherein, each standard picture in the preset training set corresponds to a label.
The KNN algorithm (K-Nearest Neighbor algorithm) is used to quickly classify the album pictures into specific categories, and since each standard picture in the training set corresponds to one label, the album picture can quickly find the corresponding label through the KNN algorithm, and each label corresponds to one picture category, so as to implement the first classification of the album picture, wherein the labels at least include any one or more of the following, for example: portrait, landscape, architecture, animals, plants, food, etc.
Step B2: and extracting the feature vector of the album picture, and sequentially calculating the Euclidean distance between the feature vector of the album picture and the feature vector of each standard picture in the preset training set.
Step B3: and obtaining K standard pictures with minimum Euclidean distance with the album pictures through a KNN algorithm.
Step B4: and counting the number of the labels of the same labels in the labels corresponding to the K standard pictures, and taking the label with the largest number of labels as the label of the album picture.
When the number of labels of the same labels in the labels corresponding to the K standard pictures is the same, selecting the label with high priority as the label of the album picture according to the preset label priority, wherein each album picture corresponds to only one label. For example, in the K standard pictures, two labels are "portrait", two labels are "landscape", and in the preset label priority, the label "portrait" is higher than the label "landscape", so that the label of the album picture is "portrait".
Step S102: and adding album pictures with the same label into one set to be cleaned to obtain a set number of sets to be cleaned.
The set number is the number of types of labels corresponding to all album pictures.
Step S103: and adding the album pictures with the same downloading route in the collection to be cleaned into a first subset to obtain a set number of first subsets.
Each collection to be cleaned comprises a set number of first subsets, wherein the set number is the type number of download paths corresponding to all album pictures in the collection to be cleaned.
Step S104: and adding the album pictures which accord with the preset size range in the first sub-set into a second sub-set to obtain a set number of second sub-sets.
Each first subset comprises a set number of second subsets, and the set number is the number of a plurality of preset size ranges.
Step S105: and taking the second subset with the number of the album pictures being more than or equal to 2 as a subset to be cleaned, and taking the album pictures in the subset to be cleaned as album pictures to be cleaned.
When the number of the album pictures is greater than or equal to 2, the second sub-set with the number of the album pictures greater than or equal to 2 is used as the sub-set to be cleaned.
In this embodiment, the album pictures are classified according to the first-level "tag", the second-level "download path" and the third-level "size range" according to the decision tree principle, and the probability of similar or identical album pictures appearing in the subset to be cleaned obtained by the classification mode is greatly improved, so that the group of pictures formed by similar or identical album pictures can be quickly obtained only by performing similarity calculation on the album pictures to be cleaned in each subset to be cleaned, the similarity calculation between every two album pictures is avoided, the speed of searching the identical or similar pictures is improved, and the calculation resources are greatly saved.
Step S106: and acquiring the gray level histograms of the photo album pictures to be cleaned in the subset to be cleaned, and calculating the difference value of the gray level histograms of any two photo album pictures to be cleaned.
The similarity among the photo album pictures to be cleaned is reflected by acquiring gray level histograms of the photo album pictures to be cleaned and utilizing a mode of calculating differences among the gray level histograms. Because the calculation cost of converting the photo album picture to be cleaned into the gray level histogram for calculation is low, the calculation power consumption of the mobile equipment can be reduced.
Specifically, the obtaining the gray level histogram of the album picture to be cleaned in the subset to be cleaned includes:
step C1: and converting the photo album picture to be cleaned into a gray level image.
Step C2: and counting the occurrence frequency of each gray level pixel value in the converted gray level image.
Step C3: and generating a gray level histogram H of the album picture to be cleaned according to the occurrence frequency of the gray level pixel value.
The gray level histogram is a function of gray level and is used for describing the number of each gray level pixel after the photo album picture to be cleaned is converted into a gray level image so as to reflect the occurrence frequency of each gray level pixel value in the gray level image. The range of gray scale pixel values is 0, 255.
Specifically, the photo album picture to be cleaned is converted into a gray histogram H according to the following formula:
H=cv2.calcHist(images,channels,mask,histSize,ranges,accumulate)；
wherein, the images represent album pictures to be cleaned;
channels represent channels (selected as [0 ]) for converting the photo album picture to be cleaned into a gray level histogram;
the mask represents a preset mask image (if the picture of the album to be cleaned has an interesting area, the mask is set as the interesting area, and if the picture of the album to be cleaned is analyzed, the mask is selected from None);
histSize represents the bin number bin of the gray histogram, preferably bin is selected to be the pixel maximum range value 255;
the range represents a pixel range [0,255] of an album picture to be cleaned after being converted into a gray level image;
accumulate is a cumulative identifier that indicates whether single histograms are allowed to be computed in multiple arrays, defaulting to false.
In this embodiment, statistics is performed on the photo album picture to be cleaned according to the gray histogram color channel distribution through the gray histogram, and the occurrence frequency of all pixels of the photo album picture to be cleaned is counted according to the gray level pixel values, as shown in fig. 2, the X-axis of the gray histogram represents the gray level pixel values, the range is [0,255], and the Y-axis represents the number of pixels conforming to the gray level pixel values of the current X-axis, so that a unique fingerprint feature value can be quickly generated for each photo album picture to be cleaned. The gray level histogram can be kept unchanged in the states of translation, rotation, scaling and the like, so that the unique gray level histogram corresponding to one photo album picture to be cleaned is ensured, and the accuracy of comparing the difference value of the photo album picture to be cleaned by using the gray level histogram is higher.
Further, the calculating the difference value of the gray level histograms of any two photo album pictures to be cleaned includes:
step D1: acquiring a gray level histogram H1 of a first album picture to be cleaned and a gray level histogram H2 of a second album picture to be cleaned in the subset to be cleaned, and calculating a difference value d between the gray level histogram H1 and the gray level histogram H2 according to the following formula:
；
wherein N represents a value range [0,255];
i represents the value range [0,255] of the gray histogram color channel of the photo album picture to be cleaned;
h1 (I) representing the distribution frequency of the gray level histogram of the first photo album picture to be cleaned at the I-th color point;
h2 (I) represents the distribution frequency of the gray level histogram of the second album picture to be cleaned under the I-th color point.
Specifically, when H1 (I) =h2 (I), the product of H1 (I) and H2 (I) is the largest, that is, the more similar the first album picture to be cleaned and the second album picture to be cleaned are, the smaller the value of the difference value d is. Therefore, the difference value d is positively correlated with the difference value of the first photo album picture to be cleaned and the second photo album picture to be cleaned, and the difference value d is negatively correlated with the similarity of the first photo album picture to be cleaned and the second photo album picture to be cleaned.
In this embodiment, the difference of gray histograms corresponding to two album pictures to be cleaned is compared by the OpenCV open source image processing library, the pasteurization distance method is used for calculation, and in the calculation process, the maximum concurrent number of multiple threads and mutual exclusion lock are set by adopting the multithreading mode for calculation due to the huge number of picture resources and large calculation amount, threads are locked before the gray histograms of the album pictures to be cleaned are stacked, and the threads are unlocked after the stacking is completed, so that the safety of each subset to be cleaned under the multithreading operation is ensured.
Step S107: and determining a target album picture to be cleaned from the subset to be cleaned, and clustering the target album picture to be cleaned and similar album pictures to be cleaned, of which the difference value is smaller than or equal to a preset difference threshold value, into a picture group according to a preset clustering algorithm.
The pictures of the album to be cleaned in the picture group are the same or similar to each other.
Specifically, the clustering, according to a preset clustering algorithm, the target album picture to be cleaned and similar album pictures to be cleaned, the difference value between which and the target album picture to be cleaned is smaller than or equal to a preset difference threshold, into a picture group includes:
Step 1: and selecting any photo album picture to be cleaned from the subset to be cleaned as a target photo album picture to be cleaned.
Step 2: judging whether similar album pictures to be cleaned exist in the subset to be cleaned, wherein the difference value of the album pictures to be cleaned is smaller than or equal to a preset difference threshold value, if yes, clustering the album pictures to be cleaned and the album pictures to be cleaned, which are similar in that the difference value of the album pictures to be cleaned is smaller than or equal to the preset difference threshold value, into a picture group, deleting the album pictures to be cleaned and the album pictures to be cleaned, which are similar in that the difference value of the album pictures to be cleaned is smaller than or equal to the preset difference threshold value, from the subset to be cleaned, and if not, deleting the album pictures to be cleaned from the subset to be cleaned.
Step 3: and (2) selecting one photo album picture to be cleaned from the rest photo album pictures to be cleaned in the sub-set to be cleaned as a target photo album picture to be cleaned, and executing the step (2) until the photo album picture to be cleaned does not exist in the sub-set to be cleaned.
Step S108: arranging the photo album pictures to be cleaned in the picture group according to a preset sequence so that a user side can clean similar photo album pictures to be cleaned in the picture group.
Further, the arranging the photo album pictures to be cleaned in the picture group according to a preset sequence for the user side to clean similar photo album pictures to be cleaned in the picture group includes the following steps:
step F1: acquiring picture quality information of each photo album picture to be cleaned in the picture group; wherein the picture quality information includes at least one of: pixel value, luminance value, picture integrity.
Step F2: inputting the picture quality information of the photo album pictures to be cleaned into a preset scoring model for scoring so as to obtain score values of each photo album picture to be cleaned.
Step F3: and arranging and displaying the photo album pictures to be cleaned in the picture group in a descending order according to the score value, and setting the photo album picture to be cleaned with the highest score value as the estimated reserved picture in the picture group.
The method and the device for scoring the photo album pictures to be cleaned can help a user side to rapidly take and place the photo album pictures. The method comprises the steps that when a user selects automatic cleaning, the estimated reserved pictures in the picture group are reserved, and the pictures of the album to be cleaned except for the estimated reserved pictures in the picture group are rapidly deleted.
Step F4: and receiving a cleaning request of a user side, deleting the photo album pictures to be cleaned selected by the user side when the cleaning request is manual cleaning, and reserving the estimated reserved pictures in the picture group and deleting the photo album pictures to be cleaned except the estimated reserved pictures in the picture group when the cleaning request is automatic cleaning.
In this embodiment, a label is added to album pictures through a KNN algorithm to obtain a to-be-cleaned set by first classifying the album pictures, then the album pictures in the to-be-cleaned set are classified for the second time according to a downloading way to obtain a first sub-set, then album pictures in the first sub-set are classified for the third time according to a preset size range to obtain a second sub-set, then the second sub-set with the number of album pictures being greater than or equal to 2 is used as the to-be-cleaned sub-set, so as to calculate a difference value of the album pictures to be cleaned in the to-be-cleaned sub-set, finally, similar or identical album pictures to be cleaned in the album picture group are clustered into a picture group, and score sorting is performed on the album pictures to be cleaned in the album picture group, so that a user can be effectively assisted in managing resource content in the album by the user, so that the user can conveniently and intuitively select media resources to be saved, or automatically clean the similar pictures, thereby saving the storage space of mobile equipment and saving more good content.
Example two
The embodiment of the invention provides an album cleaning device based on picture classification, which specifically comprises the following components as shown in fig. 3:
the adding module 301 is configured to obtain an album picture, and add a tag to the album picture through a KNN algorithm; the photo album picture is a picture stored in the photo album through a preset downloading way;
the first clustering module 302 is configured to add album pictures with the same label to one set to be cleaned to obtain a set number of sets to be cleaned;
a second aggregation module 303, configured to add album pictures with the same downloading route in the to-be-cleaned set to a first subset, so as to obtain a set number of first subsets;
a third class module 304, configured to add album pictures in the first subset, which conform to a preset size range, to a second subset, so as to obtain a set number of second subsets;
the authentication module 305 is configured to use a second subset, where the number of the album pictures is greater than or equal to 2, as a subset to be cleaned, and use the album pictures in the subset to be cleaned as album pictures to be cleaned;
the calculating module 306 is configured to obtain a gray histogram of the album pictures to be cleaned in the subset to be cleaned, and calculate a difference value of the gray histograms of any two album pictures to be cleaned;
A fourth clustering module 307, configured to determine a target album picture to be cleaned from the subset to be cleaned, and cluster the target album picture to be cleaned and a similar album picture to be cleaned, of which a difference value with the target album picture to be cleaned is less than or equal to a preset difference threshold, into a picture group according to a preset clustering algorithm;
the sorting module 308 is configured to sort the album pictures to be cleaned in the picture group according to a preset sequence, so that the user side can clean similar album pictures to be cleaned in the picture group.
Wherein, add module 301 is used for:
acquiring the adding and deleting states of the album to be processed in a set time period;
when the adding and deleting state is the adding and deleting state or the adding state, taking all pictures in the album to be processed as album pictures;
and when the adding and deleting states are adding and deleting states, taking the newly added pictures in the album to be processed as album pictures.
Further, the adding module 301 is further configured to:
acquiring a preset training set; wherein, each standard picture in the preset training set corresponds to a label;
extracting feature vectors of the album pictures, and sequentially calculating Euclidean distances between the feature vectors of the album pictures and the feature vectors of each standard picture in the preset training set;
Obtaining K standard pictures with minimum Euclidean distance with the album pictures through a KNN algorithm;
and counting the number of the labels of the same labels in the labels corresponding to the K standard pictures, and taking the label with the largest number of labels as the label of the album picture.
Wherein, the computing module 306 is configured to:
converting the photo album picture to be cleaned into a gray level image;
counting the occurrence frequency of each gray level pixel value in the converted gray level image;
and generating a gray level histogram H of the album picture to be cleaned according to the occurrence frequency of the gray level pixel value.
Further, the computing module 306 is further configured to:
acquiring a gray level histogram H1 of a first album picture to be cleaned and a gray level histogram H2 of a second album picture to be cleaned in the subset to be cleaned, and calculating a difference value d between the gray level histogram H1 and the gray level histogram H2 according to the following formula:
；
wherein N represents a value range [0,255];
i represents the value range [0,255] of the gray histogram color channel of the photo album picture to be cleaned;
h1 (I) representing the distribution frequency of the gray level histogram of the first photo album picture to be cleaned at the I-th color point;
h2 (I) represents the distribution frequency of the gray level histogram of the second album picture to be cleaned under the I-th color point.
Wherein, the fourth clustering module 307 is configured to:
step 1: randomly selecting one album picture to be cleaned from the subset to be cleaned as a target album picture to be cleaned;
step 2: judging whether similar album pictures to be cleaned exist in the subset to be cleaned, wherein the difference value of the album pictures to be cleaned and the target album pictures to be cleaned is smaller than or equal to a preset difference threshold value, if so, clustering the album pictures to be cleaned and the similar album pictures to be cleaned, wherein the difference value of the album pictures to be cleaned and the target album pictures to be cleaned is smaller than or equal to the preset difference threshold value, and deleting the album pictures to be cleaned and the similar album pictures to be cleaned from the subset to be cleaned, if not, deleting the album pictures to be cleaned from the subset to be cleaned;
step 3: and (2) selecting one photo album picture to be cleaned from the rest photo album pictures to be cleaned in the sub-set to be cleaned as a target photo album picture to be cleaned, and executing the step (2) until the photo album picture to be cleaned does not exist in the sub-set to be cleaned.
Further, the sorting module 308 is configured to:
acquiring picture quality information of each photo album picture to be cleaned in the picture group; wherein the picture quality information includes at least one of: pixel value, brightness value, picture integrity;
Inputting the picture quality information of the photo album pictures to be cleaned into a preset scoring model to score so as to obtain a score value of each photo album picture to be cleaned;
arranging and displaying the photo album pictures to be cleaned in the picture group in a descending order according to the score value, and setting the photo album picture to be cleaned with the highest score value as a pre-estimated reserved picture in the picture group;
and receiving a cleaning request of a user side, deleting the photo album pictures to be cleaned selected by the user side when the cleaning request is manual cleaning, and reserving the estimated reserved pictures in the picture group and deleting the photo album pictures to be cleaned except the estimated reserved pictures in the picture group when the cleaning request is automatic cleaning.
Example III
The present embodiment also provides a computer device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including an independent server or a server cluster formed by a plurality of servers) that can execute a program. As shown in fig. 4, the computer device 40 of the present embodiment includes at least, but is not limited to: a memory 401 and a processor 402 which can be communicatively connected to each other via a system bus. It should be noted that FIG. 4 only shows computer device 40 having components 401-402, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead.
In this embodiment, the memory 401 (i.e., readable storage medium) includes flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 401 may be an internal storage unit of the computer device 40, such as a hard disk or a memory of the computer device 40. In other embodiments, the memory 401 may also be an external storage device of the computer device 40, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the computer device 40. Of course, memory 401 may also include both internal storage units of computer device 40 and external storage devices. In this embodiment, the memory 401 is typically used to store an operating system and various types of application software installed on the computer device 40. In addition, the memory 401 can also be used to temporarily store various types of data that have been output or are to be output.
The processor 402 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other photo album cleaning chip in some embodiments. The processor 402 is generally used to control the overall operation of the computer device 40.
Specifically, in the present embodiment, the processor 402 is configured to execute a program of an album cleaning method based on picture classification stored in the memory 401, where the program of the album cleaning method based on picture classification is executed to implement the following steps:
acquiring an album picture, and adding a label to the album picture through a KNN algorithm; the photo album picture is a picture stored in the photo album through a preset downloading way;
adding album pictures with the same label into one set to be cleaned to obtain a set number of sets to be cleaned;
adding album pictures with the same downloading route in the collection to be cleaned into a first subset to obtain a set number of first subsets;
adding album pictures which accord with a preset size range in the first sub-set into a second sub-set to obtain a set number of second sub-sets;
taking a second subset with the number of album pictures being more than or equal to 2 as a subset to be cleaned, and taking the album pictures in the subset to be cleaned as album pictures to be cleaned;
Acquiring gray histograms of the photo album pictures to be cleaned in the subset to be cleaned, and calculating difference values of the gray histograms of any two photo album pictures to be cleaned;
determining a target album picture to be cleaned from the subset to be cleaned, and clustering the target album picture to be cleaned and similar album pictures to be cleaned, of which the difference value is smaller than or equal to a preset difference threshold value, into a picture group according to a preset clustering algorithm;
arranging the photo album pictures to be cleaned in the picture group according to a preset sequence so that a user side can clean similar photo album pictures to be cleaned in the picture group.
The specific embodiment process of the above method steps can be referred to as embodiment one, and the description of this embodiment is not repeated here.
Example IV
The present embodiment also provides a computer readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., having stored thereon a computer program that when executed by a processor performs the following method steps:
Acquiring an album picture, and adding a label to the album picture through a KNN algorithm; the photo album picture is a picture stored in the photo album through a preset downloading way;
adding album pictures with the same label into one set to be cleaned to obtain a set number of sets to be cleaned;
adding album pictures with the same downloading route in the collection to be cleaned into a first subset to obtain a set number of first subsets;
adding album pictures which accord with a preset size range in the first sub-set into a second sub-set to obtain a set number of second sub-sets;
taking a second subset with the number of album pictures being more than or equal to 2 as a subset to be cleaned, and taking the album pictures in the subset to be cleaned as album pictures to be cleaned;
acquiring gray histograms of the photo album pictures to be cleaned in the subset to be cleaned, and calculating difference values of the gray histograms of any two photo album pictures to be cleaned;
determining a target album picture to be cleaned from the subset to be cleaned, and clustering the target album picture to be cleaned and similar album pictures to be cleaned, of which the difference value is smaller than or equal to a preset difference threshold value, into a picture group according to a preset clustering algorithm;
Arranging the photo album pictures to be cleaned in the picture group according to a preset sequence so that a user side can clean similar photo album pictures to be cleaned in the picture group.
The specific embodiment process of the above method steps can be referred to as embodiment one, and the description of this embodiment is not repeated here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. An album cleaning method based on picture classification is characterized by comprising the following steps:
acquiring an album picture, and adding a label to the album picture through a KNN algorithm; the photo album picture is a picture stored in the photo album through a preset downloading way;
adding album pictures with the same label into one set to be cleaned to obtain a set number of sets to be cleaned;
adding album pictures with the same downloading route in the collection to be cleaned into a first subset to obtain a set number of first subsets;
adding album pictures which accord with a preset size range in the first sub-set into a second sub-set to obtain a set number of second sub-sets;
taking a second subset with the number of album pictures being more than or equal to 2 as a subset to be cleaned, and taking the album pictures in the subset to be cleaned as album pictures to be cleaned;
Acquiring gray histograms of the photo album pictures to be cleaned in the subset to be cleaned, and calculating difference values of the gray histograms of any two photo album pictures to be cleaned;
determining a target album picture to be cleaned from the subset to be cleaned, and clustering the target album picture to be cleaned and similar album pictures to be cleaned, of which the difference value is smaller than or equal to a preset difference threshold value, into a picture group according to a preset clustering algorithm;
arranging the photo album pictures to be cleaned in the picture group according to a preset sequence so that a user side can clean similar photo album pictures to be cleaned in the picture group.
2. The method for cleaning photo album based on the picture classification as set forth in claim 1, wherein the obtaining the photo album picture comprises:
acquiring the adding and deleting states of the album to be processed in a set time period;
when the adding and deleting state is the adding and deleting state or the adding state, taking all pictures in the album to be processed as album pictures;
and when the adding and deleting states are adding and deleting states, taking the newly added pictures in the album to be processed as album pictures.
3. The album cleaning method based on the picture classification according to claim 1, wherein the adding a label to the album picture by KNN algorithm comprises:
Acquiring a preset training set; wherein, each standard picture in the preset training set corresponds to a label;
extracting feature vectors of the album pictures, and sequentially calculating Euclidean distances between the feature vectors of the album pictures and the feature vectors of each standard picture in the preset training set;
obtaining K standard pictures with minimum Euclidean distance with the album pictures through a KNN algorithm;
and counting the number of the labels of the same labels in the labels corresponding to the K standard pictures, and taking the label with the largest number of labels as the label of the album picture.
4. The method for cleaning photo album based on picture classification according to claim 1, wherein the obtaining the gray level histogram of the photo album picture to be cleaned in the subset to be cleaned comprises:
converting the photo album picture to be cleaned into a gray level image;
counting the occurrence frequency of each gray level pixel value in the converted gray level image;
and generating a gray level histogram H of the album picture to be cleaned according to the occurrence frequency of the gray level pixel value.
5. The album cleaning method according to claim 4, wherein the calculating the difference value of the gray level histogram of any two album pictures to be cleaned comprises:
Acquiring a gray level histogram H1 of a first album picture to be cleaned and a gray level histogram H2 of a second album picture to be cleaned in the subset to be cleaned, and calculating a difference value d between the gray level histogram H1 and the gray level histogram H2 according to the following formula:
；
wherein N represents a value range [0,255];
i represents the value range [0,255] of the gray histogram color channel of the photo album picture to be cleaned;
h1 (I) representing the distribution frequency of the gray level histogram of the first photo album picture to be cleaned at the I-th color point;
h2 (I) represents the distribution frequency of the gray level histogram of the second album picture to be cleaned under the I-th color point.
6. The album cleaning method according to claim 1, wherein the clustering the target album picture to be cleaned and the similar album picture to be cleaned with the difference value smaller than or equal to the preset difference threshold value into a picture group according to the preset clustering algorithm comprises:
step 1: randomly selecting one album picture to be cleaned from the subset to be cleaned as a target album picture to be cleaned;
step 2: judging whether similar album pictures to be cleaned exist in the subset to be cleaned, wherein the difference value of the album pictures to be cleaned and the target album pictures to be cleaned is smaller than or equal to a preset difference threshold value, if so, clustering the album pictures to be cleaned and the similar album pictures to be cleaned, wherein the difference value of the album pictures to be cleaned and the target album pictures to be cleaned is smaller than or equal to the preset difference threshold value, and deleting the album pictures to be cleaned and the similar album pictures to be cleaned from the subset to be cleaned, if not, deleting the album pictures to be cleaned from the subset to be cleaned;
Step 3: and (2) selecting one photo album picture to be cleaned from the rest photo album pictures to be cleaned in the sub-set to be cleaned as a target photo album picture to be cleaned, and executing the step (2) until the photo album picture to be cleaned does not exist in the sub-set to be cleaned.
7. The album cleaning method according to any one of claims 1-6, wherein the arranging the album pictures to be cleaned in the group of pictures according to a preset order for the user side to clean similar album pictures to be cleaned in the group of pictures includes:
acquiring picture quality information of each photo album picture to be cleaned in the picture group; wherein the picture quality information includes at least one of: pixel value, brightness value, picture integrity;
inputting the picture quality information of the photo album pictures to be cleaned into a preset scoring model to score so as to obtain a score value of each photo album picture to be cleaned;
arranging and displaying the photo album pictures to be cleaned in the picture group in a descending order according to the score value, and setting the photo album picture to be cleaned with the highest score value as a pre-estimated reserved picture in the picture group;
And receiving a cleaning request of a user side, deleting the photo album pictures to be cleaned selected by the user side when the cleaning request is manual cleaning, and reserving the estimated reserved pictures in the picture group and deleting the photo album pictures to be cleaned except the estimated reserved pictures in the picture group when the cleaning request is automatic cleaning.
8. Photo album cleaning apparatus based on picture classification, characterized in that the apparatus comprises:
the adding module is used for obtaining album pictures and adding labels to the album pictures through a KNN algorithm; the photo album picture is a picture stored in the photo album through a preset downloading way;
the first clustering module is used for adding album pictures with the same label into one set to be cleaned to obtain a set number of sets to be cleaned;
the second aggregation module is used for adding album pictures with the same downloading route in the collection to be cleaned into a first subset to obtain a set number of first subsets;
a third class module, configured to add album pictures in the first subset, which conform to a preset size range, to a second subset, so as to obtain a set number of second subsets;
The authentication module is used for taking a second subset with the number of album pictures being more than or equal to 2 as a subset to be cleaned, and taking the album pictures in the subset to be cleaned as album pictures to be cleaned;
the calculation module is used for acquiring the gray level histograms of the photo album pictures to be cleaned in the subset to be cleaned and calculating the difference value of the gray level histograms of any two photo album pictures to be cleaned;
the fourth clustering module is used for determining a target album picture to be cleaned from the subset to be cleaned, and clustering the target album picture to be cleaned and similar album pictures to be cleaned, of which the difference value is smaller than or equal to a preset difference threshold value, into a picture group according to a preset clustering algorithm;
the sorting module is used for arranging the photo album pictures to be cleaned in the picture group according to a preset sequence so that the user side can clean similar photo album pictures to be cleaned in the picture group.
9. A computer device, the computer device comprising: memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311160963.3A CN116894008A (en) | 2023-09-11 | 2023-09-11 | Photo album cleaning method, device, equipment and storage medium based on picture classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311160963.3A CN116894008A (en) | 2023-09-11 | 2023-09-11 | Photo album cleaning method, device, equipment and storage medium based on picture classification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116894008A true CN116894008A (en) | 2023-10-17 |
Family
ID=88309794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311160963.3A Pending CN116894008A (en) | 2023-09-11 | 2023-09-11 | Photo album cleaning method, device, equipment and storage medium based on picture classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116894008A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9036943B1 (en) * | 2013-03-14 | 2015-05-19 | Amazon Technologies, Inc. | Cloud-based image improvement |
| CN106203461A (en) * | 2015-05-07 | 2016-12-07 | 中国移动通信集团公司 | A kind of image processing method and device |
| CN106326908A (en) * | 2015-06-30 | 2017-01-11 | 中兴通讯股份有限公司 | Picture management method and apparatus, and terminal equipment |
-
2023
- 2023-09-11 CN CN202311160963.3A patent/CN116894008A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9036943B1 (en) * | 2013-03-14 | 2015-05-19 | Amazon Technologies, Inc. | Cloud-based image improvement |
| CN106203461A (en) * | 2015-05-07 | 2016-12-07 | 中国移动通信集团公司 | A kind of image processing method and device |
| CN106326908A (en) * | 2015-06-30 | 2017-01-11 | 中兴通讯股份有限公司 | Picture management method and apparatus, and terminal equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2668717C1 (en) | Generation of marking of document images for training sample | |
| US8358837B2 (en) | Apparatus and methods for detecting adult videos | |
| US9031999B2 (en) | System and methods for generation of a concept based database | |
| CN102007499B (en) | Detecting facial expressions in digital images | |
| US10831814B2 (en) | System and method for linking multimedia data elements to web pages | |
| US8520909B2 (en) | Automatic and semi-automatic image classification, annotation and tagging through the use of image acquisition parameters and metadata | |
| US9798795B2 (en) | Methods for identifying relevant metadata for multimedia data of a large-scale matching system | |
| US20230376527A1 (en) | Generating congruous metadata for multimedia | |
| US8315465B1 (en) | Effective feature classification in images | |
| US20150110387A1 (en) | Method for binary classification of a query image | |
| WO2010101187A1 (en) | Method and program for creating image database, and method for retrieving image | |
| CN107223242B (en) | Method for searching for similar images in a plurality of stored images | |
| Choi et al. | Automatic face annotation in personal photo collections using context-based unsupervised clustering and face information fusion | |
| CN111191591A (en) | Watermark detection method, video processing method and related equipment | |
| Bakić et al. | Inria IMEDIA2's participation at ImageCLEF 2012 plant identification task | |
| Giouvanakis et al. | Saliency map driven image retrieval combining the bag-of-words model and PLSA | |
| CN116894008A (en) | Photo album cleaning method, device, equipment and storage medium based on picture classification | |
| CN112884866B (en) | Coloring method, device, equipment and storage medium for black-and-white video | |
| CN111178409B (en) | Image matching and recognition system based on big data matrix stability analysis | |
| CN113361426A (en) | Vehicle loss assessment image acquisition method, medium, device and electronic equipment | |
| US10360253B2 (en) | Systems and methods for generation of searchable structures respective of multimedia data content | |
| CN116561372B (en) | Personnel gear gathering method and device based on multiple algorithm engines and readable storage medium | |
| CN117033316A (en) | Photo album cleaning method and device based on picture processing algorithm and storage medium | |
| US10691642B2 (en) | System and method for enriching a concept database with homogenous concepts | |
| Sahay et al. | Visually classified & tagged video repository |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |