CN111382295B - Image search result ordering method and device - Google Patents
Image search result ordering method and device Download PDFInfo
- Publication number
- CN111382295B CN111382295B CN201811612143.2A CN201811612143A CN111382295B CN 111382295 B CN111382295 B CN 111382295B CN 201811612143 A CN201811612143 A CN 201811612143A CN 111382295 B CN111382295 B CN 111382295B
- Authority
- CN
- China
- Prior art keywords
- image
- images
- aesthetic
- determining
- search results
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013145 classification model Methods 0.000 claims abstract description 33
- 238000013210 evaluation model Methods 0.000 claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims description 47
- 230000006399 behavior Effects 0.000 claims description 14
- 230000000875 corresponding effect Effects 0.000 description 104
- 238000004891 communication Methods 0.000 description 10
- 238000011156 evaluation Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a method and a device for ordering image search results, wherein when the image search results of keywords are acquired, a first image set which belongs to a first image category is identified from images of the image search results according to an image classification model, and aesthetic scores corresponding to the images in the first image set are determined through an aesthetic evaluation model corresponding to the first image category. And when the images in the image search results are ranked, determining the ranking positions of the images in the first image set in the image search results by combining the aesthetic scores corresponding to the images in the first image set. Because the aesthetic score of one category can show the aesthetic feeling of the image to the user under the category, the image with better aesthetic feeling can be preferentially displayed to the user because the user has relatively high possibility of selecting and viewing the image with higher aesthetic score, and the image with higher aesthetic score has higher possibility of meeting the image searching requirement, so that the image searching experience is improved.
Description
Technical Field
The present application relates to the field of image searching, and in particular, to a method and apparatus for sorting image searching results.
Background
In the conventional image search, images in image search results corresponding to keywords are generally ranked by using a relevance evaluation method.
However, unlike other types of searches, the images with high relevance to the keywords are not necessarily images meeting the user requirements, so that the obtained sorting result is difficult to meet the user image search requirements according to the existing relevance evaluation mode, and the user search experience is not high.
Therefore, improving the ranking effect of the image search results is a problem that needs to be solved at present.
Disclosure of Invention
In order to solve the technical problems, the application provides a method and a device for ordering image search results, so that images with higher aesthetic scores can be preferentially displayed to users, and the image search experience of the users is improved.
The embodiment of the application discloses the following technical scheme:
In a first aspect, an embodiment of the present application provides a method for sorting image search results, where the method includes:
acquiring an image search result corresponding to a keyword, wherein the image search result comprises a plurality of images;
Identifying a first set of images from the image search results according to an image classification model; the images in the first image set belong to a first image category;
Determining aesthetic scores corresponding to the images in the first image set through aesthetic evaluation models corresponding to the first image types;
and when the images in the image search results are ranked, determining the ranking positions of the images in the first image set in the image search results by combining the aesthetic scores corresponding to the images in the first image set.
Optionally, the identifying the first image set from the image search results according to the image classification model includes:
identifying the first and second image sets from the image search results according to the image classification model; the images in the second image set belong to a second image category different from the first image category;
The method further comprises the steps of:
determining aesthetic scores corresponding to the images in the second image set through aesthetic evaluation models corresponding to the second image categories;
And when the images in the image search results are ranked, determining the ranking positions of the images in the second image set in the image search results by combining the aesthetic scores corresponding to the images in the second image set.
Optionally, the first image category has a correlation with a type to which the keyword belongs.
Optionally, if the first image category is a person category, the method further includes:
determining face analysis scores corresponding to the images in the first image set according to the face analysis model;
Determining the quality scores corresponding to the images in the first image set according to the face analysis scores corresponding to the images in the first image set and the aesthetic scores corresponding to the images in the first image set;
The determining, in combination with the aesthetic scores corresponding to the images in the first image set, the ranking positions of the images in the first image set in the image search results includes:
And determining the ordering positions of the images in the first image set in the image search results by combining the quality scores corresponding to the images in the first image set.
Optionally, the image search result is a plurality of images which are obtained according to the keyword search and have correlation with the keyword which meet a preset condition.
Optionally, if the keyword is input by the target user, the method further includes:
Determining the image clicking characteristics of the target user according to the image searching behaviors of the target user;
After determining the sorting result of the images in the image search result, adjusting the sorting result according to the image clicking feature so as to advance the sorting position of the images conforming to the image clicking feature in the image search result;
and displaying the image search result according to the adjusted sorting result.
In a second aspect, an embodiment of the present application provides an image search result sorting apparatus, where the apparatus includes an obtaining unit, an identifying unit, a determining unit, and a sorting unit:
the acquisition unit is used for acquiring an image search result corresponding to the keyword, wherein the image search result comprises a plurality of images;
the identification unit is used for identifying a first image set from the image search results according to an image classification model; the images in the first image set belong to a first image category;
The determining unit is used for determining aesthetic scores corresponding to the images in the first image set through the aesthetic evaluation models corresponding to the first image categories;
And the sorting unit is used for determining the sorting position of the images in the first image set in the image search result by combining the aesthetic scores corresponding to the images in the first image set when the images in the image search result are sorted.
Optionally, the identifying unit is further configured to identify the first image set and the second image set from the image search result according to the image classification model; the images in the second image set belong to a second image category different from the first image category;
the determining unit is further configured to determine aesthetic scores corresponding to the images in the second image set according to the aesthetic evaluation models corresponding to the second image categories;
the ranking unit is further configured to determine, when ranking the images in the image search result, a ranking position of the images in the second image set in the image search result in combination with aesthetic scores corresponding to the images in the second image set.
Optionally, the first image category has a correlation with a type to which the keyword belongs.
Optionally, if the first image category is a person category, the apparatus further includes a face analysis score determining unit and a quality score determining unit:
The face analysis score determining unit is used for determining face analysis scores corresponding to the images in the first image set according to a face analysis model;
The quality score determining unit is used for determining the quality scores corresponding to the images in the first image set according to the face analysis scores corresponding to the images in the first image set and the aesthetic scores corresponding to the images in the first image set;
the ranking unit is further configured to determine a ranking position of the images in the first image set in the image search result in combination with the quality scores corresponding to the images in the first image set.
Optionally, the image search result is a plurality of images which are obtained according to the keyword search and have correlation with the keyword which meet a preset condition.
Optionally, if the keyword is input by the target user, the device further includes an image click feature determining unit, an adjusting unit, and a display unit:
the image click feature determining unit is used for determining the image click feature of the target user according to the image searching behavior of the target user;
the adjusting unit is used for adjusting the sorting result according to the image clicking characteristics after determining the sorting result of the images in the image searching result so as to advance the sorting position of the images conforming to the image clicking characteristics in the image searching result;
The display unit is used for displaying the image search results according to the adjusted sorting results.
In a third aspect, embodiments of the present application provide an image search result sorting apparatus comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:
acquiring an image search result corresponding to a keyword, wherein the image search result comprises a plurality of images;
Identifying a first set of images from the image search results according to an image classification model; the images in the first image set belong to a first image category;
Determining aesthetic scores corresponding to the images in the first image set through aesthetic evaluation models corresponding to the first image types;
and when the images in the image search results are ranked, determining the ranking positions of the images in the first image set in the image search results by combining the aesthetic scores corresponding to the images in the first image set.
In a fourth aspect, embodiments of the present application provide a machine-readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform a method of ranking image search results as described in one or more of the first aspects.
According to the technical scheme, when the image search result which corresponds to the keyword and comprises a plurality of images is obtained, a first image set which belongs to a first image category is identified from the images of the image search result according to the image classification model, and the aesthetic scores corresponding to the images in the first image set are determined through the aesthetic evaluation model corresponding to the first image category. And when the images in the image search results are ranked, determining the ranking positions of the images in the first image set in the image search results by combining the aesthetic scores corresponding to the images in the first image set. For images belonging to one image category, the aesthetic score of the category can show that the image brings aesthetic feeling to a user under the category, and the probability that the user selects to view the images with better aesthetic feeling is relatively high, so that the sorting position of the images with higher aesthetic score is advanced, the sorting position of the images with lower aesthetic score is advanced, the images with higher aesthetic score can be preferentially displayed to the user, and the probability that the images meet the image searching requirement of the user is high, so that the image searching experience of the user is improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a method flow chart of a method for sorting image search results according to an embodiment of the present application;
FIG. 2 is a device structure diagram of a device for sorting image search results according to an embodiment of the present application;
FIG. 3 is a block diagram of an image search result sorting apparatus according to an embodiment of the present application;
Fig. 4 is a block diagram of a server according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described below with reference to the accompanying drawings.
In the conventional image search, images in image search results corresponding to keywords are generally ranked by using a relevance evaluation method. The images with high correlation with the keywords are ranked at a position relatively earlier and are preferentially displayed to the user.
However, unlike the search terms such as files and pages, the aesthetic feeling of the image directly influences whether the user is willing to click to view, for example, the relevance of one image in the image search results and the keywords is very high, but the aesthetic feeling is not satisfactory, the possibility that the user clicks to view the one image is not high, and therefore the image with high relevance to the keywords is not necessarily the image meeting the user requirement, and the problem to be solved is urgent at present.
Therefore, the embodiment of the application provides a ranking method of image search results, wherein the aesthetic score of the images of a certain image category in the image search results is determined through an image classification model and an aesthetic evaluation model, and the ranking position of the images in the image search results is adjusted by combining the aesthetic score. The sorting method may be applied to a processing device, which may be a terminal, a computer, a server, etc. The image classification model and the aesthetic evaluation model can be configured in one processing device or can be respectively configured in different processing devices.
For images belonging to a certain image category, the aesthetic score of the category can show that the image brings aesthetic feeling to a user under the category, and the probability that the user selects to view the images with better aesthetic feeling is relatively high, so that the sorting position of the images with higher aesthetic score is advanced, the sorting position of the images with lower aesthetic score is advanced, the images with higher aesthetic score can be preferentially displayed to the user, and the probability that the images meet the image searching requirement of the user is high, so that the image searching experience of the user is improved.
Next, a method for sorting image search results provided by an embodiment of the present application is described with reference to fig. 1, where the method includes:
S101: and obtaining an image search result corresponding to the keyword.
The image search result is an image which is obtained by a search engine according to a keyword and is related to the keyword, and the image search result comprises a plurality of images.
The embodiment of the application can determine the aesthetic scores of the images of a certain image category in the image search result through the image classification model and the aesthetic evaluation model, and adjust the ordering positions of the images in the image search result by combining the aesthetic scores. To increase the efficiency of adjusting the ranking position in conjunction with the aesthetic score, a targeted selection may be required to determine the aesthetic scored image.
In one possible implementation manner, the image search result is a plurality of images which are obtained according to the keyword search and have correlation with the keyword that meets a preset condition.
That is, in this possible implementation, the image search result may be a part of all images searched according to the keyword, for example, the top N images having the highest correlation.
The relevance of the part of images and the keywords is relatively high, so that the ranking positions originally obtained according to the relevance are relatively front, the possibility that the ranking positions are front after being adjusted by determining the aesthetic scores of the part of images and combining the aesthetic scores is relatively high, the images are easier to display to the user preferentially, and the possibility that the user clicks to view the part of images is further improved.
S102: a first set of images is identified from the image search results according to an image classification model.
The image classification model may be pre-trained to at least enable the function of identifying images of a certain image class from the images.
In the embodiment of the application, a first image set belonging to a first image category is identified from image search results according to an image classification model, and at least one image in the image search results is included in the first image set.
The embodiment of the application is not limited to the division mode or the division granularity of the image categories, for example, the image categories can be divided according to different display objects in the image, and can comprise people, real objects, materials, scenery and the like. The first image category may be any of the categories described above. That is, embodiments of the present application may identify for any one of the image categories in the image search results and adjust the ranking position by determining an aesthetic score for that type of image.
In one possible implementation, the first image category has a correlation with a type to which the keyword belongs. That is, when image recognition is performed on the image search result corresponding to the keyword, an image whose image type is correlated with the type of the keyword can be recognized from the image search result by the image classification model in a targeted manner.
The relevance described herein may be understood as that the type to which the keyword belongs has an association relationship, such as similar or identical, with the image type. For example, the image types include four types of people, real objects, materials and scenery, if the keyword is "Liu Dehua", and the type to which the keyword belongs is determined to be a person, then the people in the image type have correlation with the type to which the keyword belongs, and the other three image types have no correlation with the type to which the keyword belongs.
Therefore, in the implementation manner, the identified images included in the first image set have correlation with the types of the keywords, so that the degree of coincidence between the images in the first image set and the image searching requirement of the user searching through the keywords is better, and the follow-up aesthetic scoring and the sorting position adjustment are performed on the images, so that the image searching requirement of the user is more likely to be met.
It should be noted that, since the embodiment of the present application needs to determine the corresponding aesthetic evaluation model according to the image category to score the aesthetic aspect, different image categories should have different aesthetic evaluation manners, where different aesthetic evaluation manners may refer to all or part of different aesthetic evaluation manners.
For example, images with whiter, more stereoscopic character face structures, better body proportions, etc. may yield higher aesthetic scores, while images with higher color saturation, better composition proportions, etc. in landscape images may yield higher aesthetic scores. Therefore, when classifying image categories, it is necessary to consider the above situation and determine that different image categories obtained by classification have different aesthetic evaluation manners.
S103: and determining the aesthetic scores corresponding to the images in the first image set through the aesthetic evaluation models corresponding to the first image types.
The aesthetic evaluation model in this step scores aesthetic directions exclusively for images of the first image class. The aesthetic evaluation model may be pre-trained, for example, pre-trained via a deep neural network.
The aesthetic assessment model may score aesthetic directions by analyzing features in the image that are related to the aesthetic features based on the aesthetic features corresponding to the first image category. The higher the aesthetic score of an image, the better the aesthetic perception that the image gives to the user.
By means of the corresponding aesthetic evaluation model of the first image category, a corresponding aesthetic score can be determined for the images in the first image set, wherein one image has a corresponding aesthetic score.
Alternatively, the aesthetic score may be a score of 0-1.
S104: and when the images in the image search results are ranked, determining the ranking positions of the images in the first image set in the image search results by combining the aesthetic scores corresponding to the images in the first image set.
In the embodiment of the application, for the images in the first image set, the ranking positions of the images in the image search result can be determined only according to the aesthetic scores, or the ranking positions of the images with lower aesthetic scores can be adjusted according to the aesthetic scores on the basis of determining the ranking positions according to the relevance between the images in the image search result and the keywords, for example, the ranking positions of the images with higher aesthetic scores are advanced, and the ranking positions of the images with lower aesthetic scores are backward.
Whether the ranking positions of the images in the first image set in the image search results are determined by combining the aesthetic scores in any of the manners described above, the ranking positions of at least some images with higher aesthetic scores can be advanced, and the advanced display positions enable a user to view such images more quickly.
When an image search result corresponding to a keyword and comprising a plurality of images is obtained, a first image set which belongs to a first image category is identified from the images of the image search result according to an image classification model, and aesthetic scores corresponding to the images in the first image set are determined through an aesthetic evaluation model corresponding to the first image category. And when the images in the image search results are ranked, determining the ranking positions of the images in the first image set in the image search results by combining the aesthetic scores corresponding to the images in the first image set. For images belonging to one image category, the aesthetic score of the category can show that the image brings aesthetic feeling to a user under the category, and the probability that the user selects to view the images with better aesthetic feeling is relatively high, so that the sorting position of the images with higher aesthetic score is advanced, the sorting position of the images with lower aesthetic score is advanced, the images with higher aesthetic score can be preferentially displayed to the user, and the probability that the images meet the image searching requirement of the user is high, so that the image searching experience of the user is improved.
In S102, the image classification model may identify images belonging to a first image class from the image search results, and in addition, the image classification model may identify images of other image classes, such as a second image class different from the first image class. That is, images of multiple image categories may be identified from the image search results by the image classification model and a corresponding set of images formed.
So in one possible implementation, S102 may be:
and identifying the first image set and the second image set from the image search results according to the image classification model.
The images in the second set of images belong to a second image category different from the first image category. For example, the first image category is a person category, the second image category is a landscape category, and then the images in the first image set are all images of the person category, and the images in the second image category are all images of the landscape category.
It should be noted that some images may have multiple image categories, such as an image a that includes someone in the field, which may be both person and landscape, so that when a plurality of image sets of different image categories, such as a first image set and a second image set, are identified from the image search results by the image classification model, one or more images in the image search results may be in both the first image set and the second image set. For example, if the first image category is a person category and the second image category is a landscape category, the image a may be in either the first or second image set, in which case the image a may have an aesthetic score for the corresponding person category and an aesthetic score for the corresponding landscape category. In determining the ranking position of image a in the image search result in combination with the aesthetic score for image a, the ranking position of image a may be determined by considering both the aesthetic score of image a for the person class and the aesthetic score for the landscape class, for example, setting different weights to integrate the multiple aesthetic scores to obtain a total aesthetic score, and removing the ranking position of image a by the total aesthetic score; or determining the ranking position of the image a according to the higher score in the aesthetic scores of the image a corresponding to the characters and the aesthetic scores of the corresponding scenery; or if a certain image type of image a, such as a person, has a correlation with the type of keyword, the aesthetic score of the person may be used to determine the ranking position of image a.
After the first and second image sets are determined, the images in the second image set need to be scored for aesthetic direction. On the basis of the corresponding embodiment of fig. 1, the method further includes:
S201: and determining the aesthetic scores corresponding to the images in the second image set through the aesthetic evaluation models corresponding to the second image types.
The aesthetic evaluation model in this step scores aesthetic directions exclusively for images of the second image class. The aesthetic evaluation model may be pre-trained, for example, pre-trained via a deep neural network.
The aesthetic assessment model may score the aesthetic direction by analyzing features in the image that are related to the aesthetic feature based on the aesthetic feature corresponding to the second image category. The higher the aesthetic score of an image, the better the aesthetic perception that the image gives to the user.
By means of the corresponding aesthetic evaluation model of the second image category, a corresponding aesthetic score can be determined for the images in the second image set, wherein one image has a corresponding aesthetic score.
Alternatively, the aesthetic score may be a score of 0-1.
S202: and when the images in the image search results are ranked, determining the ranking positions of the images in the second image set in the image search results by combining the aesthetic scores corresponding to the images in the second image set.
In the embodiment of the application, for the images in the second image set, the ranking positions of the images in the image search result can be determined only according to the aesthetic scores, or the original ranking positions of the images in the second image set can be adjusted according to the aesthetic scores on the basis of determining the ranking positions according to the relevance between the images in the image search result and the keywords, for example, the ranking positions of the images with higher aesthetic scores are advanced, and the ranking positions of the images with lower aesthetic scores are backward.
Whether the ranking positions of the images in the second image set in the image search results are determined by combining the aesthetic scores in any of the manners described above, the ranking positions of at least some images with higher aesthetic scores can be advanced, and the advanced display positions enable a user to view such images more quickly.
In summary, because of the large differences in images of different image types, the aesthetic or appeal evaluation criteria for the images of different image types are not consistent by the user, such as for stories and characters, which differ greatly from the aesthetic evaluation criteria for both saturation and composition of images. Therefore, in the embodiment of the application, when the aesthetic direction of the images is scored, different aesthetic scoring models can be adopted for the images of different image categories, and different scoring standards and modes can be adopted for the different image categories, so that the accuracy of aesthetic feeling of the aesthetic scoring is improved, and the determined image sorting position can improve the image searching experience of a user.
Aiming at the images with the image categories of people, the embodiment of the application also provides a mode for further optimizing the sorting positions,
If the first image class is a person, in a possible implementation manner, based on the embodiment corresponding to fig. 1, the method further includes:
s301: and determining face analysis scores corresponding to the images in the first image set according to the face analysis model.
The face analysis model is used for analyzing faces in images, and can comprise detection and recognition of the analyzed faces, the number of the faces and the like. Through the face analysis process, face analysis scoring can be performed on the images in the first image set based on the analysis result. Wherein an image corresponds to a face analysis score.
It should be noted that the face analysis model may implement the above-mentioned face analysis function through one model, or may implement the above-mentioned face analysis function through a plurality of models, for example, the face analysis model may be divided into a face detection model and a face recognition model, where the face detection model may detect the positions and the number of faces in an image, and the face recognition model may identify characters corresponding to the faces in the image, and so on.
For example, the keyword is "actor a", and face information carried by each image in the image search result corresponding to the keyword can be identified through a face analysis model, for example, whether the person in the image is actor a, there are several persons, and the like.
The face analysis score may represent whether the identified and detected face in the image is associated with a person corresponding to the keyword, for example, in the image corresponding to "actor a" in the above example, if only one face is included in one image and is actor a, the face analysis score is relatively high, and if a plurality of faces are included in one image, only one face is actor a, and the face analysis score is relatively low.
By the description of the face analysis score in the previous section, the association degree between the face contained in the person image and the person corresponding to the keyword can be clearly shown by the face analysis score, or whether the image is focused on the person corresponding to the displayed keyword.
The higher the association degree between the face contained in one image and the task corresponding to the keyword, for example, the higher the face analysis score of the image when only the face of the person corresponding to the keyword is contained and the faces of other persons are not contained.
It can be seen that the level of the face analysis score can also affect the likelihood of whether the user selects the click selection. The person corresponding to the keyword can show the search requirement of the user, so that the likelihood that the user clicks and selects the image with higher association degree with the person corresponding to the keyword from the image search result is higher, that is, the higher the face analysis score of one image is, the higher the likelihood that the user clicks and selects the image is.
S302: and determining the quality scores corresponding to the images in the first image set according to the face analysis scores corresponding to the images in the first image set and the aesthetic scores corresponding to the images in the first image set.
Because each image in the first image set already has a corresponding aesthetic score and a face analysis score, the aesthetic score can reflect aesthetic feeling brought by the image to a user, the face analysis score can reflect the association degree of the face contained in the image and the person corresponding to the keyword, and both scores can be used for adjusting the ordering position of the image. In order to facilitate calculation, the two scores can be combined to comprehensively obtain the quality score corresponding to the image. In the first set of images, one image has a corresponding quality score.
When the quality score is calculated by integrating the aesthetic score and the face analysis score, the aesthetic score and the face analysis score may have different or the same weight coefficients, and how to set the weight coefficients specifically is not limited in the embodiment of the present application, for example, the weight coefficients may be preset, or the correspondence may be adjusted according to different application scenarios.
After determining the quality score, in this embodiment, one possible implementation of S104 may be as shown in S303:
S303: and determining the ordering positions of the images in the first image set in the image search results by combining the quality scores corresponding to the images in the first image set.
In the embodiment of the application, for the images in the first image set, the ranking positions of the images in the image search result can be determined only according to the quality scores, or the ranking positions of the images with lower quality scores can be adjusted according to the quality scores on the basis of determining the ranking positions according to the relevance between the images in the image search result and the keywords, for example, the ranking positions of the images with higher quality scores are advanced, and the ranking positions of the images with lower quality scores are backward.
The sorting positions of the images in the first image set in the image search results are determined by combining the quality scores in any mode, so that the sorting positions of at least partial images with higher quality scores can be advanced, and the front display positions enable a user to view the images faster, thereby improving the display effect of the image search results.
Since the image searching behaviors of different users are different, the images selected by different users by clicking are also different for the same keyword. Aiming at the phenomenon, the embodiment of the application provides a personalized ordering mode aiming at the image searching behavior of the user, and the image searching result corresponding to the user can be adjusted in a targeted manner by analyzing the image clicking characteristics of the user.
In a possible implementation manner, based on any one of the foregoing embodiments, if the keyword is input by the target user, the method further includes:
S401: and determining the image clicking characteristics of the target user according to the image searching behaviors of the target user.
The image clicking feature of the target user may represent the image clicking behavior feature of the target user when performing image searching, for example, represent what type of image the user is more interested in, and is more prone to click selection.
Optionally, the image searching behavior data of the target user can be modeled and analyzed through a deep learning method, so that the tendency and the internal rule of clicking of the image of the target user are mainly learned. For example, by analysis, it is found that the image click feature of the target user on the image includes relevance and freshness, i.e., the target user is more inclined to select an image that is highly relevant and fresher.
The types herein and the aforementioned image categories may be divided in the same manner or may be divided in different manners, and the present application is not limited thereto.
S402: and after determining the sorting result of the images in the image search result, adjusting the sorting result according to the image clicking feature so as to advance the sorting position of the images conforming to the image clicking feature in the image search result.
S403: and displaying the image search result according to the adjusted sorting result.
It should be noted that the "determining the ranking result of the images in the image search result" mentioned in S402 means that the ranking position of the images in the image set is determined in combination with the aesthetic score.
Determining a ranking position of the images in the first set of images, for example in combination with an aesthetic score; or alternatively
For example, determining a ranking position of the images in the first set of images in combination with the aesthetic score and determining a ranking position of the images in the second set of images in combination with the aesthetic score; or alternatively
Determining the ranking position of the images in the first image set in the image search result by combining the quality scores corresponding to the images in the first image set.
After determining the ordering result of the images in the image search result, the reason that the ordering result is adjusted by using the determined image clicking feature is that, because the image clicking feature can directly reflect the image search requirement characteristics of the user, if the ordering position of the images is adjusted by the image clicking feature too early, the images which are displayed to the user and mostly meet the image search requirement characteristics of the user can be caused, so that the images in the image search result are too single, the user cannot easily touch other types of images, and the user is difficult to provide various search experiences.
After the sorting results of the images in the image search results are determined, the determined image clicking characteristics are used for adjusting the sorting results, so that the image display positions meeting the image search requirement characteristics of the user in the image search results meeting the diversity are relatively forward, other types of images with high aesthetic scores or quality scores can be displayed to the user, the images meeting the image search requirement characteristics of the user are preferentially displayed on the premise of keeping the diversity of the image search results, and the image search experience of the user is further improved.
Based on the image search result sorting method provided in the corresponding embodiment of fig. 1, an embodiment of the present application provides a sorting device for image search results, referring to fig. 2, where the device includes an obtaining unit 201, an identifying unit 202, a determining unit 203, and a sorting unit 204:
the acquiring unit 201 is configured to acquire an image search result corresponding to a keyword, where the image search result includes a plurality of images;
The identifying unit 202 is configured to identify a first image set from the image search results according to an image classification model; the images in the first image set belong to a first image category;
The determining unit 203 is configured to determine, according to the aesthetic evaluation model corresponding to the first image category, aesthetic scores corresponding to the images in the first image set;
The ranking unit 204 is configured to determine, when ranking the images in the image search result, a ranking position of the images in the first image set in the image search result in combination with aesthetic scores corresponding to the images in the first image set.
Optionally, the identifying unit is further configured to identify the first image set and the second image set from the image search result according to the image classification model; the images in the second image set belong to a second image category different from the first image category;
the determining unit is further configured to determine aesthetic scores corresponding to the images in the second image set according to the aesthetic evaluation models corresponding to the second image categories;
the ranking unit is further configured to determine, when ranking the images in the image search result, a ranking position of the images in the second image set in the image search result in combination with aesthetic scores corresponding to the images in the second image set.
Optionally, the first image category has a correlation with a type to which the keyword belongs.
Optionally, if the first image category is a person category, the apparatus further includes a face analysis score determining unit and a quality score determining unit:
The face analysis score determining unit is used for determining face analysis scores corresponding to the images in the first image set according to a face analysis model;
The quality score determining unit is used for determining the quality scores corresponding to the images in the first image set according to the face analysis scores corresponding to the images in the first image set and the aesthetic scores corresponding to the images in the first image set;
the ranking unit is further configured to determine a ranking position of the images in the first image set in the image search result in combination with the quality scores corresponding to the images in the first image set.
Optionally, the image search result is a plurality of images which are obtained according to the keyword search and have correlation with the keyword which meet a preset condition.
Optionally, if the keyword is input by the target user, the device further includes an image click feature determining unit, an adjusting unit, and a display unit:
the image click feature determining unit is used for determining the image click feature of the target user according to the image searching behavior of the target user;
the adjusting unit is used for adjusting the sorting result according to the image clicking characteristics after determining the sorting result of the images in the image searching result so as to advance the sorting position of the images conforming to the image clicking characteristics in the image searching result;
The display unit is used for displaying the image search results according to the adjusted sorting results.
When an image search result corresponding to a keyword and comprising a plurality of images is obtained, a first image set which belongs to a first image category is identified from the images of the image search result according to an image classification model, and aesthetic scores corresponding to the images in the first image set are determined through an aesthetic evaluation model corresponding to the first image category. And when the images in the image search results are ranked, determining the ranking positions of the images in the first image set in the image search results by combining the aesthetic scores corresponding to the images in the first image set. For images belonging to one image category, the aesthetic score of the category can show that the image brings aesthetic feeling to a user under the category, and the probability that the user selects to view the images with better aesthetic feeling is relatively high, so that the sorting position of the images with higher aesthetic score is advanced, the sorting position of the images with lower aesthetic score is advanced, the images with higher aesthetic score can be preferentially displayed to the user, and the probability that the images meet the image searching requirement of the user is high, so that the image searching experience of the user is improved.
Based on the foregoing provided quality determining method and apparatus for a flow channel, this embodiment provides a quality determining device for a flow channel, where the quality determining device for a flow channel may be a terminal device, and fig. 3 is a block diagram of a terminal device 300 according to an exemplary embodiment. For example, the terminal device 300 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, or the like.
Referring to fig. 3, a terminal device 300 may include one or more of the following components: a processing component 302, a memory 304, a power supply component 306, a multimedia component 308, an audio component 310, an input/output (I/O) interface 312, a sensor component 314, and a communication component 316.
The processing component 302 generally controls overall operation of the terminal device 300, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 302 may include one or more processors 320 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 302 can include one or more modules that facilitate interactions between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate interaction between the multimedia component 308 and the processing component 302.
The memory 304 is configured to store various types of data to support operations at the terminal device 300. Examples of such data include instructions for any application or method operating on the device 300, contact data, phonebook data, messages, pictures, videos, and the like. The memory 304 may be implemented by any type or combination of volatile or nonvolatile memory devices 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, magnetic or optical disk.
The power supply component 306 provides power to the various components of the terminal device 300. The power supply components 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 300.
The multimedia component 308 comprises a screen between the terminal device 300 and the user providing an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 308 includes a front-facing camera and/or a rear-facing camera. The front camera and/or the rear camera may receive external multimedia data when the terminal device 300 is in an operation mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 310 is configured to output and/or input audio signals. For example, the audio component 310 includes a Microphone (MIC) configured to receive external audio signals when the device 300 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 304 or transmitted via the communication component 316. In some embodiments, audio component 310 further comprises a speaker for outputting audio signals.
The I/O interface 312 provides an interface between the processing component 302 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor assembly 314 includes one or more sensors for providing status assessment of various aspects of the terminal device 300. For example, the sensor assembly 314 may detect the on/off state of the terminal device 300, the relative positioning of the components, such as the display and keypad of the terminal device 300, the sensor assembly 314 may also detect the change in position of the terminal device 300 or a component of the terminal device 300, the presence or absence of user contact with the terminal device 300, the orientation or acceleration/deceleration of the terminal device 300, and the change in temperature of the terminal device 300. The sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 314 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 316 is configured to facilitate communication between the terminal device 300 and other devices, either wired or wireless. The terminal device 300 may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the terminal device 300 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), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 304, including instructions executable by processor 320 of terminal device 300 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
Fig. 4 is a schematic structural diagram of a server according to an embodiment of the present invention. The server 400 may vary considerably in configuration or performance and may include one or more central processing units (central processing units, CPUs) 422 (e.g., one or more processors) and memory 432, one or more storage mediums 430 (e.g., one or more mass storage devices) that store applications 442 or data 444. Wherein memory 432 and storage medium 430 may be transitory or persistent storage. The program stored on the storage medium 430 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 422 may be configured to communicate with the storage medium 430 and execute a series of instruction operations in the storage medium 430 on the server 400.
The server 400 may also include one or more power supplies 426, one or more wired or wireless network interfaces 450, one or more input/output interfaces 458, one or more keyboards 456, and/or one or more operating systems 441, such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like.
A non-transitory computer readable storage medium, which when executed by a processor of a mobile terminal, causes the mobile terminal to perform a method of quality determination of a traffic channel, the method comprising:
acquiring an image search result corresponding to a keyword, wherein the image search result comprises a plurality of images;
Identifying a first set of images from the image search results according to an image classification model; the images in the first image set belong to a first image category;
Determining aesthetic scores corresponding to the images in the first image set through aesthetic evaluation models corresponding to the first image types;
and when the images in the image search results are ranked, determining the ranking positions of the images in the first image set in the image search results by combining the aesthetic scores corresponding to the images in the first image set.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, where the above program may be stored in a computer readable storage medium, and when the program is executed, the program performs steps including the above method embodiments; and the aforementioned storage medium may be at least one of the following media: read-only memory (ROM), RAM, magnetic disk or optical disk, etc., which can store program codes.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment is mainly described in a different point from other embodiments. In particular, for the apparatus and system embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, with reference to the description of the method embodiments in part. The apparatus and system embodiments described above are merely illustrative, in which elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The foregoing is only one specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the technical scope of the present application should be included in the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims (8)
1. A method of ranking image search results, the method comprising:
acquiring an image search result corresponding to a keyword, wherein the image search result comprises a plurality of images which are obtained according to the keyword search and have correlation with the keyword meeting a preset condition;
Identifying a first set of images from the image search results according to an image classification model; the images in the first image set belong to a first image category;
Determining aesthetic scores corresponding to the images in the first image set through aesthetic evaluation models corresponding to the first image types;
When images in the image search results are ranked, determining initial ranking positions of the images in the first image set in the image search results according to the correlation between the images in the image search results and the keywords, adjusting the initial ranking positions by combining aesthetic scores corresponding to the images in the first image set, and determining final ranking positions of the images in the first image set in the image search results;
If the keyword is input by a target user, determining an image click feature of the target user according to the image searching behavior of the target user; the image clicking feature is used for representing the image clicking behavior characteristics of the target user when image searching is carried out, and comprises correlation and freshness;
After determining the sorting result of the images in the image search result, adjusting the sorting result according to the image clicking feature so as to advance the sorting position of the images conforming to the image clicking feature in the image search result;
displaying the image search result according to the adjusted sorting result;
Wherein identifying a first set of images from the image search results according to an image classification model comprises:
identifying the first and second image sets from the image search results according to the image classification model; the images in the second image set belong to a second image category different from the first image category;
And if the first image which is simultaneously in the first image set and the second image set exists and the image category of the first image has correlation with the type of the keyword, adopting the aesthetic score of the first image category as the aesthetic score of the first image.
2. The method according to claim 1, wherein the method further comprises:
determining aesthetic scores corresponding to the images in the second image set through aesthetic evaluation models corresponding to the second image categories;
And when the images in the image search results are ranked, determining the ranking positions of the images in the second image set in the image search results by combining the aesthetic scores corresponding to the images in the second image set.
3. The method of claim 1, wherein if the first image category is a person category, the method further comprises:
determining face analysis scores corresponding to the images in the first image set according to the face analysis model;
Determining the quality scores corresponding to the images in the first image set according to the face analysis scores corresponding to the images in the first image set and the aesthetic scores corresponding to the images in the first image set;
The determining, in combination with the aesthetic scores corresponding to the images in the first image set, the ranking positions of the images in the first image set in the image search results includes:
And determining the ordering positions of the images in the first image set in the image search results by combining the quality scores corresponding to the images in the first image set.
4. An image search result sorting device, characterized in that the device comprises an acquisition unit, an identification unit, a determination unit and a sorting unit:
The acquisition unit is used for acquiring an image search result corresponding to the keyword, wherein the image search result comprises a plurality of images which are obtained according to the keyword search and have the correlation with the keyword meeting the preset condition;
the identification unit is used for identifying a first image set from the image search results according to an image classification model; the images in the first image set belong to a first image category;
The determining unit is used for determining aesthetic scores corresponding to the images in the first image set through the aesthetic evaluation models corresponding to the first image categories;
The sorting unit is used for determining an initial sorting position of the images in the first image set in the image search result according to the correlation between the images in the image search result and the keywords when the images in the image search result are sorted, adjusting the initial sorting position by combining the aesthetic scores corresponding to the images in the first image set, and determining a final sorting position of the images in the first image set in the image search result;
if the keyword is input by the target user, the device further comprises an image click feature determining unit, an adjusting unit and a display unit:
The image click feature determining unit is used for determining the image click feature of the target user according to the image searching behavior of the target user; the image clicking feature is used for representing the image clicking behavior characteristics of the target user when image searching is carried out, and comprises correlation and freshness;
the adjusting unit is used for adjusting the sorting result according to the image clicking characteristics after determining the sorting result of the images in the image searching result so as to advance the sorting position of the images conforming to the image clicking characteristics in the image searching result;
The display unit is used for displaying the image search results according to the adjusted sorting results;
The identification unit is specifically configured to:
identifying the first and second image sets from the image search results according to the image classification model; the images in the second image set belong to a second image category different from the first image category;
And if the first image which is simultaneously in the first image set and the second image set exists and the image category of the first image has correlation with the type of the keyword, adopting the aesthetic score of the first image category as the aesthetic score of the first image.
5. The apparatus of claim 4, wherein the device comprises a plurality of sensors,
The determining unit is further configured to determine aesthetic scores corresponding to the images in the second image set according to the aesthetic evaluation models corresponding to the second image categories;
the ranking unit is further configured to determine, when ranking the images in the image search result, a ranking position of the images in the second image set in the image search result in combination with aesthetic scores corresponding to the images in the second image set.
6. The apparatus according to claim 4, wherein if the first image category is a person, the apparatus further comprises a face analysis score determination unit and a quality score determination unit:
The face analysis score determining unit is used for determining face analysis scores corresponding to the images in the first image set according to a face analysis model;
The quality score determining unit is used for determining the quality scores corresponding to the images in the first image set according to the face analysis scores corresponding to the images in the first image set and the aesthetic scores corresponding to the images in the first image set;
the ranking unit is further configured to determine a ranking position of the images in the first image set in the image search result in combination with the quality scores corresponding to the images in the first image set.
7. An apparatus for ranking image search results, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:
acquiring an image search result corresponding to a keyword, wherein the image search result comprises a plurality of images which are obtained according to the keyword search and have correlation with the keyword meeting a preset condition;
Identifying a first set of images from the image search results according to an image classification model; the images in the first image set belong to a first image category;
Determining aesthetic scores corresponding to the images in the first image set through aesthetic evaluation models corresponding to the first image types;
When images in the image search results are ranked, determining initial ranking positions of the images in the first image set in the image search results according to the correlation between the images in the image search results and the keywords, adjusting the initial ranking positions by combining aesthetic scores corresponding to the images in the first image set, and determining final ranking positions of the images in the first image set in the image search results;
If the keyword is input by a target user, determining an image click feature of the target user according to the image searching behavior of the target user; the image clicking feature is used for representing the image clicking behavior characteristics of the target user when image searching is carried out, and comprises correlation and freshness;
After determining the sorting result of the images in the image search result, adjusting the sorting result according to the image clicking feature so as to advance the sorting position of the images conforming to the image clicking feature in the image search result;
displaying the image search result according to the adjusted sorting result;
Wherein identifying a first set of images from the image search results according to an image classification model comprises:
identifying the first and second image sets from the image search results according to the image classification model; the images in the second image set belong to a second image category different from the first image category;
And if the first image which is simultaneously in the first image set and the second image set exists and the image category of the first image has correlation with the type of the keyword, adopting the aesthetic score of the first image category as the aesthetic score of the first image.
8. A machine readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform a method of ranking image search results as recited in one or more of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811612143.2A CN111382295B (en) | 2018-12-27 | 2018-12-27 | Image search result ordering method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811612143.2A CN111382295B (en) | 2018-12-27 | 2018-12-27 | Image search result ordering method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111382295A CN111382295A (en) | 2020-07-07 |
| CN111382295B true CN111382295B (en) | 2024-04-30 |
Family
ID=71219559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811612143.2A Active CN111382295B (en) | 2018-12-27 | 2018-12-27 | Image search result ordering method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111382295B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114328359A (en) * | 2020-09-27 | 2022-04-12 | 广州市久邦数码科技有限公司 | Playing method and system of audio electronic book |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332034A (en) * | 2011-10-21 | 2012-01-25 | 中国科学院计算技术研究所 | Portrait picture retrieval method and device |
| CN102799635A (en) * | 2012-06-27 | 2012-11-28 | 天津大学 | Image set ordering method driven by user |
| CN103699612A (en) * | 2013-12-13 | 2014-04-02 | 中国科学院深圳先进技术研究院 | Image retrieval ranking method and device |
| CN103988202A (en) * | 2011-11-25 | 2014-08-13 | 微软公司 | Image attractiveness based indexing and searching |
| CN107153838A (en) * | 2017-04-19 | 2017-09-12 | 中国电子科技集团公司电子科学研究院 | A kind of photo automatic grading method and device |
| CN107729384A (en) * | 2017-09-18 | 2018-02-23 | 维沃移动通信有限公司 | Image ranking method and mobile terminal |
| EP3321855A1 (en) * | 2016-11-15 | 2018-05-16 | Houzz, Inc. | Aesthetic search engine |
| CN108288027A (en) * | 2017-12-28 | 2018-07-17 | 新智数字科技有限公司 | A kind of detection method of picture quality, device and equipment |
| WO2018192245A1 (en) * | 2017-04-19 | 2018-10-25 | 中国电子科技集团公司电子科学研究院 | Automatic scoring method for photo based on aesthetic assessment |
| CN108897685A (en) * | 2018-06-28 | 2018-11-27 | 百度在线网络技术（北京）有限公司 | Method for evaluating quality, device, server and the medium of search result |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9286325B2 (en) * | 2013-05-21 | 2016-03-15 | Xerox Corporation | Methods and systems for ranking images using semantic and aesthetic models |
| US9659384B2 (en) * | 2014-10-03 | 2017-05-23 | EyeEm Mobile GmbH. | Systems, methods, and computer program products for searching and sorting images by aesthetic quality |
-
2018
- 2018-12-27 CN CN201811612143.2A patent/CN111382295B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332034A (en) * | 2011-10-21 | 2012-01-25 | 中国科学院计算技术研究所 | Portrait picture retrieval method and device |
| CN103988202A (en) * | 2011-11-25 | 2014-08-13 | 微软公司 | Image attractiveness based indexing and searching |
| CN102799635A (en) * | 2012-06-27 | 2012-11-28 | 天津大学 | Image set ordering method driven by user |
| CN103699612A (en) * | 2013-12-13 | 2014-04-02 | 中国科学院深圳先进技术研究院 | Image retrieval ranking method and device |
| EP3321855A1 (en) * | 2016-11-15 | 2018-05-16 | Houzz, Inc. | Aesthetic search engine |
| CN107153838A (en) * | 2017-04-19 | 2017-09-12 | 中国电子科技集团公司电子科学研究院 | A kind of photo automatic grading method and device |
| WO2018192245A1 (en) * | 2017-04-19 | 2018-10-25 | 中国电子科技集团公司电子科学研究院 | Automatic scoring method for photo based on aesthetic assessment |
| CN107729384A (en) * | 2017-09-18 | 2018-02-23 | 维沃移动通信有限公司 | Image ranking method and mobile terminal |
| CN108288027A (en) * | 2017-12-28 | 2018-07-17 | 新智数字科技有限公司 | A kind of detection method of picture quality, device and equipment |
| CN108897685A (en) * | 2018-06-28 | 2018-11-27 | 百度在线网络技术（北京）有限公司 | Method for evaluating quality, device, server and the medium of search result |
Non-Patent Citations (5)
| Title |
|---|
| Chaoran Cui ; Huidi Fang ; Xiang Deng ; Xiushan Nie ; Hongshuai Dai ; Yilong Yin.Distribution-oriented Aesthetics Assessment for Image Search.SIGIR'17: PROCEEDINGS OF THE 40TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL.2017,第[1013-1016]页. * |
| Mithun Biswas ; Rafiqul Islam ; Gautam Kumar Shom ; Nabeel Mohammed ; Sifat Momen ; Nafees Mansoor ; Anowarul Abedin.Application of image retrieval for aesthetic evaluation and improvement suggestion of isolated Bangla handwritten characters.2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).2017,第[149-154]页. * |
| 可计算图像美学研究进展;王伟凝;蚁静缄;贺前华;中国图象图形学报;20120816;第17卷(第08期);第[893-901]页 * |
| 图像重排序技术的研究进展;赵小艳;刘宏哲;袁家政;杨少鹏;;计算机科学;20180515(第05期);第[15-23]页 * |
| 基于语义感知的图像美学质量评估方法;杨文雅;宋广乐;崔超然;尹义龙;;计算机应用;第38卷(第11期);第[3216-3220]页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111382295A (en) | 2020-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10141025B2 (en) | Method, device and computer-readable medium for adjusting video playing progress | |
| CN111859020B (en) | Recommendation method, recommendation device, electronic equipment and computer readable storage medium | |
| CN106095465B (en) | Method and device for setting identity image | |
| CN107315487B (en) | Input processing method and device and electronic equipment | |
| CN107784045B (en) | Quick reply method and device for quick reply | |
| CN109783656B (en) | Recommendation method and system of audio and video data, server and storage medium | |
| CN107291772B (en) | Search access method and device and electronic equipment | |
| CN109918565B (en) | Processing method and device for search data and electronic equipment | |
| CN106815291B (en) | Search result item display method and device and search result item display device | |
| CN110764627B (en) | Input method and device and electronic equipment | |
| CN111382339A (en) | Search processing method and device and search processing device | |
| US11546663B2 (en) | Video recommendation method and apparatus | |
| CN110110207B (en) | Information recommendation method and device and electronic equipment | |
| CN112784142A (en) | Information recommendation method and device | |
| CN107491453B (en) | Method and device for identifying cheating web pages | |
| CN112307281A (en) | Entity recommendation method and device | |
| CN112015277B (en) | Information display method and device and electronic equipment | |
| CN111382295B (en) | Image search result ordering method and device | |
| CN111177521A (en) | Method and device for determining query term classification model | |
| CN110046308B (en) | Sequencing strategy determination method and device and electronic equipment | |
| CN111859097B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN112115341A (en) | Content display method, device, terminal, server, system and storage medium | |
| CN107908729B (en) | Interface display method and device | |
| CN107301188B (en) | Method for acquiring user interest and electronic equipment | |
| CN113965792A (en) | Video display method and device, electronic equipment and readable storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |