CN113705496A - Poster selection method, device, equipment and storage medium - Google Patents
Poster selection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113705496A CN113705496A CN202111023826.6A CN202111023826A CN113705496A CN 113705496 A CN113705496 A CN 113705496A CN 202111023826 A CN202111023826 A CN 202111023826A CN 113705496 A CN113705496 A CN 113705496A
- Authority
- CN
- China
- Prior art keywords
- poster
- processing result
- determining
- scoring
- scored
- 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
- 238000010187 selection method Methods 0.000 title claims abstract description 28
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 11
- 239000003086 colorant Substances 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 24
- 230000008569 process Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image recognition and discloses a poster selection method, a poster selection device, poster selection equipment and a storage medium, wherein the method comprises the following steps: obtaining a poster to be evaluated; detecting index information of the poster to be scored, and determining a scoring processing result of the index information; determining a grading result of the poster to be graded according to a basic score and the grading processing result; and performing descending processing on the scoring result, and determining a target poster in the posters to be scored. The method comprises the steps of identifying input posters to be scored, detecting various indexes, determining grading processing results of the indexes according to grading rules of the indexes, adding the grading processing results of the indexes on the basis of basic scores, and obtaining final scores, so that the aim of quickly selecting better posters is fulfilled.
Description
Technical Field
The present invention relates to the field of image recognition technologies, and in particular, to a poster selection method, device, apparatus, and storage medium.
Background
It is often seen in daily life that when some wonderful pictures in a video are displayed as posters, generally, the video is subjected to frame extraction processing, a plurality of pictures of the video pictures are extracted, and then the pictures are screened by eyes through a traditional method, so that the work is heavy easily, and a better poster cannot be selected quickly.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a poster selection method, a poster selection device, poster selection equipment and a storage medium, and aims to solve the technical problem of how to quickly select a better poster in the prior art.
To achieve the above object, the present invention provides a poster selection method, comprising the steps of:
obtaining a poster to be evaluated;
detecting index information of the poster to be scored, and determining a scoring processing result of the index information;
determining a grading result of the poster to be graded according to a basic score and the grading processing result;
and carrying out preset sequencing processing on the grading result to obtain a sequencing result, and determining a target poster in the posters to be graded according to the sequencing result.
Optionally, the index information includes face information;
the detecting the index information of the poster to be scored and determining the scoring processing result of the index information comprise:
detecting whether the poster to be evaluated has face information or not;
if the poster to be evaluated has the face information, extracting the features of the face information of the poster to be evaluated, and determining the coordinate position of the face and the clear state of the face;
and determining a grading processing result of the index information according to the face coordinate position and the face clear state.
Optionally, determining a scoring processing result of the index information according to the face coordinate position and the face clarity state includes:
if the area of the region covered by the face coordinate position is smaller than a preset area, determining a first grading processing result;
if the face clear state is in a fuzzy state, determining a second grading processing result;
if the face coordinate position appears in the first preset area at the bottom of the poster to be scored, determining a third scoring processing result;
if the poster to be scored has a face coordinate position in a second preset area of the left edge and the right edge, determining a fourth scoring processing result;
and determining a grading processing result of the face information according to the first grading processing result, the second grading processing result, the third grading processing result and the fourth grading processing result.
Optionally, the index information includes a picture color;
the detecting the index information of the poster to be scored and determining the scoring processing result of the index information comprise:
detecting the picture color of the poster to be evaluated, and determining the hue, saturation and brightness of the pixel point of the poster to be evaluated;
and if the hue difference value of the pixel point is less than or equal to a first preset value, the saturation difference value is less than or equal to a second preset value and the brightness difference value is less than or equal to a third preset value, determining the grading processing result of the picture color.
Optionally, the index information includes a black border, including:
the detecting the index information of the poster to be scored and determining the scoring processing result of the index information comprise:
detecting whether the poster to be evaluated has a black edge or not;
and if the poster to be scored has a black edge, determining a scoring processing result of the black edge.
Optionally, the index information includes a font;
the detecting the index information of the poster to be scored and determining the scoring processing result of the index information comprise:
detecting whether the poster to be evaluated has a font or not;
and if the poster to be scored has a font, determining a scoring processing result of the font.
Optionally, the scoring processing result includes a scoring processing result of the face information, a scoring processing result of the picture color, a scoring processing result of the black edge, and a scoring processing result of the font;
the step of determining the scoring result of the poster to be scored according to the basic score and the scoring processing result comprises the following steps of:
and obtaining the scoring result of the poster to be scored according to the basic score, the scoring processing result of the face information, the scoring processing result of the picture color, the scoring processing result of the black edge and the scoring processing result of the font.
Furthermore, to achieve the above object, the present invention also proposes a poster selection device including:
the acquisition module is used for acquiring the poster to be evaluated;
the detection module is used for detecting the index information of the poster to be scored and determining a scoring processing result of the index information;
the scoring module is used for determining a scoring result of the poster to be scored according to a basic score and the scoring processing result;
and the determining module is used for presetting a sorting treatment on the grading result to obtain a sorting result and determining a target poster in the posters to be graded according to the sorting result.
Further, to achieve the above object, the present invention also proposes a poster selection apparatus comprising: a memory, a processor and a poster selection program stored on the memory and executable on the processor, the poster selection program being configured to implement the steps of the poster selection method as described above.
Furthermore, to achieve the above object, the present invention also proposes a storage medium having stored thereon a poster selection program which, when executed by a processor, implements the steps of the poster selection method as described above.
The method comprises the steps of obtaining a poster to be evaluated; detecting index information of the poster to be scored, and determining a scoring processing result of the index information; determining a grading result of the poster to be graded according to a basic score and the grading processing result; and performing descending processing on the scoring result, and determining a target poster in the posters to be scored. The method comprises the steps of identifying input posters to be scored, detecting various indexes, determining grading processing results of the indexes according to grading rules of the indexes, adding the grading processing results of the indexes on the basis of basic scores, and obtaining final scores, so that the aim of quickly selecting better posters is fulfilled.
Drawings
FIG. 1 is a schematic diagram of a poster selection apparatus for a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a poster selection method of the present invention;
FIG. 3 is a schematic flow chart of a second embodiment of a poster selection method of the present invention;
FIG. 4 is a flow chart of scoring in an embodiment of a poster selection method of the present invention;
fig. 5 is a block diagram of the structure of a first embodiment of the poster selection apparatus of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a poster selection device structure of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the poster selection apparatus may comprise: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the poster selection apparatus and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a poster selection program.
In the poster selection apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the poster selection device of the present invention may be provided in the poster selection device, which calls the poster selection program stored in the memory 1005 through the processor 1001 and executes the poster selection method provided by the embodiment of the present invention.
An embodiment of the present invention provides a poster selection method, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a poster selection method according to the present invention.
In this embodiment, the poster selection method includes the steps of:
step S10: and obtaining the poster to be evaluated.
It should be noted that the execution body of the present embodiment may be a poster selection device, and may also be other devices that can implement the same or similar functions.
It should be understood that the poster to be scored, which includes a plurality of image frames to be processed, is obtained by determining the plurality of image frames to be processed through frame extraction processing of the video to be processed.
Step S20: and detecting the index information of the poster to be scored, and determining a scoring processing result of the index information.
It can be understood that index information can be face information, picture color, black edge and font, therefore, through discerning the poster to be scored, obtain the face information of people in the poster to be scored, the picture color of the poster, whether take black edge and whether take index information such as characters, then formulate the rule of scoring to each item of index information, to not meeting the index condition, carry out the score branch processing, thereby obtain face information score processing result, picture color score processing result, black edge score processing result and font score processing result.
Step S30: and determining the scoring result of the poster to be scored according to the basic score and the scoring processing result.
It should be understood that the basic score may be set by a person skilled in the art, and the basic score may be 300 in a specific implementation process, which is not limited in this embodiment, and the final poster scoring result to be scored is obtained by giving one basic score 300 and performing summation processing on the face information scoring processing result, the image color scoring processing result, the black edge scoring processing result, and the font scoring processing result according to each scoring processing result.
Step S40: and carrying out preset sequencing processing on the grading result to obtain a sequencing result, and determining a target poster in the posters to be graded according to the sequencing result.
It should be noted that if the scoring result of the poster to be scored is higher, it indicates that the probability that the poster to be scored is determined as the target poster is higher, and if the scoring result of the poster to be scored is lower, it indicates that the probability that the poster to be scored is determined as the target poster is lower, so that the scoring results are sorted in descending order from big to small, thereby obtaining a sorting result, and the poster to be scored with the largest scoring result is determined as the target poster of the video to be processed.
The embodiment obtains the poster to be evaluated; detecting index information of the poster to be scored, and determining a scoring processing result of the index information; determining a grading result of the poster to be graded according to a basic score and the grading processing result; and performing descending processing on the scoring result, and determining a target poster in the posters to be scored. The method comprises the steps of identifying input posters to be scored, detecting various indexes, determining grading processing results of the indexes according to grading rules of the indexes, adding the grading processing results of the indexes on the basis of basic scores, and obtaining final scores, so that the aim of quickly selecting better posters is fulfilled.
Referring to fig. 3, fig. 3 is a schematic flow chart of a second embodiment of a poster selection method of the present invention.
Based on the first embodiment described above, the poster selection method of the present embodiment includes, at the step S20:
step S201: and detecting whether the poster to be evaluated has face information.
It should be understood that the index information includes face information, and therefore, whether the poster to be scored has the face information may be detected through a face detection model, and the face detection model may be a pyramid _ lite _ mobile in a specific implementation process, which is not limited in this embodiment.
It should be noted that, if the poster to be scored does not have face information, that is, a face is not detected, the scoring processing result of the index information is the score reduction processing of the preset score, where the score reduction processing of the preset score may be 120 scores, which is not limited in this embodiment, and therefore, when a face is not detected, the scoring processing result of the index information is 120 scores.
Step S202: and if the poster to be evaluated has the face information, extracting the features of the face information of the poster to be evaluated, and determining the coordinate position of the face and the clear state of the face.
It can be understood that if the poster to be scored has face information, that is, a face is detected, the face of the poster to be scored is subjected to feature extraction through the face detection model, so that a face coordinate position and a face clarity state are determined, wherein the face coordinate position can be coordinates of the face relative to the upper left corner of an original picture and face width and height information.
Step S203: and determining a grading processing result of the index information according to the face coordinate position and the face clear state.
It can be understood that comprehensive analysis can be performed according to the area occupied by the face coordinate position, the definition of the face and the like, so that the grading processing result of the index information is determined.
Further, the step S203 includes:
and if the area of the region covered by the face coordinate position is smaller than a preset area, determining a first grading processing result.
It can be understood that the area of the area covered by the face coordinate position may be a face area of the face, and the preset area may be 10% of the entire area of the poster to be scored, which is not limited in this embodiment, therefore, if the area of the face is less than 10% of the entire area of the poster to be scored, the first scoring processing result is minus 30%, and further, if the area of the face is greater than or equal to 10% of the entire area of the poster to be scored, the first scoring processing result is minus 0%.
And if the human face clear state is in a fuzzy state, determining a second grading processing result.
It should be noted that, by analyzing the current face clarity state, it is determined whether the face clarity state is in the fuzzy state, that is, if the face is in the fuzzy state, the second scoring processing result is minus 30 points, and further, if the face is in the clarity state, the second scoring processing result is minus 0 point.
And if the face coordinate position appears in the first preset area at the bottom of the poster to be scored, determining a third scoring processing result.
It should be understood that the first preset area may be a bottom quarter of the poster to be scored, and this embodiment does not limit this, so that if a coordinate position of a face head appears in the bottom quarter of the poster to be scored, the third scoring processing result is minus 40 points, and further, if a coordinate position of a face head does not appear in the bottom quarter of the poster to be scored, the third scoring processing result is minus 0 points.
And if the poster to be scored has a face coordinate position in a second preset area of the left edge and the right edge, determining a fourth scoring processing result.
It can be understood that the second preset area may be a tenth area of the left and right edges of the poster to be scored, which is not limited in this embodiment, therefore, if the coordinate position of the head of the face appears in the tenth area of the left and right edges of the poster to be scored, the fourth scoring processing result is to be decremented by 20, and further, if the coordinate position of the head of the face does not appear in the tenth area of the left and right edges of the poster to be scored, the fourth scoring processing result is to be decremented by 0.
And determining a grading processing result of the face information according to the first grading processing result, the second grading processing result, the third grading processing result and the fourth grading processing result.
It should be understood that, if the above description is satisfied, the scoring processing result of the face information is obtained by performing summation on the first scoring processing result, the second scoring processing result, the third scoring processing result, and the fourth scoring processing result to obtain a final scoring processing result of the face information. For example, if the face information of the current poster to be scored meets the condition that the area of the face region of the face is less than 10% of the whole area of the poster to be scored, the face is in a fuzzy state, the head of the face appears in the quarter region at the bottom of the poster to be scored and the head of the face appears in the tenth region at the left edge and the right edge of the poster to be scored, the scoring processing result of the face information is minus 120 points, and correspondingly, if the area of the face region of the poster to meet the condition that the face is less than 10% of the whole area of the poster to be scored, the head of the face appears in the quarter region at the bottom of the poster to be scored and the head of the face appears in the tenth region at the left edge and the right edge of the poster to be scored, the scoring processing result of the face information is minus 90 points.
Further, the index information includes a picture color, and the step S20 further includes:
and detecting the picture color of the poster to be evaluated, and determining the hue, saturation and brightness of the pixel point of the poster to be evaluated.
It can be understood that the tone, saturation and brightness of the poster pixel point to be evaluated are determined by detecting the picture color of the poster to be evaluated and converting the current color mode of the picture color of the poster to be evaluated into the HSB mode, wherein the conversion relationship can be set by a person skilled in the art, and the embodiment does not limit the conversion relationship.
And if the hue difference value of the pixel point is less than or equal to a first preset value, the saturation difference value is less than or equal to a second preset value and the brightness difference value is less than or equal to a third preset value, determining the grading processing result of the picture color.
It should be understood that, according to the determined hue, saturation and brightness of the poster pixel point to be evaluated, the hue difference value, saturation difference value and brightness difference value between adjacent pixels can be calculated, and the hue maximum difference value, saturation maximum difference value and brightness maximum difference value are further screened out, so as to judge whether the hue maximum difference value is less than or equal to a first preset value, whether the saturation maximum difference value is less than or equal to a second preset value and whether the brightness maximum difference value is less than or equal to a third preset value.
It can be understood that the first preset value, the second preset value, and the third preset value can be set by those skilled in the art, which is not limited in this embodiment, and in the specific implementation process, the first preset value, the second preset value, and the third preset value can be 10, so that by determining that if the hue maximum difference value is less than or equal to 10, the saturation maximum difference value is less than or equal to 10, and the brightness maximum difference value is less than or equal to 10, the scoring processing result of the picture color is minus 30 minutes, and further, if the hue maximum difference value is greater than 10, the saturation maximum difference value is greater than 10, and/or the brightness maximum difference value is greater than 10, the scoring processing result of the picture color is minus 0 minute.
Further, the index information includes a black border, and the step S20 further includes:
and detecting whether the poster to be evaluated has a black edge.
It is understood that the black edge refers to a black part of the image frame of the poster to be scored except the picture content, and can be generally positioned above the image content, below the image content, on the left side of the image content and/or on the right side of the image content.
It should be understood that whether the poster to be evaluated has the black edge or not is mainly determined by converting the poster to be evaluated into a gray-scale picture, and then performing corrosion, expansion, mean value filtering and binarization processing on the converted picture. The corrosion process is to eliminate the boundary point of the object, reduce the target, eliminate the noise point smaller than the structural element and enlarge the dark area; the expansion is to merge all background points contacting with the object into the object to enlarge the object, so that the hollow in the object can be supplemented, and the bright area can be enlarged; the binarization processing is that all pixel points of an image are classified according to 256 gray scales, each pixel point represents a gray scale, and then the pixel points higher than a certain gray scale display white and the pixel points lower than the certain gray scale display black.
And if the poster to be scored has a black edge, determining a scoring processing result of the black edge.
It should be understood that by checking whether a black edge exists on the top or the bottom of the poster to be scored, if the black edge appears on the top or the bottom of the poster to be scored, the scoring processing result of the black edge is minus 40 points, and further, if the black edge does not appear on the top or the bottom of the poster to be scored, the scoring processing result of the black edge is minus 0 points.
Further, the index information includes a text, and the step S20 further includes:
and detecting whether the poster to be evaluated has a font or not.
It should be understood that whether the poster to be scored has a font is checked through a character recognition model, wherein the character recognition model may be set by a person skilled in the art, and the embodiment does not limit this, and may be, in a specific implementation process, a chinese _ text _ detection _ db _ mobile.
And if the poster to be scored has a black edge, determining a scoring processing result of the black edge.
It can be understood that by checking whether the poster to be scored has a font, when a character appears in the poster to be scored, the scoring processing result of the black edge is minus 20 points, and further, when no character appears in the poster to be scored, the scoring processing result of the black edge is minus 0 point.
Further, the step S30 includes:
step S301: and obtaining the scoring result of the poster to be scored according to the basic score, the scoring processing result of the face information, the scoring processing result of the picture color, the scoring processing result of the black edge and the scoring processing result of the font.
It should be understood that the basic score may be set by a person skilled in the art, and may be 300 points in the implementation process, which is not done in the present embodiment, so that the scoring result of the poster to be scored is obtained by summing the basic score and the scoring processing result of the face information, the scoring processing result of the picture color, the scoring processing result of the black edge, and the scoring processing result of the font. For example, when the index information of the poster to be scored is checked, if no human face is recognized and characters appear on the picture, the scoring result of the poster to be scored is 300+ (-120) + (-20), so that the scoring result of the poster to be scored is 160 points.
As can be appreciated, a scoring flow chart is shown in fig. 4, by entering the poster to be scored. Calculating face score by subtracting 120 points when no face is detected, 30 points when the area of the face region of a person is less than 10%, 30 points when the face is in a blurred state, 40 points when the head of a person is present in the bottom quarter region, and 20 points when the head region of a person is present in the left and right side edges in the tenth region, color score face score by subtracting 30 points when the maximum difference H/S/B of the screen HSB is respectively within 10, black score edge score by subtracting 40 points when the top and bottom are black edges, text score detect score by subtracting 20 points when the word of a text is present in the screen, therefore, the final score final _ score may be calculated by face _ score, color _ score, black _ edge _ score, and text _ detect _ score, wherein the final score final _ score is calculated by the following formula:
final_score＝300+face_score+color_score+black_edge_score+black_edge_score+te xt_detect_score。
in the embodiment, by detecting the face information, the picture color, the black edge and the font in the index information, if the poster to be evaluated has the face information, the poster to be evaluated is detected; if the poster to be evaluated has the face information, extracting the features of the face information of the poster to be evaluated, and determining the coordinate position of the face and the clear state of the face; determining a grading processing result of the index information according to the face coordinate position and the face clear state; detecting the picture color of the poster to be scored, and determining the hue, saturation and brightness of the pixel point of the poster to be scored; if the hue difference value of the pixel point is less than or equal to a first preset value, the saturation difference value is less than or equal to a second preset value and the brightness difference value is less than or equal to a third preset value, determining a grading processing result of the picture color; detecting whether the poster to be evaluated has a black edge or not; if the poster to be scored has a black edge, determining a scoring processing result of the black edge; detecting whether the poster to be evaluated has a font or not; if the poster to be scored has the font, determining a scoring processing result of the font, identifying the poster to be scored, acquiring the face coordinate information of a person, the color of the poster, whether the poster is provided with a black edge or not and whether the poster is provided with characters or not, determining rules for each index, and performing score reduction processing on the condition that the poster is not in accordance with the index, thereby realizing the accuracy of quickly selecting the better poster.
Furthermore, an embodiment of the present invention also proposes a storage medium having a poster selection program stored thereon, which when executed by a processor implements the steps of the poster selection method as described above.
Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.
Referring to fig. 5, fig. 5 is a block diagram showing the structure of a first embodiment of the poster selection apparatus of the present invention.
As shown in fig. 5, a poster selection device according to an embodiment of the present invention includes:
and the acquisition module 10 is used for acquiring the poster to be evaluated.
It should be understood that the poster to be scored, which includes a plurality of image frames to be processed, is obtained by determining the plurality of image frames to be processed through frame extraction processing of the video to be processed.
And the detection module 20 is used for detecting the index information of the poster to be scored and determining a scoring processing result of the index information.
It can be understood that index information can be face information, picture color, black edge and font, therefore, through discerning the poster to be scored, obtain the face information of people in the poster to be scored, the picture color of the poster, whether take black edge and whether take index information such as characters, then formulate the rule of scoring to each item of index information, to not meeting the index condition, carry out the score branch processing, thereby obtain face information score processing result, picture color score processing result, black edge score processing result and font score processing result.
And the scoring module 30 is used for determining a scoring result of the poster to be scored according to the basic score and the scoring processing result.
It should be understood that the basic score may be set by a person skilled in the art, and the basic score may be 300 in a specific implementation process, which is not limited in this embodiment, and the final poster scoring result to be scored is obtained by giving one basic score 300 and performing summation processing on the face information scoring processing result, the image color scoring processing result, the black edge scoring processing result, and the font scoring processing result according to each scoring processing result.
And the determining module 40 is used for presetting a ranking for the scoring result to obtain a ranking result, and determining a target poster in the posters to be scored according to the ranking result.
It should be noted that if the scoring result of the poster to be scored is higher, it indicates that the probability that the poster to be scored is determined as the target poster is higher, and if the scoring result of the poster to be scored is lower, it indicates that the probability that the poster to be scored is determined as the target poster is lower, so that the scoring results are sorted in descending order from big to small, thereby obtaining a sorting result, and the poster to be scored with the largest scoring result is determined as the target poster of the video to be processed.
In an embodiment, the detection module 20 is further configured to detect whether the poster to be scored has human face information; if the poster to be evaluated has the face information, extracting the features of the face information of the poster to be evaluated, and determining the coordinate position of the face and the clear state of the face; and determining a grading processing result of the index information according to the face coordinate position and the face clear state.
In an embodiment, the scoring module 30 is further configured to determine a second scoring processing result if the face clarity state is in a fuzzy state; if the face coordinate position appears in the first preset area at the bottom of the poster to be scored, determining a third scoring processing result; if the poster to be scored has a face coordinate position in a second preset area of the left edge and the right edge, determining a fourth scoring processing result; and determining a grading processing result of the face information according to the first grading processing result, the second grading processing result, the third grading processing result and the fourth grading processing result.
In an embodiment, the detection module 20 is further configured to detect a picture color of the poster to be scored, and determine a hue, a saturation, and a brightness of a pixel point of the poster to be scored; and if the hue difference value of the pixel point is less than or equal to a first preset value, the saturation difference value is less than or equal to a second preset value and the brightness difference value is less than or equal to a third preset value, determining the grading processing result of the picture color.
In an embodiment, the detection module 20 is further configured to detect whether a black edge exists in the poster to be evaluated; and if the poster to be scored has a black edge, determining a scoring processing result of the black edge.
In an embodiment, the detection module 20 is further configured to detect whether a font exists in the poster to be scored; and if the poster to be scored has a font, determining a scoring processing result of the font.
In an embodiment, the scoring module 30 is further configured to obtain a scoring result of the poster to be scored according to a basic score, a scoring processing result of the face information, a scoring processing result of the picture color, a scoring processing result of the black border, and a scoring processing result of the font.
For other embodiments or specific implementation methods of the poster selection device according to the present invention, reference may be made to the above-mentioned method embodiments, which are not described in detail herein.
It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not elaborately described in this embodiment may be referred to a poster selection method provided in any embodiment of the present invention, and are not described herein again.
Further, it is to 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 system 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 system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A poster selection method, comprising:
obtaining a poster to be evaluated;
detecting index information of the poster to be scored, and determining a scoring processing result of the index information;
determining a grading result of the poster to be graded according to a basic score and the grading processing result;
and carrying out preset sequencing processing on the grading result to obtain a sequencing result, and determining a target poster in the posters to be graded according to the sequencing result.
2. A poster selection method as defined in claim 1, wherein the indicator information comprises face information;
the detecting the index information of the poster to be scored and determining the scoring processing result of the index information comprise:
detecting whether the poster to be evaluated has face information or not;
if the poster to be evaluated has the face information, extracting the features of the face information of the poster to be evaluated, and determining the coordinate position of the face and the clear state of the face;
and determining a grading processing result of the face information according to the face coordinate position and the face clear state.
3. A poster selection method as defined in claim 2, wherein determining a scoring processing result of the face information based on the face coordinate position and the face clarity status comprises:
if the area of the region covered by the face coordinate position is smaller than a preset area, determining a first grading processing result;
if the face clear state is in a fuzzy state, determining a second grading processing result;
if the face coordinate position appears in the first preset area at the bottom of the poster to be scored, determining a third scoring processing result;
if the poster to be scored has a face coordinate position in a second preset area of the left edge and the right edge, determining a fourth scoring processing result;
and determining a grading processing result of the face information according to the first grading processing result, the second grading processing result, the third grading processing result and the fourth grading processing result.
4. A poster selection method as defined in claim 1, wherein the indicator information comprises a picture color;
the detecting the index information of the poster to be scored and determining the scoring processing result of the index information comprise:
detecting the picture color of the poster to be evaluated, and determining the hue, saturation and brightness of the pixel point of the poster to be evaluated;
and if the hue difference value of the pixel point is less than or equal to a first preset value, the saturation difference value is less than or equal to a second preset value and the brightness difference value is less than or equal to a third preset value, determining the grading processing result of the picture color.
5. A poster selection method as defined in claim 1, wherein the indicator information comprises a black border, comprising:
the detecting the index information of the poster to be scored and determining the scoring processing result of the index information comprise:
detecting whether the poster to be evaluated has a black edge or not;
and if the poster to be scored has a black edge, determining a scoring processing result of the black edge.
6. A poster selection method as defined in claim 1, wherein the indicator information comprises a font;
the detecting the index information of the poster to be scored and determining the scoring processing result of the index information comprise:
detecting whether the poster to be evaluated has a font or not;
and if the poster to be scored has a font, determining a scoring processing result of the font.
7. A poster selection method as defined in any of claims 1-6, wherein the scoring processing results comprise scoring processing results of face information, scoring processing results of picture colors, scoring processing results of black borders, and scoring processing results of fonts;
the step of determining the scoring result of the poster to be scored according to the basic score and the scoring processing result comprises the following steps of:
and obtaining the scoring result of the poster to be scored according to the basic score, the scoring processing result of the face information, the scoring processing result of the picture color, the scoring processing result of the black edge and the scoring processing result of the font.
8. A poster selection device, characterized in that it comprises:
the acquisition module is used for acquiring the poster to be evaluated;
the detection module is used for detecting the index information of the poster to be scored and determining a scoring processing result of the index information;
the scoring module is used for determining a scoring result of the poster to be scored according to a basic score and the scoring processing result;
and the determining module is used for presetting sequencing processing on the grading result to obtain a sequencing result and determining a target poster in the posters to be graded according to the sequencing result.
9. A poster selection device, characterized in that it comprises: a memory, a processor, and a poster selection program stored on the memory and executable on the processor, the poster selection program configured to implement the poster selection method of any of claims 1 to 7.
10. A storage medium, characterized in that the storage medium has stored thereon a poster selection program which, when executed by a processor, implements a poster selection method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111023826.6A CN113705496A (en) | 2021-08-31 | 2021-08-31 | Poster selection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111023826.6A CN113705496A (en) | 2021-08-31 | 2021-08-31 | Poster selection method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113705496A true CN113705496A (en) | 2021-11-26 |
Family
ID=78657186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111023826.6A Pending CN113705496A (en) | 2021-08-31 | 2021-08-31 | Poster selection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705496A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046245A (en) * | 2015-08-28 | 2015-11-11 | 深圳英飞拓科技股份有限公司 | Video face detection and evaluation method |
| WO2019037346A1 (en) * | 2017-08-25 | 2019-02-28 | 广州视源电子科技股份有限公司 | Method and device for optimizing human face picture quality evaluation model |
| CN110363126A (en) * | 2019-07-04 | 2019-10-22 | 杭州视洞科技有限公司 | A kind of plurality of human faces real-time tracking and out of kilter method |
| CN111711771A (en) * | 2020-05-20 | 2020-09-25 | 北京奇艺世纪科技有限公司 | Image selection method and device, electronic equipment and storage medium |
| CN111784658A (en) * | 2020-06-29 | 2020-10-16 | 厦门市美亚柏科信息股份有限公司 | Quality analysis method and system for face image |
| CN112383830A (en) * | 2020-11-06 | 2021-02-19 | 北京小米移动软件有限公司 | Video cover determining method and device and storage medium |
| CN113011385A (en) * | 2021-04-13 | 2021-06-22 | 深圳市赛为智能股份有限公司 | Face silence living body detection method and device, computer equipment and storage medium |
-
2021
- 2021-08-31 CN CN202111023826.6A patent/CN113705496A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046245A (en) * | 2015-08-28 | 2015-11-11 | 深圳英飞拓科技股份有限公司 | Video face detection and evaluation method |
| WO2019037346A1 (en) * | 2017-08-25 | 2019-02-28 | 广州视源电子科技股份有限公司 | Method and device for optimizing human face picture quality evaluation model |
| CN110363126A (en) * | 2019-07-04 | 2019-10-22 | 杭州视洞科技有限公司 | A kind of plurality of human faces real-time tracking and out of kilter method |
| CN111711771A (en) * | 2020-05-20 | 2020-09-25 | 北京奇艺世纪科技有限公司 | Image selection method and device, electronic equipment and storage medium |
| CN111784658A (en) * | 2020-06-29 | 2020-10-16 | 厦门市美亚柏科信息股份有限公司 | Quality analysis method and system for face image |
| CN112383830A (en) * | 2020-11-06 | 2021-02-19 | 北京小米移动软件有限公司 | Video cover determining method and device and storage medium |
| CN113011385A (en) * | 2021-04-13 | 2021-06-22 | 深圳市赛为智能股份有限公司 | Face silence living body detection method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232713B (en) | Image target positioning correction method and related equipment | |
| CN109948566B (en) | Double-flow face anti-fraud detection method based on weight fusion and feature selection | |
| CN112990205B (en) | Method and device for generating handwritten character sample, electronic equipment and storage medium | |
| CN114402369A (en) | Human body posture recognition method and device, storage medium and electronic equipment | |
| JP3490482B2 (en) | Edge and contour extraction device | |
| CN111738252A (en) | Method and device for detecting text lines in image and computer system | |
| CN112102207A (en) | Method and device for determining temperature, electronic equipment and readable storage medium | |
| JP2018152026A (en) | Character recognition method and computer program | |
| CN114581928A (en) | Form identification method and system | |
| CN108804652B (en) | Method and device for generating cover picture, storage medium and electronic device | |
| CN113705496A (en) | Poster selection method, device, equipment and storage medium | |
| JP2012155586A (en) | Image binarization method and image binarization device | |
| CN112884074B (en) | Image design method, equipment, storage medium and device based on decision tree | |
| JP2022067086A (en) | Digitalized writing processing | |
| CN114241356A (en) | Wood board color identification method and device, electronic equipment and storage medium | |
| US11749021B2 (en) | Retrieval device, control method, and non-transitory storage medium | |
| CN116584100A (en) | Image space detection suitable for overlay media content | |
| CN112749769A (en) | Graphic code detection method and device, computer equipment and storage medium | |
| US10134163B2 (en) | Dynamic detection of an object framework in a mobile device captured image | |
| CN111476800A (en) | Character region detection method and device based on morphological operation | |
| CN106934814B (en) | Background information identification method and device based on image | |
| CN112507999B (en) | Non-invasive user interface input item identification method based on visual characteristics | |
| JP2007058819A (en) | Index information generation device | |
| JP2003271973A (en) | Method and program for image processing | |
| Mancas | Image perception: Relative influence of bottom-up and top-down attention |
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 |