CN117114655B - Quality analysis and comparison method for film after restoration - Google Patents
Quality analysis and comparison method for film after restoration Download PDFInfo
- Publication number
- CN117114655B CN117114655B CN202311144137.XA CN202311144137A CN117114655B CN 117114655 B CN117114655 B CN 117114655B CN 202311144137 A CN202311144137 A CN 202311144137A CN 117114655 B CN117114655 B CN 117114655B
- Authority
- CN
- China
- Prior art keywords
- film
- detection time
- time point
- repair
- restoration
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 115
- 238000011156 evaluation Methods 0.000 claims abstract description 65
- 238000013441 quality evaluation Methods 0.000 claims description 37
- 238000001303 quality assessment method Methods 0.000 claims description 26
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 21
- 238000012502 risk assessment Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000007654 immersion Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/752—Contour matching
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of film restoration, and particularly discloses a quality analysis and comparison method after film restoration, which comprises the following steps: the method comprises the steps of film damage evaluation, second film repair judgment, third film repair detection, fourth film repair analysis, fifth film repair quality judgment, sixth film repair quality analysis, seventh film repair quality judgment, eighth film repair quality comprehensive analysis, and further ensures film definition, so that film repair quality analysis accuracy is improved, film content understanding and immersion of a viewer are ensured, film repair efficiency and value are improved, and accordingly repair effect is ensured to meet expectations and good film viewing experience.
Description
Technical Field
The invention relates to the technical field of motion picture film restoration, in particular to a quality analysis and comparison method after motion picture film restoration.
Background
Movies, which are an important form of art, record important segments of human culture, history and art, and many early movie works have suffered from time, environment and storage conditions, and need to be repaired and protected. The quality analysis of the repaired film can ensure that the repair work meets professional standards and requirements, which has important significance for preserving film heritage and inheriting film culture, the film is used as a traditional carrier of films, and carries precious culture and historical heritage, the preservation and repair of the film are important tasks for protecting the film heritage, and the quality analysis of the film after repair is an important link in the film protection and recovery work, so the quality analysis of the film after repair is extremely necessary.
In the prior art, the quality analysis of the repaired cinematographic film can meet the current requirements to a certain extent, but certain defects exist, and the quality analysis is specifically implemented in the following layers: (1) In the prior art, the quality of the film after the film is repaired is mostly analyzed from the appearance of the film, the attention of the viewer during the projection of the film after the film is repaired is not high, the further verification of the film after the film is repaired is lacking, the problems of blurring, low definition, noise and the like can occur during the film projection, the quality analysis of the film after the film is repaired is not high due to the neglect of the prior art, the efficiency and the value of the film repair are reduced, and therefore, the repair effect is difficult to meet the expectations and good film viewing experience is difficult to ensure.
(2) In the prior art, when the appearance of the film is analyzed, the attention degree of the fuzzy risk of the film is not high, the problem of the fuzzy of the film can reduce the definition and detail display of images, the definition of the film is difficult to ensure due to the neglect of the aspect of the prior art, and the repair quality of the film is further reduced to a certain extent, so that the understanding and immersion of a film content of a viewer are influenced.
Disclosure of Invention
In order to overcome the defects in the background technology, the embodiment of the invention provides a quality analysis and comparison method for a film after repairing, which can effectively solve the problems related to the background technology.
The aim of the invention can be achieved by the following technical scheme: a method for quality analysis and comparison after motion picture film restoration, comprising: step one, film damage evaluation: and extracting original images corresponding to each film from the cloud database, detecting each film, further obtaining images corresponding to each film at each detection time point, and analyzing damage evaluation coefficients corresponding to each film at each detection time point according to the images.
Step two, film restoration judgment: and analyzing each film to be repaired and the corresponding repair time point according to the damage evaluation coefficient of each film at each detection time point, and acquiring the pre-repair image corresponding to each film to be repaired.
Step three, detecting after the film restoration: marking each repaired film to be repaired as each repaired film, and collecting images of each repaired film to obtain repaired images corresponding to each repaired film.
Fourth, analysis after the film restoration: and analyzing the restoration quality evaluation index corresponding to each restoration film according to the restoration post-restoration image and the restoration pre-restoration image corresponding to each restoration film.
Judging the restoration quality of the film: screening each substandard repairing film according to the repairing quality evaluation index corresponding to each repairing film, and repairing each substandard repairing film.
Step six, analyzing the repairing quality of the repairing film which does not reach the standard: and the analysis method is consistent with the analysis method of the repair quality assessment indexes corresponding to the repair film, so that the repair quality assessment indexes corresponding to the unqualified repair film are analyzed.
Step seven, judging the restoration quality of the non-standard restoration film: comparing the restoration quality evaluation indexes corresponding to the non-standard restoration cinema films with a predefined restoration quality evaluation index threshold, and executing the step eight if all the restoration quality evaluation indexes corresponding to the non-standard restoration cinema films are larger than or equal to the predefined restoration quality evaluation index threshold, otherwise, executing the step five.
Step eight, comprehensively analyzing the repairing quality of the film: and (3) screening the film, and further obtaining screening evaluation parameters corresponding to the film, so as to analyze the comprehensive restoration quality evaluation index corresponding to the film.
Further, the projection evaluation parameters comprise post-viewing evaluation corresponding to each user.
Further, the specific analysis method for analyzing the damage evaluation coefficient corresponding to each motion picture film at each detection time point comprises the following steps: acquiring the original contour corresponding to each film according to the original image corresponding to each film, and acquiring the corresponding area S i ' where i is denoted as the number of each motion picture film, i=1, 2, n.
Acquiring the outline of each film corresponding to each detection time point according to the image of each film corresponding to each detection time point, and performing superposition comparison on the outline and the original outline corresponding to each film, thereby acquiring the superposition area S corresponding to each film im Where m is expressed as the number of each test time point, m=1, 2,..i.
Analyzing scratch risk coefficient epsilon corresponding to each film at each detection time point according to original images corresponding to each film and images corresponding to each film at each detection time point im And a fouling risk coefficient eta im And analyzing the color coincidence index mu corresponding to each film at each detection time point im Fuzzy risk assessment index
Comprehensively analyzing damage evaluation coefficients of each film at each detection time pointWherein lambda is 1 、λ 2 、λ 3 、λ 4 、λ 5 Respectively expressed as a predefined deformation risk assessment coefficient, a scratch risk coefficient, a dirt risk coefficient and a colorAnd weight influence factors corresponding to the similarity evaluation index and the fuzzy risk evaluation index.
Further, the scratch risk coefficient corresponding to each film at each detection time point is analyzed by the specific analysis method: and obtaining each original scratch area corresponding to each motion picture film.
Acquiring the area I of each film corresponding to each original scratch area ij Where j is denoted as the number of each original scratch area, j=1, 2.
Similarly, the area I 'of each film corresponding to each scratch area at each detection time point is obtained' imp Where p is denoted as the number of each scratch area, p=1, 2.
Counting the number M 'of the corresponding original scratch areas of each film' i And counting the number M of scratch areas corresponding to each detection time point of each film im Thereby analyzing scratch risk coefficient corresponding to each film at each detection time point
Further, the specific analysis method of the fouling risk coefficient corresponding to each film at each detection time point is as follows: and acquiring each gray value corresponding to each motion picture film at each detection time point according to the image corresponding to each motion picture film at each detection time point, and further extracting the water stain gray value range from the cloud database.
The analysis method of each original scratch area corresponding to each film is consistent, each water stain area corresponding to each film at each detection time point is analyzed, and the corresponding area N is obtained imh Where h is denoted as the number of the water spot area, h=1, 2,..g.
Counting the number U 'of water stain areas corresponding to each detection time point of each film' im Further analyzing the water stain risk coefficient corresponding to each detection time point of each filmWherein N ', U' are respectively denoted as predefined permissionsWater spot area, number of allowed water spot areas.
And similarly, analyzing the oil stain risk coefficient corresponding to each film at each detection time point.
Average processing is carried out on the water stain risk coefficient and the oil stain risk coefficient corresponding to each film at each detection time point, and the result is used as the dirt risk coefficient eta corresponding to each film at each detection time point im 。
Further, the specific analysis method for analyzing the color coincidence index corresponding to each motion picture film at each detection time point comprises the following steps: acquiring chromaticity value Y corresponding to each set point of each motion picture film at each detection time point according to the image corresponding to each detection time point ifm Where f is denoted as the number of each water spot area, f=1, 2.
Obtaining chromaticity value Y of each set point according to original image corresponding to each film if ′。
Analyzing color difference coefficients corresponding to each set point of each film at each detection time pointWhere Y' is the allowable error of the predefined chromaticity.
Comparing the color difference coefficient corresponding to each distribution point of each film at each detection time point with a predefined color difference coefficient threshold value, if the color difference coefficient of a certain distribution point is greater than or equal to the color difference coefficient threshold value, marking the distribution point as a color deviation distribution point, further counting each color deviation distribution point corresponding to each detection time point of each film, and counting the number J of the color deviation distribution points corresponding to each detection time point of each film im 。
Counting the number J of corresponding arrangement points of each film i ' and further comprehensively analyzing the color coincidence index of each film corresponding to each detection time pointWhere t is the number of points to be laid out.
Further, the fuzzy risk assessment index corresponding to each film at each detection time point is analyzed by the specific analysis method as follows: dividing images corresponding to each film at each detection time point according to a set area to obtain each sub-image corresponding to each film at each detection time point, and obtaining the corresponding definition according to the sub-images, thereby obtaining the definition QX of each edge sub-area corresponding to each film at each detection time point imb And the definition QX of each intermediate subregion imr Where b is denoted as the number of each edge sub-region, b=1, 2,..d, r is denoted as the number of each intermediate sub-region, r=1, 2,..w.
Similarly, obtaining the original definition QI corresponding to each edge sub-region to which each motion picture film belongs according to the original image corresponding to each motion picture film ib And obtain the original definition QI corresponding to each intermediate subregion of each film ir 。
Comprehensively analyzing fuzzy risk assessment indexes corresponding to each film at each detection time pointWhere d is the number of edge subregions, w is the number of intermediate subregions, γ 1 、γ 2 Respectively expressed as predefined edge sub-region blur, intermediate sub-region blur corresponding duty cycle factors.
Further, the analysis is performed on the restoration quality evaluation index corresponding to each restoration film. The analysis method for analyzing the damage evaluation coefficients of each film at each detection time point is consistent, and the repair damage evaluation coefficients of each film are analyzed according to the repaired image and the pre-repair image of each filmWhere v is denoted as the number of each repair motion picture film, v=1, 2,..u.
Acquiring repair time points corresponding to the repair film, and further acquiring damage evaluation coefficients corresponding to the repair film at the repair time points
Analyzing the repair quality assessment index corresponding to each repair film
Further, the analysis method for the comprehensive restoration quality assessment index corresponding to the film comprises the following steps: and analyzing the projection quality evaluation index xi corresponding to the film according to the projection evaluation parameters corresponding to the film.
Obtaining the repair quality evaluation index corresponding to the last repair of each repair filmAnd selecting the maximum repair quality assessment index from the above>And minimum repair quality assessment index->Thereby analyzing the comprehensive restoration quality assessment index corresponding to the filmWherein u is the number of repair film strips, +.>Evaluating the index for a predefined repair quality tolerance, χ 1 、χ 2 、χ 3 Respectively expressed as a predefined projection quality assessment index, a restoration quality deviation and a weight coefficient corresponding to the restoration quality assessment index.
Further, the specific analysis method for analyzing the projection quality evaluation index corresponding to the film comprises the following steps: extracting the post-viewing evaluation corresponding to each user from the projection evaluation parameters corresponding to the film, and constructing each user according to the post-viewing evaluationUser-corresponding post-observation evaluation keyword set F c Where c is denoted as the number of each user, c=1, 2.
Extracting a film quality keyword set E from a cloud database, and analyzing film evaluation coefficients corresponding to each user accordingly
Marking each user corresponding to the film evaluation coefficient larger than or equal to the predefined film evaluation coefficient threshold as each satisfied user, and further counting the number theta of the satisfied users.
Counting the number of users theta' and comprehensively analyzing the projection quality evaluation index corresponding to the filmWhere z is the number of users.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects: (1) The invention analyzes the damage condition corresponding to each film in film damage evaluation, thereby providing powerful data support for later determination of whether the film needs to be repaired.
(2) The invention judges the film needing to be repaired in film repair judgment, thereby laying a foundation for the analysis of the repair quality of the subsequent film.
(3) According to the invention, the appearance of the film is analyzed through the aspects of deformation, color, blurring and the like of the film in the film after restoration analysis, so that the defect of low attention to the blurring risk of the film in the prior art is overcome, the definition of the film is ensured, the accuracy of the restoration quality analysis of the film is improved to a certain extent, and the understanding and immersion of a film viewer on the film content are ensured.
(4) According to the invention, in the comprehensive analysis of the quality of the film restoration, the film appearance is analyzed, and the evaluation of the viewers during projection is analyzed after the film restoration, so that the defect of low attention of the viewers during projection after the film restoration in the prior art is overcome, the film restoration is subsequently verified, the accuracy of the quality analysis after the film restoration is further ensured, the film restoration efficiency and value are improved, and the restoration effect is ensured to meet expectations and good film viewing experience is provided.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a quality analysis and comparison method for a motion picture film after repair, comprising: step one, film damage evaluation: and extracting original images corresponding to each film from the cloud database, detecting each film, further obtaining images corresponding to each film at each detection time point, and analyzing damage evaluation coefficients corresponding to each film at each detection time point according to the images.
In a specific embodiment of the present invention, the analyzing the damage evaluation coefficient corresponding to each motion picture film at each detection time point includes: acquiring the original contour corresponding to each film according to the original image corresponding to each film, and acquiring the corresponding area S i ' where i is denoted as the number of each motion picture film, i=1, 2, n.
According to each electricityThe image corresponding to each detection time point of the film is used for obtaining the outline corresponding to each detection time point of each film, and the outline is overlapped and compared with the original outline corresponding to each film, so as to obtain the corresponding overlapping area S im Where m is expressed as the number of each test time point, m=1, 2,..i.
Analyzing scratch risk coefficient epsilon corresponding to each film at each detection time point according to original images corresponding to each film and images corresponding to each film at each detection time point im And a fouling risk coefficient eta im And analyzing the color coincidence index mu corresponding to each film at each detection time point im Fuzzy risk assessment index
Comprehensively analyzing damage evaluation coefficients of each film at each detection time pointWherein lambda is 1 、λ 2 、λ 3 、λ 4 、λ 5 Respectively expressed as a predefined deformation risk assessment coefficient, a scratch risk coefficient, a dirt risk coefficient, a color similarity assessment index and a weight influence factor corresponding to the fuzzy risk assessment index.
In a specific embodiment of the present invention, the scratch risk coefficient corresponding to each motion picture film at each detection time point is analyzed by the specific analysis method: and obtaining each original scratch area corresponding to each motion picture film.
It should be noted that, the specific analysis method for obtaining each original scratch area corresponding to each motion picture film is as follows: and extracting a scratch gray value range from the cloud database, acquiring each gray value corresponding to each film according to the original image corresponding to each film, comparing the gray value with the scratch gray value range, marking the gray value as a scratch gray value if a certain gray value is in the scratch gray value range, counting each scratch gray value corresponding to each film according to the scratch gray value, acquiring the region corresponding to each scratch gray value corresponding to each film, and marking the region as each original scratch region corresponding to each film.
Acquiring the area I of each film corresponding to each original scratch area ij Where j is denoted as the number of each original scratch area, j=1, 2.
Similarly, the area I 'of each film corresponding to each scratch area at each detection time point is obtained' imp Where p is denoted as the number of each scratch area, p=1, 2.
Counting the number M of the corresponding original scratch areas of each film i ' and counting the number M of scratch areas corresponding to each detection time point of each film im Thereby analyzing scratch risk coefficient corresponding to each film at each detection time point
In a specific embodiment of the present invention, the specific analysis method of the fouling risk coefficient corresponding to each motion picture film at each detection time point is as follows: and acquiring each gray value corresponding to each motion picture film at each detection time point according to the image corresponding to each motion picture film at each detection time point, and further extracting the water stain gray value range from the cloud database.
The analysis method of each original scratch area corresponding to each film is consistent, each water stain area corresponding to each film at each detection time point is analyzed, and the corresponding area N is obtained imh Where h is denoted as the number of the water spot area, h=1, 2,..g.
Counting the number U 'of water stain areas corresponding to each detection time point of each film' im Further analyzing the water stain risk coefficient corresponding to each detection time point of each filmWhere N ', U' are denoted as predefined water-allowed areas, number of water-allowed areas, respectively.
And similarly, analyzing the oil stain risk coefficient corresponding to each film at each detection time point.
Average processing is carried out on the water stain risk coefficient and the oil stain risk coefficient corresponding to each film at each detection time point, and the result is used as the dirt risk coefficient eta corresponding to each film at each detection time point im 。
In a specific embodiment of the present invention, the analyzing the color coincidence index corresponding to each motion picture film at each detection time point includes: acquiring chromaticity value Y corresponding to each set point of each motion picture film at each detection time point according to the image corresponding to each detection time point ifm Where f is denoted as the number of each water spot area, f=1, 2.
Obtaining chromaticity value Y 'of each set point according to the original image corresponding to each film' if 。
Analyzing color difference coefficients corresponding to each set point of each film at each detection time pointWhere Y' is the allowable error of the predefined chromaticity.
Comparing the color difference coefficient corresponding to each distribution point of each film at each detection time point with a predefined color difference coefficient threshold value, if the color difference coefficient of a certain distribution point is greater than or equal to the color difference coefficient threshold value, marking the distribution point as a color deviation distribution point, further counting each color deviation distribution point corresponding to each detection time point of each film, and counting the number J of the color deviation distribution points corresponding to each detection time point of each film im 。
Counting the number J of corresponding arrangement points of each film i ' and further comprehensively analyzing the color coincidence index of each film corresponding to each detection time pointWhere t is the number of points to be laid out.
In a specific embodiment of the present invention, the analysis of the fuzzy risk assessment corresponding to each motion picture film at each detection time pointThe index, its concrete analysis method is: dividing images corresponding to each film at each detection time point according to a set area to obtain each sub-image corresponding to each film at each detection time point, and obtaining the corresponding definition according to the sub-images, thereby obtaining the definition QX of each edge sub-area corresponding to each film at each detection time point imb And the definition QX of each intermediate subregion imr Where b is denoted as the number of each edge sub-region, b=1, 2,..d, r is denoted as the number of each intermediate sub-region, r=1, 2,..w.
Similarly, obtaining the original definition QI corresponding to each edge sub-region to which each motion picture film belongs according to the original image corresponding to each motion picture film ib And obtain the original definition QI corresponding to each intermediate subregion of each film ir 。
Comprehensively analyzing fuzzy risk assessment indexes corresponding to each film at each detection time pointWhere d is the number of edge subregions, w is the number of intermediate subregions, γ 1 、γ 2 Respectively expressed as predefined edge sub-region blur, intermediate sub-region blur corresponding duty cycle factors.
The invention analyzes the damage condition corresponding to each film in film damage evaluation, thereby providing powerful data support for later determination of whether the film needs to be repaired.
Step two, film restoration judgment: and analyzing each film to be repaired and the corresponding repair time point according to the damage evaluation coefficient of each film at each detection time point, and acquiring the pre-repair image corresponding to each film to be repaired.
It should be noted that, the specific analysis method of each film to be repaired and the corresponding repair time point thereof is as follows: comparing the damage evaluation coefficient corresponding to each film at each detection time point with a predefined damage evaluation coefficient threshold, if the damage evaluation coefficient corresponding to a certain film at a certain detection time point is greater than or equal to the damage evaluation coefficient threshold, marking the film as a film to be repaired, marking the detection time point as a repairing time point, and further analyzing each film to be repaired and the repairing time point corresponding to the film.
It should be further noted that, the pre-repair image corresponding to each film to be repaired specifically includes: and each to-be-repaired shadow film is corresponding to the image of the repair time point.
The invention judges the film needing to be repaired in film repair judgment, thereby laying a foundation for the analysis of the repair quality of the subsequent film.
Step three, detecting after the film restoration: marking each repaired film to be repaired as each repaired film, and collecting images of each repaired film to obtain repaired images corresponding to each repaired film.
Fourth, analysis after the film restoration: and analyzing the restoration quality evaluation index corresponding to each restoration film according to the restoration post-restoration image and the restoration pre-restoration image corresponding to each restoration film.
In a specific embodiment of the present invention, the analysis is performed on the quality assessment index of the repair for each of the repair film strips. The analysis method for analyzing the damage evaluation coefficients of each film at each detection time point is consistent, and the repair damage evaluation coefficients of each film are analyzed according to the repaired image and the pre-repair image of each filmWhere v is denoted as the number of each repair motion picture film, v=1, 2,..u.
Acquiring repair time points corresponding to the repair film, and further acquiring damage evaluation coefficients corresponding to the repair film at the repair time points
Analyzing the repair quality assessment index corresponding to each repair film
According to the invention, the appearance of the film is analyzed through the aspects of deformation, color, blurring and the like of the film in the film after restoration analysis, so that the defect of low attention to the blurring risk of the film in the prior art is overcome, the definition of the film is ensured, the accuracy of the restoration quality analysis of the film is improved to a certain extent, and the understanding and immersion of a film viewer on the film content are ensured.
Judging the restoration quality of the film: screening each substandard repairing film according to the repairing quality evaluation index corresponding to each repairing film, and repairing each substandard repairing film.
Step six, analyzing the repairing quality of the repairing film which does not reach the standard: and the analysis method is consistent with the analysis method of the repair quality assessment indexes corresponding to the repair film, so that the repair quality assessment indexes corresponding to the unqualified repair film are analyzed.
Step seven, judging the restoration quality of the non-standard restoration film: comparing the restoration quality evaluation indexes corresponding to the non-standard restoration cinema films with a predefined restoration quality evaluation index threshold, and executing the step eight if all the restoration quality evaluation indexes corresponding to the non-standard restoration cinema films are larger than or equal to the predefined restoration quality evaluation index threshold, otherwise, executing the step five.
Step eight, comprehensively analyzing the repairing quality of the film: and (3) screening the film, and further obtaining screening evaluation parameters corresponding to the film, so as to analyze the comprehensive restoration quality evaluation index corresponding to the film.
In a specific embodiment of the present invention, the projection evaluation parameter includes a post-viewing evaluation corresponding to each user.
In a specific embodiment of the present invention, the analysis method for analyzing the comprehensive repair quality assessment index corresponding to the motion picture film includes: and analyzing the projection quality evaluation index xi corresponding to the film according to the projection evaluation parameters corresponding to the film.
Obtaining the repair quality evaluation index corresponding to the last repair of each repair filmAnd selecting the maximum repair quality assessment index from the above>And minimum repair quality assessment index->Thereby analyzing the comprehensive restoration quality assessment index corresponding to the filmWherein u is the number of repair film strips, +.>Evaluating the index for a predefined repair quality tolerance, χ 1 、χ 2 、χ 3 Respectively expressed as a predefined projection quality assessment index, a restoration quality deviation and a weight coefficient corresponding to the restoration quality assessment index.
In a specific embodiment of the present invention, the analysis method for analyzing the projection quality assessment index corresponding to the motion picture film includes: extracting the post-view evaluation corresponding to each user from the projection evaluation parameters corresponding to the film, and then constructing a post-view evaluation keyword set F corresponding to each user c Where c is denoted as the number of each user, c=1, 2.
Extracting a film quality keyword set E from a cloud database, and analyzing film evaluation coefficients corresponding to each user accordingly
Marking each user corresponding to the film evaluation coefficient larger than or equal to the predefined film evaluation coefficient threshold as each satisfied user, and further counting the number theta of the satisfied users.
Counting the number of users theta' and comprehensively analyzing the projection quality evaluation index corresponding to the filmWhere z is the number of users.
According to the invention, in the comprehensive analysis of the quality of the film restoration, the film appearance is analyzed, and the evaluation of the viewers during projection is analyzed after the film restoration, so that the defect of low attention of the viewers during projection after the film restoration in the prior art is overcome, the film restoration is subsequently verified, the accuracy of the quality analysis after the film restoration is further ensured, the film restoration efficiency and value are improved, and the restoration effect is ensured to meet expectations and good film viewing experience is provided.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art of describing particular embodiments without departing from the structures of the invention or exceeding the scope of the invention as defined by the claims.
Claims (1)
1. A method for quality analysis and comparison after motion picture film restoration, comprising:
step one, film damage evaluation: extracting original images corresponding to each film from a cloud database, detecting each film, further obtaining images corresponding to each film at each detection time point, and analyzing damage evaluation coefficients corresponding to each film at each detection time point according to the images;
the specific analysis method for analyzing the damage evaluation coefficient corresponding to each film at each detection time point comprises the following steps:
acquiring the original contour corresponding to each film according to the original image corresponding to each film, and acquiring the corresponding areaWherein->Number expressed as each motion picture film, +.>；
Acquiring the outline of each film at each detection time point according to the image of each film at each detection time point, and performing superposition comparison between the outline and the original outline of each film, thereby acquiring the superposition area corresponding to each filmWherein->Number expressed as each detection time point, +.>；
Analyzing scratch risk coefficients corresponding to each motion picture film at each detection time point according to original images corresponding to each motion picture film and images corresponding to each motion picture film at each detection time pointAnd risk factor of smudge->And analyzing the color coincidence index +.f corresponding to each film at each detection time point>And fuzzy risk assessment index->；
Comprehensive analysis of each motion picture film at each detection timeDamage assessment coefficient for point correspondenceWherein->、/>、/>、/>、/>Respectively representing the weight influence factors corresponding to the predefined deformation risk assessment coefficient, the scratch risk coefficient, the dirt risk coefficient, the color similarity assessment index and the fuzzy risk assessment index;
the scratch risk coefficient corresponding to each film at each detection time point is analyzed by the specific analysis method:
acquiring each original scratch area corresponding to each film;
acquiring the area of each film corresponding to each original scratch areaWherein->Represented as the number of each original scratch area,；
similarly, the area of each scratch area corresponding to each detection time point of each film is obtainedWherein->Number expressed as each scratch area, +.>；
Counting the number of the corresponding original scratch areas of each filmAnd counting the number of scratch areas corresponding to each film at each detection time point>Thereby analyzing scratch risk coefficient corresponding to each film at each detection time point；
The specific analysis method of the fouling risk coefficient corresponding to each film at each detection time point comprises the following steps:
acquiring each gray value corresponding to each motion picture film at each detection time point according to the image corresponding to each motion picture film at each detection time point, and further extracting a water stain gray value range from a cloud database;
the analysis method of each original scratch area corresponding to each film is consistent, each water stain area corresponding to each film at each detection time point is analyzed, and the corresponding area is obtainedWherein->Indicated as the number of the water-affected area,；
counting the number of water stain areas corresponding to each detection time point of each filmMeasuring amountFurther analyzing the water stain risk coefficient corresponding to each detection time point of each film>Wherein->、/>Respectively expressed as a predefined water-allowed area and the number of water-allowed areas;
similarly, analyzing oil stain risk coefficients corresponding to each film at each detection time point;
average processing the water stain risk coefficient and the oil stain risk coefficient corresponding to each film at each detection time point, and taking the result as the dirt risk coefficient corresponding to each film at each detection time point；
The specific analysis method for analyzing the color coincidence index of each film at each detection time point comprises the following steps:
acquiring chromaticity values corresponding to each set point of each motion picture film at each detection time point according to the images corresponding to each motion picture film at each detection time pointWherein->Number expressed as each water spot area, +.>；
Obtaining chromaticity value of each set point according to original image corresponding to each film；
Analyzing color difference coefficients corresponding to each set point of each film at each detection time pointWherein->An allowable error for a predefined chromaticity;
comparing the color difference coefficient corresponding to each distribution point of each film at each detection time point with a predefined color difference coefficient threshold value, if the color difference coefficient of a certain distribution point is greater than or equal to the color difference coefficient threshold value, marking the distribution point as a color deviation distribution point, further counting each color deviation distribution point corresponding to each detection time point of each film, and counting the number of color deviation distribution points corresponding to each detection time point of each film；
Counting the number of corresponding arrangement points of each filmFurther comprehensively analyzing the color coincidence index +.>Wherein->The number of the points is set;
the fuzzy risk assessment index corresponding to each film at each detection time point is analyzed by the specific analysis method:
dividing the image corresponding to each film at each detection time point according to the set area to obtain each filmThe corresponding sub-images of the film are obtained according to the sub-images corresponding to the detection time points, so as to obtain the definition of the edge sub-areas corresponding to the detection time pointsAnd definition of the respective intermediate subregion +.>WhereinNumber denoted as edge subregion>，/>Expressed as the number of each intermediate subregion, +.>；
Similarly, obtaining the original definition corresponding to each edge sub-region of each motion picture film according to the original image corresponding to each motion picture filmAnd obtaining the original definition corresponding to each middle subarea of each film>；
Comprehensively analyzing fuzzy risk assessment indexes corresponding to each film at each detection time pointWherein->For the number of edge subregions, +.>For the number of intermediate subregions, +.>、/>The corresponding duty factors are respectively expressed as predefined edge sub-region blurring and middle sub-region blurring;
step two, film restoration judgment: according to the damage evaluation coefficients of the film films corresponding to the detection time points, further analyzing the film films to be repaired and the corresponding repair time points thereof, and obtaining pre-repair images corresponding to the film films to be repaired;
step three, detecting after the film restoration: marking each repaired film to be repaired as each repaired film, and collecting images of each repaired film to obtain repaired images corresponding to each repaired film;
fourth, analysis after the film restoration: analyzing the restoration quality evaluation index corresponding to each restoration film according to the restoration post-restoration image and the restoration pre-restoration image corresponding to each restoration film;
analyzing the repair quality evaluation indexes corresponding to each repair film;
the analysis method for analyzing the damage evaluation coefficients of each film at each detection time point is consistent, and the repair damage evaluation coefficients of each film are analyzed according to the repaired image and the pre-repair image of each filmWherein->Number indicated as each repair film, +.>；
Acquiring repair time points corresponding to the repair film, and further acquiring damage evaluation coefficients corresponding to the repair film at the repair time points；
Analyzing the repair quality assessment index corresponding to each repair film；
Judging the restoration quality of the film: screening each substandard repairing film according to the repairing quality evaluation index corresponding to each repairing film, and repairing each substandard repairing film;
step six, analyzing the repairing quality of the repairing film which does not reach the standard: the analysis method of the repair quality evaluation indexes corresponding to the repair film is consistent with that of the repair film, so that the repair quality evaluation indexes corresponding to the unqualified repair film are analyzed;
step seven, judging the restoration quality of the non-standard restoration film: comparing the restoration quality evaluation indexes corresponding to the non-standard restoration cinema films with a predefined restoration quality evaluation index threshold, and executing the step eight if all the restoration quality evaluation indexes corresponding to the non-standard restoration cinema films are greater than or equal to the predefined restoration quality evaluation index threshold, otherwise, executing the step five;
step eight, comprehensively analyzing the repairing quality of the film: projecting the film, and further obtaining projection evaluation parameters corresponding to the film, so as to analyze the comprehensive restoration quality evaluation index corresponding to the film;
the projection evaluation parameters comprise post-observation evaluation corresponding to each user;
the comprehensive repair quality assessment index corresponding to the analytical cinema film comprises the following specific analysis methods:
analyzing the projection quality evaluation index corresponding to the film according to the projection evaluation parameter corresponding to the film；
Obtaining the repair quality evaluation index corresponding to the last repair of each repair filmAnd selecting the maximum repair quality assessment index from the above>And minimum repair quality assessment index->Thereby analyzing the comprehensive restoration quality assessment index corresponding to the filmWherein->For repairing the number of motion picture films +.>Evaluating the allowed error of the index for a predefined repair quality, < >>、/>、/>Respectively representing the weight coefficients corresponding to the predefined projection quality evaluation index, the restoration quality deviation and the restoration quality evaluation index;
the specific analysis method for analyzing the projection quality assessment index corresponding to the film comprises the following steps:
extracting the post-viewing evaluation corresponding to each user from the projection evaluation parameters corresponding to the film, thereby obtaining the post-viewing evaluation corresponding to each userConstructing a set of post-observation evaluation keywords corresponding to each userWherein->Number expressed as each user->；
Extracting a set of motion picture film quality keywords from a cloud databaseAnd further analyzing movie evaluation coefficients corresponding to respective users accordingly +.>；
Marking each user corresponding to the film evaluation coefficient larger than or equal to the predefined film evaluation coefficient threshold as each satisfied user, and further counting the number of the satisfied users；
Counting the number of usersFurther, the projection quality evaluation index corresponding to the film is comprehensively analyzedWherein->Is the number of users.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311144137.XA CN117114655B (en) | 2023-09-06 | 2023-09-06 | Quality analysis and comparison method for film after restoration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311144137.XA CN117114655B (en) | 2023-09-06 | 2023-09-06 | Quality analysis and comparison method for film after restoration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117114655A CN117114655A (en) | 2023-11-24 |
| CN117114655B true CN117114655B (en) | 2024-04-12 |
Family
ID=88810792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311144137.XA Active CN117114655B (en) | 2023-09-06 | 2023-09-06 | Quality analysis and comparison method for film after restoration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117114655B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117805145B (en) * | 2024-02-28 | 2024-05-14 | 西安汉华建筑实业有限公司 | Aluminum template surface defect detection method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002310916A (en) * | 2001-04-10 | 2002-10-23 | Sony Corp | Movie film inspecting device and method therefor, camera device therefor, and light source device |
| CN101865859A (en) * | 2009-04-17 | 2010-10-20 | 华为技术有限公司 | Detection method and device for image scratch |
| KR101026081B1 (en) * | 2010-01-22 | 2011-03-31 | 금오공과대학교 산학협력단 | Reversible watermark inserting and original image restoring methods |
| CN103093298A (en) * | 2012-06-18 | 2013-05-08 | 北京航星永志科技有限公司 | Multi-version digital archive management and application method for image or video file |
| US8681213B1 (en) * | 2013-09-05 | 2014-03-25 | Lasergraphics Inc. | Motion picture film scanner with automated failed splice recovery |
| CN105679221A (en) * | 2016-03-31 | 2016-06-15 | 广东欧珀移动通信有限公司 | Chromatic aberration detection method and device and terminal |
| CN106558016A (en) * | 2015-09-25 | 2017-04-05 | 灵然创智（天津）动画科技发展有限公司 | A kind of 4K video display cloud makes streamline |
| CN110475118A (en) * | 2019-07-11 | 2019-11-19 | 北京工业大学 | A kind of old film flicker removal method based on attention mechanism deep-cycle network |
| CN116233485A (en) * | 2022-12-28 | 2023-06-06 | 杭州当虹科技股份有限公司 | Method and system for managing and scheduling video and audio digital restoration based on artificial intelligence |
| CN116630203A (en) * | 2023-07-19 | 2023-08-22 | 科大乾延科技有限公司 | Integrated imaging three-dimensional display quality improving method |
-
2023
- 2023-09-06 CN CN202311144137.XA patent/CN117114655B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002310916A (en) * | 2001-04-10 | 2002-10-23 | Sony Corp | Movie film inspecting device and method therefor, camera device therefor, and light source device |
| CN101865859A (en) * | 2009-04-17 | 2010-10-20 | 华为技术有限公司 | Detection method and device for image scratch |
| KR101026081B1 (en) * | 2010-01-22 | 2011-03-31 | 금오공과대학교 산학협력단 | Reversible watermark inserting and original image restoring methods |
| CN103093298A (en) * | 2012-06-18 | 2013-05-08 | 北京航星永志科技有限公司 | Multi-version digital archive management and application method for image or video file |
| US8681213B1 (en) * | 2013-09-05 | 2014-03-25 | Lasergraphics Inc. | Motion picture film scanner with automated failed splice recovery |
| CN106558016A (en) * | 2015-09-25 | 2017-04-05 | 灵然创智（天津）动画科技发展有限公司 | A kind of 4K video display cloud makes streamline |
| CN105679221A (en) * | 2016-03-31 | 2016-06-15 | 广东欧珀移动通信有限公司 | Chromatic aberration detection method and device and terminal |
| CN110475118A (en) * | 2019-07-11 | 2019-11-19 | 北京工业大学 | A kind of old film flicker removal method based on attention mechanism deep-cycle network |
| CN116233485A (en) * | 2022-12-28 | 2023-06-06 | 杭州当虹科技股份有限公司 | Method and system for managing and scheduling video and audio digital restoration based on artificial intelligence |
| CN116630203A (en) * | 2023-07-19 | 2023-08-22 | 科大乾延科技有限公司 | Integrated imaging three-dimensional display quality improving method |
Non-Patent Citations (2)
| Title |
|---|
| Majed Chambah著."影片数字化修复图像质量评价方法(上)".《现代电影技术》.2010,第2010年卷(第3期),第46-50 页. * |
| 吴兵 等."电影胶片档案数字化修复过程研究".《兰台世界》.2015,第2015年卷(第26期),第96-97页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117114655A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117114655B (en) | Quality analysis and comparison method for film after restoration | |
| Yuan et al. | Image haze removal via reference retrieval and scene prior | |
| CN103942758A (en) | Dark channel prior image dehazing method based on multiscale fusion | |
| CN111127376B (en) | Digital video file repairing method and device | |
| CN115908415B (en) | Edge-based defect detection method, device, equipment and storage medium | |
| CN109300127A (en) | Defect inspection method, device, computer equipment and storage medium | |
| CN112215780B (en) | Image evidence obtaining and resistance attack defending method based on class feature restoration fusion | |
| CN106651792A (en) | Method and device for removing strip noise of satellite image | |
| CN111062895B (en) | Microscopic image restoration method based on multi-view-field segmentation | |
| CN113365103B (en) | Automatic bad frame detection method, device, equipment, storage medium and program product | |
| Chen et al. | Specular Removal of Industrial Metal Objects Without Changing Lighting Configuration | |
| Li et al. | Underwater image restoration using oblique gradient operator and light attenuation prior | |
| Gunawan et al. | Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer | |
| Wang et al. | Fast Blur Detection Algorithm for UAV Crack Image Sets | |
| CN109598227B (en) | Single-image mobile phone source re-identification method based on deep learning | |
| JP5873099B2 (en) | Method and apparatus for automatically repairing film | |
| CN113298857A (en) | Bearing defect detection method based on neural network fusion strategy | |
| Lee et al. | Visibility dehazing based on channel-weighted analysis and illumination tuning | |
| CN113095400A (en) | Deep learning model training method for machine vision defect detection | |
| Russo | New method for measuring the detail preservation of noise removal techniques in digital images | |
| Tang et al. | No-reference quality assessment for image sharpness and noise | |
| CN104809712B (en) | A kind of image fast repairing method based on rough set | |
| CN116912429B (en) | Three-dimensional reconstruction method and system for high-definition video IG (inter-group) material | |
| CN117745615A (en) | Substation scene-oriented ray difference elimination method | |
| CN117689652A (en) | Quality evaluation method for multi-camera image fusion |
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 |