CN109800718A - A kind of video portrait comparison method - Google Patents
A kind of video portrait comparison method Download PDFInfo
- Publication number
- CN109800718A CN109800718A CN201910060449.XA CN201910060449A CN109800718A CN 109800718 A CN109800718 A CN 109800718A CN 201910060449 A CN201910060449 A CN 201910060449A CN 109800718 A CN109800718 A CN 109800718A
- Authority
- CN
- China
- Prior art keywords
- sample
- video
- comparison
- file
- portrait
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000007689 inspection Methods 0.000 claims abstract description 18
- 239000000463 material Substances 0.000 claims abstract description 9
- 238000003032 molecular docking Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012797 qualification Methods 0.000 claims description 3
- 238000004321 preservation Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 229910017435 S2 In Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007873 sieving Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a kind of video portrait comparison methods, the method includes S1: obtaining sample video, sample video is pre-processed, the pretreatment corresponding with files, the initial survey of sample video, the normalized of sample video, sample video upload comprising sample video;Obtain sample file;S2: carrying out secondary treatment to sample video, sample file, and the secondary treatment includes that sequence of pictures and material screen, and is screened by material, selects the picture with special characteristic;S3: to after secondary treatment sample and sample inspection is compared;S4: survey report is generated according to the result of comparison inspection.The present invention meets the standard specifications of video portrait identification;The working efficiency of judicial expertise personnel is greatly improved, can be made from the arrangement of heavy video image, Classification Management, image making, preservation and document and save the plenty of time, efficiency improves 70% or more.
Description
Technical field
The present invention relates to field of image processing more particularly to a kind of video portrait comparison methods.
Background technique
Judicial expertise is the stringent very high process of accurate science, law court sentence reason in play it is very big
Effect, judicial expertise originally mainly carry out optical sieving and comparison by artificial one by one.
But due to artificial subjective participation, there are the following problems:
1) low efficiency needs one by one to find out image among this, it is also necessary to by one comparison;This is greatly
The efficiency for affecting judicial expertise, also consume a large amount of cost of labor;
2) result is disputed on, and due to artificial subjectivity, influences the reliability of result.
To solve the above-mentioned problems, the present invention proposes a kind of video portrait comparison method.
Summary of the invention
To solve the above-mentioned problems, the present invention proposes a kind of video portrait comparison method, and the method comprises the following steps,
S1: obtain sample video, sample video is pre-processed, it is described pretreatment comprising sample video it is corresponding with files,
The upload of the initial survey of sample video, the normalized of sample video, sample video;Obtain sample file;
S2: carrying out secondary treatment to sample video, sample file, and the secondary treatment includes that sequence of pictures and material screen,
It is screened by material, selects the picture with special characteristic;
S3: to after secondary treatment sample and sample inspection is compared;
S4: survey report is generated according to the result of comparison inspection.
Sample video concrete mode corresponding with files is, corresponding with sample video according to case volume information.
The initial survey of the sample video judges whether sample video is qualified;
If unqualified, sample video is reacquired;
If qualified, subsequent normalized is carried out.
The specific implementation of the normalized of the sample video is to carry out format normalizing to all sample videos
Change processing.
The normalized further include the relevant parameter of video is corrected it is unified, the parameter include coding ginseng
Number, code rate, timestamp.
In the S1, uploads and normalization is one of using the following two kinds strategy, 1) first uploaded locally, rear
Platform is normalized;2) it is first normalized, then is uploaded locally.
The policy selection of use is uploaded and normalized according to network environment and CPU usage.
The acquisition sample file can be video file, be also possible to picture file;If video file, then in S2
In, it is also necessary to the corresponding video file of sample file is serialized.
Initial survey in the S2 includes the successively serializing of image, picture making operation, the comparison inspection packet in the S3
Compared containing arranged side by side comparisons, overlapping comparison, docking, measurement compares, one of 3D portrait comparison or a variety of, to sample and sample into
Row compares and mark.
It is according to the specific method that the result of comparison inspection generates survey report in the S4, according to comparing and mark knot
Fruit carries out similarity judgement, exports qualification result data, sample and sample comprising mark in the monitoring result according to similarity
The overall situation of this and comprehensive assessment sample and sample portrait feature met with difference, makes certainty and uncertainty
Expert opinion, i.e. " certainly same ", " negative is same ", " tendency is certainly same ", " tendency negative is same ".
The beneficial effects of the present invention are: meet the standard specifications of video portrait identification;Follow video image identification
Process flow, and by initial survey, inspection, comparison inspection, document make the judicial mirror that several processes meet video image respectively
Fix the number of workers's workflow;The working efficiency of judicial expertise personnel is greatly improved, it can be from the whole of heavy video image
The plenty of time is saved in reason, Classification Management, image making, preservation and document production, and efficiency improves 70% or more.
Detailed description of the invention
Fig. 1 is structural schematic diagram of the invention;
Fig. 2 is the structural schematic diagram of the preferred embodiment of the present invention.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, now control attached drawing 1-2 illustrates this
The specific embodiment of invention.
A kind of video portrait comparison method, the method comprises the following steps,
S1: obtain sample video, sample video is pre-processed, it is described pretreatment comprising sample video it is corresponding with files,
The upload of the initial survey of sample video, the normalized of sample video, sample video;Obtain sample file;
S2: carrying out secondary treatment to sample video, sample file, and the secondary treatment includes that sequence of pictures and material screen,
It is screened by material, selects the picture with special characteristic;
S3: to after secondary treatment sample and sample inspection is compared;
S4: survey report is generated according to the result of comparison inspection.
Sample video concrete mode corresponding with files is, corresponding with sample video according to case volume information.
The initial survey of the sample video judges whether sample video is qualified;
If unqualified, sample video is reacquired;
If qualified, subsequent normalized is carried out.
The specific implementation of the normalized of the sample video is to carry out format normalizing to all sample videos
Change processing.
The normalized further include the relevant parameter of video is corrected it is unified, the parameter include coding ginseng
Number, code rate, timestamp.
In the S1, uploads and normalization is one of using the following two kinds strategy, 1) first uploaded locally, rear
Platform is normalized;2) it is first normalized, then is uploaded locally.
The policy selection of use is uploaded and normalized according to network environment and CPU usage.
Specifically, can be comprehensive to carry out strategy according to network environment, the occupancy of local cpu, the occupancy of backstage CPU
Selection;Its priority can be arbitrarily designated.For example, can according to backstage CPU usage, network environment, local cpu it is preferential
Grade sequence carries out policy selection, if CPU occupancy in backstage is excessively high, direct local cpu is handled;If backstage CPU occupies lower, net
Network environment is preferable, then is directly uploaded to background process;If backstage CPU is occupied, lower, network environment is poor, direct processing locality
After upload.
Preferably, video file is also possible to picture file;If video file, then according to the process of Fig. 2, in S2,
It also needs to serialize the corresponding video file of sample file.
Preferably, the initial survey in the S2 includes the successively serializing of image, picture making operation, the comparison in the S3
Examine compared comprising arranged side by side comparisons, overlapping comparison, docking, measurement compares, 3D portrait one of compares or a variety of, to sample with
Sample is compared and marks.
The object of the comparison and mark includes the face shapes such as eyebrow shape, eye shape, mouth shape, pinna shape
Shape and shape of face etc..
As a preferred solution, compared in comparison inspection as comparison arranged side by side, overlapping comparison, docking comparison, measurement,
One of 3D portrait comparison or a variety of selections, depend on monitoring result therein.
Under usual situation, selects 2-3 kind comparison method to be compared, if the similarity of comparison result reaches threshold value A, recognize
To be similar, and export analog result;
If the similarity of comparison result is not up to threshold value A, but reach threshold value B, is then re-introduced into other comparison inspection methods, then
It is secondary to test, and comprehensive new similarity result, provide analog result;
If the similarity of comparison result is not up to threshold value B, then it is assumed that dissimilar.
Wherein, threshold value A, threshold value B, threshold value C successively successively decrease.
Preferably, be according to the specific method that the result of comparison inspection generates survey report in the S4, according to comparing and
Annotation results carry out similarity judgement, export qualification result data, the inspection comprising mark in the monitoring result according to similarity
Material and sample, and the final result judged.
It is specific to obtain similarity judging result, a variety of alignments can also be directly carried out, and if only if all ratio other side
The similarity result that formula provides, is all larger than threshold value A, then it is assumed that and it is similar, under remaining situation, similitude is exported according to situation.
It should be noted that for simple description, therefore, it is stated as a systems for each embodiment of the method above-mentioned
The combination of actions of column, but those skilled in the art should understand that, the application is not limited by the described action sequence, because
For according to the application, certain some step be can be performed in other orders or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, related movement and unit not necessarily this Shen
It please be necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in some embodiment
Part, reference can be made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, ROM, RAM etc..
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (10)
1. a kind of video portrait comparison method, which is characterized in that the method comprises the following steps,
S1: obtain sample video, sample video is pre-processed, it is described pretreatment comprising sample video it is corresponding with files,
The upload of the initial survey of sample video, the normalized of sample video, sample video;Obtain sample file;
S2: carrying out secondary treatment to sample video, sample file, and the secondary treatment includes that sequence of pictures and material screen,
It is screened by material, selects the picture with special characteristic;
S3: to after secondary treatment sample and sample inspection is compared;
S4: survey report is generated according to the result of comparison inspection.
2. a kind of video portrait comparison method as described in claim 1, which is characterized in that pair of the sample video and files
The concrete mode answered is, corresponding with sample video according to case volume information.
3. a kind of video portrait comparison method as claimed in claim 2, which is characterized in that the initial survey of the sample video is sentenced
Whether disconnected sample video is qualified;
If unqualified, sample video is reacquired;
If qualified, subsequent normalized is carried out.
4. a kind of video portrait comparison method as claimed in claim 3, which is characterized in that at the normalization of the sample video
The specific implementation of reason is to carry out format normalized to all sample videos.
5. a kind of video portrait comparison method as claimed in claim 4, which is characterized in that the normalized further includes pair
The relevant parameter of video is corrected unified, and the parameter includes coding parameter, code rate, timestamp.
6. a kind of video portrait comparison method as claimed in claim 5, which is characterized in that in the S1, upload and normalize
Using one of the following two kinds strategy, 1) first uploaded locally, it is being normalized from the background;2) first returned locally
One changes, then is uploaded.
7. a kind of video portrait comparison method as claimed in claim 6, which is characterized in that occupied according to network environment and CPU
Rate is uploaded and is normalized the policy selection of use.
8. a kind of video portrait comparison method as described in claim 1, which is characterized in that the acquisition sample file can be
Video file is also possible to picture file;If video file, then in S2, it is also necessary to sample file corresponding video text
Part is serialized.
9. a kind of video portrait comparison method as described in one of claim 1-8, which is characterized in that the initial survey packet in the S2
Successively serializing, the picture making operation of image are included, the comparison inspection in the S3 includes comparison, overlapping comparison, docking arranged side by side
It compares, measure one of comparison, the comparison of 3D portrait or a variety of, sample and sample are compared and are marked.
10. a kind of video portrait comparison method as described in one of claim 1-8, which is characterized in that in the S4 according to than
The specific method for generating survey report to the result of inspection is, according to comparing and annotation results, similarity judgement is carried out, according to phase
Qualification result data are exported like degree, the sample comprising mark and sample and comprehensive assessment sample and sample in the monitoring result
The overall situation of this portrait feature met with difference, makes the expert opinion of certainty and uncertainty, i.e., " certainly same ",
" negative is same ", " tendency is certainly same ", " tendency negative is same ".
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910060449.XA CN109800718A (en) | 2019-01-22 | 2019-01-22 | A kind of video portrait comparison method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910060449.XA CN109800718A (en) | 2019-01-22 | 2019-01-22 | A kind of video portrait comparison method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109800718A true CN109800718A (en) | 2019-05-24 |
Family
ID=66560122
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910060449.XA Pending CN109800718A (en) | 2019-01-22 | 2019-01-22 | A kind of video portrait comparison method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109800718A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101324919A (en) * | 2007-06-15 | 2008-12-17 | 上海银晨智能识别科技有限公司 | Photograph video contrast method |
CN101655860A (en) * | 2009-09-16 | 2010-02-24 | 北京中盾安全技术开发公司 | Video aided analytical method for criminal investigation and case detection and system |
CN107423266A (en) * | 2017-07-17 | 2017-12-01 | 韩继召 | Expertise management method applied to judicial expertise/forensic science mechanism |
CN107729562A (en) * | 2017-11-09 | 2018-02-23 | 成都钰月科技有限责任公司 | The video data digging system and method for portrait automatic identification |
CN108052882A (en) * | 2017-11-30 | 2018-05-18 | 广东云储物联视界科技有限公司 | A kind of operating method of intelligent safety defense monitoring system |
-
2019
- 2019-01-22 CN CN201910060449.XA patent/CN109800718A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101324919A (en) * | 2007-06-15 | 2008-12-17 | 上海银晨智能识别科技有限公司 | Photograph video contrast method |
CN101655860A (en) * | 2009-09-16 | 2010-02-24 | 北京中盾安全技术开发公司 | Video aided analytical method for criminal investigation and case detection and system |
CN107423266A (en) * | 2017-07-17 | 2017-12-01 | 韩继召 | Expertise management method applied to judicial expertise/forensic science mechanism |
CN107729562A (en) * | 2017-11-09 | 2018-02-23 | 成都钰月科技有限责任公司 | The video data digging system and method for portrait automatic identification |
CN108052882A (en) * | 2017-11-30 | 2018-05-18 | 广东云储物联视界科技有限公司 | A kind of operating method of intelligent safety defense monitoring system |
Non-Patent Citations (2)
Title |
---|
中华人民共和国司法部司法鉴定管理局: "录像资料鉴定规范", 《司法鉴定规范》 * |
惠生武等: "《公安学科实验教学指导》", 31 July 2012 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104679818B (en) | A kind of video key frame extracting method and system | |
CN109284733A (en) | A kind of shopping guide's act of omission monitoring method based on yolo and multitask convolutional neural networks | |
US10726332B2 (en) | Generating a training model based on feedback | |
CN111401722B (en) | Intelligent decision method and intelligent decision system | |
CN110763685B (en) | Artificial intelligent detection method and device for DFB semiconductor laser chip surface defects | |
US11132618B2 (en) | Generating a training model based on feedback | |
CN110503198B (en) | Method, device, equipment and storage medium for acquiring neural network test report | |
CN108710576B (en) | Data set expansion method based on heterogeneous migration and software defect prediction method | |
CN107945003A (en) | Credit estimation method and device | |
CN109558298B (en) | Alarm execution frequency optimization method based on deep learning model and related equipment | |
CN108446688B (en) | Face image gender judgment method and device, computer equipment and storage medium | |
CN117011563B (en) | Road damage inspection cross-domain detection method and system based on semi-supervised federal learning | |
CN116563293B (en) | Photovoltaic carrier production quality detection method and system based on machine vision | |
CN110751191A (en) | Image classification method and system | |
CN112949456B (en) | Video feature extraction model training and video feature extraction method and device | |
CN110728315B (en) | Real-time quality control method, system and equipment | |
CN111090585B (en) | Crowd-sourcing task closing time automatic prediction method based on crowd-sourcing process | |
CN109800718A (en) | A kind of video portrait comparison method | |
CN115620083B (en) | Model training method, face image quality evaluation method, equipment and medium | |
Li et al. | Social network change detection using a genetic algorithm based back propagation neural network model | |
CN113591767A (en) | Method and device for determining image recognition evaluation value, storage medium and electronic device | |
CN115272249B (en) | Defect detection method, device, computer equipment and storage medium | |
CN117517176B (en) | Automatic processing method and device for flow cytometry data | |
CN111242235B (en) | Similar characteristic test data set generation method | |
Irokosu | Performance Comparison of CNN-based Semantic Segmentation on Indoor and Outdoor Scenes |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190524 |