CN107958220B - Face library compression processing method based on face recognition and intelligent device thereof - Google Patents
Face library compression processing method based on face recognition and intelligent device thereof Download PDFInfo
- Publication number
- CN107958220B CN107958220B CN201711282530.XA CN201711282530A CN107958220B CN 107958220 B CN107958220 B CN 107958220B CN 201711282530 A CN201711282530 A CN 201711282530A CN 107958220 B CN107958220 B CN 107958220B
- Authority
- CN
- China
- Prior art keywords
- face
- face image
- image information
- snapshot
- information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The application discloses a face library compression processing method based on face recognition and an intelligent device thereof, wherein the method comprises the following steps: acquiring snapshot face image information in a video stream; identifying a face library according to the snapshot face image information to obtain comparison face image information matched with the snapshot face image information in the face library; and under the condition that the image quality of the snapshot face image information is higher than that of the contrast face image information, replacing the snapshot face image information with the contrast face image information to complete compression. The mode of replacing the contrast image in the face library by the image with higher image quality is adopted, the aims of reducing the storage amount and compressing the face library are achieved, and the technical problem of huge storage amount caused by too many face pictures in the related technology is solved.
Description
Technical Field
The application relates to the field of face recognition, in particular to a face library compression processing method based on face recognition and an intelligent device thereof.
Background
Video monitoring plays an increasingly large role in the field of modern security and protection, and the application range is increasingly wide, for example, in the safe city plan which is vigorously popularized in China in recent years, the video monitoring is relied on to play a great role in the field of public security and protection.
However, in the video monitoring system based on face recognition of most camera manufacturers and software manufacturers, face images are mainly detected by adopting a face detection and tracking technology and then stored in the system, and then snapshot is performed when necessary, and a face library is retrieved. The method has the defect that if the same person appears in one camera more than once, the same person can shoot and store a plurality of face pictures in a certain time, so that the storage capacity is huge, and therefore, a face library compression processing method based on face recognition and an intelligent device thereof are urgently needed to solve the technical problem that the storage capacity is huge due to too many face pictures shot in the related technology.
Disclosure of Invention
The application mainly aims to provide a face library compression processing method based on face recognition and an intelligent device thereof, so as to solve the technical problem of huge storage capacity caused by too many face pictures taken by a snapshot in the related technology.
The application provides a face library compression processing method based on face recognition, which comprises the following steps:
acquiring snapshot face image information in a video stream;
identifying in a face library according to the snapshot face image information to obtain comparison face image information matched with the snapshot face image information in the face library;
comparing the image quality of the snapshot face image information with the image quality of the comparison face image information; and
and if the quality of the information image of the snapshot face image is higher than that of the information image of the comparison face image, replacing the information of the snapshot face image with the information of the comparison face image.
Further, the method for acquiring the information of the snapshot face image in the video stream further includes:
decoding the video stream to obtain a plurality of snap-shot pictures;
marking the time anchor point range of the picture;
and carrying out face recognition on the plurality of pictures, and extracting the pictures with face characteristics as the information of the snapshot face image.
Further, the method identifies a face library according to the snapshot face image information to obtain comparison face image information matched with the snapshot face image information in the face library, and further includes:
dividing a time axis of the face library into a plurality of periodic segments, wherein the time length of each periodic segment is assigned;
acquiring the corresponding periodic segment on the time axis of the face library as a target periodic segment according to the marked time anchor point range;
and identifying the snapshot face image information and the face library on the target period segment to obtain the comparison face image information matched with the snapshot face image information on the target period segment.
Further, in the case that the quality of the information image of the snap-shot face image is higher than that of the information image of the contrast face image, the information of the snap-shot face image is substituted for the information of the contrast face image to complete compression, the method further comprises:
replacing the compared face image information in the face library with the snapshot face image for storage;
and storing the time anchor point range of the snapshot human face image.
Further, the real-time video stream is obtained through a video monitoring system.
Further, the face recognition is biological recognition of the face.
The present application further provides an intelligent device, including:
the acquisition module is used for acquiring the information of the snapshot face image in the video stream;
the recognition module is used for recognizing a face library according to the snapshot face image information to obtain comparison face image information matched with the snapshot face image information in the face library;
the comparison module is used for comparing the image quality of the snapshot face image information with the image quality of the comparison face image information;
and the replacing module is used for replacing the information of the snapshot face image with the information of the comparison face image to complete compression under the condition that the quality of the information image of the snapshot face image is higher than that of the information image of the comparison face image.
Further, the decoding module is used for decoding the video stream to obtain a plurality of captured pictures;
the marking module is used for marking the time anchor point range of the picture;
the recognition module is also used for carrying out face recognition detection on the plurality of pictures and extracting the pictures with face characteristics as the snapshot face image information.
Further, the segmentation module is used for segmenting the time axis of the face library into a plurality of periodic segments, wherein the time length of each periodic segment is assigned;
the acquisition module is used for acquiring the corresponding periodic segment on the time axis of the face library as a target periodic segment according to the marked time anchor point range;
the recognition module is further configured to recognize the captured face image information and the face library on the target period segment, and obtain the comparison face image information matched with the captured face image information on the target period segment.
Further, the storage module is configured to replace the comparative face image information in the face library with the snapshot face image for storage; and the time anchor point range of the snapshot human face image is also stored.
In the embodiment of the application, the mode of replacing the contrast image in the face library by the image with higher image quality is adopted, so that the purposes of reducing the storage amount and compressing the face library are achieved, the technical effect of extracting the picture with the highest image quality for storage when a plurality of face pictures are captured is realized, and the technical problem of huge storage amount caused by too many captured face pictures in the related technology is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a schematic diagram of an embodiment of a work flow chart of a compression processing method of the present application; and
fig. 2 is a schematic diagram of a smart device architecture diagram of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, the method includes steps S101 to S104 as follows:
step S101, obtaining snapshot face image information in a video stream;
step S102, identifying in a face library according to the snap face image information to obtain comparative face image information matched with the snap face image information in the face library;
step S103, comparing the image quality of the snap face image information and the image quality of the comparison face image information, and
and step S104, if the quality of the information image of the snapshot face image is higher than that of the information image of the comparison face image, replacing the information of the snapshot face image with the information of the comparison face image.
Firstly, the face image information in the acquired video stream is mainly used for identifying the face, and can be adjusted according to specific requirements in practical application to capture other image targets (such as arms, accessories and the like) needing to be monitored. Then, the face library is identified according to the captured face image information to obtain comparison face image information matched with the captured face image information in the face library, specifically, the face library is a face picture library (or a picture library of other main bodies) which is previously connected in series by a time axis, and retrieval and comparison are performed according to the captured face image information to identify a matching item (namely, the comparison face image information). And comparing the image quality of the snapshot face image information with the image quality of the comparison face image information, wherein the comparison at the moment is the image quality. And selecting a picture with better quality to perform subsequent storage work. If the information quality of the snapshot face image is high, the snapshot face image can be replaced. In the process, the face library only keeps the number of the original face library for the face images of the same person. The problem that the face image of the same person is continuously increased is avoided, and the function of compressing the face library is realized. Because the face library in the related art will be continuously increased according to the newly acquired face image information, in this embodiment, the data takes the picture as a carrier. The method can also be expanded to the field of compression of signals and data, and the information of the snapshot face image and the information of the comparison face image are not limited to only pictures, and can also be in the form of data and signals.
In another optional embodiment, the acquiring of the snapshot facial image information in the video stream includes:
step a: decoding the video stream to obtain a plurality of snap-shot pictures;
step b: marking the time anchor point range of the picture;
step c: and carrying out face recognition detection on the plurality of pictures, and extracting the pictures with face characteristics as the snapshot face image information.
Secondly, in addition to the acquisition of the image itself in the above embodiment, the temporal anchor point range in the video stream is marked for the following steps that may be used. Specifically, the video stream is decoded to obtain a plurality of pictures, where the pictures include pictures with human face features and pictures without human face features. (i.e., background-only pictures) while the pictures are being acquired, marking their specific temporal nodes on the time axis in the video stream, i.e., the temporal anchor point ranges;
and after the face recognition detection is carried out on the picture information, taking the picture with the face characteristics as the snapshot face image information in the embodiment, and carrying out the subsequent steps.
In another optional embodiment, the recognizing a face library according to the captured face image information to obtain comparative face image information in the face library, where the comparative face image information is matched with the captured face image information, includes:
the method comprises the following steps: dividing a time axis of the face library into a plurality of periodic segments, wherein the time length of each periodic segment is assigned;
step two: acquiring the corresponding periodic segment on the time axis of the face library as a target periodic segment according to the marked time anchor point range;
step three: and identifying the snapshot face image information and the face library on the target period segment to obtain the comparison face image information matched with the snapshot face image information on the target period segment.
Thirdly, in addition to the steps in the above embodiment, in order to prevent that only one picture (or possibly one piece of data) is stored in the same person in the whole video stream, the time axis of the whole video stream is divided into a plurality of period segments, specifically, the time axis of the face library is divided into a plurality of period segments, wherein the time length of each period segment is assigned (the assignment is assumed to be Q); acquiring a period segment corresponding to the whole time axis of the video stream according to the time anchor point range marked in the step, wherein the period segment is the target period segment; in this embodiment, it is obvious that the time axis of the face library should correspond to the time axis of the video stream. Thus, data (i.e. pictures or data information) of a person in different periods is periodically stored in the whole video stream.
In another optional embodiment, in the case that the image quality of the snap face image information is higher than that of the contrast face image information, the snap face image information replaces the contrast face image information to complete compression,
replacing the compared face image information in the face library with the snapshot face image for storage;
and storing the time anchor point range of the snapshot human face image.
In addition to the compression process described above, its temporal anchor range should also be recorded for back-check and reference.
In another alternative embodiment, comprising:
in the related art, the video stream may be obtained in real time by a video monitoring system, or the information stream may be obtained in other manners.
In another alternative embodiment, comprising:
the face recognition is a face biometric recognition technology. Of course, other methods may be used for face recognition.
The specific implementation mode is as follows:
and acquiring the real-time video stream through the video monitoring system, decoding the video stream to obtain a plurality of pictures, and marking the time anchor point range of the plurality of pictures one by one. And carrying out face recognition on the plurality of pictures, reserving the picture with the face characteristics as the face image information for the next step. The step of marking the time anchor point range can also be placed after the step of face recognition, the processing amount is reduced, only the pictures with the face features are marked, and the pictures without the face features are abandoned. Converting the picture with the human face characteristics into the information of the snapshot human face image; the face image information can exist in the form of pictures and can also be related corresponding data information.
And searching a face library according to the snapshot face image information, wherein a data model which corresponds to the snapshot face image information and can be compared is adopted in a data mode in the face library. And finding out the data (namely the comparison face image information) of the same person corresponding to the matching, and if the data quality in the snapshot face image information is higher (specifically, the image quality is higher), replacing and updating the corresponding comparison face image information in the face library. In addition, if the image quality of the comparison facial image information is higher, replacement updating is abandoned, and the original comparison facial image information is still kept.
Based on the basic method, important pictures or data are omitted in order to prevent that only one required picture or related data is replaced and updated in one video stream. Therefore, the face library is divided into period segments, and the same main body (the picture or data information of the same face) can be stored in each period segment. And comparing, replacing and storing the period segments corresponding to the video stream by using the marks of the time anchor point range of the picture.
From the above description, it can be seen that the present invention achieves the following technical effects:
in the embodiment of the application, the mode of replacing the contrast image in the face library by the image with higher image quality is adopted, so that the purposes of reducing the storage amount and compressing the face library are achieved, the technical effect of extracting the picture with the highest image quality for storage when a plurality of face pictures are captured is realized, and the technical problem of huge storage amount caused by too many captured face pictures in the related technology is solved.
In addition, the situation that the same target only stores one picture or data in the video stream and omits important information is prevented by carrying out periodic segment segmentation on the face library.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present invention, there is also provided an intelligent apparatus for implementing the compression method, as shown in fig. 2, the apparatus includes:
the acquisition module 101 is used for acquiring snapshot face image information in a video stream;
the recognition module 102 is configured to recognize a face library according to the captured face image information to obtain comparative face image information in the face library, where the comparative face image information is matched with the captured face image information;
the comparison module 103 is used for comparing the image quality of the snapshot facial image information with the image quality of the comparison facial image information;
and the replacing module 104 is used for replacing the information of the snapshot face image with the information of the comparison face image to complete compression under the condition that the quality of the information image of the snapshot face image is higher than that of the information image of the comparison face image.
Further, the decoding module is used for decoding the video stream to obtain a plurality of captured pictures;
the marking module is used for marking the time anchor point range of the picture;
the recognition module 102 is further configured to perform face recognition detection on the plurality of pieces of picture information, and extract the picture with the face feature as the captured face image information.
Further, the segmentation module is used for segmenting the time axis of the face library into a plurality of periodic segments, wherein the time length of each periodic segment is assigned;
the obtaining module 101 is configured to obtain the period segment corresponding to the time axis of the face library as a target period segment according to the marked time anchor point range;
the recognition module is further configured to recognize the captured face image information and the face library on the target period segment, and obtain the comparison face image information matched with the captured face image information on the target period segment.
Further, the storage module is configured to replace the comparative face image information in the face library with the snapshot face image for storage; and the time anchor point range of the snapshot human face image is also stored.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The invention relates to a snapshot face library compression method and a snapshot face library compression system based on face recognition, which utilize a face recognition biological recognition technology to perform matching retrieval on a historical face snapshot within a period of time, if the historical face is matched, two face images are compressed into one image (one with high image quality is used for replacing one with low quality), and meanwhile, time anchor point range data of the snapshot are recorded and used for conducting reverse check by retrieving corresponding stored video stream data through a time anchor point range.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (6)
1. A face library compression processing method based on face recognition is characterized by comprising the following steps:
acquiring snapshot face image information in a video stream;
identifying in a face library according to the snapshot face image information to obtain comparison face image information matched with the snapshot face image information in the face library;
comparing the image quality of the snapshot face image information with the image quality of the comparison face image information; and
if the quality of the information image of the snap-shot face image is higher than that of the information image of the contrast face image, replacing the information of the snap-shot face image with the information of the contrast face image, and acquiring the information of the snap-shot face image in the video stream further comprises:
decoding the video stream to obtain a plurality of snap-shot pictures;
marking the time anchor point range of the picture;
carrying out face recognition on a plurality of pictures, and extracting the pictures with face characteristics as the information of the snapshot face images; the step of recognizing a face library according to the snapshot face image information to obtain comparison face image information matched with the snapshot face image information in the face library further comprises the following steps: dividing a time axis of the face library into a plurality of periodic segments, wherein the time length of the periodic segments is preset;
acquiring the corresponding periodic segment on the time axis of the face library as a target periodic segment according to the marked time anchor point range;
and identifying the snapshot face image information and the face library on the target period segment to obtain the comparison face image information matched with the snapshot face image information on the target period segment.
2. The method of claim 1, wherein when the quality of the captured facial image information is higher than that of the contrast facial image information, the captured facial image information is substituted for the contrast facial image information to complete compression, and the method further comprises:
replacing the compared face image information in the face library with the snapshot face image for storage;
and storing the time anchor point range of the snapshot face image information.
3. The face library compression processing method based on face recognition as claimed in claim 1, wherein the video stream is obtained in real time by a video surveillance system.
4. The face library compression processing method based on face recognition according to claim 1, wherein the face recognition is biometric recognition of a face.
5. A smart device, comprising:
the acquisition module is used for acquiring the information of the snapshot face image in the video stream;
the recognition module is used for recognizing a face library according to the snapshot face image information to obtain comparison face image information matched with the snapshot face image information in the face library;
the comparison module is used for comparing the image quality of the snapshot face image information with the image quality of the comparison face image information;
the replacing module is used for replacing the information of the snapshot face image with the information of the comparison face image to complete compression under the condition that the quality of the information image of the snapshot face image is higher than that of the information image of the comparison face image;
the decoding module is used for decoding the video stream to obtain a plurality of captured pictures;
the marking module is used for marking the time anchor point range of the picture;
the recognition module is also used for carrying out face recognition detection on the plurality of pictures and extracting the pictures with face characteristics as the snapshot face image information;
the segmentation module is used for segmenting the time axis of the face library into a plurality of periodic segments, wherein the time length of each periodic segment is assigned;
the acquisition module is used for acquiring the corresponding periodic segment on the time axis of the face library as a target periodic segment according to the marked time anchor point range;
the recognition module is further configured to recognize the captured face image information and the face library on the target period segment, and obtain the comparison face image information matched with the captured face image information on the target period segment.
6. The smart device of claim 5, wherein;
the storage module is used for replacing the comparative face image information in the face library with the snapshot face image for storage; and the time anchor point range of the snapshot human face image is also stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711282530.XA CN107958220B (en) | 2017-12-06 | 2017-12-06 | Face library compression processing method based on face recognition and intelligent device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711282530.XA CN107958220B (en) | 2017-12-06 | 2017-12-06 | Face library compression processing method based on face recognition and intelligent device thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107958220A CN107958220A (en) | 2018-04-24 |
| CN107958220B true CN107958220B (en) | 2021-03-12 |
Family
ID=61958230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711282530.XA Active CN107958220B (en) | 2017-12-06 | 2017-12-06 | Face library compression processing method based on face recognition and intelligent device thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107958220B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230112822A1 (en) * | 2021-10-08 | 2023-04-13 | Realtek Semiconductor Corporation | Character recognition method, character recognition device and non-transitory computer readable medium |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110719398B (en) * | 2018-07-12 | 2021-07-20 | 浙江宇视科技有限公司 | A method and device for determining a face capture object |
| CN111161206A (en) * | 2018-11-07 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Image capturing method, monitoring camera and monitoring system |
| CN109903412A (en) * | 2019-02-01 | 2019-06-18 | 北京清帆科技有限公司 | A kind of intelligent check class attendance system based on face recognition technology |
| CN111831841B (en) * | 2019-04-19 | 2023-09-05 | 杭州海康威视数字技术股份有限公司 | Information retrieval method, device, electronic equipment and storage medium |
| CN110196924B (en) * | 2019-05-31 | 2021-08-17 | 银河水滴科技(宁波)有限公司 | Method and device for constructing characteristic information base and method and device for tracking target object |
| JP7238738B2 (en) * | 2019-11-19 | 2023-03-14 | トヨタ自動車株式会社 | Image processing system, processing device, relay device and program |
| CN112560772B (en) * | 2020-12-25 | 2024-05-14 | 北京百度网讯科技有限公司 | Face recognition method, device, equipment and storage medium |
| CN113283305B (en) * | 2021-04-29 | 2024-03-26 | 百度在线网络技术（北京）有限公司 | Face recognition method, device, electronic equipment and computer readable storage medium |
| CN114491126A (en) * | 2021-12-31 | 2022-05-13 | 飞诺门阵(北京)科技有限公司 | Image library updating method, system, electronic equipment and storage medium |
| CN115050078B (en) * | 2022-07-01 | 2025-02-28 | 济南博观智能科技有限公司 | A method, device, electronic device and storage medium for reporting facial images |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6188452B2 (en) * | 2013-06-28 | 2017-08-30 | キヤノン株式会社 | Image processing apparatus, image processing method, and program |
| CN103942525A (en) * | 2013-12-27 | 2014-07-23 | 高新兴科技集团股份有限公司 | Real-time face optimal selection method based on video sequence |
| CN105389566B (en) * | 2015-11-13 | 2018-09-11 | 广东欧珀移动通信有限公司 | Fingerprint identification method, the update method of fingerprint template, device and mobile terminal |
| CN105938552B (en) * | 2016-06-29 | 2020-04-24 | 北京旷视科技有限公司 | Face recognition method and device for automatically updating base map |
| CN106548148A (en) * | 2016-10-26 | 2017-03-29 | 北京意泰物联软件科技有限公司 | Method and system for identifying unknown face in video |
| CN107358146B (en) * | 2017-05-22 | 2018-05-22 | 深圳云天励飞技术有限公司 | Method for processing video frequency, device and storage medium |
-
2017
- 2017-12-06 CN CN201711282530.XA patent/CN107958220B/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230112822A1 (en) * | 2021-10-08 | 2023-04-13 | Realtek Semiconductor Corporation | Character recognition method, character recognition device and non-transitory computer readable medium |
| US11922710B2 (en) * | 2021-10-08 | 2024-03-05 | Realtek Semiconductor Corporation | Character recognition method, character recognition device and non-transitory computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107958220A (en) | 2018-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107958220B (en) | Face library compression processing method based on face recognition and intelligent device thereof | |
| CN109166261B (en) | Image processing method, device and equipment based on image recognition and storage medium | |
| EP2864930B1 (en) | Self learning face recognition using depth based tracking for database generation and update | |
| US9710490B2 (en) | System, apparatus, method, program and recording medium for processing image | |
| CN104573111B (en) | A structured storage and pre-retrieval method for pedestrian data in surveillance video | |
| CN111163259A (en) | Image capturing method, monitoring camera and monitoring system | |
| CN109195011B (en) | Video processing method, device, equipment and storage medium | |
| CN110290346B (en) | Bidding video acquisition method based on intelligent video analysis | |
| CN104463117A (en) | Sample collection method and system used for face recognition and based on video | |
| JP2006031678A (en) | Image processing | |
| CN110647822A (en) | High-altitude parabolic behavior identification method and device, storage medium and electronic equipment | |
| CN114139015A (en) | Video storage method, device, equipment and medium based on key event identification | |
| Asim et al. | A key frame based video summarization using color features | |
| CN111241928A (en) | Face recognition base optimization method, system, equipment and readable storage medium | |
| CN109800329B (en) | Monitoring method and device | |
| CN109740003A (en) | A kind of archiving method and device | |
| CN110705469A (en) | Face matching method and device and server | |
| CN109857891A (en) | A kind of querying method and device | |
| CN109800318A (en) | A kind of archiving method and device | |
| CN102693292B (en) | RFID-based Video Processing and Fast Retrieval Method for Inland Ships | |
| Komagal et al. | Real time background subtraction techniques for detection of moving objects in video surveillance system | |
| CN111177436B (en) | Face feature retrieval method, device and equipment | |
| CN111738042A (en) | Identification method, device and storage medium | |
| CN109783663B (en) | Archiving method and device | |
| CN104182959A (en) | Target searching method and target searching device |
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 |