CN112132794A

CN112132794A - Text positioning method, device and equipment for audit video and readable storage medium

Info

Publication number: CN112132794A
Application number: CN202010960493.9A
Authority: CN
Inventors: 沈隆; 范渊
Original assignee: Hangzhou Dbappsecurity Technology Co Ltd
Current assignee: Hangzhou Dbappsecurity Technology Co Ltd
Priority date: 2020-09-14
Filing date: 2020-09-14
Publication date: 2020-12-25

Abstract

The application relates to a text positioning method, a text positioning device, text positioning equipment and a computer readable storage medium for an audit video. The text positioning method for the audit video comprises the following steps: acquiring a text query instruction input by a user in an input box corresponding to an audit video; determining a video frame image of an audit video; extracting character images in the video frame images by adopting an angular point algorithm; identifying character information corresponding to the character query instruction in the character image and identifying a time point corresponding to the character information; and positioning the text information according to the time point. Through the application, the problem of low auditing efficiency of the fort machine in the related technology is solved, and the auditing efficiency of the fort machine is improved.

Description

Text positioning method, device and equipment for audit video and readable storage medium

Technical Field

The present application relates to the field of video processing, and in particular, to a text positioning method, apparatus, device, and computer-readable storage medium for auditing videos.

Background

The operation and maintenance auditing system is a uniform operation and maintenance entry of user assets (a database, a server, network equipment, storage equipment and the like), and achieves the purpose of risk control through identity authentication, authority control and operation auditing. The most core function of the operation and maintenance auditing system is operation and maintenance + auditing, and the operation and maintenance is mainly supported by a protocol and comprises SSH, TELNET, RDP, VNC, FTP, SFTP and the like; the main types of auditing are character type session auditing, graphic session auditing and database session auditing, and by checking auditing contents, tracing can be realized, and comprehensive cognition on system risks can be realized.

The current mature operation and maintenance auditing system can reach the degree of providing effective information for an administrator quickly in character type session auditing, but in graphic auditing, more information query needs to be carried out by means of video playback, a large amount of time and energy can be consumed, and accurate positioning can not be carried out on an operation command and a time point. Meanwhile, the audit of the returned statement information cannot be effectively identified and audited.

In the related technology, the bastion machine can only audit and block the command line input by operation and maintenance or management personnel during operation and maintenance, but cannot effectively identify and block the returned content, and the corresponding operation and maintenance process and the content can only be viewed through the content in video playback. The fortress machine is equivalent to only doing forward proxy in the operation and maintenance process, effective control cannot be conducted on the content returned by the asset end, the audit video playback is mainly used for viewing at present, and the audit efficiency and the operation and maintenance safety are reduced by the mode.

At present, an effective solution is not provided aiming at the problem of low auditing efficiency of the bastion machine in the related technology.

Disclosure of Invention

The embodiment of the application provides a character positioning method, a character positioning device and a computer readable storage medium for an audit video, and aims to at least solve the problem of low audit efficiency of bastion machines in the related technology.

In a first aspect, an embodiment of the present application provides a text positioning method for an audit video, which is applied to a bastion machine, and includes:

acquiring a text query instruction input by a user in an input box corresponding to an audit video;

determining a video framing image of the audit video;

extracting character images in the video frame images by adopting an angular point algorithm;

identifying character information corresponding to the character query instruction in the character image, and identifying a time point corresponding to the character information;

and positioning the text information according to the time point.

In some embodiments, the extracting text images from the video frame images by using a corner point algorithm includes:

carrying out corner detection on the video frame images to obtain corner images;

preprocessing the corner image to obtain a preprocessed image, wherein the preprocessing comprises the following steps: binarization treatment, expansion treatment and corrosion treatment;

and extracting the character image in the preprocessed image.

In some embodiments, the preprocessing the corner image to obtain a preprocessed image includes:

performing corner filtering on the corner image;

and preprocessing the angle image subjected to the angular point filtering to obtain a preprocessed image.

In some embodiments, identifying text information in the text image corresponding to the text query instruction comprises:

extracting character information in the character image;

converting the character information in the character image into character information in a preset format;

and searching the text information corresponding to the text query instruction from the text information in the preset format.

In some embodiments, after identifying text information in the text image corresponding to the text query instruction and identifying a time point corresponding to the text information, the method further includes:

and storing the character information and the time point corresponding to the character information.

In some of these embodiments, the corner point algorithm comprises: harris corner algorithm.

In some embodiments, after the text information is located according to the time point, the method further includes:

and displaying the text information and the time point corresponding to the text information.

In a second aspect, an embodiment of the present application further provides a text positioning device for an audit video, which is applied to a bastion machine, and includes:

the first acquisition module is used for acquiring a text query instruction input by a user in an input box corresponding to the audit video;

the determining module is used for determining a video frame image of the audit video;

the first extraction module is used for extracting character images in the video frame images by adopting an angular point algorithm;

the first identification module is used for identifying the character information corresponding to the character query instruction in the character image and identifying the time point corresponding to the character information;

and the positioning module is used for positioning the text information according to the time point.

In a third aspect, an embodiment of the present application provides a text positioning apparatus for auditing videos, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor, when executing the computer program, implements the text positioning method for auditing videos as described in the first aspect.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the text positioning method for auditing videos as described in the first aspect.

Compared with the related art, the text positioning method, the text positioning device, the text positioning equipment and the computer readable storage medium for the audit video, provided by the embodiment of the application, are used for acquiring the text query instruction input by the user in the input box corresponding to the audit video; determining a video frame image of an audit video; extracting character images in the video frame images by adopting an angular point algorithm; identifying character information corresponding to the character query instruction in the character image and identifying a time point corresponding to the character information; according to the time point, the character information is positioned, the problem that the auditing efficiency of the bastion machine in the related technology is low is solved, and the auditing efficiency of the bastion machine is improved.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is a block diagram of a hardware structure of a terminal of a text positioning method for an audit video according to an embodiment of the present application;

FIG. 2 is a flow diagram of a text-locating method of auditing videos according to an embodiment of the present application;

FIG. 3 is a flow diagram of a text-locating method for auditing videos according to a preferred embodiment of the present application;

FIG. 4 is a block diagram of a text-locating device for auditing videos according to an embodiment of the present application;

fig. 5 is a schematic diagram of a hardware structure of a text-locating device for auditing videos according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any creative effort belong to the protection scope of the present application.

It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.

Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.

The method provided by the embodiment can be executed in a terminal, a computer or a similar operation device. Taking an example of running on a terminal, fig. 1 is a hardware structure block diagram of the terminal of the text positioning method for auditing videos according to the embodiment of the present application. As shown in fig. 1, the terminal may include one or more (only one shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and optionally, a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the terminal. For example, the terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.

The memory 104 can be used for storing computer programs, for example, software programs and modules of application software, such as a computer program corresponding to the text positioning method for auditing videos in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-mentioned method. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.

The embodiment also provides a character positioning method of the audit video, which can be applied to the bastion machine and a character recognition system of the bastion machine, and the application to the bastion machine is taken as an example below. Fig. 2 is a flowchart of a text-locating method for auditing videos according to an embodiment of the present application, where the flowchart includes the following steps, as shown in fig. 2:

step S201, obtaining a text query instruction input by a user in an input box corresponding to the audit video.

In this step, the user can input the text to be searched according to the input box. By the method, the user can conveniently input the corresponding text query instruction.

It should be noted that: the bastion machine is used in a specific network environment, and in order to ensure that the network and the data are not invaded and damaged by external and internal users, various technical means are used for monitoring and recording the operation behaviors of operation and maintenance personnel on the devices such as servers, network devices, safety devices, databases and the like in the network, so as to realize centralized alarming, timely processing, auditing and responsibility determination.

Step S202, determining video frame images of the audit video.

In this step, in order to facilitate the positioning of the text information, the audit video may be framed into a plurality of video framing images, and at the same time, the time point corresponding to each video framing image may also be determined during framing. The point in time may be a point in time of a video framing image in an audit video.

Step S203, extracting character images in the video frame images by adopting an angular point algorithm.

It should be noted that the corner point algorithm is a character detection method based on edges, and the principle of corner point detection is as follows: if either gray scale direction is shifted around, the image of the pixel that proves to produce a large change is a corner point. And the corner algorithm can determine whether the corner is a corner by setting a threshold T when determining the corner, then extracting an operator based on the character corner which is a point feature of a basic signal, obtaining a matrix N connected with correlation coefficients, obtaining a first-order curvature of the correlation data as a characteristic value of the matrix N through a series of preset algorithms, and comparing curvature values of the matrix N and the first-order curvature to determine whether the matrix N is the corner.

In this step, the corner algorithm may be a Harris corner algorithm, or may be another corner algorithm capable of implementing the present scheme.

The corner detection using the Harris algorithm can be implemented in the following manner.

Firstly, the gradient I of the video frame image g in the x direction and the y direction is obtained_x，I_yAs shown in formulas (1-1), (1-2) and (1-3):

then, a semi-positive definite symmetric matrix N can be obtained from the obtained gradient, as shown in formulas (1-4):

then, the moment is determinedEigenvalues of array N

According to

To make a corresponding determination:

(1) if it is

Are all small, it means that g is flat at that point and there are no edges or corner points.

(2) If it is

A large value and a small value indicate that g is not flat at the point, becomes a ridge, where there is a small shift perpendicular to the ridge, and will consequently change significantly, which may be a corner point.

(3) If it is

Is large, it means that g moves slightly in any direction at the point, g will change significantly, and the point may be a corner point.

And finally, counting the angular point quantity, as shown in the formula (1-5):

where Det (N) is the determinant of matrix N and Tra (N) is the trace of matrix N.

And then comparing the obtained R with a preset threshold value T:

(1) r < T, then the point is not a corner point;

(2)

the point is a corner point.

In the related art, most characters are ORC (Optical Character Recognition), and the Character Recognition rate of a large number of OCR Character Recognition algorithms is not high, and some lower characters are even lower than 50%; meanwhile, the supported asset system is high in limitation, and the support for the versions above the windows server2016 is poor.

In the application, the method for detecting the corner by using the corner algorithm also improves the recognition rate of the ORC characters.

In some embodiments, step S203 may be implemented by: carrying out corner detection on the video frame images to obtain corner images; preprocessing the angle point image to obtain a preprocessed image, wherein the preprocessing comprises the following steps: binarization treatment, expansion treatment and corrosion treatment; and extracting the character image in the preprocessed image. In this embodiment, after the binarization of the image of the angle points, the expansion operation is performed to connect the angle points in the image together, and then the erosion operation is performed to flatten the connected angle points, so that the character areas and the background generate obvious edges, thereby realizing the detection of the angle points of the video frame image and determining the character image in the video frame image.

It should be noted that there may be some non-text corners in the corners identified by Harris algorithm. Since the embodiment of the present application recognizes the text added by the user at a later time, not the text in the background of the video image, some features of the artificial subtitles may be utilized to locate the text.

The artificial captions are mainly characterized by the following points:

(1) aggregation property. The characters added later by people are often distributed in a horizontal or vertical rectangular frame in a centralized way. Therefore, a small range often contains more Harris corners.

(2) The artificial subtitles are single in color selection and greatly different in brightness from the background. Therefore, after binarization is carried out, the angular points in the region are linked together through expansion operation, and then the linked angular points are flattened through corrosion operation, so that the character region and the background generate obvious edges.

(3) The characters are spaced at a certain interval, and the interval is a fixed value.

(4) The basic character of the text, and the most important character of the text which can use the Harris algorithm, is that the text contains rich corner information.

Therefore, in some embodiments, based on the features of the artificial subtitles, a corner filtering method may be used for identifying text corners and non-text corners, that is, a corner image is preprocessed, and obtaining a preprocessed image includes: carrying out corner filtering on the corner image; and preprocessing the angle image subjected to the angular point filtering to obtain a preprocessed image. By the method, the non-character corners in the corner image can be filtered out, so that the character recognition rate is further improved.

In this embodiment, the corner filtering may be implemented by:

step A, if the size of an image is w × h, defining a for loop i as 0: w, j is 0: h, f (i, j) represents whether a corner point exists at the point (i, j), 1 is present, 0 is absent, and the formula (1-6) shows that:

when cnt (i) < a fixed value, i represents i rows without corner points.

Step B, the aggregation of the artificial subtitles can associate that a rectangular frame with a certain size around the point (i, j) is possibly a required text area, as shown in the formula (3-9):

and C, repeating the step B.

The text regions (w 1: w2, h 1: h2) can be obtained by the above method. w1 is the starting point in the x direction, and w2 is the end point in the x direction; h1 is the starting point in the y direction and h2 is the ending point in the y direction. Displaying a text area in the original image, namely the text area required by the user, setting the color value of the text area to be 255 (white), namely the image needing to be repaired next, and setting the color of the text area to be 204 (gray), namely the mark area of the image needing to be repaired next, namely the target area f _ mask.

In order to improve the rigor of character recognition, a verification work of a character region can be further added, the character region obtained in the process of the embodiment is traversed, and if the sum of the number of corner points in the character region is less than a certain fixed value, the character region is not the required character region and can be omitted.

Step S204, identifying the character information corresponding to the character query instruction in the character image, and identifying the time point corresponding to the character information.

In this step, the text image obtained in step S203 is identified, and corresponding text information and a time point corresponding to the text information are queried from the text image according to the text query instruction, where the time point may be the same time point as a time point corresponding to a video frame image corresponding to the text information. So as to locate the text message.

In some of the embodiments, text information in the text image is extracted; converting the character information in the character image into character information in a preset format; and searching the text information corresponding to the text query instruction from the text information in the preset format. In this embodiment, the predetermined format may be a character of the predetermined format for easy searching.

Step S205, positioning the character information according to the time point.

Based on the steps S201 to S205, the character image in the video frame image is extracted through the corner algorithm, then the character information corresponding to the character query instruction in the character image is identified, the time point corresponding to the character information is identified, finally the character information is positioned according to the time point, the checking is not needed according to the audit video playback, the problem that the auditing efficiency of the bastion machine in the related technology is low is solved, and the auditing efficiency of the bastion machine is improved.

In some embodiments, after identifying the text information corresponding to the text query instruction in the text image and identifying the time point corresponding to the text information, the method may further include storing the text information and the time point corresponding to the text information. By the method, when the subsequent user inquires the text information, the time point corresponding to the text information can be directly called from the database, and the positioning process of the text information is simplified.

In some embodiments, after the text information is located according to the time point, the text information and the time point corresponding to the text information may be further displayed. In this way, the monitoring is convenient for the user.

Through the embodiment, when the auditor checks the audit video, the bastion machine can automatically call the corner algorithm, extract characters from the audit video and record the time point of the video corresponding to the characters. In the embodiment, the auditor only needs to input the character instruction to be searched in the input field, and the character recognition system of the bastion machine can locate the time point corresponding to the audit video, so that the auditor can conveniently check the audit video, and the audit efficiency and the coverage are improved.

The embodiments of the present application are described and illustrated below by means of preferred embodiments.

Fig. 3 is a flow chart of a text location method for an audit video according to a preferred embodiment of the present application, which is applied to a text recognition system of a bastion machine. As shown in fig. 3, the preferred process includes the following steps:

step S301, acquiring a text query instruction input by a user in an input box corresponding to the audit video.

And step S302, performing video framing on the audit video to obtain a video framing image.

Step S303, Harris corner detection is carried out on the video frame image to obtain a corner image.

And step S304, carrying out binarization on the angular point image obtained in the step S303, and then carrying out expansion first and corrosion later on the image to obtain a character image.

Step S305, locating the character information corresponding to the character query instruction in the character image.

Step S306, converting the text information into a preset format and storing the text information.

In the embodiment, a function module of the character recognition system is added and embedded into an auditing interface of the bastion machine, when an auditor checks the video, the function module is automatically called to recognize the video characters, and the result is returned to the query module, so that the auditor can conveniently check the video.

Based on the above embodiments, the embodiment of the application is a character recognition algorithm based on an angular point algorithm, operational characters in a video can be effectively recognized by combining an operation and maintenance audit video and the angular point algorithm, document output (namely character information) is formed, a query module (namely an input column) can also be provided, an auditor can query according to actual required en character content, a video recording time point of a character corresponding to a corresponding character query instruction is quickly located, the audit efficiency is greatly improved, meanwhile, the audit granularity is greatly refined, and the tracing is more efficient and faster.

The embodiment also provides a text positioning device for an audit video, which is used for implementing the above embodiments and preferred embodiments, and the description of the text positioning device is omitted. As used hereinafter, the terms "module," "unit," "subunit," and the like may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 4 is a block diagram of a text-locating apparatus for auditing videos according to an embodiment of the present application, as shown in fig. 4, the apparatus including:

the obtaining module 41 is configured to obtain a text query instruction input by a user in an input box corresponding to the audit video;

a determining module 42, coupled to the obtaining module 41, for determining a video framing image of the audit video;

an extracting module 43, coupled to the determining module 42, configured to extract text images in the video frame images by using an angular point algorithm;

an identifying module 44, coupled to the extracting module 43, for identifying text information in the text image corresponding to the text query instruction, and identifying a time point corresponding to the text information;

and a positioning module 45, coupled to the identifying module 44, for positioning the text message according to the time point.

In some of these embodiments, the extraction module 43 includes: the detection unit is used for carrying out corner detection on the video frame images to obtain corner images; the preprocessing unit is used for preprocessing the angle image to obtain a preprocessed image, wherein the preprocessing comprises the following steps: binarization treatment, expansion treatment and corrosion treatment; and the first extraction unit is used for extracting the character image in the preprocessed image.

In some of these embodiments, the pre-processing module comprises: the filtering subunit is used for carrying out corner filtering on the corner image; and the preprocessing subunit is used for preprocessing the angle image subjected to the angular point filtering to obtain a preprocessed image.

In some of these embodiments, identification module 44 includes: the second extraction unit is used for extracting the character information in the character image; the conversion unit is used for converting the character information in the character image into the character information in a preset format; and the searching unit is used for searching the text information corresponding to the text query instruction from the text information in the preset format.

In some of these embodiments, the apparatus further comprises: and the storage module is used for storing the text information and the time point corresponding to the text information.

In some of these embodiments, the apparatus further comprises: and the display module is used for displaying the text information and the time point corresponding to the text information.

The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.

In addition, the text positioning method for auditing videos in the embodiment of the present application described in conjunction with fig. 2 can be implemented by text positioning equipment for auditing videos. Fig. 5 is a schematic diagram of a hardware structure of a text-locating device for auditing videos according to an embodiment of the present application.

A text-locating device for auditing videos may include a processor 51 and a memory 52 having stored thereon computer program instructions.

Specifically, the processor 51 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.

Memory 52 may include, among other things, mass storage for data or instructions. By way of example, and not limitation, memory 52 may include a Hard Disk Drive (Hard Disk Drive, abbreviated to HDD), a floppy Disk Drive, a Solid State Drive (SSD), flash memory, an optical Disk, a magneto-optical Disk, magnetic tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 52 may include removable or non-removable (or fixed) media, where appropriate. The memory 52 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 52 is a Non-Volatile (Non-Volatile) memory. In particular embodiments, Memory 52 includes Read-Only Memory (ROM) and Random Access Memory (RAM). The ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), Electrically rewritable ROM (EAROM), or FLASH Memory (FLASH), or a combination of two or more of these, where appropriate. The RAM may be a Static Random-Access Memory (SRAM) or a Dynamic Random-Access Memory (DRAM), where the DRAM may be a Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), an Extended data output Dynamic Random-Access Memory (EDODRAM), a Synchronous Dynamic Random-Access Memory (SDRAM), and the like.

The memory 52 may be used to store or cache various data files that need to be processed and/or used for communication, as well as possible computer program instructions executed by the processor 51.

The processor 51 may read and execute the computer program instructions stored in the memory 52 to implement any of the above-described embodiments of text-based methods for auditing video.

In some of these embodiments, the text-locating device that audits the video may also include a communication interface 53 and bus 50. As shown in fig. 5, the processor 51, the memory 52, and the communication interface 53 are connected via the bus 50 to complete mutual communication.

The communication interface 53 is used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present application. The communication interface 53 may also enable communication with other components such as: the data communication is carried out among external equipment, image/data acquisition equipment, a database, external storage, an image/data processing workstation and the like.

Bus 50 includes hardware, software, or both to couple the components of the text-locating device that audits video to each other. Bus 50 includes, but is not limited to, at least one of the following: data Bus (Data Bus), Address Bus (Address Bus), Control Bus (Control Bus), Expansion Bus (Expansion Bus), and Local Bus (Local Bus). By way of example, and not limitation, Bus 50 may include an Accelerated Graphics Port (AGP) or other Graphics Bus, an Enhanced Industry Standard Architecture (EISA) Bus, a Front-Side Bus (Front Side Bus), an FSB (FSB), a Hyper Transport (HT) Interconnect, an ISA (ISA) Bus, an InfiniBand (InfiniBand) Interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a microchannel Architecture (MCA) Bus, a PCI (Peripheral Component Interconnect) Bus, a PCI-Express (PCI-X) Bus, a Serial Advanced Technology Attachment (SATA) Bus, a Video Electronics Bus (audio Association) Bus, abbreviated VLB) bus or other suitable bus or a combination of two or more of these. Bus 50 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.

The text positioning device for the audit video can execute the text positioning method for the audit video in the embodiment of the application based on the acquired text query instruction input by the user in the input box corresponding to the audit video, so that the text positioning method for the audit video described in combination with fig. 2 is realized.

In addition, in combination with the text positioning method for the audit video in the above embodiment, the embodiment of the present application may provide a computer-readable storage medium to implement. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the above embodiments of a text-locating method for auditing videos.

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A character positioning method for an audit video is applied to a bastion machine and is characterized by comprising the following steps:

determining a video framing image of the audit video;

and positioning the text information according to the time point.

2. The method of claim 1, wherein extracting text images from the video framing images using a corner algorithm comprises:

and extracting the character image in the preprocessed image.

3. The method of claim 2, wherein the pre-processing the corner image to obtain a pre-processed image comprises:

performing corner filtering on the corner image;

4. The method of claim 1, wherein identifying textual information in the textual image that corresponds to the textual query instruction comprises:

extracting character information in the character image;

5. The method of claim 1, wherein after identifying text information in the text image corresponding to the text query instruction and identifying a time point corresponding to the text information, the method further comprises:

6. The text-spotting method of auditing videos of claim 1 where the corner-point algorithm comprises: harris corner algorithm.

7. The text-locating method for auditing videos of claim 1, wherein after locating the text information according to the time point, the method further comprises:

8. The utility model provides a text positioner of audit video, is applied to fort machine, its characterized in that includes:

9. A word locating device for auditing videos, comprising a memory, a processor and a computer program stored on the memory and run on the processor, characterized in that the processor, when executing the computer program, implements a word locating method for auditing videos according to any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which program, when executed by a processor, implements a text-locating method for auditing videos according to any one of claims 1 to 7.