Internet live broadcast defect pre-inspection system

Abstract

The present invention relates to an Internet live broadcast defect pre-inspection system, comprising: an intelligent detection mechanism, which is arranged in a live broadcast test terminal, and is used to identify the image area occupied by the flash eye shadow in the step-by-step mapping screen as the flash eye shadow existence area based on the color imaging characteristics of the flash eye shadow, and then judge whether the flash eye shadow contacts the first detection instruction or the second detection instruction corresponding to the host's facial contour based on various visual information of the flash eye shadow existence area; an on-site notification mechanism, which is used to execute a test notification action corresponding to the flash eye shadow contacting the host's facial contour when receiving the first detection instruction. Through the present invention, it is possible to judge whether the flash eye shadow contacts the host's facial contour based on various visual information of the flash eye shadow existence area, thereby completing the intelligent detection and on-site notification of the defective makeup of the host's facial flash eye shadow that is too close to the facial contour, causing the facial contour lines to be overly illuminated, thereby highlighting wrinkles and pores.

Description

Technical Field

[0001] The present invention relates to the field of live broadcast monitoring, and in particular to an Internet live broadcast defect pre-inspection system. Background Art

[0002] There are many types of live broadcasts, including but not limited to online show broadcasts and online information broadcasts. Online show broadcasts mainly focus on the host's talent display, daily life or interaction with fans; online information broadcasts focus on recording and broadcasting a certain event or activity through professional "photographers". In addition, live broadcasts also cover a variety of types such as pan-entertainment, pan-life, vertical fields (such as e-commerce, finance, and food), and the second dimension (such as virtual games, online robots, and VR).

[0003] Since the host is the most important display content in the live broadcast environment, the host's image is the object of great concern in every live broadcast room. For example, the host's image in the live broadcast screen can be optimized by selecting people with better image and temperament, stylists with high makeup skills, technicians with strong special effects design capabilities, and high-quality lighting facilities. The details of the optimization are reflected in all aspects. For example, it is necessary to avoid the host's facial flash eye shadow being too close to the facial contour, thereby over-illuminating the facial contour lines and highlighting the defects of wrinkles and pores. Obviously, the existing technology lacks a targeted high-precision detection mechanism. Summary of the invention

[0004] In order to solve the above-mentioned problems in the prior art, the present invention provides an Internet live broadcast defect pre-inspection system, which can identify the image area occupied by the flash eye shadow in a step-by-step mapping picture as the flash eye shadow existence area based on the color imaging characteristics of the flash eye shadow, identify the image area occupied by the facial contour in the step-by-step mapping picture as the contour existence area based on the color imaging characteristics of the facial contour, and use the arithmetic mean of each depth of field value corresponding to each pixel point in the flash eye shadow existence area after removing the maximum value and the minimum value as the first reference depth of field value, and use the arithmetic mean of each depth of field value corresponding to each pixel point in the contour existence area after removing the maximum value and the minimum value as the second reference depth of field value. When the difference between the first reference depth of field value and the second reference depth of field value is between 0 and the set depth of field limit and there are overlapping pixels in the flash eye shadow existence area and the contour existence area, a first detection instruction corresponding to the flash eye shadow contacting the host's facial contour is issued, otherwise, a second detection instruction corresponding to the flash eye shadow not contacting the host's facial contour is issued, thereby completing the intelligent detection and on-site notification of the defective makeup of the host's face in which the flash eye shadow is too close to the facial contour, resulting in excessive illumination of the facial contour lines and highlighting wrinkles and pores.

[0005] According to the present invention, a system for pre-checking defects in Internet live broadcast is provided, the system comprising:

[0006] The photoelectric collection mechanism is arranged in the live broadcast test terminal, and is used to perform a photoelectric sensing action on the host's face before the host goes live, so as to obtain and output a corresponding photoelectric sensing picture;

[0007] A step-by-step mapping mechanism, which is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, comprises a front-end mapping component, a mid-end mapping component and a terminal mapping component, and is used to step-by-step perform a gamma correction operation, a wavelet filtering operation and an image content enhancement operation based on logarithmic transformation on the received photoelectric sensing picture, so as to obtain and output a corresponding step-by-step mapping picture;

[0008] An intelligent detection mechanism is arranged in the live broadcast test terminal and connected to the step-by-step mapping mechanism, and is used to identify the image area occupied by the flash eye shadow in the step-by-step mapping screen as the flash eye shadow existence area based on the color imaging characteristics of the flash eye shadow, identify the image area occupied by the facial contour in the step-by-step mapping screen as the contour existence area based on the color imaging characteristics of the facial contour, take the arithmetic mean of each depth of field value corresponding to each pixel point in the flash eye shadow existence area after removing the maximum value and the minimum value as the first reference depth of field value, take the arithmetic mean of each depth of field value corresponding to each pixel point in the contour existence area after removing the maximum value and the minimum value as the second reference depth of field value, and when the difference between the first reference depth of field value and the second reference depth of field value is between 0 and the set depth of field limit and there are overlapping pixels in the flash eye shadow existence area and the contour existence area, issue a first detection instruction corresponding to the flash eye shadow contacting the host's facial contour, otherwise, issue a second detection instruction corresponding to the flash eye shadow not contacting the host's facial contour;

[0009] The on-site notification mechanism is arranged in the live broadcast test terminal and connected to the intelligent detection mechanism, and is used to execute the test notification action corresponding to the flash eye shadow contacting the anchor's facial contour when receiving the first detection instruction, and is also used to suspend the execution of the test notification action corresponding to the flash eye shadow contacting the anchor's facial contour when receiving the second detection instruction;

[0010] Among them, the step-by-step mapping mechanism is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, including a front-end mapping component, a mid-end mapping component and a terminal mapping component, which is used to step by step perform gamma correction operations, wavelet filtering operations and image content enhancement operations based on logarithmic transformation on the received photoelectric sensing picture to obtain and output the corresponding step-by-step mapping picture, including: the front-end mapping component is connected to the photoelectric collection mechanism, and is used to perform gamma correction operations on the received photoelectric sensing picture.

[0011] It can be seen that the present invention has at least the following three main inventive concepts:

[0012] Firstly: based on the color imaging features of the glitter eye shadow, an image area occupied by the glitter eye shadow in the step-by-step mapping picture is identified as a glitter eye shadow existing area; based on the color imaging features of the facial contour, an image area occupied by the facial contour in the step-by-step mapping picture is identified as a contour existing area;

[0013] Secondly: the arithmetic mean of the depth of field values ​​corresponding to the pixels in the area where the flash eye shadow exists is removed from the maximum and minimum values ​​is taken as the first reference depth of field value, and the arithmetic mean of the depth of field values ​​corresponding to the pixels in the area where the contour exists is removed from the maximum and minimum values ​​is taken as the second reference depth of field value;

[0014] Again: when the difference between the first reference depth of field value and the second reference depth of field value is between 0 and the set depth of field limit and there are overlapping pixels in the area where the flash eye shadow exists and the area where the contour exists, a first detection instruction corresponding to the flash eye shadow contacting the host's facial contour is issued; otherwise, a second detection instruction corresponding to the flash eye shadow not contacting the host's facial contour is issued, thereby completing the intelligent detection and on-site notification of the host's facial flash eye shadow being too close to the facial contour, over-illuminating the facial contour lines and highlighting the defective makeup of wrinkles and pores. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0016] Figure 1 The structure block diagram of the Internet live broadcast defect pre-inspection system according to the primary embodiment of the present invention is shown.

[0017] Figure 2 It is a structural block diagram of an Internet live broadcast defect pre-inspection system according to a secondary embodiment of the present invention.

[0018] Figure 3 The present invention is a structural block diagram of an Internet live broadcast defect pre-inspection system according to another embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will describe in detail an embodiment of the Internet live broadcast defect pre-check system of the present invention with reference to the accompanying drawings.

[0020] Figure 1 The structure block diagram of the Internet live broadcast defect pre-check system according to the primary embodiment of the present invention is shown, and the system includes:

[0021] The photoelectric collection mechanism is arranged in the live broadcast test terminal, and is used to perform a photoelectric sensing action on the host's face before the host goes live, so as to obtain and output a corresponding photoelectric sensing picture;

[0022] A step-by-step mapping mechanism, which is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, comprises a front-end mapping component, a mid-end mapping component and a terminal mapping component, and is used to step-by-step perform a gamma correction operation, a wavelet filtering operation and an image content enhancement operation based on logarithmic transformation on the received photoelectric sensing picture, so as to obtain and output a corresponding step-by-step mapping picture;

[0023] Specifically, the step-by-step mapping mechanism is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, including a front-end mapping component, a mid-end mapping component and a terminal mapping component, and is used to step-by-step perform a gamma correction operation, a wavelet filtering operation and an image content enhancement operation based on logarithmic transformation on the received photoelectric sensing picture to obtain and output a corresponding step-by-step mapping picture, including: selecting and using different ASIC chips to respectively implement the front-end mapping component, the mid-end mapping component and the terminal mapping component;

[0024] An intelligent detection mechanism is arranged in the live broadcast test terminal and connected to the step-by-step mapping mechanism, and is used to identify the image area occupied by the flash eye shadow in the step-by-step mapping screen as the flash eye shadow existence area based on the color imaging characteristics of the flash eye shadow, identify the image area occupied by the facial contour in the step-by-step mapping screen as the contour existence area based on the color imaging characteristics of the facial contour, take the arithmetic mean of each depth of field value corresponding to each pixel point in the flash eye shadow existence area after removing the maximum value and the minimum value as the first reference depth of field value, take the arithmetic mean of each depth of field value corresponding to each pixel point in the contour existence area after removing the maximum value and the minimum value as the second reference depth of field value, and when the difference between the first reference depth of field value and the second reference depth of field value is between 0 and the set depth of field limit and there are overlapping pixels in the flash eye shadow existence area and the contour existence area, issue a first detection instruction corresponding to the flash eye shadow contacting the host's facial contour, otherwise, issue a second detection instruction corresponding to the flash eye shadow not contacting the host's facial contour;

[0025] The on-site notification mechanism is arranged in the live broadcast test terminal and connected to the intelligent detection mechanism, and is used to execute the test notification action corresponding to the flash eye shadow contacting the anchor's facial contour when receiving the first detection instruction, and is also used to suspend the execution of the test notification action corresponding to the flash eye shadow contacting the anchor's facial contour when receiving the second detection instruction;

[0026] Specifically, the on-site notification mechanism is arranged in the live broadcast test terminal and connected to the intelligent detection mechanism, and is used to execute the test notification action corresponding to the flash eye shadow contacting the anchor's facial contour when receiving the first detection instruction, and is also used to suspend the execution of the test notification action corresponding to the flash eye shadow contacting the anchor's facial contour when receiving the second detection instruction. The on-site notification mechanism is a voice notification mechanism;

[0027] Among them, the step-by-step mapping mechanism is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, including a front-end mapping component, a mid-end mapping component and a terminal mapping component, which is used to step-by-step perform a gamma correction operation, a wavelet filtering operation and an image content enhancement operation based on logarithmic transformation on the received photoelectric sensing picture to obtain and output the corresponding step-by-step mapping picture, including: the front-end mapping component is connected to the photoelectric collection mechanism, and is used to perform a gamma correction operation on the received photoelectric sensing picture;

[0028] Among them, the step-by-step mapping mechanism is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, including a front-end mapping component, a mid-end mapping component and a terminal mapping component, which is used to step by step perform gamma correction operations, wavelet filtering operations and image content enhancement operations based on logarithmic transformation on the received photoelectric sensing picture to obtain and output the corresponding step-by-step mapping picture. It also includes: the mid-end mapping component is connected to the front-end mapping component to perform wavelet filtering operations on the received picture signal.

[0029] Figure 2 It is a structural block diagram of an Internet live broadcast defect pre-inspection system according to a secondary embodiment of the present invention.

[0030] Compared to Figure 1 , Figure 2 The Internet live broadcast defect pre-inspection system may also include:

[0031] A parameter configuration device, connected to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, respectively, for providing the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component with their respective required parameter configuration services;

[0032] The parameter configuration device is respectively connected to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, and is used to provide the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component with the parameter configuration services required by each of them, including: the parameter configuration device uses an IIC configuration bus to provide the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component with the parameter configuration services required by each of them;

[0033] The parameter configuration device uses the IIC configuration bus to provide the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component with the parameter configuration services required by each of them, including: the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component have different IIC configuration addresses respectively;

[0034] The intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively have different IIC configuration addresses, including: the different IIC configuration addresses respectively have by the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component are binary numerical representation modes;

[0035] And wherein, the different IIC configuration addresses respectively possessed by the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component are in a binary numerical representation mode, including: the byte lengths of the different IIC configuration addresses respectively possessed by the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component are equal.

[0036] Figure 3 The present invention is a structural block diagram of an Internet live broadcast defect pre-inspection system according to another embodiment of the present invention.

[0037] Compared to Figure 1 , Figure 3 The Internet live broadcast defect pre-inspection system may also include:

[0038] A positioning operation device, connected to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, respectively, for providing positioning services to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively;

[0039] Wherein, the positioning operation device is respectively connected with the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, and is used to provide positioning services for the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively, including: the positioning operation device adopts the GPS positioning mechanism to provide GPS positioning services for the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively;

[0040] And wherein, the positioning operation device is respectively connected to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, and is used to provide positioning services for the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively, including: the positioning operation device adopts the Beidou positioning mechanism to provide Beidou positioning services for the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively.

[0041] In addition, in the Internet live broadcast defect pre-inspection system, a step-by-step mapping mechanism is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, including a front-end mapping component, a mid-end mapping component and an end mapping component, which are used to step by step perform gamma correction operations, wavelet filtering operations and image content enhancement operations based on logarithmic transformation on the received photoelectric sensing picture to obtain and output the corresponding step-by-step mapping picture. It also includes: the end mapping component is connected to the mid-end mapping component, which is used to perform image content enhancement operations based on logarithmic transformation on the received picture signal to obtain and output the corresponding step-by-step mapping picture.

[0042] The Internet live broadcast defect pre-inspection system of the present invention can solve the technical problem in the prior art of lacking an identification mechanism for defective makeup such as the glitter eye shadow on the host's face being too close to the facial contour, over-illuminating the facial contour lines and thus highlighting wrinkles and pores. The system can identify the image area occupied by the glitter eye shadow in the step-by-step mapping screen as the glitter eye shadow existence area based on the color imaging characteristics of the glitter eye shadow, and then determine whether the glitter eye shadow contacts the host's facial contour based on various visual information of the glitter eye shadow existence area, thereby completing intelligent detection and on-site notification of defective makeup such as the glitter eye shadow on the host's face being too close to the facial contour, over-illuminating the facial contour lines and thus highlighting wrinkles and pores.

[0043] In the foregoing specification, the invention has been described with reference to specific exemplary embodiments of the invention. It will be apparent, however, that various modifications and changes may be made thereto without departing from the broad spirit and scope of the invention as set forth in the appended claims. The specification should therefore be regarded as illustrative rather than restrictive.

Claims

1. An Internet live broadcast defect pre-inspection system, characterized in that: The system comprises: The photoelectric collection mechanism is arranged in the live broadcast test terminal, and is used to perform a photoelectric sensing action on the host's face before the host goes live, so as to obtain and output a corresponding photoelectric sensing picture; A step-by-step mapping mechanism, which is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, comprises a front-end mapping component, a mid-end mapping component and a terminal mapping component, and is used to step-by-step perform a gamma correction operation, a wavelet filtering operation and an image content enhancement operation based on logarithmic transformation on the received photoelectric sensing picture, so as to obtain and output a corresponding step-by-step mapping picture; an intelligent detection mechanism, arranged in the live broadcast test terminal and connected to the step-by-step mapping mechanism, for identifying the image area occupied by the flash eye shadow in the step-by-step mapping screen as the flash eye shadow existence area based on the color imaging characteristics of the flash eye shadow, identifying the image area occupied by the facial contour in the step-by-step mapping screen as the contour existence area based on the color imaging characteristics of the facial contour, taking the arithmetic mean of each depth of field value corresponding to each pixel point in the flash eye shadow existence area after removing the maximum value and the minimum value as the first reference depth of field value, taking the arithmetic mean of each depth of field value corresponding to each pixel point in the contour existence area after removing the maximum value and the minimum value as the second reference depth of field value, and issuing a first detection instruction corresponding to the state that the flash eye shadow is in contact with the host's facial contour when the difference between the first reference depth of field value and the second reference depth of field value is between 0 and a set depth of field limit and there are overlapping pixels in the flash eye shadow existence area and the contour existence area, otherwise, issuing a second detection instruction corresponding to the state that the flash eye shadow is not in contact with the host's facial contour; The on-site notification mechanism is arranged in the live broadcast test terminal and connected to the intelligent detection mechanism, and is used to execute the test notification action corresponding to the state that the flash eye shadow contacts the anchor's facial contour when receiving the first detection instruction, and is also used to suspend the execution of the test notification action corresponding to the state that the flash eye shadow contacts the anchor's facial contour when receiving the second detection instruction; Among them, the step-by-step mapping mechanism is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, including a front-end mapping component, a mid-end mapping component and a terminal mapping component, which is used to step by step perform gamma correction operations, wavelet filtering operations and image content enhancement operations based on logarithmic transformation on the received photoelectric sensing picture to obtain and output the corresponding step-by-step mapping picture, including: the front-end mapping component is connected to the photoelectric collection mechanism, and is used to perform gamma correction operations on the received photoelectric sensing picture.

2. The Internet live broadcast defect pre-check system according to claim 1, characterized in that: A step-by-step mapping mechanism is arranged in the live broadcast test terminal and connected to the photoelectric collection mechanism, including a front-end mapping component, a mid-end mapping component and a terminal mapping component, which is used to step-by-step perform gamma correction operations, wavelet filtering operations and image content enhancement operations based on logarithmic transformation on the received photoelectric sensing picture to obtain and output the corresponding step-by-step mapping picture. It also includes: the mid-end mapping component is connected to the front-end mapping component to perform wavelet filtering operations on the received picture signal.

3. The Internet live broadcast defect pre-check system according to claim 2, characterized in that: The system further comprises: A parameter configuration device, connected to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, respectively, for providing the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component with their respective required parameter configuration services; Among them, the parameter configuration device is respectively connected to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, and is used to provide the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component with their respective required parameter configuration services, including: the parameter configuration device uses the IIC configuration bus to provide the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component with their respective required parameter configuration services.

4. The Internet live broadcast defect pre-check system as claimed in claim 3, characterized in that: The parameter configuration device uses the IIC configuration bus to provide the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component with their respective required parameter configuration services, including: the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component have different IIC configuration addresses respectively.

5. The Internet live broadcast defect pre-check system as claimed in claim 4, characterized in that: The intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively have different IIC configuration addresses, including: the different IIC configuration addresses of the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component are binary numerical representation modes.

6. The Internet live broadcast defect pre-check system according to claim 5, characterized in that: The different IIC configuration addresses respectively possessed by the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component are in a binary numerical representation mode, including: the byte lengths of the different IIC configuration addresses respectively possessed by the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component are equal.

7. The Internet live broadcast defect pre-check system as claimed in claim 2, characterized in that: The system further comprises: The positioning operation device is respectively connected to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, and is used to provide positioning services for the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively.

8. The Internet live broadcast defect pre-check system according to claim 7, characterized in that: The positioning operation device is respectively connected to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, and is used to provide positioning services for the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively, including: the positioning operation device adopts the GPS positioning mechanism to provide GPS positioning services for the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively.

9. The Internet live broadcast defect pre-checking system according to claim 7, characterized in that: The positioning operation device is respectively connected to the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component, and is used to provide positioning services for the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively, including: the positioning operation device adopts the Beidou positioning mechanism to provide Beidou positioning services for the intelligent detection mechanism, the front-end mapping component, the mid-end mapping component and the terminal mapping component respectively.

Images