Man-machine interaction system applying image component acquisition

Abstract

The invention relates to a man-machine interaction system applying image component acquisition. The man-machine interaction system comprises a mark processing mechanism, a content input mechanism, a multiple enhancement mechanism, a content judgment device and a transfer operation device. The man-machine interaction system applying image component acquisition is intelligent in design and simple and convenient to operate.

Description

Technical Field

[0001] The present invention relates to the field of human-computer interaction, and in particular to a human-computer interaction system using image component acquisition. Background Art

[0002] Human-computer interaction is a discipline that studies the interactive relationship between a system and its users. It mainly studies the interactive relationship between humans and machines, and usually uses image acquisition to feed back human information to the machine.

[0003] The invention with application publication number CN109889753A provides a binocular camera system and its application method, which uses a camera module to collect video images and inputs them into a video image processing subsystem; the video image processing subsystem processes the video images in two ways, and uses a resolution conversion module to convert the resolution, converting the 4K image into 2K; the second image passes through the processor, and is processed by calling the visual source library opencv for skin color inspection, and then converted and output by the resolution conversion module to a 2K image; the two images are output to the video image processing subsystem through the subsystem output end, and the processed video image is obtained, completing the detection of the video image. However, the processing of information in human-computer interaction needs to be further strengthened. Summary of the invention

[0004] In order to overcome the technical problems in the prior art, the present invention proposes a human-computer interaction system using image component acquisition, the system comprising: A marking processing mechanism is used to mark the live broadcasting room broadcasting during the night time as a key inspection live broadcasting room for indecent inspection, and is also used to mark the live broadcasting room broadcasting during the day time as a non-key inspection live broadcasting room for non-indecent inspection; A content input mechanism, connected to the mark processing mechanism, is used to input the live image of the key inspection live room to obtain the on-site input image; A multiple enhancement mechanism, comprising a distortion processing device, an artifact removal device and a real-time filtering device, wherein the distortion processing device is connected to the content input mechanism and is used to perform distortion correction processing on the received on-site input image to obtain and output a corresponding distortion processed image, the artifact removal device is connected to the distortion processing device and is used to perform artifact removal processing on the received distortion processed image to obtain and output a corresponding artifact removed image, and the real-time filtering device is connected to the artifact removal device and is used to perform Gaussian high-pass filtering processing on the received artifact removed image to obtain and output a corresponding real-time filtered image; a content determination device connected to the multiple enhancement mechanism and comprising a directional detection device, a numerical analysis device and a determination execution device, wherein the numerical analysis device is respectively connected to the directional detection device and the determination execution device, wherein the content determination device is used to obtain a reference cyan brightness value, a reference magenta brightness value, a reference yellow brightness value and a reference black brightness value of each pixel column of the pattern occupied by the host in the real-time filtered image, and the reference yellow brightness value of each pixel column corresponding to the host is set to be the arithmetic mean of multiple yellow brightness values ​​obtained by removing the maximum value and the minimum value of each yellow brightness value corresponding to each pixel point on the pixel column, and the content determination device is further used to issue a suspected indecent play instruction when the difference between the reference yellow brightness value of each pixel column corresponding to the host and the upper limit threshold of the yellow brightness value interval corresponding to the human skin color is less than or equal to the set difference limit, otherwise, issue a normal play instruction; The transfer operation device is connected to the content determination device and is used to mark the key inspection live room corresponding to the on-site recorded image as a manual inspection live room to transfer it to the manual inspection queue when receiving a suspected indecent playback instruction.

[0005] The human-computer interaction system for applying image component acquisition of the present invention is intelligently designed and easy to operate. Since the skin color inspection of the human imaging area of ​​the host can be set for the live studio broadcasting live at night time, when the entire human imaging area is close to the upper threshold of the yellow brightness value interval corresponding to the human skin color, the live studio broadcasting live at night time is marked as a manual inspection live studio to be transferred to the manual inspection queue for manual strict inspection, thereby ensuring the inspection efficiency while avoiding missed inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The embodiments of the present invention will be described below with reference to the accompanying drawings.

[0007] Figure 1 It is a block diagram of the internal structure of a human-computer interaction system using image component acquisition according to Embodiment 1 of the present invention.

[0008] Figure 2 It is a block diagram of the internal structure of a human-computer interaction system using image component acquisition according to Embodiment 2 of the present invention.

[0009] Figure 3 1 is a block diagram of the internal structure of a human-computer interaction system using image component acquisition according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0010] One application of human-computer interaction is live broadcasting. The threshold for online live broadcasting is low, the number of participants is large, and people from all walks of life can participate. As a result, the quality of the anchors is uneven, the videos are mixed, and vulgar and indecent images are frequently seen. Vulgarity and indecent content are a major cancer of online live broadcasting and have become a cash cow for some illegal live broadcasting businesses. These illegal live broadcasting businesses rely on live broadcasting content such as indecent performances on online live broadcasting platforms to earn income, which has a bad impact on the healthy growth of minors and the entire live broadcasting environment.

[0011] In the prior art, indecent live broadcasts are generally broadcast at night, and the review of indecent live broadcasts requires a large amount of manpower and material resources to be arranged at night. That is, it is necessary to use human eyes to check the skin color of the host's human imaging area in the live broadcast room during the night time. Obviously, this review mode consumes too much manpower and material resources at night, and it is difficult to ensure detection accuracy.

[0012] The implementation scheme of the human-computer interaction system using image component acquisition of the present invention will be described in detail below with reference to the accompanying drawings.

[0013] Implementation 1 Figure 1 The internal structure block diagram of the human-computer interaction system using image component acquisition according to Embodiment 1 of the present invention is shown, and the system includes: A marking processing mechanism is used to mark the live broadcasting room broadcasting during the night time as a key inspection live broadcasting room for indecent inspection, and is also used to mark the live broadcasting room broadcasting during the day time as a non-key inspection live broadcasting room for non-indecent inspection; For example, the marking processing mechanism is used to mark the live broadcast room broadcasting during the night time period as a key inspection live broadcast room for indecent inspection, and is also used to mark the live broadcast room broadcasting during the day time period as a non-key inspection live broadcast room for non-indecent inspection, including: the marking processing mechanism has a built-in timing operation unit, which is used to provide timing service information for the day time period; A content input mechanism, connected to the mark processing mechanism, is used to input the live image of the key inspection live room to obtain the on-site input image; A multiple enhancement mechanism, comprising a distortion processing device, an artifact removal device and a real-time filtering device, wherein the distortion processing device is connected to the content input mechanism and is used to perform distortion correction processing on the received on-site input image to obtain and output a corresponding distortion processed image, the artifact removal device is connected to the distortion processing device and is used to perform artifact removal processing on the received distortion processed image to obtain and output a corresponding artifact removed image, and the real-time filtering device is connected to the artifact removal device and is used to perform Gaussian high-pass filtering processing on the received artifact removed image to obtain and output a corresponding real-time filtered image; a content determination device connected to the multiple enhancement mechanism and comprising a directional detection device, a numerical analysis device and a determination execution device, wherein the numerical analysis device is respectively connected to the directional detection device and the determination execution device, wherein the content determination device is used to obtain a reference cyan brightness value, a reference magenta brightness value, a reference yellow brightness value and a reference black brightness value of each pixel column of the pattern occupied by the host in the real-time filtered image, and the reference yellow brightness value of each pixel column corresponding to the host is set to be the arithmetic mean of multiple yellow brightness values ​​obtained by removing the maximum value and the minimum value of each yellow brightness value corresponding to each pixel point on the pixel column, and the content determination device is further used to issue a suspected indecent play instruction when the difference between the reference yellow brightness value of each pixel column corresponding to the host and the upper limit threshold of the yellow brightness value interval corresponding to the human skin color is less than or equal to the set difference limit, otherwise, issue a normal play instruction; A transfer operation device connected to the content determination device is used to mark the key inspection live room corresponding to the on-site recorded image as a manual inspection live room to transfer it to the manual inspection queue when receiving a suspected indecent broadcast instruction; Wherein, the mobile operating device is also used to mark the key inspection live broadcast room corresponding to the on-site recorded image as a non-key inspection live broadcast room when receiving a normal playback instruction; Among them, the content determination device is used to obtain the reference cyan brightness value, reference magenta brightness value, reference yellow brightness value and reference black brightness value of each pixel column of the pattern occupied by the set anchor in the real-time filtered image. The reference yellow brightness value of each pixel column corresponding to the set anchor is the arithmetic mean of multiple yellow brightness values ​​obtained by removing the maximum and minimum values ​​of each yellow brightness value corresponding to each pixel point on the pixel column, including: each pixel point on the pixel column has a cyan brightness value, a magenta brightness value, a yellow brightness value and a black brightness value in the CMYK color space.

[0014] Implementation 2 Figure 2 It is a block diagram of the internal structure of a human-computer interaction system using image component acquisition according to Embodiment 2 of the present invention.

[0015] Compared to Figure 1 , Figure 2 The human-computer interaction system for image component acquisition can also include the following components: a heat analysis device, connected to the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, respectively, for measuring the instantaneous internal heat of each of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device; Wherein, the heat analysis device is respectively connected with the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, and is used to respectively measure the instantaneous internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, including: the heat analysis device includes a plurality of heat measurement units, which are respectively connected with the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, so as to complete the measurement of the instantaneous internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device; Wherein, the heat analysis device comprises a plurality of heat measurement units, which are used to be respectively connected with the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device to complete the respective measurement of the instant internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, including: the plurality of heat measurement units are a plurality of heat sensors, which are used to be respectively connected with the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device to complete the respective measurement of the instant internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device; Wherein, the plurality of heat measurement units are a plurality of heat sensors, which are used to be connected to the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device respectively, so as to complete the respective measurement of the instant internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device respectively, including: the internal structures of the plurality of heat sensors are the same; And wherein, the multiple heat measuring units are multiple heat sensors, which are used to be connected to the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device respectively, so as to complete the separate measurement of the real-time internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device respectively, and also include: the multiple heat sensors have the same heat measurement upper limit value and heat measurement lower limit value.

[0016] Implementation 3 Figure 3 1 is a block diagram of the internal structure of a human-computer interaction system using image component acquisition according to Embodiment 3 of the present invention.

[0017] Compared to Figure 1 , Figure 3 The human-computer interaction system for image component acquisition can also include the following components: an embedded processor, connected to the plurality of heat measurement units of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, respectively, for realizing on-site configuration of the real-time working mode of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device; Wherein, the embedded processor is respectively connected to the plurality of heat measurement units of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, and is used to realize the on-site configuration of the real-time working mode of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, including: the embedded processor is a processor with an ARM 13 core; And wherein, the embedded processor is respectively connected to multiple heat measurement units of the content entry mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, and is used to realize the on-site configuration of the real-time working mode of the content entry mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, including: the embedded processor has built-in registers, timers and static storage devices.

[0018] In addition, in the human-computer interaction system using image component acquisition, the content determination device is used to obtain the reference cyan brightness value, reference magenta brightness value, reference yellow brightness value and reference black brightness value of each pixel column of the pattern occupied by the set anchor in the real-time filtered image. The reference yellow brightness value of each pixel column corresponding to the set anchor is the arithmetic mean of multiple yellow brightness values ​​obtained by removing the maximum and minimum values ​​of each yellow brightness value corresponding to each pixel point on the pixel column, and also includes: the cyan brightness value, magenta brightness value, yellow brightness value and black brightness value of each pixel point on the pixel column in the CMYK color space are all between 0-255.

[0019] The technical features of the present invention are as follows: A: For live broadcast rooms broadcasting at night, skin color inspection is performed on the host's human imaging area. When the entire human imaging area is close to the upper threshold of the yellow brightness value range corresponding to the human skin color, the live broadcast room broadcasting at night is marked as a manual inspection live broadcast room and transferred to the manual inspection queue for manual strict inspection, thereby improving the inspection efficiency of indecent broadcast rooms; B: obtaining reference cyan brightness value, reference magenta brightness value, reference yellow brightness value and reference black brightness value of each pixel column of the pattern occupied by the host in the real-time filtered image, setting the reference yellow brightness value of each pixel column corresponding to the host to be the arithmetic mean of multiple yellow brightness values ​​obtained by removing the maximum and minimum values ​​of each yellow brightness value corresponding to each pixel point on the pixel column, and the content judgment device is further used to issue a suspected indecent play instruction when the difference between the reference yellow brightness value of each pixel column corresponding to the host and the upper limit threshold of the yellow brightness value interval corresponding to the human skin color is less than or equal to the set difference limit, otherwise, issue a normal play instruction; C: A content determination device with a customized structure design including a directional detection device, a numerical analysis device, and a determination execution device is used to provide a hardware basis for setting abnormal determination of the anchor's entity color.

[0020] Although the invention has been described with reference to the structures disclosed herein, it is not limited to the details set forth, but this application is intended to cover modifications or variations within the scope of the appended claims.

Claims

1. A human-computer interaction system using image component acquisition, characterized in that: The system comprises: A marking processing mechanism is used to mark the live broadcasting room broadcasting during the night time as a key inspection live broadcasting room for indecent inspection, and is also used to mark the live broadcasting room broadcasting during the day time as a non-key inspection live broadcasting room for non-indecent inspection; A content input mechanism, connected to the mark processing mechanism, is used to input the live image of the key inspection live room to obtain the on-site input image; A multiple enhancement mechanism, comprising a distortion processing device, an artifact removal device and a real-time filtering device, wherein the distortion processing device is connected to the content input mechanism and is used to perform distortion correction processing on the received on-site input image to obtain and output a corresponding distortion processed image, the artifact removal device is connected to the distortion processing device and is used to perform artifact removal processing on the received distortion processed image to obtain and output a corresponding artifact removed image, and the real-time filtering device is connected to the artifact removal device and is used to perform Gaussian high-pass filtering processing on the received artifact removed image to obtain and output a corresponding real-time filtered image; a content determination device connected to the multiple enhancement mechanism and comprising a directional detection device, a numerical analysis device and a determination execution device, wherein the numerical analysis device is respectively connected to the directional detection device and the determination execution device, wherein the content determination device is used to obtain a reference cyan brightness value, a reference magenta brightness value, a reference yellow brightness value and a reference black brightness value of each pixel column of the pattern occupied by the host in the real-time filtered image, and the reference yellow brightness value of each pixel column corresponding to the host is set to be the arithmetic mean of multiple yellow brightness values ​​obtained by removing the maximum value and the minimum value of each yellow brightness value corresponding to each pixel point on the pixel column, and the content determination device is further used to issue a suspected indecent play instruction when the difference between the reference yellow brightness value of each pixel column corresponding to the host and the upper limit threshold of the yellow brightness value interval corresponding to the human skin color is less than or equal to the set difference limit, otherwise, issue a normal play instruction; The transfer operation device is connected to the content determination device and is used to mark the key inspection live room corresponding to the on-site recorded image as a manual inspection live room to transfer it to the manual inspection queue when receiving a suspected indecent playback instruction.

2. The human-computer interaction system using image component acquisition according to claim 1, characterized in that: The mobile operating device is also used to mark the key inspection live broadcast room corresponding to the on-site recorded image as a non-key inspection live broadcast room when receiving a normal playback instruction; Among them, the content determination device is used to obtain the reference cyan brightness value, reference magenta brightness value, reference yellow brightness value and reference black brightness value of each pixel column of the pattern occupied by the set anchor in the real-time filtered image. The reference yellow brightness value of each pixel column corresponding to the set anchor is the arithmetic mean of multiple yellow brightness values ​​obtained by removing the maximum and minimum values ​​of each yellow brightness value corresponding to each pixel point on the pixel column, including: each pixel point on the pixel column has a cyan brightness value, a magenta brightness value, a yellow brightness value and a black brightness value in the CMYK color space.

3. The human-computer interaction system using image component acquisition as claimed in claim 2, characterized in that: The system further comprises: a heat analysis device, connected to the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, respectively, for measuring the instantaneous internal heat of each of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device; Among them, the thermal analysis device is respectively connected with the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, and is used to respectively measure the instantaneous internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device. The thermal analysis device includes multiple heat measurement units, which are respectively connected with the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device to complete the individual measurements of the instantaneous internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device.

4. The human-computer interaction system using image component acquisition as claimed in claim 3, characterized in that: The thermal analysis device includes a plurality of heat measuring units, which are used to be respectively connected to the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device to complete the respective measurement of the real-time internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device. The plurality of heat measuring units are a plurality of heat sensors, which are used to be respectively connected to the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device to complete the respective measurement of the real-time internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device.

5. The human-computer interaction system using image component acquisition as claimed in claim 4, characterized in that: The multiple heat measuring units are multiple heat sensors, which are used to be connected to the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device respectively, so as to complete the respective measurements of the real-time internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, including: the internal structures of the multiple heat sensors are the same.

6. The human-computer interaction system using image component acquisition as claimed in claim 5, characterized in that: The multiple heat measuring units are multiple heat sensors, which are used to be connected to the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device respectively to complete the separate measurement of the real-time internal heat of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device respectively, and also include: the multiple heat sensors have the same heat measurement upper limit value and heat measurement lower limit value.

7. The human-computer interaction system using image component acquisition as claimed in any one of claims 3 to 6, characterized in that: The system further comprises: The embedded processor is respectively connected to the multiple heat measurement units of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, and is used to realize the on-site configuration of the real-time working mode of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device.

8. The human-computer interaction system using image component acquisition as claimed in claim 7, characterized in that: The embedded processor is respectively connected to the multiple heat measurement units of the content entry mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, and is used to realize the on-site configuration of the real-time working mode of the content entry mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, including: the embedded processor is a processor with an ARM 13 core.

9. The human-computer interaction system using image component acquisition according to claim 7, characterized in that: The embedded processor is respectively connected to the multiple heat measurement units of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, and is used to realize the on-site configuration of the real-time working mode of the content input mechanism, the multiple enhancement mechanism, the content determination device and the transfer operation device, including: the embedded processor has built-in registers, timers and static storage devices.

Images