Method for identifying facial expression language

Abstract

A method for identifying a facial expression language belongs to the technical field of language identification, and comprises the following steps: forming a source image cluster 1 according to an image 1 and an image 2; performing image processing on the source image cluster I to obtain a processed image cluster I; forming an image cluster entry I according to the source image cluster I and the processing image cluster I; storing the first image cluster entry; the first image comprises a child facial expression image; the second image comprises a body language image, and the body language image is transmitted to the image classification unit by the acquisition unit; the image processing comprises hash processing or coding processing, so that the body language image transmitted by the acquisition unit and other image information of the vehicle are processed and then stored, the reliability of facial expression language image control is improved, and the facial expression language is prevented from being leaked or read, written and mistakenly changed by malicious persons.

Description

Technical Field

[0001] The invention belongs to the technical field of language recognition, and in particular relates to a method for recognizing facial expression language. Background Art

[0002] Facial expressions play a vital role in social interactions. They help people quickly judge the other person's emotional state and adjust their communication style accordingly. For example, when you see someone smiling, you usually think that the other person is friendly or satisfied; but when you see a frown or unhappy expression, you realize that the other person may be dissatisfied or worried. In addition, facial expressions can also affect other people's emotions and behaviors. For example, a sincere smile can relieve tension, while a fake smile may make people feel uneasy.

[0003] Among the methods for recognizing facial expression language, the existing technical solution with patent publication number "CN115578409A" is currently generally used to achieve it, and its collection unit is used to collect children's facial expression and body language image samples and transmit them to the image classification unit for classification.

[0004] When collecting images of children's facial expressions and body language, the images are often damaged or lost, making it impossible to fully restore the entire image information. In the absence of sufficient reliable methods, the images are often read and written by malicious people, modified or even wrongly modified, which introduces a considerable image reliability risk. Summary of the invention

[0005] In order to solve the defects in the prior art, the present invention proposes a device and method for performing recognition on facial expression language, which forms a source image cluster one based on image one and image two; performs image processing on the source image cluster one to obtain a processed image cluster one; forms an image cluster entry one based on the source image cluster one and the processed image cluster one; and stores the image cluster entry one; here, the image one includes a child's facial expression image; the image two includes a body language image, and the body language image is transmitted from a collection unit to an image classification unit; the image processing includes hash processing or encoding processing, so that the body language image transmitted by the collection unit and other image information of the vehicle are processed and stored, thereby improving the reliability of facial expression language image control and preventing facial expression language from being leaked or read, written, or modified by malicious persons.

[0006] The present invention uses the following technical solutions.

[0007] A method for recognizing facial expression language, comprising:

[0008] The collecting unit collects samples of children's facial expressions and body language images and transmits them to the image classification unit for processing and then classifies the processed images;

[0009] The method in which the collecting unit collects the samples of the children's facial expressions and body language images and transmits them to the image classification unit for processing comprises:

[0010] Forming a source image cluster 1 according to the image 1 and the image 2;

[0011] Performing image processing on the source image cluster one to obtain processed image cluster one;

[0012] According to the source image cluster one and the processed image cluster one, an image cluster entry one is formed;

[0013] The image cluster entry 1 is stored.

[0014] A device for digitally encoding facial expression language, comprising:

[0015] The acquisition unit is communicatively connected with the image classification unit;

[0016] The acquisition unit is used to collect samples of children's facial expressions and body language images and transmit them to the image classification unit for processing and then classifying the processed images;

[0017] The device for performing digital coding on facial expression language also includes:

[0018] A forming module 1, which is used to form a source image cluster 1 according to the image 1 and the image 2;

[0019] A processing module, configured to perform image processing on the source image cluster 1 to obtain a processed image cluster 1;

[0020] A forming module 2, which is used to form an image cluster entry 1 according to the source image cluster 1 and the processed image cluster 1;

[0021] A storage module is used to store the image cluster entry one.

[0022] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include:

[0023] A source image cluster 1 is formed based on image 1 and image 2; image processing is performed on the source image cluster 1 to obtain a processed image cluster 1; an image cluster entry 1 is formed based on the source image cluster 1 and the processed image cluster 1; and the image cluster entry 1 is stored; here, the image 1 includes a child's facial expression image; the image 2 includes a body language image, and the body language image is transmitted from the acquisition unit to the image classification unit; the image processing includes hash processing or encoding processing, so that the body language image transmitted by the acquisition unit and other image information of the vehicle are processed and then stored, thereby improving the reliability of facial expression language image control and preventing facial expression language from leaking or being read, written, and modified by malicious persons. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a partial flow chart of the method for recognizing facial expression language described in the present invention;

[0025] Figure 2 It is a partial structural schematic diagram of the device for recognizing facial expression language described in the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the following will be combined with the drawings in the embodiments of the present invention to clearly and completely express the technical solution of the present invention. The embodiments expressed in this application are only some embodiments of the present invention, not all embodiments. According to the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without making creative work are all within the protection scope of the present invention.

[0027] like Figure 1 As shown, a method for recognizing facial expression language according to the present invention comprises:

[0028] The collecting unit collects samples of children's facial expressions and body language images and transmits them to the image classification unit for processing and then classifies the processed images;

[0029] The method in which the collecting unit collects the samples of the children's facial expressions and body language images and transmits them to the image classification unit for processing comprises:

[0030] Forming a source image cluster 1 according to the image 1 and the image 2;

[0031] Performing image processing on the source image cluster one to obtain processed image cluster one;

[0032] According to the source image cluster one and the processed image cluster one, an image cluster entry one is formed;

[0033] The image cluster entry 1 is stored.

[0034] In a preferred but non-limiting embodiment of the present invention, the image one includes a child's facial expression image; the image two includes a body language image, and the body language image is transmitted to the image classification unit via the acquisition unit; the image processing includes hash processing or encoding processing.

[0035] In a preferred but non-limiting embodiment of the present invention, forming a source image cluster one based on image one and image two includes: aggregating image one, image two and coding coefficient one to form the source image cluster one.

[0036] In a preferred but non-limiting embodiment of the present invention, image processing is performed on the source image cluster 1 to obtain a processed image cluster 1, including: performing hash processing on the source image cluster 1 to obtain a hash value 1, and performing entropy coding or linear coding on the hash value 1 using a coding coefficient 1 to achieve coding processing to obtain a processed image cluster 1.

[0037] In a preferred but non-limiting embodiment of the present invention, forming an image cluster entry one according to the source image cluster one and the processed image cluster one comprises: aggregating the source image cluster one and the processed image cluster one to form an image cluster entry one;

[0038] Here, the coding coefficient is formed by a background computer and allocated to the image classification unit.

[0039] In a preferred but non-limiting embodiment of the present invention, the method for performing recognition on facial expression language further comprises:

[0040] Perform hash processing on image three to obtain hash value two; the image three includes previous image cluster entry one;

[0041] Fill the hash value two into the image cluster entry one.

[0042] In a preferred but non-limiting embodiment of the present invention, the method for performing recognition on facial expression language further comprises:

[0043] The hash value of the image entry 1 is transmitted to the collection unit according to a predefined time period, wherein the hash value of the image entry 1 is obtained by performing a hash process on the image cluster entry 1, and the hash value of the image entry 1 is stored through the collection unit; the collection unit is used to perform a hash process based on the hash value of the image entry 1 and an identification code defined by the collection unit itself, obtain the stored entry hash value, and transmit it to the image classification unit;

[0044] Receive and store the storage entry hash value responded by the collection unit.

[0045] In a preferred but non-limiting embodiment of the present invention, the method for recognizing facial expression language further comprises:

[0046] Obtaining a source image cluster 1 and a processed image cluster 1 in the image cluster entry 1;

[0047] Performing image verification according to the obtained source image cluster one and the processed image cluster one;

[0048] The image verification is performed by the verification end according to the following method:

[0049] Obtaining a decoding coefficient 1 through a background computer, and performing decoding processing on the processing image cluster 1 using the decoding coefficient 1 to obtain a hash value 1;

[0050] Performing hash processing on the source image cluster one to obtain a verification hash value one;

[0051] Performing verification on the hash value by applying a verification hash value;

[0052] Here, the encoding coefficient 1 is different from the decoding coefficient 1, and the different coefficients are generated by a background computer.

[0053] In a preferred but non-limiting embodiment of the present invention, the method for recognizing facial expression language further comprises:

[0054] Obtaining hash value 2 in image cluster entry 1;

[0055] Get the previous image cluster entry 1 corresponding to the image cluster entry 1.

[0056] In a preferred but non-limiting embodiment of the present invention, the image verification is performed by the verification end according to the following method:

[0057] Performing hash processing on the previous image cluster entry 1 to obtain a verification hash value 2;

[0058] The hash value 2 is verified by using the verification hash value 2.

[0059] In a preferred but non-limiting embodiment of the present invention, the method for recognizing facial expression language further comprises:

[0060] Under normal operating conditions of the image classification unit, a coefficient pair and an aggregation coefficient one are formed, wherein the coefficient pair includes an encoding coefficient one and a decoding coefficient one;

[0061] Under the normal operation condition of the image classification unit, the aggregation coefficient 1 is segmented to form three segmentation coefficients; any pair of the three segmentation coefficients can be aggregated into the aggregation coefficient 1;

[0062] The coding coefficient is transmitted to the background computer, and one pair of the three segment coefficients is transmitted to the remote computer and the background computer respectively.

[0063] In a preferred but non-limiting embodiment of the present invention, forming a source image cluster one according to image one and image two includes: performing aggregation on image one and image two to form a source image cluster one;

[0064] Performing image processing on the source image cluster 1 to obtain a processed image cluster 1, comprising: under normal operating conditions of the image classification unit, performing encoding processing on the source image cluster 1 using an aggregation coefficient 1 to obtain an encoded image 1; performing hash processing on the source image cluster 1 to obtain a hash value 1; performing marking processing on the hash value 1 using a decoding coefficient 1 to obtain a marked image 1; and aggregating the encoded image 1, hash value 1 and marked image 1 to form a processed image cluster 1.

[0065] According to the source image cluster 1 and the processed image cluster 1, forming an image cluster entry 1, comprising: using the processed image cluster 1 as the image cluster entry 1;

[0066] Here, the image cluster entry one is the first image cluster entry one of the image classification unit.

[0067] In a preferred but non-limiting embodiment of the present invention, forming a source image cluster one according to image one and image two includes: performing aggregation on image one and image two to form a source image cluster one;

[0068] Performing image processing on the source image cluster one to obtain a processed image cluster one, including: under normal operating conditions of the image classification unit, performing encoding processing on the source image cluster one using a clustering coefficient one to obtain a coded image one; performing hash processing on the source image cluster one to obtain a hash value one; performing marking processing on the hash value one and the hash value one in the previous image cluster entry one using a decoding coefficient one to obtain a marked image one; or, performing marking processing on the hash value one and the hash value of the previous image cluster entry one using a decoding coefficient one to obtain a marked image one; forming a processed image cluster one based on the source image cluster one, the hash value one and the marked image one.

[0069] In a preferred but non-limiting embodiment of the present invention, forming an image cluster entry one according to the source image cluster one and the processed image cluster one comprises: treating the processed image cluster one as the image cluster entry one;

[0070] Here, the image cluster entry one is the Pth image cluster entry one of the image classification unit, where P is a positive integer and P≥2.

[0071] In a preferred but non-limiting embodiment of the present invention, the method for recognizing facial expression language further comprises:

[0072] The image cluster entry is transmitted to the remote computer and the background computer.

[0073] In a preferred but non-limiting embodiment of the present invention, the method for recognizing facial expression language further comprises:

[0074] The method further comprises:

[0075] Obtaining a hash value 1, a coded image 1 and a marked image 1 in the image cluster entry 1;

[0076] Under the normal operation condition of the image classification unit or the processing space set by the background computer, the encoded image is decoded using the aggregation coefficient to obtain a source image cluster, and the processing space set by the background computer forms the aggregation coefficient according to any pair of the three segmentation coefficients;

[0077] Performing image verification according to the source image cluster 1, the hash value 1 and the marked image 1;

[0078] The image verification is performed by the verification end according to the following method:

[0079] Performing hash processing on the source image cluster to obtain a verification hash value;

[0080] Performing verification on the hash value using a verification hash value;

[0081] The image verification is also performed by the background computer according to the following method:

[0082] The marked image is verified by applying the encoding coefficient and the hash value.

[0083] In a preferred but non-limiting embodiment of the present invention, the method for recognizing facial expression language further comprises:

[0084] Under the normal operation condition of the image classification unit, the aggregation coefficient 1 is encoded by using the encoding coefficient 1 to form the encoding factor 1, and the encoding factor 1 is sent to the storage space of the image classification unit;

[0085] When it is required to use coding factor one under the normal operating condition of the image classification unit, the coding factor one is sent to the normal operating condition of the image classification unit through the storage space of the image classification unit, and the coding factor one is decoded using decoding coefficient one under the normal operating condition of the image classification unit to obtain aggregation coefficient one.

[0086] In a preferred but non-limiting embodiment of the present invention, the method for recognizing facial expression language further comprises:

[0087] Obtaining hash value 1 in the image cluster entry 1, encoded image 1, marked image 1 and hash value 1 in the previous image cluster entry 1; or,

[0088] Obtaining a hash value 1, a coded image 1, a marked image 1 and a hash value of a previous image cluster entry 1 in the image cluster entry 1;

[0089] Under the normal operation condition of the image classification unit or the processing space set by the background computer, the encoded image is decoded using the aggregation coefficient to obtain a source image cluster, and the processing space specified by the background computer forms the aggregation coefficient according to any pair of the three segmentation coefficients;

[0090] Performing image verification according to the source image cluster 1, the hash value 1, the marked image 1 and the hash value 1 in the previous image cluster entry 1, or according to the source image cluster 1, the hash value 1, the marked image 1 and the hash value of the previous image cluster entry 1;

[0091] The image verification is performed by the verification end according to the following method:

[0092] Performing hash processing on the source image cluster to obtain a verification hash value;

[0093] Performing verification on the hash value using a verification hash value;

[0094] The image verification is also performed by the background computer according to the following method:

[0095] The marked image 1 is verified by using the coding coefficient 1, the hash value 1 and the hash value 1 in the previous image cluster entry 1, or the coding coefficient 1, the hash value 1 and the hash value of the previous image cluster entry 1.

[0096] like Figure 2 As shown, the device for digitally encoding facial expression language according to the present invention comprises:

[0097] The acquisition unit is communicatively connected with the image classification unit;

[0098] The acquisition unit is used to collect samples of children's facial expressions and body language images and transmit them to the image classification unit for processing and then classifying the processed images;

[0099] The device for performing digital coding on facial expression language also includes:

[0100] A forming module 1, which is used to form a source image cluster 1 according to the image 1 and the image 2;

[0101] A processing module, configured to perform image processing on the source image cluster 1 to obtain a processed image cluster 1;

[0102] A forming module 2, which is used to form an image cluster entry 1 according to the source image cluster 1 and the processed image cluster 1;

[0103] A storage module is used to store the image cluster entry one.

[0104] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include:

[0105] A source image cluster 1 is formed based on image 1 and image 2; image processing is performed on the source image cluster 1 to obtain a processed image cluster 1; an image cluster entry 1 is formed based on the source image cluster 1 and the processed image cluster 1; and the image cluster entry 1 is stored; here, the image 1 includes a child's facial expression image; the image 2 includes a body language image, and the body language image is transmitted from the acquisition unit to the image classification unit; the image processing includes hash processing or encoding processing, so that the body language image transmitted by the acquisition unit and other image information of the vehicle are processed and then stored, thereby improving the reliability of facial expression language image control and preventing facial expression language from leaking or being read, written, and modified by malicious persons.

[0106] The present disclosure can be a system, method and / or computer program product. The computer program product can include a computer readable backup medium carrying computer readable program instructions for causing a processor to achieve each aspect of the disclosure.

[0107] The computer readable backup medium can be a tangible network capable of retaining and backing up the instructions used by the instruction execution network. The computer readable backup medium can be, but is not limited to, an electrical backup network, a magnetic backup network, an optical backup network, an electromagnetic backup network, a semiconductor backup network, or any suitable combination thereof. Further examples of computer readable backup media (non-exhaustive list) include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (HD-ROM), digital versatile disk (DXD), memory stick, floppy disk, mechanically encoded network circuits, such as punch cards or protrusions in grooves with instructions backed up thereon, and any suitable combination thereof. Computer readable backup media as used herein is not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through power line cables), or electrical signals transmitted through wires.

[0108] The computer readable program instructions expressed herein can be downloaded from the computer readable backup medium to each inference / processing grid line, or downloaded to an external computer or external backup grid line through a wireless network, such as the Internet, a local area network, a wide area network and / or a wireless network. The wireless network can include copper transmission cables, power transmission lines, wireless transmission, routers, firewalls, switches, gateway computers and / or edge service devices. The wireless network adapter card or wireless network interface in each inference / processing grid line receives the computer readable program instructions from the wireless network and forwards the computer readable program instructions for storage in the computer readable backup medium in each inference / processing grid line.

[0109] The computer program instructions for performing the operations of the present disclosure can be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, conditional setting values, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Sdaletal A, H++, etc., and conventional procedural programming languages ​​such as "H" language or similar programming languages. The computer-readable program instructions can be executed completely on the client computer, partially on the client computer, as a separate software package, partially on the client computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the client computer through any wireless network, including a local area network (LAb) or a wide area network (WAb), or can be connected to an external computer (just like using an Internet service provider to connect through the Internet). In some embodiments, the electronic circuit is customized by using the state values ​​of computer-readable program instructions, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), and the electronic circuit can execute computer-readable program instructions to achieve each aspect of the overhead disclosure.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any arbitrary modifications or equivalent replacements that do not deviate from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for recognizing facial expression language, characterized in that: include: The collecting unit collects samples of children's facial expressions and body language images and transmits them to the image classification unit for processing and then classifies the processed images; The method in which the collecting unit collects the samples of the children's facial expressions and body language images and transmits them to the image classification unit for processing comprises: Forming a source image cluster 1 according to the image 1 and the image 2; Performing image processing on the source image cluster one to obtain processed image cluster one; According to the source image cluster one and the processed image cluster one, an image cluster entry one is formed; The image cluster entry 1 is stored.

2. The method for recognizing facial expression language according to claim 1, wherein: The first image includes a child's facial expression image; the second image includes a body language image, and the body language image is transmitted to the image classification unit via the acquisition unit; the image processing includes hash processing or encoding processing; The method forms a source image cluster one according to the image one and the image two, comprising: aggregating the image one, the image two and the coding coefficient one to form the source image cluster one.

3. The method for recognizing facial expression language according to claim 2, wherein: Performing image processing on the source image cluster 1 to obtain a processed image cluster 1, comprising: performing hash processing on the source image cluster 1 to obtain a hash value 1, performing coding processing on the hash value 1 using a coding coefficient 1 to obtain a processed image cluster 1; According to the source image cluster 1 and the processed image cluster 1, forming an image cluster entry 1, comprising: aggregating the source image cluster 1 and the processed image cluster 1 to form an image cluster entry 1; Here, the coding coefficient is formed by a background computer and allocated to the image classification unit.

4. The method for recognizing facial expression language according to claim 3, wherein: The method for performing recognition on facial expression language also includes: Perform hash processing on image three to obtain hash value two; the image three includes previous image cluster entry one; Fill the hash value two into the image cluster entry one.

5. The method for recognizing facial expression language according to claim 4, characterized in that: The method for performing recognition on facial expression language also includes: The hash value of the image entry 1 is transmitted to the collection unit according to a predefined time period, wherein the hash value of the image entry 1 is obtained by performing a hash process on the image cluster entry 1, and the hash value of the image entry 1 is stored through the collection unit; the collection unit is used to perform a hash process based on the hash value of the image entry 1 and an identification code defined by the collection unit itself, obtain the stored entry hash value, and transmit it to the image classification unit; Receive and store the hash value of the storage entry responded by the collection unit; The method for performing recognition on facial expression language also comprises: Obtaining a source image cluster 1 and a processed image cluster 1 in the image cluster entry 1; Performing image verification according to the obtained source image cluster one and the processed image cluster one; The image verification is performed by the verification end according to the following method: Obtaining a decoding coefficient 1 through a background computer, and performing decoding processing on the processing image cluster 1 using the decoding coefficient 1 to obtain a hash value 1; Performing hash processing on the source image cluster one to obtain a verification hash value one; Performing verification on the hash value by applying a verification hash value; Here, the encoding coefficient 1 is different from the decoding coefficient 1, and the different coefficients are generated by a background computer.

6. The method for recognizing facial expression language according to claim 5, characterized in that: The method for performing recognition on facial expression language also comprises: Obtaining hash value 2 in image cluster entry 1; Get the previous image cluster entry 1 corresponding to the image cluster entry 1. Preferably, the image verification is performed by the verification end according to the following method: Performing hash processing on the previous image cluster entry 1 to obtain a verification hash value 2; Performing verification on the hash value 2 using the verification hash value 2; The method for performing recognition on facial expression language also comprises: Under normal operating conditions of the image classification unit, a coefficient pair and an aggregation coefficient one are formed, wherein the coefficient pair includes an encoding coefficient one and a decoding coefficient one; Under the normal operation condition of the image classification unit, the aggregation coefficient 1 is segmented to form three segmentation coefficients; any pair of the three segmentation coefficients can be aggregated into the aggregation coefficient 1; The coding coefficient is transmitted to the background computer, and one pair of the three segment coefficients is transmitted to the remote computer and the background computer respectively.

7. The method for recognizing facial expression language according to claim 6, characterized in that: Forming a source image cluster 1 according to the image 1 and the image 2, comprising: performing aggregation on the image 1 and the image 2 to form the source image cluster 1; The method comprises: performing image processing on the source image cluster 1 to obtain a processed image cluster 1, comprising: under the normal operation condition of the image classification unit, performing encoding processing on the source image cluster 1 using an aggregation coefficient 1 to obtain an encoded image 1; performing hash processing on the source image cluster 1 to obtain a hash value 1; performing marking processing on the hash value 1 using a decoding coefficient 1 to obtain a marked image 1; and aggregating the encoded image 1, the hash value 1 and the marked image 1 to form a processed image cluster 1; According to the source image cluster 1 and the processed image cluster 1, forming an image cluster entry 1, comprising: using the processed image cluster 1 as the image cluster entry 1; Here, the image cluster entry one is the first image cluster entry one of the image classification unit.

8. The method for recognizing facial expression language according to claim 7, characterized in that: Forming a source image cluster 1 according to the image 1 and the image 2, comprising: performing aggregation on the image 1 and the image 2 to form the source image cluster 1; Performing image processing on the source image cluster 1 to obtain a processed image cluster 1, comprising: under the normal operating condition of the image classification unit, performing encoding processing on the source image cluster 1 using a clustering coefficient 1 to obtain an encoded image 1; performing hash processing on the source image cluster 1 to obtain a hash value 1; performing marking processing on the hash value 1 and a hash value 1 in a previous image cluster entry 1 using a decoding coefficient 1 to obtain a marked image 1; or performing marking processing on the hash value 1 and a hash value of a previous image cluster entry 1 using a decoding coefficient 1 to obtain a marked image 1; forming a processed image cluster 1 according to the source image cluster 1, the hash value 1 and the marked image 1; According to the source image cluster one and the processed image cluster one, forming an image cluster entry one, comprising: treating the processed image cluster one as the image cluster entry one; Here, the image cluster entry one is the Pth image cluster entry one of the image classification unit, where P is a positive integer and P≥2.

9. The method for recognizing facial expression language according to claim 8, characterized in that: The method for performing recognition on facial expression language also comprises: transmitting the image cluster entry to the remote computer and the background computer; The method for performing recognition on facial expression language also comprises: Obtaining a hash value 1, a coded image 1 and a marked image 1 in the image cluster entry 1; Under the normal operation condition of the image classification unit or the processing space set by the background computer, the encoded image is decoded using the aggregation coefficient to obtain a source image cluster, and the processing space set by the background computer forms the aggregation coefficient according to any pair of the three segmentation coefficients; Performing image verification according to the source image cluster 1, the hash value 1 and the marked image 1; The image verification is performed by the verification end according to the following method: Performing hash processing on the source image cluster to obtain a verification hash value; Performing verification on the hash value using a verification hash value; The image verification is also performed by the background computer according to the following method: Perform verification on the marked image using the encoding coefficient and the hash value. The method for performing recognition on facial expression language also comprises: Under the normal operation condition of the image classification unit, the aggregation coefficient 1 is encoded by using the encoding coefficient 1 to form the encoding factor 1, and the encoding factor 1 is sent to the storage space of the image classification unit; When it is required to use the coding factor 1 under the normal operation condition of the image classification unit, the coding factor 1 is sent to the normal operation condition of the image classification unit through the storage space of the image classification unit, and the coding factor 1 is decoded by using the decoding coefficient 1 under the normal operation condition of the image classification unit to obtain the aggregation coefficient 1; The method for performing recognition on facial expression language also comprises: Obtaining hash value 1 in the image cluster entry 1, encoded image 1, marked image 1 and hash value 1 in the previous image cluster entry 1; or, Obtaining a hash value 1, a coded image 1, a marked image 1 and a hash value of a previous image cluster entry 1 in the image cluster entry 1; Under the normal operation condition of the image classification unit or the processing space set by the background computer, the encoded image is decoded using the aggregation coefficient to obtain a source image cluster, and the processing space specified by the background computer forms the aggregation coefficient according to any pair of the three segmentation coefficients; Performing image verification according to the source image cluster 1, the hash value 1, the marked image 1 and the hash value 1 in the previous image cluster entry 1, or according to the source image cluster 1, the hash value 1, the marked image 1 and the hash value of the previous image cluster entry 1; The image verification is performed by the verification end according to the following method: Performing hash processing on the source image cluster to obtain a verification hash value; Performing verification on the hash value using a verification hash value; The image verification is also performed by the background computer according to the following method: The marked image 1 is verified by using the coding coefficient 1, the hash value 1 and the hash value 1 in the previous image cluster entry 1, or the coding coefficient 1, the hash value 1 and the hash value of the previous image cluster entry 1.

10. A device for digitally encoding facial expression language, characterized in that: include: The acquisition unit is communicatively connected with the image classification unit; The acquisition unit is used to collect samples of children's facial expressions and body language images and transmit them to the image classification unit for processing and then classifying the processed images; The device for performing digital coding on facial expression language also includes: A forming module 1, which is used to form a source image cluster 1 according to the image 1 and the image 2; A processing module, configured to perform image processing on the source image cluster 1 to obtain a processed image cluster 1; A forming module 2, which is used to form an image cluster entry 1 according to the source image cluster 1 and the processed image cluster 1; A storage module is used to store the image cluster entry one.

Images