Depression grade distribution generation method

Abstract

The invention discloses a depression grade distribution generation method, which comprises the following steps that face images are used as training data, each face image is marked as a single-mark BDI-II score which is used as a corresponding description degree, the sum of all the description degrees is equal to 1 and is used for representing the depression severity degree of a human face, the value of the BDI-II score is 0-63, and the value of the BDI-II score is 0-63; depression score distribution of each face image is generated through Gaussian distribution; according to the mapping relation between the depression score and the depression level, a four-dimensional mark distribution is set to describe depression level information of the facial image, each element represents the description degree of the corresponding level, and the mark distribution is depression level distribution. The depression score distribution is converted into grade distribution by means of the relationship between depression scores and grades. In the training process, one face image can be used for real depression level learning and can also be used for learning of other related depression levels, the effect of augmenting training data can be achieved, and the problem of insufficient training data is relieved.

Description

Technical Field

[0001] The present invention relates to the technical field of emotion recognition, and in particular to a method for generating depression level distribution. Background Art

[0002] Existing methods usually only use BDI-II scores to train a prediction model, and then use the model to give a predicted BDI-II score and further give a depression level diagnosis. These methods ignore the uncertainty and inaccuracy of BDI-II score annotation. There is a certain ambiguity between the different options of the BDI-II questionnaire, and the assessee will usually choose a similar option, which leads to a certain uncertainty and inaccuracy in the BDI-II score itself. For example, a face image with a BDI-II score of 20 will also be labeled as 19 or 21 with a certain probability. Existing methods treat BDI-II scores as absolutely correct labels, ignoring the uncertainty of the standard process, resulting in unstable recognition performance. These methods only consider BDI-II scores during training, but do not consider depression level information, resulting in poor performance of the model when diagnosing depression levels. BDI-II scores and depression levels describe the depression information of a face from a fine-grained and coarse-grained perspective, respectively, and there is a strong correlation between the two. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a method for generating a depression grade distribution.

[0004] The objective of the present invention is achieved through the following technical solutions: The present invention provides a method for generating a depression level distribution, comprising the following steps: S1. Depression score distribution generation: facial images are used as training data, and each facial image is annotated with a single-label BDI-II score as its corresponding descriptive degree. The sum of all descriptive degrees is equal to 1, which is used to represent the severity of depression of the face. The BDI-II score ranges from 0 to 63. The depression score distribution of each facial image is generated through Gaussian distribution; S2. Depression level distribution generation: According to the mapping relationship between depression scores and depression levels, a 4-dimensional marker distribution is set to describe the depression level information of the facial image. Each element represents the descriptive degree of the corresponding level, and the marker distribution is the depression level distribution.

[0005] Preferably, the step S1 specifically includes the following steps: S11. Assume that the training data is , ,in Indicates facial images, For the The single-label BDI-II depression score corresponding to the facial image; facial images, through Gaussian distribution Generate the corresponding depression score distribution, where is the depression score, is the standard deviation which is usually set to 1. is the mean, is the standard deviation; S12, through the formula Normalize, where is the normalized parameter; depression score The corresponding descriptive degrees constitute a 64-dimensional label distribution = ,in Depression score for The descriptive degree, arrive Indicates all The depression score distribution of each facial image is generated by taking the value of

[0006] Preferably, the step S2 specifically comprises: Represents four levels of depression, The descriptive degree is calculated by the following formula: ;in Indicates level Corresponding depression score interval; The descriptive degree is the sum of all descriptive degrees in the corresponding depression score range. The descriptive degrees of all levels constitute a 4-dimensional label distribution , called the depression level distribution.

[0007] The beneficial effects of the present invention are: 1) This application uses the relationship between depression scores and levels to convert depression score distribution into level distribution. During the training process, a face image can be used for learning the real depression level as well as for learning other related depression levels, which can increase the training data and alleviate the problem of insufficient training data. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of the steps of a method for generating a depression level distribution according to an embodiment of the present invention; Figure 2 A schematic diagram of depression level distribution generation according to a method for generating depression level distribution according to an embodiment of the present invention. DETAILED DESCRIPTION

[0009] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0010] The present invention provides a method for generating depression level distribution, which converts depression score distribution into level distribution by using the relationship between depression score and level. Similarly, during the training process, a face image can be used for both real depression level learning and other related depression level learning, which can increase the training data and alleviate the problem of insufficient training data. The specific steps of this application are shown in the schematic diagram. Figure 1 As shown, the following steps are included: S1. Depression score distribution generation: facial images are used as training data, and each facial image is annotated with a single-label BDI-II score as its corresponding descriptive degree. The sum of all descriptive degrees is equal to 1, which is used to represent the severity of depression of the face. The BDI-II score ranges from 0 to 63. The depression score distribution of each facial image is generated through Gaussian distribution; S2. Depression level distribution generation: According to the mapping relationship between depression scores and depression levels, a 4-dimensional marker distribution is set to describe the depression level information of the facial image. Each element represents the descriptive degree of the corresponding level, and the marker distribution is the depression level distribution.

[0011] Specifically, the step S1 comprises the following steps: S11. Assume that the training data is , ,in Indicates facial images, For the The single-label BDI-II depression score corresponding to the facial image; facial images, through Gaussian distribution Generate the corresponding depression score distribution, where is the depression score, is the standard deviation which is usually set to 1. is the mean, is the standard deviation; S12, through the formula Normalize, where is the normalization parameter; depression score The corresponding descriptive degrees constitute a 64-dimensional label distribution = ,in Depression score for The descriptive degree, arrive Indicates all The depression score distribution of each facial image is generated by taking the value of

[0012] Specifically, in step S2, according to the BDI-II score, the severity of depression can be divided into four levels: "none", "mild", "moderate", and "severe", as shown in Table 1.

[0013] Table 1 BDI-II scores and corresponding depression levels BDI-II score Depression level 0-13 none 14-19 Mild 20-28 medium 29-63 serious The depression score represents the depression information of the face image from a fine-grained level, while the depression level describes the depression information of the face from a coarse-grained level, and the two annotation information are related. In practical applications, it is often necessary to diagnose the patient's depression level. Therefore, the present invention jointly considers the depression score and level to capture the depression information contained in the face from two granularities. There is also a certain degree of uncertainty in the depression level, and the definition is not completely absolute. For example, a face image with a depression score of 19 can be considered to be "mild" depressed, but it is also very likely to be determined to be "moderate" depressed. To this end, the present application describes the depression level information of the face image by generating a 4-dimensional marker distribution, and each element represents the descriptive degree of the corresponding level, specifically including: use Represents four levels of depression, The descriptive degree is calculated by the following formula: ;in Indicates level Corresponding depression score interval; The descriptive degree is the sum of all descriptive degrees in the corresponding depression score range. The descriptive degrees of all levels constitute a 4-dimensional label distribution , called depression level distribution. The schematic diagram of depression level distribution generation is as follows Figure 2 As shown in the figure, an example of how to generate a grade distribution from a depression score distribution is shown: the sum of the descriptive degrees corresponding to all values ​​in the interval [0, 13] is used as the descriptive degree of the depression grade "none", and the descriptive degrees of other depression grades are generated in a similar way. We use the formula Generate a distribution of depression levels for each face image.

[0014] The above is only a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art shall not deviate from the spirit and scope of the present invention, and shall be within the scope of protection of the claims attached to the present invention.

Claims

1. A method for generating a depression level distribution, characterized in that: The following steps are involved: S1. Depression score distribution generation: facial images are used as training data, and each facial image is annotated with a single-label BDI-II score as its corresponding descriptive degree. The sum of all descriptive degrees is equal to 1, which is used to represent the severity of depression of the face. The BDI-II score ranges from 0 to 63. The depression score distribution of each facial image is generated through Gaussian distribution; S2. Depression level distribution generation: According to the mapping relationship between depression scores and depression levels, a 4-dimensional marker distribution is set to describe the depression level information of the facial image. Each element represents the descriptive degree of the corresponding level, and the marker distribution is the depression level distribution.

2. The method for generating a depression level distribution according to claim 1, characterized in that: The step S1 specifically includes the following steps: S11. Assume that the training data is , ,in Indicates facial images, For the The single-label BDI-II depression score corresponding to the facial image; facial images, through Gaussian distribution Generate the corresponding depression score distribution, where is the depression score, is the standard deviation which is usually set to 1. is the mean, is the standard deviation; S12, through the formula Normalize, where is the normalized parameter; depression score The corresponding descriptive degrees constitute a 64-dimensional label distribution = ,in Depression score for The descriptive degree, arrive Indicates all The depression score distribution of each facial image is generated by taking the value of 3. A method for generating a depression level distribution according to claim 2, characterized in that , the step S2 specifically includes: Represents four levels of depression, The descriptive degree is calculated by the following formula: ;in Indicates level Corresponding depression score interval; The descriptive degree is the sum of all descriptive degrees in the corresponding depression score range. The descriptive degrees of all levels constitute a 4-dimensional label distribution , called the depression level distribution.

Images