KR101000492B1 - Apparatus and method for diagnosis of psychological symptoms corresponding to analysis of coloring patterns in art therapy assessment and medium of recording its program - Google Patents

Abstract

This study is to analyze various factors of color painted on patterns that can be used for art therapy techniques and factors related to concentration of work and to diagnose psychological symptoms by searching knowledge based on responses to questionnaires. More specifically, providing a questionnaire to the diagnosis subject; Acquiring questionnaire response information of the diagnosis subject from a response to the questionnaire; Receiving an analysis target picture according to a pattern coloring task of the diagnosis subject; Analyzing a color factor and a concentration factor of the analysis target picture; And diagnosing psychological symptoms of the diagnosis subject by searching for knowledge from a knowledge database based on at least one of the color factor and the concentration factor and the questionnaire response information. Analyze the personal disposition and pattern coloring of the colors collected through the questionnaire to build a database of interpretations on the factors (color factors, concentration factors, etc.) acquired, and analyze the factors given any colored patterns. And search for and provide corresponding knowledge.

Art therapy, glyphs, coloring, color factors, concentration, psychological symptoms

Description

Apparatus and method for diagnosis of psychological symptoms corresponding to analysis of coloring patterns in art therapy assessment and medium of recording its program}

The present invention relates to a method for diagnosing psychological symptoms, and more particularly, to a method for diagnosing psychological symptoms by analyzing and evaluating various factors (color factor and concentration factor) of a patterned picture.

Common coloring art therapy techniques, including Mandala's pattern coloring techniques, have been proven to be widely used in the diagnosis and treatment of psychological and mental conditions. Coloring (including mandala and common pattern coloring) has been known as a tool for looking back on yourself by focusing on the spirit of the worker, establishing and harmonizing inner order, and finding your own. The fact that the inside of the worker is expressed during the coloring process has proved experimentally that the inner tension is relieved and therefore healed.

Art therapists can extract fairly accurate information about the state of mind, even from the relatively poor response of paintings. Therefore, the coloring task can be a useful art therapy method for providing useful information to identify the mental and psychological state of the patient and to provide a guide of treatment.

Coloring works are useful for treating anxiety, guilt, lethargy, moody, nightmares, indifference, and various types of social evasion and psychotherapy. It has the effect of suppressing impulses.

In art therapy, art therapists observe the forms, symbols, lines, and colors that appear in paintings. Colors will be the most important factor when painting patterns. There has been no way to automatically analyze and judge color-related factors by computer and knowledge base. And an important factor in the coloring work is the concentration of the work. Unknowingly calming yourself while forgetting everything and working on it is a basic art therapy function of painting. Therefore, how diligent work in the coloring work will have a significant effect on the effect of art therapy.

In addition, there has been no expert system for interpreting factors related to personal disposition collected by questionnaires and factors obtained through the analysis of colored patterns.

Accordingly, the present invention builds a database of knowledge related to the interpretation of factors (color factors, concentration factors, etc.) obtained by analyzing individual dispositions and pattern colorings for colors collected through questionnaires. Provided are methods and apparatus for diagnosing psychological symptoms, if any, for analyzing factors and searching for and providing knowledge.

In addition, the present invention provides a method and apparatus for diagnosing psychological symptoms, given a series of colored patterns, for detecting the change and providing the corresponding knowledge.

In addition, the present invention provides a method and apparatus for diagnosing psychological symptoms by automatically analyzing hundreds to thousands of pictures in a short time to reduce the effort and time required for a general pattern coloring analysis.

According to an aspect of the invention, providing a questionnaire to a diagnosis subject; Acquiring questionnaire response information of the diagnosis subject from a response to the questionnaire; Receiving an analysis target picture according to a pattern coloring task of the diagnosis subject; Analyzing a color factor and a concentration factor of the analysis target picture; And diagnosing psychological symptoms of the diagnosis subject by searching for knowledge from a knowledge database based on at least one of the color factor and the concentration factor and the questionnaire response information.

Here, the providing of the questionnaire and obtaining the questionnaire response information, and receiving the analysis target picture and analyzing the color factor and the concentration factor may be performed simultaneously or in any order.

Acquiring the questionnaire response information may search for knowledge from the knowledge database based on a response to the questionnaire to obtain the questionnaire response information.

The receiving of the analysis target picture may include receiving two or more analysis target pictures sequentially, and diagnosing the psychological symptom may search for knowledge from the knowledge database based on a difference between analysis results of two or more analysis target pictures. The psychological change of the diagnosis subject may be predicted.

The analyzing of the color factor and the concentration factor of the analysis target picture may include determining the color factor and analyzing the concentration factor, and the determination of the color factor and the concentration factor may be performed at random. It can be done in sequence or simultaneously.

The determining of the color factor may include: recognizing a color used in the analysis target picture; Converting the color into any one of a plurality of preset representative colors; Extracting a primary color factor of the analysis target picture from the converted representative color; And determining a second color factor of the analysis target picture from the first color factor.

Recognizing the color may include: dividing the analysis target picture in pixel units; And recognizing a color painted on the pixel.

In the representative color conversion step, the color may be converted into any one of representative colors by color classification of a predetermined number of colors. Alternatively, the representative color conversion step may include converting the color into any one of the first representative colors by color classification of a predetermined number of colors; And re-converting to one of the second representative colors based on the color classification of another preset number of colors, wherein the number of the first representative colors is greater than the number of the second representative colors.

The primary color factor extraction step may extract any one of the number of colors used, the type of colors, the area for each color, the number of clusters, the contour line, and a combination thereof.

The secondary color factor determination step includes the secondary color factors of the main color and the subtitle color, the secondary color factors of the primary and secondary colors, the secondary color factors of the warm and cold colors, the secondary color factors of the complementary colors, and the variety of colors. At least one secondary color factor among the secondary color factors of may be calculated as quantitative data.

On the other hand, analyzing the concentration factor, measuring the completeness of the analysis target picture; Measuring the accuracy of the analysis target picture; And determining a concentration factor of the pattern coloring task based on the completeness and the accuracy.

In the concentration determining step, the concentration factor may be determined using a multiple linear regression analysis method using the completeness and the accuracy as an explanatory variable and the concentration as a dependent variable.

The perfection measurement step may measure the ratio of the number of pixels painted in the mood pattern to the total number of pixels of the basic pattern of the analysis target picture.

The accuracy measuring step may measure the degree of agreement between the cluster of the basic pattern of the analysis target picture and the color cluster of the analysis target picture with the accuracy.

The measuring accuracy may include calculating a number of pixels for each representative color in any basic pattern cluster; Determining a representative color having the largest number of pixels as a color accurately painted in the basic pattern cluster; Repeating the pixel number calculation step and the color determination step for all basic glyph clusters; Summing up the number of pixels of the correctly painted color in all the basic glyph clusters; And determining the value obtained by dividing the sum of the sum of the number of pixels by the total number of pixels of the analysis target picture with the accuracy.

In the determining of the correctly painted color, when the representative color having the largest number of pixels is white, it may be regarded as a basic pattern cluster without painting the basic pattern cluster, and it may be determined that the number of pixels accurately painted in the basic pattern cluster is not included.

According to another aspect of the present invention, a pattern coloring analysis module for receiving an analysis target picture according to the pattern coloring task of the diagnosis subject, and analyzing the color factor and concentration factor of the analysis target picture; A questionnaire response information input module for providing a questionnaire to the diagnosis subject and obtaining questionnaire response information of the diagnosis subject from a response to the questionnaire; A knowledge database storing knowledge linking the personal disposition, the color factor, and the concentration factor with psychological symptoms; And a psychological symptom diagnosis module for diagnosing psychological symptoms of the subject by searching for knowledge from the knowledge database based on at least one of the color factor and the concentration factor and the questionnaire response information. do.

The apparatus may further include a history database for storing a result analyzed by the pattern coloring analysis module, wherein the psychological symptom diagnosis module includes a difference between an analysis result of a current analysis target picture and an analysis result of a past analysis target picture stored in the history database. The psychological change of the diagnosis subject may be predicted by searching for knowledge from the knowledge database based on.

Meanwhile, the above-described psychological symptom diagnosis method may be performed by a computer, and may be recorded in a computer readable recording medium for recording a program to be executed in the computer.

Other aspects, features, and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.

Psychological symptom diagnosis method according to the present invention by building a database of knowledge related to the interpretation of the factors (color factors, concentration factors, etc.) obtained by analyzing the individual disposition and pattern coloring of the colors collected through the questionnaire, Given the colored patterns, the factors can be analyzed and the corresponding knowledge explored and provided.

In addition, given a series of colored patterns, it is possible to detect the change and provide corresponding knowledge.

In addition, it automatically analyzes hundreds to thousands of pictures in a short time, saving time and effort for the expert in analyzing common coloring patterns.

As the invention allows for various changes and numerous embodiments, particular embodiments will be illustrated in the drawings and described in detail in the written description. However, this is not intended to limit the present invention to specific embodiments, it should be understood to include all transformations, equivalents, and substitutes included in the spirit and scope of the present invention. In the following description of the present invention, if it is determined that the detailed description of the related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting of the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, the terms "comprise" or "have" are intended to indicate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, and one or more other features. It is to be understood that the present invention does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, components, or a combination thereof.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram illustrating a psychological symptom diagnosis apparatus according to an embodiment of the present invention, FIG. 2 is a flowchart of a psychological symptom diagnosis method according to an embodiment of the present invention, and FIG. 3 is a questionnaire for diagnosing psychological symptoms. It is an illustration.

Referring to FIG. 1, a psychological symptom diagnosis apparatus 10, a pattern coloring analysis module 11, a questionnaire response information input module 12, a psychological symptom diagnosis module 13, a knowledge database 14, and a history database 15 Is shown.

The pattern coloring analysis module 11 analyzes patterns painted by a diagnosis subject (eg, a child, a psychotherapy subject, etc.) who are generally the subject of art therapy, and analyzes preset factors (color factor, concentration factor, etc.). Quantitative data are provided (step S21). The pattern coloring analysis module 11 will be described in detail later with reference to FIGS. 4 to 16.

The survey response information input module 12 acquires personal propensity through a questionnaire or the like (step S22). Referring to FIG. 3, a questionnaire form according to an embodiment is illustrated. The questionnaire is about color and obtains information about preferred and dislike colors (see questions 1 and 2), the current psychological state of the subject (see questions 3 and 5), and color disposition (see questions 4 and 6).

Such a questionnaire may be provided to a diagnosis subject through a user interface provided in the psychological symptom diagnosis apparatus 10. The screen as shown in FIG. 3 is provided on the display screen, and the questionnaire response information of the diagnosis subject may be acquired by clicking or dragging and dropping the corresponding color icon for each item. Alternatively, the questionnaire response information of the diagnosis subject may be obtained by inputting numbers, symbols, and letters corresponding to the corresponding color for each item.

Here, the glyph coloring analysis module 11 receives a picture and analyzes glyph coloring, and the questionnaire response information input module 12 provides a questionnaire and obtains a response thereto in any order or simultaneously. .

The psychological symptom diagnosis module 13 is based on the factors analyzed in the pattern coloring analysis module 11 (color factor, concentration factor, etc.) and the questionnaire response information obtained from the questionnaire response information input module 12 based on the knowledge database. The psychological symptom of the subject to be diagnosed is diagnosed by searching for the knowledge stored in 14 and providing corresponding knowledge (step S23). In diagnosing a psychological symptom, knowledge stored in the knowledge database 14 and past history information stored in the history database 15 (for example, an analysis result of a pattern painted in the past by a diagnosis subject) may be utilized.

The knowledge database 14 includes both knowledge about the colors that appear in a general picture, knowledge about the colors that appear in a given pattern (e.g., mandala, etc.), knowledge about those colors, and knowledge that links personal propensity information. Knowledge of the psychological change obtained from the difference between the above-described colored patterns is stored.

Various knowledge may be stored in the knowledge database 14, some of which will be described below.

This knowledge is expressed in the form of IF THEN. IF THEN format is as follows. Not all representations of knowledge need to follow this form completely, and some representations may be omitted.

IF (n) condition 1, or condition 2, or. . . , or condition n,

THEN (m) result1, result2,. . . , Result m [degree of confidence of knowledge; Expression form].

.

Where n is the number of or conditions and m is the number of results. Multiple conditions of and are represented by one condition. When and and or are applied simultaneously in the result, it is indicated as and / or. If the confidence level of knowledge is 1, it is expressed as "is", 2 is "will be", 3 is "may be", 4 is "may be", 5 is "sometimes" And the like. In the screen providing, if the expression style is 1, it is expressed in the form of "is", and if it is 2, it is represented in the form of "is". In other cases, the statement may be displayed.

The following knowledge is used as an example to explain how to express knowledge.

"If you see a lot of red on the mandala, you're in a positive sense, you're healthy, you've got the energy to change, and you're hurting, destructive anger and pain." "

The content of the above knowledge is expressed as IF THEN rule as follows.

[Knowledge 1]

IF (2) subject color = red or subtitle = red,

THEN (4) Healthy survival, an energy being to acquire inner wisdom, anger with wounds and destructiveness, suffering [3; One].

Examples of knowledge linking the dispositions of individuals who responded to the survey with the colors in the colored patterns are:

"If you are happy with the subject color of the mandala in the document, it is judged to be in a good mood."

[Knowledge 2]

IF (1) input # 6 (3) = subject color,

THEN (1) current mood = good condition [2; 2].

Here, input # i (j) means the answer of the rumor item (j) of the question i of the questionnaire shown in FIG.

Color not only has a physical effect on human thinking processes and actions, but also subconscious mental effects beyond human consciousness. It is recognized that color is closely related to emotion. How to react to color and what color to use provides important information in analyzing the person's current emotional state. Although colors do not have the same meaning for everyone, the emotional meaning of red is regarded as violence, passion, aggressiveness, anger, and yellow as capacity and brown as shyness.

It has been reported that children with severe sexual abuse or depressed patients use only one or two colors in the picture. Patients with mental trauma choose color to express their mental pain, anxiety, fear, sadness, loneliness and despair. Children who suffer from natural disasters such as earthquakes, typhoons, and plane crashes tend to use only one, two, or at most three colors, and the colors are black, white, and in some cases red.

As described above, several expressions are presented as an example regarding the knowledge of colors appearing in general pictures used in art therapy. This knowledge also applies to the method for diagnosing psychological symptoms according to the present invention.

[Knowledge 3]

IF (0),

THEN "Johannes Itten wrote in his iconic art education book, The Art of Colors," Color is the energy that affects us in a positive or negative way irrespective of our consciousness. " △△△ through the color of the mandala prepared by the character and psychology to analyze and provide the results. "

[Knowledge 4]

IF (0),

THEN "In this system we have given meaning to and interpreted the colors in your mandala. But these meanings and interpretations are very common. All colors have both positive and negative meanings. It depends on the environment, experiences, and cultures that have grown up, so the meaning and interpretation of the colors provided by this system can be very different. "

Knowledges 3 and 4 are general knowledge to be shown at the beginning of the psychological symptom diagnosis apparatus according to the present invention in providing a diagnosis result, it is obvious that the present invention is not limited thereto.

Knowledge of colors in common pictures:

[Knowledge 5]

IF (1) number of colors used ≤ 2,

THEN (2) Serious sexual abuse experiences and / or depression.

[Knowledge 6]

IF (1) Number of Colors Used ≤ 3 and Colors Used = Black, White, Red,

THEN (1) Natural disasters such as earthquakes, typhoons and plane crashes.

[Knowledge 7]

IF subject color = red and red ratio ≥ 0.5,

THEN "You need to soften your violent and aggressive personality, or you're a passionate personality and look angry."

[Knowledge 8]

IF subject color = yellow and yellow ratio ≥ 0.3,

THEN Carrying character.

[Knowledge 9]

IF subject color = brown and brown ratio ≥ 0.3

THEN shy character.

[Knowledge 10]

IF (6) Subject color = red, or subject color = orange, or subject color = yellow, or subcolor = red and subcolor ratio ≥ 0.2, or subcolor = orange and subcolor ratio ≥ 0.2, or subcolor = Ratio of yellow and subcolor ≥ 0.2,

THEN "As an outgoing personality, you are active and free to express yourself. You seem to grow up with affection and want to depend on someone. Your relationships with others are smooth and well-matched. Self-centered. But cooperative and well adapted to the new environment. "

[Knowledge 11]

IF (1) the ratio of red ≥ 0.5,

THEN "I need to doubt whether I am mentally or mentally abnormal."

[Knowledge 12]

IF (1) the ratio of red ≤ 0.03,

THEN "You need to wonder if you're not too passive, what you lack the willingness to do, or if you're not too passive in your arguments."

[Knowledge 13]

IF complementary color = blue-orange,

The friction between desire to have a THEN relationship and achievement-oriented effort.

[Knowledge 14]

IF cold color ratio ≥ 0.7,

THEN "△△△ seems to be a very calm owner who reasonably solves the problems at hand."

Related Knowledge:

[Knowledge 15]

IF subject color = red,

THEN Positive aspects: love, sense, passion, self-confidence, strength, authority, endurance, independence, joy of life, life desire, acquisition, vitality, strong will, courage, improvisation, honesty, gratitude, forgiveness, human, extrovert or Negative aspects: instinct, anger, hate, self-pity, self-satisfaction, impatient personality, rude, dominant, arrogant, violent, cruel.

[Knowledge 16]

IF subject color = orange,

THEN Two-sided and / or self-consciousness and self-confidence and carelessness, careless disposition or energetic destination orientation and resonance.

[Knowledge 17]

IF subject color = orange,

THEN Positive aspects: energy, optimism, life needs, vitality, vitality, courage, strength, openness, youthful vitality, health, self-confidence, kindness, pure, sincere, joy, passion, self-confidence, independence, constructive, social, Delicacy, crisp, food-loving, energetic, sporty or negative aspects: power greed, self-examination, disdain, disposition to solve problems, morbid anorexia (or bulimia nervosa), alcoholism, arrogance.

Personal orientation knowledge:

Knowledge 18

IF input # 3 ≠ input # 5,

THEN "There is a contradiction in the response to the article. Please write more carefully."

[Knowledge19]

IF subject color = input # 6 (3),

THEN "△△△ seems to be happy now."

[Knowledge 20]

IF input # 4 (1) = input # 4 (2) and input # 4 (1) ≠ input # 4 (3),

THEN "△△△ 's closer to my father than my mother."

Knowledge of changing pattern coloring:

[Knowledge 21]

IF (5) (number of previous colors) x 1.3 ≤ number of current colors, or (number of previous clusters) x 1.3 ≤ number of current clusters, or (previous completeness) x 1.3 ≤ current completeness, or (previous accuracy) x 1.3 ≤ current accuracy, or (previous concentration) x 1.3 ≤ current concentration,

THEN "I wrote this with more sincerity than when I wrote the mandala, and I think you feel better than ever."

[Knowledge 22]

IF (1) previous subject color = red and current subject color = blue,

THEN "I feel calmer and cooler than before."

[Knowledge 23]

IF (1) the ratio of previous warm colors x 1.3 ≤ the ratio of current warm colors,

THEN "I feel more active and free than before."

In Knowledge 21, 23, 1.3 is a variable for detecting change and can be changed to any value.

In addition to the above-described knowledge, knowledge of various contents may be stored in the knowledge database 14.

In the diagnosis subject using the psychological symptom diagnosis apparatus 10, the history database 15 stores the analysis result of the pattern painted in the past by the diagnosis subject, and compares the result with the analysis result of the current painted pattern. It can be used when you want to measure psychological changes.

In addition, the psychological symptom diagnosing apparatus 10 may further include a result providing module. The result providing module may provide a pattern coloring analysis result shown in FIG. 17 and a psychological symptom diagnosis result shown in FIG. 18.

Hereinafter, the pattern coloring analysis module 11 will be described in detail with reference to FIGS. 4 to 16.

FIG. 4 is a block diagram of a pattern coloring analysis module according to an embodiment of the present invention, FIG. 5 is a block diagram of a color factor analysis unit included in a pattern coloring analysis module, and FIG. 6 is included in a pattern coloring analysis module. 7 is a block diagram illustrating a concentration factor analysis unit, and FIG. 7 is a flowchart illustrating a pattern coloring analysis method according to an embodiment of the present invention. 8 is a view showing a basic pattern according to an embodiment of the present invention, Figure 9 is a picture of the analysis target is colored on the basic pattern shown in FIG. FIG. 10 is a diagram illustrating a case in which a representative color image is converted from an analysis target figure, and FIG. 11 is a diagram illustrating a main color and a complementary color among primary color factors of an analysis target figure, and FIG. 13 is a view showing primary colors and secondary colors, FIG. 13 is a view showing warm colors and cold colors among the primary color factors of the analysis target picture, FIG. 14 is a view showing clusters extracted from the analysis target picture, and FIG. This is a diagram where the cluster of basic patterns overlaps with the cluster of the figure to be analyzed.

4 to 6, the pattern coloring analysis module 11, the input unit 110, the noise removing unit 120, the color factor analysis unit 130, the concentration factor analysis unit 140, and the color recognition module 131. ), Representative color conversion module 133, primary color factor extraction module 135, secondary color factor determination module 137, completeness measurement module 141, accuracy measurement module 143, concentration factor determination module 145 ) Is shown.

The input unit 110 receives a picture to be analyzed for pattern coloring (step S200). The picture painted by the diagnosis subject is subjected to the pattern coloring analysis. In the following, for the convenience of understanding and explanation of the invention, it is assumed that the figure to be analyzed is a geometric pattern given to a mandala (circle) colored in various colors, but in addition, general figure patterns such as people, birds, dogs, trees, etc. Can be analyzed.

The diagnosis subjects paint various colors within the basic pattern, which is the geometric pattern given to the mandala 800 shown in FIG. An example of a picture in which a diagnosis subject is painted in various colors (hereinafter referred to as an analysis object picture 900) is shown in FIG. 9.

The input unit 110 receives a picture file digitized and digitized using an image sensor such as scanned by a scanner or photographed by a camera. The picture file may have an image file type such as BMP, GIF, JPEG, TIF, etc. that may be analyzed for each pixel in a digital device such as a computer, or may have a file type that may be interpreted by the pattern coloring analysis module 11.

The noise removing unit 120 removes noise such as an unpainted portion, a weakly painted portion, and an overlapped portion, unlike the intention of the diagnosis subject (step S210). The noise removing unit 120 removes the noise of the picture through a blurring and clustering process. In the blurring process, a median 3 × 3 mask, which is generally used for noise reduction of an image, is applied. This will be apparent to those of ordinary skill in the art, detailed description thereof will be omitted. In the clustering process, the colors in the picture collect similar colors. In addition, it is possible to segment a color image using color features and spatial connectivity of pixels. The noise removing unit 120 may be additionally included in the pattern coloring analysis module 11 in order to increase the reliability of the analysis.

The pattern coloring analysis module 11 analyzes a color factor and a concentration factor on an input picture. Color factors and concentration factors can be analyzed in any order or simultaneously.

First, the color factor analysis is performed in the color factor analyzer 130 (step S220). The color factor analysis unit 130 analyzes the color of the picture input to the input unit 110. The picture is analyzed by dividing it into pixels. For example, if the picture is 480 × 640, it is divided into 307,200 pixels and analyzed.

Referring to FIG. 5, the color factor analyzer 130 includes a color recognition module 131, a representative color conversion module 133, a primary color factor extraction module 135, and a secondary color factor determination module 137. do.

The color recognition module 131 recognizes colors used for each pixel of the picture file input to the input unit 110 (step S221).

The representative color conversion module 133 converts the color recognized by the color recognition module 131 into one of a plurality of preset representative colors (step S223). The color space representing a plurality of preset representative colors varies according to the purpose and concept of RGB, YUV, HSV, LUV, CIEXYZ, CIELAB, HVC, and the like. Among these, HVC, called Munsell color system, is similar to color recognition by human eyes. HVC has three attributes of color, hue, value, and saturation, and color can be expressed as HV / C. Hereinafter, the present invention will be described on the assumption that the representative colors are classified and set based on the HVC, but it is obvious that the colors can be classified and set by other color spaces.

The representative color conversion module 133 converts the color of each pixel into one of the representative colors according to the classification of the preset number of colors. Alternatively, the image may be converted into any one of the first representative colors according to the classification of more colors, and then reconverted into one of the second representative colors according to the classification of fewer colors.

Hereinafter, for convenience of understanding and explanation of the present invention will be described based on 15 color classification and / or 47 color classification.

Based on the HVC, the color classification which has 15 colors classified by the object color name according to Korean Industrial Standard KS A 0011 as the representative color is called '15 color classification '. Representative colors by 15 color classification are as shown in Table 1 below. A set of representative colors by 15 color classifications

A15 = {red, orange, yellow, light green, green, teal, blue, indigo, violet, purple, pink, brown, white, grey, black}

Indicated by. Table 1 below is given (h _i , v _i , c _i ) values for each representative color I included in A15.

The representative color conversion module 133 converts the color of the picture into the representative color included in A15 according to the 15 color classifications shown in Table 1 above. The method of finding the closest representative color in converting the representative color is as follows.

The distance is defined as a measure of the color difference between the colors in the picture and the 15 representative colors. The National Bureau of Standards (NBS) uses Equation 1 below as a distance measure of two colors (h ₁ , v ₁ , c ₁ ) and (h ₂ , v ₂ , c ₂ ) in the HVC space. present.

dis [(h ₁ , v ₁ , c ₁ ), (h ₂ , v ₂ , c ₂ )] is called the NBS distance between the two colors. The representative color with the shortest NBS distance from the color is set as the representative color closest to the color, and the color is converted into the representative color.

According to another embodiment of the present invention, the representative color may be further subdivided by 47 color classifications in addition to 15 color classifications. For example, red is subdivided into dark red, red, and light red. 47 color classifications are defined in Korean Industrial Standard KS A 0011. The representative color classification is called '47 color classification ', and the set of representative colors according to the 47 color classification is called A47.

It is possible to classify colors by 15 color classification after classifying by 47 color classification. Humans are divided into red lines, blue lines, green lines, etc., and the differences between these lines are insignificant. For example, the difference between the blue system and the green system can be distinguished by the slightest difference, but the NBS distance according to the 15-color classification does not have a big difference, and thus sometimes changes. Therefore, after classifying each color of the picture in detail by 47 color classification, and combining each color with the same or similar system according to the 15 color classification, it is possible to convert the color of the picture to the representative color according to the 15 color classification accurately. do.

A method of classifying a color (h, v, c) of a given picture as a representative color according to 47 color classifications is to find a representative color j that satisfies Equation 2 below.

That is, the representative color conversion module 133 according to another embodiment finds a first representative color satisfying Equation 2 between a color of a given picture and a first representative color according to 47 color classifications, and then, the first representative color and the first representative color. Find the second representative color closest to the first representative color by determining the NBS distance between the second representative colors according to the 15 color classifications, and determine the second representative color as the representative color to convert the color of the given picture into the representative color. .

A picture file 1000 classified as a representative color according to 15 color classifications by the representative color conversion module 133 is illustrated in FIG. 10.

The primary color factor extracting module 135 extracts a predetermined primary color factor with respect to the picture file classified as the representative color according to the 15 color classification by the representative color conversion module 133 (step S225).

The primary color factor may be the number of colors, the type of colors, the area per color, the number of clusters per color, and the contour of the color. The number and type of colors are also important factors in the evaluation of general art therapy, and the mixing of colors, the suitability of colors, and the degree of use of colors may be additionally considered.

The number of colors means the number of representative colors used in the picture file classified as the representative color according to the 15 color classification, and the type of colors is the type of representative colors used in the picture file classified as the representative color according to the 15 color classification Means. The area by color means the number of pixels classified as the representative color by the representative color, and the number of clusters by color means the number of such clusters when the minimum area in which any representative color is continuously painted is one cluster. .

The outline of the color means the boundary between the representative colors for the picture files classified as the representative colors according to the 15 color classifications. The pixels corresponding to the contour coordinates are extracted by changing the representative colors of the pixels in the top, bottom, left, and right directions of the arbitrary pixels, and the set of the contour coordinates becomes the outline.

The secondary color factor determination module 137 determines the secondary color factor using the extracted primary color factor (step S227). The secondary color factor determination module 137 determines the secondary color factor by using a knowledge base built in advance from the extracted primary color factor. As the secondary color factors, the main color and sub-color, primary and secondary colors, warm and cold colors, complementary colors, and variety of colors may be determined. The condition for determining the secondary color factor, that is, the knowledge base, may be stored in advance in the secondary color factor determination module 137.

Details of the secondary color factors are as follows.

(i) Subject colors and subtitle colors are defined as follows.

The subject color is the most used color and the subtitle color is the second most used color. However, if the painted area is less than the A% (for example, 20%, etc.) of the entire area of the figure or the basic pattern (e.g., the outermost circle in the case of the mandala) that is the object of the pattern coloring analysis. It can be assumed that there is no subtitle color.

After converting the analysis target image 900 illustrated in FIG. 9 to a representative color (see 1000 in FIG. 10), the most used color among the representative colors is 30.1% of purple (see 1100 in FIG. 11). The next most used color is red, which accounts for 22.0%. Therefore, these are judged as the main color and the subtitle color, respectively.

(ii) The primary and secondary colors are defined as follows.

Primary colors are red, blue, and yellow. Secondary colors are green, purple, and orange. The primary color is represented by yellow (see 1200 in FIG. 12) and the secondary color is represented by green (see 1210 in FIG. 12). The primary color is 40.4% and the secondary color is 34.0%.

(iii) Complementary color is defined as follows.

The third most commonly used color, with an area of over the main and sub-colors or B% (e.g. 12%), is (1) red and cyan, (2) blue and orange, (3) indigo and orange, ( 4) yellow and violet or (5) green and purple. Referring to FIG. 11, yellow is 14.4%, the third most commonly used color (see 1110 of FIG. 11), and since the main color is purple (see 1100 of FIG. 11), it is determined that there are complementary colors of yellow and violet.

(iv) Warm and cold colors are defined as follows.

Warm colors are red, orange and yellow, and cold colors are blue and indigo. Referring to FIG. 13, a warm color is represented by red (see 1300 in FIG. 13), and a cold color is represented by blue (see 1310 in FIG. 13). Warm color is 40.4% and cold color is 4.0%.

(v) The variety of colors is defined as follows.

Refers to the general concept of the use of color, which is evaluated individually by the art evaluator's professional experience and knowledge.

There are two ways of evaluating color diversity.

First way:

Step 1. The greater the number of colors used, the higher the variety of colors.

Step 2. If the number of colors used is the same, the greater the number of clusters, the higher the variety of colors. Here, the cluster means the minimum area surrounded by the outline.

Step 3. If both the number of colors used and the number of clusters are the same, the longer the outline length, the higher the color variety.

Second way:

Apply the regression model, a statistical method. In this model, the dependent variable is the evaluation of the diversity of the color of the art evaluator, and the independent variables are the number of colors, the number of clusters, the slope of the contour line, and the color used. Independent variables representing the colors used are represented by one less than the number of possible colors.

As described above, the secondary color factor determination module 137 may determine various secondary color factors from the primary color factor extracted by the primary color factor extraction module 135.

In addition to the color factor analysis, the concentration factor analyzer 140 analyzes the concentration factor (step S230).

Referring to FIG. 6, the concentration factor analyzer 140 may include a completeness measurement module 141, an accuracy measurement module 143, and a concentration factor determination module 145.

The completeness measurement module 141 measures the completeness of the coloring task of the diagnosis subject from the analysis target image 900 (step S231). The completeness is measured as the ratio of the number of pixels painted within the basic pattern to the total number of pixels of the basic pattern (eg, the circle disposed at the outermost portion of the basic pattern shown in FIG. 8).

The accuracy measuring module 143 measures the accuracy of the coloring task of the diagnosis subject from the analysis target picture 900 (step S233). The accuracy is measured from the degree of correspondence between the cluster of basic patterns and the color cluster of the image 900 to be analyzed. The color cluster of the analysis target image 900 may be derived using the contour extracted by the primary color factor extraction module 135. The basic pattern cluster means a minimum area surrounded by lines in a given basic pattern. Referring to FIG. 8, the number of basic pattern clusters is 64. The color cluster means a minimum area continuously painted with the same color in the analysis target image 900. Referring to FIG. 14, the number of color clusters is 18. The overlapping form of the basic pattern cluster and the color cluster is shown in FIG. 15.

A method for quantitatively deriving the degree of agreement between the basic pattern cluster and the color cluster is illustrated in FIG. 16. 16 is a flowchart of a method of measuring accuracy according to an embodiment of the present invention. Here, it is assumed that the color of each pixel is converted to the representative color.

Areas other than the basic pattern are excluded (step S1600).

The number of pixels is calculated for each representative color in any basic pattern cluster (step S1610). The representative color having the largest number of pixels is determined as the color accurately painted in the basic pattern cluster (step S1620). If the representative color with the largest number of pixels is white, the basic pattern cluster is considered unpainted, and the basic pattern cluster determines that the number of pixels accurately painted is not.

Steps S1610 to S1620 are repeated for each basic pattern cluster (step S1630).

Then, the number of pixels of exactly painted colors in each basic pattern cluster is added (step S1640).

The value obtained by dividing the number of pixels of the color accurately painted by the total number of pixels of the analysis target picture is determined with accuracy (step S1650).

Through the above-described method, the accuracy measuring module 143 may measure the accuracy as quantitative data.

The concentration factor determination module 145 determines the concentration factor based on the completeness measured by the completeness measurement module 141 and the accuracy measured by the accuracy measurement module 143 (step S235).

In the present invention, the degree of concentration may be related to the number of colors and the number of clusters as well as the degree of completeness and accuracy. This relationship is explained by the following regression method.

Collect n analytical picture samples, and m evaluators rank and rank concentrations. The picture with the highest concentration is rank 1, and the lowest picture is rank n. The rank average of m people for the sample sample i to be analyzed is expressed as Y _i . Multiple linear regression analysis is applied with the number of colors in each sample as X _i1 , the number of clusters as X _i2 , the degree of completeness as X _i3 , and the accuracy as X _i4 .

That is, the regression model is as shown in Equation 3 below.

Y _i = β ₀ + β ₁ X _i1 + β ₂ X _i2 + β ₃ X _i3 + β ₄ X _i4 + ε _i , i = 1, 2, ..., n

Here, ε _i assumes a normal distribution that is independent of each other and that all have mean 0 and variance σ ² .

β ₀ is a constant coefficient, β ₁ is the number of colors, β ₂ is the number of clusters, β ₃ is the coefficient of completeness, and β ₄ is the coefficient of accuracy.

β ₁ , β ₂ , β ₃ , and β ₄ are negative in sign. The higher the number of colors and clusters, and the higher the degree of completeness and accuracy, the smaller the rank, which is the dependent variable, that is, the higher the concentration.

In addition, the standardized value to grasp the relative influence on the concentration of each independent variable

Y _i '= {(Y _i -S (Y)} / S (Y),

X _ij '= {(X _ij -S (X _j )} / S (X _j ), i = 1, 2, ..., n, j = 1, 2, 3, 4

It also provides the results of standard regression analysis using. Where S (Y) and S (X _j ) represent the sample standard deviations of Y and X _j , respectively.

In one embodiment, the analysis data in the case where 58 images of analysis subjects (n = 58) are collected as samples is as follows.

The regression analysis results are shown in Table 2 below.

As a result of applying stepwise regression to the collected data, the number of colors (X ₁ ), the number of clusters (X ₂ ), and the accuracy (X ₃ ) were selected as variables to explain the concentration of the evaluator. . The completeness was excluded because of the high correlation between completeness and accuracy.

Finally the regression function is Y _{= 65.171 - 2.973 X 1 - 0.666} X 2 - X ₃ is 0.241.

The coefficient of determination indicating the goodness of fit of the model is R ² = 0.740, and the model is sufficient for application. The standard error was estimated at 8.44.

Negative sign of the coefficients is a desirable result as described above. That is, the more the number of colors and clusters as explanatory variables, and the higher the accuracy, the lower the rank value (the higher the concentration) as the dependent variable. For example, when the number of clusters and the accuracy are constant, the number of colors used increases by one, and the ranking value of the concentration decreases by 2.973 on average.

The regression function using the standardized values of the independent variables is Y ' = - it is _{0.337 X 3 '- 0.461 X 1} ' - 0.239 X 2 '. For example, when the accuracy increases by 1-sample standard deviation (22.56%), the ranking value decreases by 0.337-sample standard deviation (16.12) = 5.43 (higher concentration). The magnitude of the influence of the explanatory variable on the concentration from the standardized coefficients is in the order of color number, accuracy, and cluster number.

As described above, the concentration factor analyzer 140 determines the concentration factor and calculates the concentration factor as quantitative data.

The pattern coloring analysis module 11 may provide the color factor analyzed by the color factor analyzer 130 and the concentration factor analyzed by the concentration factor analyzer 140 as quantitative data. The evaluator will be able to apply the art therapy using the output data corresponding to the picture to be analyzed.

The pattern coloring analysis module 11 according to the embodiment of the present invention described above is accurate and objective information (for example, primary color factors (number, type, number of clusters, contours, etc.), secondary color factors ( Subject and subtitle colors, primary and secondary colors, complementary colors, warm and cold colors, color variations, etc.) and concentration factors (calculated from completeness and accuracy) are output as quantitative data. The evaluator uses the quantitative data output to diagnose the psychological symptom of the subject who is colored the analysis subject.

FIG. 17 is a diagram illustrating a result of analyzing colored patterns in a pattern coloring analysis module 11 according to an embodiment of the present invention.

Referring to FIG. 17, primary color factors such as a picture of a colored pattern, a percentage of each color, a number of colors, and a number of clusters, a main color, a sub-color, a complementary color, a primary color and a secondary color, and a warm color Secondary color factors such as color and light, and concentration factors of accuracy, completeness, and concentration are analyzed.

The psychological symptom diagnosis module 13 diagnoses based on the results analyzed by the pattern coloring analysis module 11 (see FIG. 17) and the results obtained by the questionnaire response information input module 12 (see FIG. 3). Diagnose the psychological symptoms of the subject. The result is shown in FIG.

The analysis results shown in FIGS. 17 and / or 18 may be provided in graphics and diagrams for easy grasp by the user.

In addition, according to another embodiment of the present invention, the psychological symptom diagnosis apparatus 10 may predict a psychological change of a diagnosis subject by analyzing a difference between two or more pictures (colored patterns). In this case, the psychological symptom diagnosing apparatus 10 may include a history database 15. The psychological symptom diagnosis module 13 compares the analysis result of the past picture stored in the history database 15 with the analysis result of the current picture analyzed by the glyph coloring analysis module 12 and compares it from the knowledge database 14. By predicting and providing knowledge based on the result, the psychological change of the diagnosis subject is predicted.

19 and 20 show past and present pictures of patterns colored by the same diagnosis subject. Here, it is assumed that the diagnosis subject answered the question as shown in FIG. 3 as follows.

Question 1. (1) Favorite color: Red, (2) Disliked color: Black

Question 2. Favorite color among (1) primary colors: Red, (2) Favorite color of secondary colors: Orange, (3) Favorite color of achromatic colors: White

Question 3. The face that corresponds to my heart now: happiness

Question 4. (1) My Color: Red, (2) Father's Color: Blue, (3) Mother's Color: Green

Question 5. I feel now: very happy

Question 6. (1) Color when sad: grey, (2) Color when angry: black, (3) Color when happy: red.

The results of analyzing the pattern coloring shown in FIG. 19 and the pattern coloring shown in FIG. 20 are shown in Table 3 below.

The pattern coloring analysis results of the figure shown in FIG. 19 and the figure shown in FIG. 20 are as follows. Looking at the differences between the two plots, we can predict that a positive change in psychology is occurring due to better numbers in all aspects of accuracy, number of colors, number of clusters, completeness, and concentration. The increasing use of primary and warm colors can predict emotionally active changes.

That is, the psychological symptom diagnosing apparatus 10 may search for and provide the knowledge of the knowledge database 14 from the difference between the two pictures to predict and provide the psychological change of the diagnosis subject as described above. Here, the related knowledge is [Knowledge 1], [Knowledge 2], [Knowledge 3], [Knowledge 4], [Knowledge 13], [Knowledge 15], [Knowledge 19], [Knowledge 21].

Meanwhile, the above-described accuracy measuring method, pattern coloring analysis method, and psychological symptom diagnosis method can be prepared by a computer program. The codes and code segments that make up the program can be easily deduced by a computer programmer in the field. In addition, the program is stored in a computer readable media, and read and executed by a computer to implement a method for providing a document search service. The information storage medium includes a magnetic recording medium, an optical recording medium, and a carrier wave medium.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention as defined in the appended claims. It will be understood that the invention may be varied and varied without departing from the scope of the invention.

1 is a block diagram of a symptom prediction apparatus according to an embodiment of the present invention.

2 is a flow chart of a method for diagnosing psychological symptoms according to an embodiment of the present invention.

3 is an illustration of a questionnaire for diagnosing psychological symptoms.

Figure 4 is a block diagram of a pattern coloring analysis module according to an embodiment of the present invention.

5 is a block diagram of a color factor analysis unit included in the pattern coloring analysis module.

Figure 6 is a block diagram of a concentration factor analysis unit included in the pattern coloring analysis module.

7 is a flow chart of a pattern coloring analysis method according to an embodiment of the present invention.

8 is a view showing a basic pattern according to an embodiment of the present invention.

FIG. 9 is an analysis target picture in which the basic pattern shown in FIG. 8 is colored.

10 is a diagram illustrating a case where a representative color conversion of the analysis target picture is performed;

11 is a diagram showing a subject color and complementary colors among the primary color factors of the analysis target picture;

12 is a view showing a primary color and a secondary color among the primary color factors of the analysis target picture;

13 is a view showing warm and cold colors of the primary color factors of the analysis target picture.

14 is a diagram showing a cluster extracted from an analysis target picture.

15 is a diagram in which a cluster of basic patterns overlaps with a cluster of the analysis target figure.

16 is a flowchart of a method of measuring accuracy according to an embodiment of the present invention.

17 is a pattern coloring analysis results according to an embodiment of the present invention.

18 is a psychological symptom diagnosis result according to an embodiment of the present invention.

19 and 20 show past and present pictures of a pattern painted by the same diagnosis subject.

<Description of the symbols for the main parts of the drawings>

10: psychological symptom device

11: pattern coloring analysis module 12: questionnaire response information input module

13: Psychological Symptom Diagnosis Module 14: Knowledge Database

15: history database

110: input unit 120: noise canceling unit

130: color factor analysis unit

131: color recognition module 133: representative color conversion module

135: primary color factor extraction module 137: secondary color factor determination module

140: concentration factor analysis unit

141: completeness measurement module 143: accuracy measurement module

145: concentration factor determination module

Claims (20)

In the method for diagnosing psychological symptoms, Receiving response information about a questionnaire of a diagnosis subject; Receiving analysis object image information which is a picture painted by the diagnosis subject in a predetermined basic pattern; Calculating color factor information of the analysis target image information; Calculating concentration factor information of the analysis target image information; and Extracting at least one of the calculated color factor information and the calculated concentration factor information and psychological symptom information corresponding to the response information from a knowledge database, The color factor information is information including at least one of the number of converted representative colors, the type of the representative colors, the number of color clusters, and the contour information of the representative colors. The representative color is at least one color among a color classification of a predetermined number of colors, and the color cluster is a minimum area in which the representative color is continuously painted, The concentration factor information is completeness information which is a ratio of the total number of pixels located on the basic pattern and the number of pixels colored in the basic pattern; Psychotic symptom diagnosis method, characterized in that calculated using the accuracy information that is the ratio of the sum of the number of pixels of the maximum number of pixels of the representative pattern of each basic pattern cluster to the total number of pixels of the analysis target image information. . delete delete delete The method of claim 1, Calculating color factor information of the analysis target image information and calculating concentration factor information of the analysis target image information are performed in any order or simultaneously. The method of claim 1, The calculating of the color factor information may include: Converting a color of each pixel included in the analysis target image information into one of representative colors; Calculating first color factor information from the representative color; And Further calculating second color factor information from the representative color; The first color factor information is information including at least one of the number of converted representative colors, the type of the representative colors, the number of color clusters, and the contour information of the representative colors. The second color factor information may include at least one of subject color information and subtitle color information, wherein the subject color information is a color having a maximum number of pixels for each color of the representative color of the analysis target image information. And a second largest number of pixels for each color of the representative color of the analysis target image information. delete The method of claim 6, The second color factor information further includes at least one of first primary color information, second secondary color information, warm color information, and light color information. The primary color information is information on at least one color of red, yellow, and blue, The secondary color information is information on at least one color of orange, green, and violet, The warm color information is information on at least one of red, orange, and yellow colors. The cold color information is psychological symptom diagnosis method, characterized in that the information on at least one color of blue, indigo blue. The method of claim 1, The representative color is a color included in the 15 color classification according to the Korean Industrial Standard KS A 0011 or a color included in the 47 color classification according to KS A 0011. The method of claim 1, The step of converting the color of each pixel included in the analysis target image information into any one of the representative colors may be performed using the following Equation 1 (h _1, v _1, c ₁ ): And the National Bureau of Standards (NBS) distance is converted to the shortest representative color (h _2, v _2, c ₂₎ . [Equation 1]

Here, h ₁ and h ₂ are color information (Hue), v ₁ and v ₂ are brightness information (Value), and c ₁ and c ₂ are chroma information (Chroma). The method of claim 1, Calculating concentration factor information of the analysis target image information And the concentration factor information is calculated using a multiple linear regression analysis method using the completeness information and the accuracy information as an explanatory variable and the concentration factor information as a dependent variable. The method of claim 1, The accuracy information is Computing the number of pixels corresponding to each representative color among the pixels included in each basic glyph cluster Selecting a cluster subject color corresponding to each of the basic pattern clusters, wherein the cluster subject color is a color having a maximum number of pixels among representative colors of the basic pattern clusters; Summing the number of pixels of the cluster subject colors selected corresponding to the basic pattern clusters; And And calculating the accuracy information by dividing the pixel numbers of the sum of the cluster subject colors by the total number of pixels of the analysis target image information. delete delete A computer readable recording program for executing a method for diagnosing the psychological symptom according to any one of claims 1, 5, 6, 8 to 10, 11 and 12 on a computer. Record carrier. A questionnaire response information input module for receiving response information on a questionnaire of a diagnosis subject; A pattern coloring analysis module configured to receive analysis object image information, which is a picture painted by the diagnosis subject, into a predetermined basic pattern, and calculate color factor information and concentration factor information of the analysis object image information; Including at least one information of the calculated color factor information and the calculated concentration factor information and psychological symptom information corresponding to the response information from the knowledge database comprises a psychological symptom module, The color factor information is information including at least one of converted number of representative colors, type of representative colors, number of color clusters, and outline information of the representative colors, and the representative colors are color classifications of a preset number of colors. At least one of the colors, wherein the color cluster is a minimum area painted with the representative color continuously, The concentration factor information sums the completeness information which is the ratio of the total number of pixels positioned on the basic pattern to the number of pixels painted in the basic pattern and the number of pixels having the maximum number of pixels among the representative colors of each basic pattern cluster. And psychological symptoms calculated using accuracy information, which is a ratio of the number of one pixel to the total number of pixels of the analysis target image information. The method of claim 16, Further comprising a history database for storing the results analyzed by the pattern coloring analysis module, The psychological symptom diagnosis module predicts a psychological change of the diagnosis subject based on a difference between psychological symptom information corresponding to current analysis target image information and psychological symptom information of past analysis target image information stored in the history database. Psychological Symptom Diagnosis Device. The method of claim 16, The pattern coloring analysis module A color factor information analyzer for calculating color factor information included in the analysis target image information; And a concentration factor information analysis unit for calculating concentration factor information included in the analysis target image information. The method of claim 18, The color factor information analysis unit A color recognition module recognizing a color of each pixel included in the analysis target image information; The representative color conversion module for converting the recognized color of each pixel into one of the representative colors; And And a color factor information extraction module for extracting the color factor information from the converted representative color. The method of claim 18, Concentration factor information analysis unit A completeness measurement module for calculating completeness information that is a ratio of the total number of pixels positioned on the basic pattern and the number of pixels colored in the basic pattern; An accuracy measuring module for calculating accuracy information, which is a ratio of the sum of the number of pixels of the maximum number of pixels among the representative colors of the basic pattern clusters to the total number of pixels of the analysis target image information; And And a concentration factor determining module for calculating the concentration factor information by using the multiple linear regression analysis method using the completeness information and the accuracy information as explanatory variables and the concentration factor information as a dependent variable. Diagnostic device.

Images