Evaluation method

Abstract

An evaluation method according to the present disclosure is for evaluating scalp hair, the evaluation method including: a presentation step (S102) for presenting, to a subject, the entire scalp hair when viewed in at least a certain direction; a data acquisition step (S103) for tracking the movement of the subject's sightline with respect to the scalp hair to acquire sightline data; and an evaluation step (S104) for conducting the evaluation of the scalp hair on the basis of the sightline data. The evaluation method also includes a condition presentation step (S101) for presenting, to the subject, observation conditions relating to scalp hair before implementing the data acquisition step.

Description

Evaluation method

[0001] This disclosure relates to an evaluation method for evaluating hair.

[0002] Patent Document 1 discloses an information processing apparatus including means for presenting an image including a face to a user, means for acquiring gaze information regarding the movement of the user's gaze, means for calculating the deviation of the user's gaze in the image based on the gaze information, means for determining recommendation information regarding the image based on the deviation of the gaze, and means for presenting the recommendation information.

[0003] Specifically, a line connecting the midpoint of the line connecting both eyes of the presented face image and the center of the nose is used as a reference line to divide the face into left and right. The gaze distribution on the left side of the face (the frequency of directing the gaze to the left side when looking at the face) and the gaze distribution on the right side of the face (the frequency of directing the gaze to the right side when looking at the face) are obtained. When the gaze distribution on the right side of the face is a predetermined value or more, presenting the recommendation information is performed.

[0004] Note that in Patent Document 1, there is a research result that the sense of self appears in the right half of the face, and it is explained that when a person looks at their own face reflected in a mirror, there is a tendency to feel a sense of self on the right side from the observer.

[0005] Also, Patent Document 1 describes that there is a research result that humans and primates tend to look at the left half of the face from the observer when gazing at people or animals.

[0006] From these research results, in Patent Document 1, it is explained that a makeup simulation image (face image) with a gaze distribution on the right side of the face being a predetermined value or more can also be said to be an image in which the user's potential evaluation exceeds a certain standard (for example, an image with a certain degree of high interest, an image with a certain degree of self - feeling, an image with a certain degree of affinity, or an image with a certain degree of impression).

[0007] International Publication No. 2019 / 208152

[0008] Incidentally, while evaluations related to the face (for example, evaluations of makeup, evaluations of the impression with a mask on, etc.) are available, evaluations of hair are limited to only a few aspects, such as the measurement of the cuticle of a single hair, hair friction, and shine.

[0009] This is because it is difficult to quantify the subjective evaluation of the overall finish of the hair and translate it into a highly objective qualitative or quantitative evaluation.

[0010] This disclosure is made in light of these circumstances, and one of its purposes is to provide a more objective method for evaluating hair.

[0011] The evaluation method of the present disclosure is an evaluation method for evaluating hair, the evaluation method comprising: a presentation step of presenting the entire hair of a subject as seen from at least one direction; a data acquisition step of tracking the movement of the subject's gaze toward the hair and acquiring gaze data; and an evaluation step of performing an evaluation of the hair based on the gaze data.

[0012] This disclosure provides a method for evaluating hair with increased objectivity.

[0013] This is a perspective view showing an evaluation device for performing the hair evaluation method of the first embodiment of this disclosure. This is a block diagram showing the hardware configuration of the evaluation device for performing the hair evaluation method of the first embodiment of this disclosure. This is a block diagram showing the software configuration of the evaluation device for performing the hair evaluation method of the first embodiment of this disclosure. This is a flowchart showing the flow of the hair evaluation method of the first embodiment of this disclosure. This is a diagram showing the output screen displaying an image of the entire hair presented to the subject by the image presentation unit of the first embodiment of this disclosure. This is a diagram showing the state of the gaze data acquired in a test example of the first embodiment of this disclosure. This is a diagram showing the state of the gaze data acquired in a second test example of the first embodiment of this disclosure. This is a diagram for explaining an example of dividing hair into multiple locations in the second embodiment of this disclosure.

[0014] The embodiments for implementation (hereinafter referred to as "Embodiments") will be described in detail below with reference to the attached drawings. Throughout the description of the embodiments, the same elements will be denoted by the same numbers or reference numerals.

[0015] Furthermore, the dimensional ratios in the drawings differ from the actual dimensional ratios and are merely for illustrative purposes to make the explanation easier to understand; there is no guarantee that identical parts are depicted with the same dimensions across different drawings.

[0016] Furthermore, for the sake of readability, in drawings, only some of the parts with the same attribute that exist in multiple locations may be assigned reference numerals.

[0017] <<First Embodiment>> An evaluation method for evaluating hair according to the first embodiment of this disclosure, and an evaluation apparatus 1 for performing the evaluation method, will be described with reference to Figures 1 to 7.

[0018] Furthermore, "hair" is not limited to natural hair, but also includes non-natural hair such as wigs, and refers to hair that the subject recognizes to some extent as a hairstyle.

[0019] Figure 1 is a perspective view showing an evaluation apparatus 1 that performs an evaluation method for evaluating hair according to the first embodiment of this disclosure. Figure 2 is a block diagram showing the hardware configuration of the evaluation apparatus 1 that performs an evaluation method for evaluating hair according to the first embodiment of this disclosure.

[0020] As will be described later, the evaluation device is equipped with an eye tracker that has an output screen 61 (monitor) positioned on the upper side and an imaging unit 53 configured for eye tracking on the lower side. This makes it easier for the evaluation device to adopt an output screen 61 suitable for presenting a hair image (hairstyle) of near life-size to the subject. The output screen 61 is most preferably a 23.8-inch monitor, for example.

[0021] However, it is not limited to this. The evaluation device may be, for example, a notebook personal computer (notebook PC) or a desktop PC (personal computer). The evaluation device is acceptable as long as it can have an eye tracker, which is configured for eye tracking, attached to the bottom of the screen.

[0022] Furthermore, the evaluation device 1 may be in the form of a tablet terminal, and the evaluation device 1 may also be composed of multiple machines.

[0023] For example, the evaluation device 1 may include a machine (such as a mechanically configured machine like a physical server or a virtually configured machine like a cloud server) that performs some of the processing described below (such as the evaluation steps described later), separate from the eye tracker. In this case, the necessary data (such as gaze data described later) is sent from the eye tracker via the network to a machine separate from the eye tracker (a physical server or cloud server). This machine may be configured to perform the evaluation processing.

[0024] In other words, the evaluation processing unit 140, described later, may be configured as a separate machine (physical server or cloud server) from the eye tracker.

[0025] In this case, the results of the evaluation process can be sent back to the other machine wherever the output is desired.

[0026] For example, if you want to output the results of the evaluation process to the output unit 60 (output screen 61, sound output unit (not shown)) described later, you can send the evaluation results back to the eye tracker from the machine that performed the evaluation process, which is a different machine from the eye tracker.

[0027] <Hardware Configuration of Evaluation Device 1> As shown in Figures 1 and 2, the evaluation device 1 has a hardware configuration comprising a CPU 10 (see Figure 2), a ROM 20 (see Figure 2), a RAM 30 (see Figure 2), a storage unit 40 (see Figure 2), an input unit 50, an output unit 60, and a communication unit 70 (see Figure 2).

[0028] As shown in Figure 2, the CPU 10, ROM 20, RAM 30, storage unit 40, input unit 50, output unit 60, and communication unit 70 are connected by a bus BS to enable mutual exchange of data and other information.

[0029] [CPU 10] The CPU 10 is a Central Processing Unit that controls the entire evaluation device 1 according to the program and installed applications.

[0030] Alternatively, instead of the CPU 10, a GPU (Graphics Processing Unit) that controls the entire evaluation device 1 may be used.

[0031] [ROM20] ROM20 is a Read Only Memory that stores programs and parameters that do not require modification.

[0032] For example, ROM20 stores programs for eye tracking (also known as gaze tracking), which will be described later. These programs are then loaded into RAM30, and the CPU10 performs eye tracking control according to these loaded programs.

[0033] The specific eye-tracking method may follow either the bright pupil method or the dark pupil method, or it may be a combination of both.

[0034] [RAM 30] RAM 30 is Random Access Memory that temporarily stores programs and data supplied from external devices, etc.

[0035] For example, RAM 30 temporarily stores data such as the viewpoint position (described later) and the time spent at that viewpoint position (described later) acquired by eye tracking.

[0036] [Storage Unit 40] The storage unit 40 is a non-volatile storage device (for example, a hard disk) that stores data that needs to be saved.

[0037] For example, the memory unit 40 stores image data of the subject's hair, observation conditions (described later) to be presented to the subject, and so on.

[0038] Note that the storage unit 40 may store data such as the viewpoint position (described later) acquired by eye tracking and the dwell time (described later) at that viewpoint position.

[0039] [Input unit 50] The input unit 50 is a part for performing inputs such as when an operator, a subject, or the like operates the evaluation device 1.

[0040] Note that the input unit 50 is also a part for inputting (capturing) the movement of the eyes of the subject during eye tracking into the evaluation device 1.

[0041] Specifically, as shown in FIG. 1, the input unit 50 includes a wireless keyboard 51, a wireless mouse 52, an imaging unit 53, and a sound acquisition unit (not shown).

[0042] (Wireless keyboard 51) The wireless keyboard 51 includes a first input area 51A where inputs such as letters can be made provided on the left side, and a second input unit 51B provided with a numeric keypad or the like for inputting numbers.

[0043] For example, the subject can select an answer to observation conditions or the like by operating the second input unit 51B as described later.

[0044] Note that the answer of the subject to observation conditions or the like described later may be that the subject answers orally, and the sound acquisition unit (not shown) acquires the oral answer by voice recognition.

[0045] Also, it is not necessarily the case that the subject must answer observation conditions or the like, and there may be cases where an answer is not required.

[0046] On the other hand, instead of the wireless keyboard 51, the evaluation device 1 may connect a notebook PC or the like via USB and use the keyboard unit of the notebook PC as a keyboard for inputs or the like.

[0047] Thus, it is not limited to the wireless keyboard 51, and any configuration that can perform necessary input operations is acceptable.

[0048] (Wireless Mouse 52) The wireless mouse 52 is the part that is operated when moving the position of the cursor on the screen.

[0049] Also, the wireless mouse 52 can be a common one, and it is possible for the subject or the like to display an operation menu by right-clicking and determine the cursor position by left-clicking.

[0050] Note that when a notebook PC or the like is connected by USB as described above, the click pad provided integrally with the notebook PC may be utilized to perform the same operations as a mouse.

[0051] (Imaging Unit 53) The imaging unit 53 is the part that acquires the movement of the eyes of the subject during eye tracking, and includes a camera and a near-infrared LED.

[0052] And the part having this imaging unit 53 is an eye tracker which is a configuration for performing eye tracking. The imaging unit 53 is located below the output screen 61 (monitor) described later and can be adjusted to an angle suitable for eye tracking.

[0053] Specifically, the eye tracker irradiates light from the near-infrared LED, acquires an image of the eyeball with the camera, and the CPU 10 calculates the line of sight of the subject using the position of the pupil and the reflection of the illumination according to a program for eye tracking.

[0054] Also, in the first embodiment, an eye tracker having an imaging unit 53 for performing eye tracking is provided below the output screen 61, but it is not necessary to be limited to this.

[0055] That is, the eye tracker may be a wearable type having a glasses shape or a goggle shape.

[0056] (Sound Acquisition Unit) Although not shown in the figure, the sound acquisition unit is a microphone built in the evaluation device 1 and acquires the voice of the subject or the like.

[0057] [Output Unit 60] The output unit 60 includes an output screen 61 and a sound output unit (not shown).

[0058] (Output screen 61) The output screen 61 is a monitor, and is used to display, for example, an image of hair based on image data of hair, and to present the image of hair to the subject.

[0059] Furthermore, the output screen 61 may be used to present observation conditions (described later) to the subject.

[0060] The output screen 61 may be a touch panel, in which case it will have some of the functions of the input unit 50.

[0061] (Sound output section) The sound output section, although not shown in the diagram, is a speaker built into the evaluation device 1 and may be used, for example, to present observation conditions (described later) to the subject.

[0062] Furthermore, when using the output unit 60 to present observation conditions (described later) to the subjects, either the output screen 61 or the sound output unit may be used instead.

[0063] Furthermore, both the output screen 61 and the sound output unit may be used to present the observation conditions (described later) to the subjects.

[0064] Furthermore, the observation conditions (described later) and other information may be presented to the subjects by another method (described later) that does not use the output unit 60.

[0065] [Communication Unit 70] The communication unit 70 is an interface for communicating with the outside world (for example, sending and receiving data).

[0066] The communication unit 70 includes, for example, a transceiver that can connect to the network via a wired connection, a transceiver that can connect to the network wirelessly, and so on. The communication unit 70 also performs wireless communication with the wireless keyboard 51 and the wireless mouse 52.

[0067] Furthermore, the transceivers used for wireless network connection are not limited to those that connect directly; they may also be transceivers used for wireless communication between a Wi-Fi® router and another device.

[0068] <Software Configuration of Evaluation Device 1> Figure 3 is a block diagram showing the software configuration of evaluation device 1, which performs the evaluation method for evaluating hair according to the first embodiment of the present disclosure.

[0069] As shown in Figure 3, the evaluation device 1 includes, as a software configuration, a condition presentation unit 110, an image presentation unit 120, a tracking processing unit 130, an evaluation processing unit 140, and a storage unit 150.

[0070] [Condition Presentation Unit 110] The condition presentation unit 110 presents observation conditions, specifying from what perspective the subject should observe the hair images presented to them.

[0071] As will be explained in more detail later, the condition presentation unit 110 presents observation conditions (observation objectives) for the subject to observe the hair, such as "Which hairstyle do you find preferable?" or "Which hairstyle do you find undesirable?" when presenting two or more images of hair simultaneously.

[0072] Specifically, the condition presentation unit 110 performs the process of outputting the observation conditions (observation purpose) as text on the output screen 61, or the process of outputting the conditions as sound from the sound output unit (not shown).

[0073] The condition presentation unit 110 may also output the observation conditions (observation purpose) as text on the output screen 61, and may also output the observation conditions (observation purpose) as sound from the sound output unit (not shown).

[0074] Specifically, the observation conditions (observation objectives) are stored in the memory unit 150 (described later) as text data such as written documents or audio data, and the condition presentation unit 110 presents the observation conditions (observation objectives) to the subject based on that data.

[0075] Furthermore, text data such as sentences and audio data with the same observation conditions (observation purpose) are linked, and the condition presentation unit 110 uses the linked data when performing both text output and audio output.

[0076] [Image Presentation Unit 120] The image presentation unit 120 presents the image of the hair to be presented to the subject by displaying it on the output screen 61.

[0077] Specifically, the memory unit 150, described later, stores image data of the hair, and the image presentation unit 120 displays this image data on the output screen 61, thereby presenting the image of the hair to the subject.

[0078] [Tracking Processing Unit 130] The tracking processing unit 130 performs a series of eye-tracking processes, that is, a series of processes to track the movement of the subject's gaze and acquire gaze data.

[0079] The tracking processing unit 130 performs a position identification process to determine, for example, the position on the image of the subject's hair where their gaze is directed.

[0080] Furthermore, the evaluation device 1 can recognize the position of each hair image displayed on the output screen 61 as the position of a pixel on the output screen 61 (also called a pixel coordinate). The evaluation device 1 can also identify the gaze position in the position identification process by determining which pixel on the output screen 61 the gaze is directed towards.

[0081] In this way, by aligning the position of the hair on the image with the position of the gaze through pixel coordinates, the tracking processing unit 130 can identify the position of the subject's gaze on the image of the hair.

[0082] Furthermore, the tracking processing unit 130 performs a stationary determination process to determine whether the subject's gaze remains fixed on the gaze position identified in the position identification process.

[0083] In the first embodiment, for example, the positioning process is performed at the eye-tracking sampling rate, for example, 120 Hz (120 times per second).

[0084] Then, the tracking processing unit 130 only needs to determine that the gaze is stationary (i.e., that the gaze is still) if the distance between consecutive gaze positions identified in the position identification process is within a predetermined distance.

[0085] Conversely, the tracking processing unit 130 only needs to determine that the gaze is moving if the distance between consecutive gaze positions identified in the position identification process exceeds a predetermined distance.

[0086] However, the above criteria are merely examples, and other criteria may be used as long as they allow for the determination of whether the gaze is stationary or moving.

[0087] For example, the tracking processing unit 130 may use the 10 consecutive gaze positions identified in the position identification process to determine multiple distances between consecutive gaze positions in order to reduce the impact of disturbances. The tracking processing unit 130 may then perform an averaging process of the multiple distances obtained, and if the averaged distance is within a predetermined distance, it may determine that the gaze is stationary.

[0088] Furthermore, if the tracking processing unit 130 determines that the gaze is fixed, it performs a dwell time acquisition process to acquire the dwell time.

[0089] In other words, the tracking processing unit 130 sets the measurement start point as the point when it determines in the stationary determination process that the gaze is stationary. Next, the tracking processing unit 130 sets the measurement end point as the point when it determines in the stationary determination process that the gaze is not stationary (i.e., it determines that the gaze is moving). The tracking processing unit 130 then performs a stationary time acquisition process to obtain the time from the measurement start point to the measurement end point as the stationary time.

[0090] On the other hand, if the tracking processing unit 130 determines that the gaze is not fixed, it performs a movement speed acquisition process to acquire the movement speed of the viewpoint between consecutive viewpoint positions.

[0091] In other words, the tracking processing unit 130 calculates the speed of movement based on the time and distance traveled from one viewpoint position to the next.

[0092] The line of sight is allowed to remain stationary at a certain position, and this position is designated as the first stationary line of sight position. Then, the line of sight begins to move, and the next position where the line of sight stops is designated as the second stationary line of sight position. The speed of movement (speed of the line of sight movement) may be calculated by dividing the distance the line of sight moves between the first and second stationary line of sight positions (distance between the first and second stationary line of sight positions) by the travel time (travel time from the first stationary line of sight position to the second stationary line of sight position).

[0093] Alternatively, the movement speed (speed of gaze movement) may be the eye movement speed (also called saccade speed) obtained by dividing the rotation angle of the eyeball observed when the gaze changes from the first stationary gaze position to the second stationary gaze position by the rotation time of the eyeball that takes for the angle of the eyeball to change from the first stationary gaze position to the angle of the second stationary gaze position.

[0094] Furthermore, the tracking processing unit 130 performs a movement distance acquisition process to obtain the distance moved from one viewpoint position to the next, and a movement order acquisition process to obtain the order in which viewpoint positions move.

[0095] Furthermore, the movement order acquisition process not only obtains the order in which the viewpoint positions move, but also, for example, the viewpoint position where the subject's gaze was initially directed (the viewpoint position where the gaze first stopped).

[0096] Furthermore, some of the processes performed by the tracking processing unit 130 described above do not need to be performed sequentially along with tracking the subject's gaze.

[0097] In other words, the tracking processing unit 130 tracks the subject's eye movements, records the identified viewpoint position along with the time it was identified, and processes it all at once before the evaluation processing unit 140 (described later) performs the evaluation.

[0098] Therefore, any processing that can be done later in batches without causing problems may be done all at once.

[0099] [Evaluation Processing Unit 140] The evaluation processing unit 140 performs an evaluation of the hair based on the eye-tracking data acquired by the tracking processing unit 130 (the position of the subject's gaze on the hair, the time spent at each gaze position, the order in which the gaze positions move, the speed of movement from one gaze position to the next, the distance traveled between gaze positions, the initial gaze position, etc.).

[0100] As will be explained in detail later, the evaluation processing unit 140 evaluates the hair based on gaze data, taking into account the observation conditions presented by the condition presentation unit 110, which determine from what viewpoint the subject should observe the hair image presented to them.

[0101] For example, evaluation information regarding what kind of evaluation to perform on the hair based on the eye-tracking data for each observation condition is stored in the memory unit 150 (described later), linked to the observation conditions. The evaluation processing unit 140 performs an evaluation of the hair based on the eye-tracking data according to this evaluation information.

[0102] [Storage Unit 150] The storage unit 150 is a part that stores, for example, observation conditions, hair image data (image data of hair), evaluation information, and other information (for example, gaze data). The storage unit 150 is a functional part that is made operational so that the data (information) stored in the ROM 20, RAM 30, and storage unit 40, etc., can be used for necessary processing.

[0103] <Flowchart of the evaluation method for assessing hair> Next, we will explain the overview of the evaluation method for assessing hair, referring to the flowchart, and then we will explain the actual verification results, etc.

[0104] Figure 4 is a flowchart showing the flow of the evaluation method for evaluating hair according to the first embodiment of the present disclosure.

[0105] Note that the flowchart in Figure 4 assumes that the program for evaluating hair has already been started in the evaluation device 1, and that the operator has already performed the operation to start the evaluation.

[0106] Furthermore, it is assumed that the observation conditions to be presented to the subject have already been selected by the operator when initiating this evaluation.

[0107] Alternatively, the operator may verbally present the observation conditions to the subjects, and the operator may use the evaluation device 1 to select which observation conditions from those registered in the evaluation device 1 were presented to the subjects.

[0108] Furthermore, the image (image data) showing the entire hair stored in the memory unit 150 has already been selected by the operator. More specifically, the operator has not selected a single image data, but rather a group of multiple image data (also called an image data set) that may be used for presentation.

[0109] In this example, the image data used to represent the entire head of hair will be one in which two images of hair are displayed simultaneously on the output screen 61.

[0110] (S101) In S101, the condition presentation unit 110 presents the observation conditions to the subject. In this example, for example, the condition presentation unit 110 displays the following message on the output screen 61: "We will now display two images of hair. Which one do you find preferable?"

[0111] As mentioned earlier, the presentation of these observation conditions may also be done by audio output from a sound output unit (not shown).

[0112] Furthermore, as mentioned earlier, S101 may also involve the operator verbally presenting the observation conditions to the subject.

[0113] The process in S101 is an example of a condition presentation step in which observation conditions regarding hair are presented to the subject before the data acquisition step (described later) according to the present invention is carried out.

[0114] (S102) In S102, the image display unit 120 presents the image of the entire head of hair to the subject on the output screen 61.

[0115] Figure 5 shows the output screen 61 displaying an image of the entire head of hair presented to the subject by the image presentation unit 120 of the first embodiment of the present disclosure.

[0116] In Figure 5, the evaluation device 1 other than the output screen 61 is omitted from the illustration, and the overall image of the hair is schematically shown.

[0117] Furthermore, the process in S102 is an example of a presentation step in which the subject according to the present invention is shown the entirety of the hair as viewed from at least one direction (in this example, the rear side), and as shown in Figure 5, the presentation step according to the present invention is an example of a step in which multiple (specifically two) strands of hair are shown to the subject simultaneously.

[0118] (S103) In S103, the tracking processing unit 130 tracks the movement of the subject's gaze toward the hair and acquires gaze data.

[0119] The process in step S103 is an example of a data acquisition step that tracks the movement of a subject's gaze toward their hair and acquires gaze data according to the present invention.

[0120] For example, the tracking processing unit 130 acquires the gaze position on the subject's hair and the time spent at that gaze position as gaze data.

[0121] Specifically, as explained earlier, the tracking processing unit 130 performs a position identification process to determine where on the image of the hair the subject's gaze is directed. The tracking processing unit 130 then performs a retention determination process to determine whether the subject's gaze is fixed on the gaze position identified in the position identification process. If the tracking processing unit 130 determines that the gaze is fixed, it performs a retention time acquisition process to obtain the retention time. As a result, the tracking processing unit 130 obtains, as gaze data, the viewpoint position on the hair where the gaze was fixed and the retention time at that gaze position.

[0122] The process in S103 is performed for a predetermined time (for example, 10 seconds), and once that predetermined time has elapsed, the process proceeds to the next step.

[0123] (S104) In S104, the evaluation processing unit 140 performs an evaluation of the hair. This step S104 is an example of an evaluation step in which an evaluation of the hair is performed based on the gaze data according to the present invention.

[0124] Specifically, the evaluation processing unit 140, in response to the observation condition "Which do you find preferable?", evaluates which of the two presented hairs the subject perceived as preferable, based on gaze data including the gaze position and the time spent at that gaze position, and the processing of the series of flowcharts is completed.

[0125] The processing in S104 is an example of an evaluation step according to the present invention, which performs evaluation based on the total dwell time for each hair (described later) based on gaze data. Specifically, the evaluation results will be explained by illustrating them with test examples (first test example and second test example).

[0126] <Example of the first trial> In the actual trial, 20 Japanese women aged 20 to 29 were used as subjects, and their hair was evaluated according to the evaluation method described above.

[0127] Furthermore, since this was positioned as a test for the evaluation step, participants were asked to answer which they preferred after processing S103.

[0128] Specifically, the evaluation device 1 presents the subject with an observation condition (S101) asking them to later answer which they found more preferable. The evaluation device 1 then displays an image on the output screen 61 that simultaneously shows the two hairs shown in Figure 5 (S102). While the evaluation device 1 is displaying this image (for 10 seconds in this example), it acquires eye-tracking data (S103), and Figure 6 shows this acquired eye-tracking data.

[0129] Figure 6 is a diagram showing the state of gaze data acquired in the first test example of the first embodiment of the present disclosure, where the gaze retention state is represented by an outline, and the area inside the outline indicates an area with a longer retention time.

[0130] Figure 6 schematically shows the state of eye-tracking data based on the eye-tracking data of a particular subject.

[0131] Specifically, the image shown in Figure 5 illustrates the state of the dwell time at the line of sight.

[0132] Furthermore, in order to avoid influencing the subjects' evaluations, the situation shown in Figure 6 was not shown to the subjects, nor was it explained to them.

[0133] As can be seen in Figure 6, the hair on the left side, which appears neater, has a larger area where the hair remained for a longer time.

[0134] Furthermore, from the eye-tracking data, the total time the gaze remained on the left side of the head and the total time the gaze remained on the right side of the head were calculated for each subject. Next, the average total time the gaze remained on the left side of the head (average for 20 subjects) and the average total time the gaze remained on the right side of the head (average for 20 subjects) were calculated.

[0135] Specifically, the average total retention time for hair on the left side was 4.65 ± 1.20 seconds, and the average total retention time for hair on the right side was 3.00 ± 1.22 seconds.

[0136] Furthermore, 19 out of 20 subjects indicated that they preferred hair on the left side of their head, while only 1 out of 20 subjects indicated that they preferred hair on the right side.

[0137] As can be seen from this, in S104, the evaluation processing unit 140, in response to the observation condition of "Which do you find preferable?", can evaluate the two presented hairs by determining which has a longer total dwell time based on the gaze data, and conclude that the one with the longer total dwell time is preferable.

[0138] In other words, the evaluation information stored in the memory unit 150 should be linked to the observation condition of "which one is preferred," and the evaluation should indicate that the one with the longer total dwell time is preferred.

[0139] Furthermore, the observation conditions are not questions that would inadvertently and subjectively lead users to a particular hairstyle, as could happen with stylists. Moreover, the evaluation information linked to these observation conditions reflects the latent preferences of the target individuals, such as users, in the eye-tracking data, allowing for a highly objective evaluation of hair.

[0140] In addition, although not explained in detail above, the same subjects were presented with images of hair in a random order in five trials. Therefore, the sample size for the trial was 20 people x 5 trials, totaling 100 samples, and the trial obtained objective results where subjects may have viewed different images of hair. The display of neatly arranged hair on the left side was adjusted for each trial.

[0141] <Second Test Example> Next, a second test example of the first embodiment relating to this disclosure will be described. In the second test example, the number of subjects and their age range are the same as in the first test example (20 Japanese women aged 20 to 29).

[0142] However, the subjects in the second trial were different from those in the first trial, and the observation condition was "Which do you find less desirable?", which differed from the first trial.

[0143] Furthermore, since the second trial example, like the first trial example, was positioned as a test for the evaluation step, the question of which one participants found undesirable was asked to be answered after the processing in S103.

[0144] Specifically, the evaluation device 1 presents the subject with an observation condition (S101) asking them to answer later which of the following they find undesirable. Subsequently, the evaluation device 1 displays an image on the output screen 61 that simultaneously presents the two strands of hair shown in Figure 5 (S102), and acquires eye-tracking data (S103) while this image is displayed (for 10 seconds in this example).

[0145] Figure 7 is a diagram showing the state of the gaze data acquired in the second test example of the first embodiment of the present disclosure, and corresponds to Figure 6.

[0146] In Figure 7, as in Figure 6, the stationary state of the line of sight is represented by an enclosed area, indicating that the area within the enclosed area has a longer stationary time.

[0147] Similarly to Figure 6, Figure 7 schematically shows the state of eye-tracking data based on the eye-tracking data of a particular subject.

[0148] As can be seen in Figure 7, this time, the hair on the right side of the head, which is slightly less neat than the hair on the left side, had a larger area where the hair remained for a longer time.

[0149] Then, as in the first trial example, when the average total retention time (average of 20 subjects) was calculated, the average total retention time for hair on the left side was 2.42 ± 1.02 seconds, and the average total retention time for hair on the right side was 4.98 ± 1.10 seconds.

[0150] Furthermore, one out of 20 subjects reported that they disliked the hair on the left side of their head, while 19 out of 20 subjects reported that they disliked the hair on the right side of their head.

[0151] As can be seen from this, in S104, the evaluation processing unit 140, in order to evaluate according to the observation condition of "Which do you find undesirable?", should evaluate the hair with the longer total dwell time based on the gaze data of the two presented hairs as undesirable.

[0152] In other words, the evaluation information stored in the memory unit 150 should be linked to the observation condition of "which one is considered undesirable," and the evaluation information should indicate that the one with the longer total dwell time is undesirable.

[0153] As described above, in the first embodiment, an objective evaluation of multiple hairs can be performed.

[0154] In the above description, specifically, the evaluation device 1 presents two strands of hair to the subject simultaneously, but it may also present three or more strands of hair to the subject.

[0155] Furthermore, although the above explanation described an example in which the evaluation device 1 performs the data acquisition step (S103) for 10 seconds to acquire gaze data, the duration of the data acquisition step (S103) should also be appropriately determined according to the number of hairs presented simultaneously.

[0156] <<Second Embodiment>> Next, the evaluation method for evaluating hair according to the second embodiment of the present disclosure, and the evaluation apparatus 1 for performing the evaluation method, will be described with reference to Figure 8.

[0157] Since the evaluation method and evaluation apparatus 1 of the second embodiment are basically the same as those of the first embodiment, the following description will mainly focus on the differences from the first embodiment, and descriptions of similar points may be omitted.

[0158] In the first embodiment, as shown in Figures 5, 6, and 7, two strands of hair were presented simultaneously, but the second embodiment differs in that only one strand of hair is presented to the subject.

[0159] In other words, in this embodiment, the presentation step (S102) according to the present invention is a step of presenting a single strand of hair to the subject.

[0160] The evaluation device 1 then divides the single strand of hair into multiple sections and performs an evaluation based on gaze data, including the gaze position and the time spent at each gaze position, similar to the first embodiment.

[0161] Furthermore, the evaluation device 1 may perform the evaluation in the second embodiment based on the sequence of movement of the gaze position, the speed of movement from the previous gaze position to the next gaze position (saccade speed), and the distance between the previous gaze position and the next gaze position (i.e., the distance traveled).

[0162] As described later, the evaluation step (S104) in the second embodiment is an embodiment in which the evaluation step according to the present invention divides the hair into multiple locations and performs an evaluation based on the total dwell time for each location, which includes gaze position and dwell time at the gaze position, according to gaze data.

[0163] <Test Example> Next, we will explain in more detail the evaluation method for evaluating hair in the second embodiment while describing a test example.

[0164] Furthermore, as this was positioned as a test for the evaluation step, in the presentation of observation conditions (S101), participants were asked to rate their preference for their hair on a 9-point scale from 1 to 9 (1: undesirable, 9: favorable) and to provide their response later. In addition, after the process of acquiring eye-tracking data (S103), the participants (17 participants) were asked to provide their response.

[0165] For example, in the case of a nine-point rating of preference, the subject may input their response into the evaluation device 1 by operating a second input unit 51B equipped with a numeric keypad or the like for inputting numbers.

[0166] Alternatively, the operator could verbally obtain the evaluation from the subject and then input the data themselves.

[0167] Figure 8 is a diagram illustrating an example of dividing the hair into multiple sections according to the second embodiment of the present disclosure.

[0168] As shown in Figure 8, in the second embodiment, the hair was divided into four sections from top to bottom: the crown A1, above the ears A2, above the shoulders A3, and the ends of the hair A4. Based on gaze data including the gaze position and the time spent at the gaze position, the evaluation device 1 determined the total time spent at the crown A1, above the ears A2, above the shoulders A3, and the total time spent at the ends of the hair A4 for each subject.

[0169] Then, the degree of preference mentioned above was plotted on the vertical axis, and the total dwell time was plotted on the horizontal axis, and the correlation coefficients for the top of the head (A1), above the ears (A2), above the shoulders (A3), and hair tips (A4) were calculated.

[0170] Specifically, each participant was presented with multiple images of hair (also called hair samples), and was asked to rate their preference for each hair sample on a 9-point scale for the top of the head (A1), above the ears (A2), above the shoulders (A3), and the ends of the hair (A4).

[0171] Then, for each of the same hair samples—the top of the head A1, above the ears A2, above the shoulders A3, and the ends of the hair A4—the median of the evaluation scores given by each subject on a 9-point scale was calculated, and this median was used as the degree of preference for the top of the head A1, above the ears A2, above the shoulders A3, and the ends of the hair A4 of that hair sample.

[0172] In other words, the degree of preference for the crown A1 of hair sample A is defined as the median score of the 9-point scale that each subject gave to the crown A1 of hair sample A.

[0173] Similarly, the degree of preference for the earlobe A2 portion of hair sample A is defined as the median of the 9-point rating scale that each subject gave to the earlobe A2 portion of hair sample A.

[0174] Similarly, for hair sample B, which is separate from hair sample A, the median of the 9-point rating scores given by each subject for the top of the head A1, above the ears A2, above the shoulders A3, and the ends of the hair A4 of hair sample B was used as the degree of preference.

[0175] In other words, for each hair sample being evaluated, the vertical axis uses values ​​that are close to the degree of preference for each area: the crown (A1), above the ears (A2), above the shoulders (A3), and the ends of the hair (A4).

[0176] Then, using the results for one hair sample as one sample point plotted on the graph, the correlation coefficients were calculated for each of the following areas: the crown of the head A1, above the ears A2, above the shoulders A3, and the ends of the hair A4, based on the multiple sample points plotted on the graph obtained from the multiple hair samples presented.

[0177] Specifically, we calculated the following correlation coefficients: correlation coefficient 1 with the degree of preference (median, as explained earlier) on the vertical axis and the total dwell time at the top of the head A1 on the horizontal axis; correlation coefficient 2 with the degree of preference (median, as explained earlier) on the vertical axis and the total dwell time above the ears A2 on the horizontal axis; correlation coefficient 3 with the degree of preference (median, as explained earlier) on the vertical axis and the total dwell time above the shoulders A3 on the horizontal axis; and correlation coefficient 4 with the degree of preference (median, as explained earlier) on the vertical axis and the total dwell time at the ends of the hair A4 on the horizontal axis.

[0178] The correlation coefficients were -0.42 for correlation coefficient 1, -0.48 for correlation coefficient 2, -0.32 for correlation coefficient 3, and -0.71 for correlation coefficient 4.

[0179] In other words, in all the categorized sections, the overall trend is that the dwell time (or perceived dwell time) tends to be longer when the situation is unfavorable than when it is favorable, and the total dwell time obtained by adding up the total dwell times calculated for each section also tends to be longer.

[0180] Therefore, if the presentation step (S102) is a step in which a single strand of hair is presented to the subject, then in S104, the evaluation processing unit 140 can divide the hair into multiple sections and, based on gaze data including the gaze position and the time spent at the gaze position, evaluate the total time spent at each section as undesirable, which is considered to be one evaluation method.

[0181] On the other hand, when we examined the trends in more detail for each area, such as the top of the head A1, above the ears A2, above the shoulders A3, and the ends of the hair A4, we found that different trends could be observed depending on the condition of the hair and the area.

[0182] For example, regarding the condition of hair (such as frizz or excessive shine), viewers tended to linger longer when the hair was undesirable.

[0183] Furthermore, regarding hair tip A4, it has become clear that people tend to judge the impression in a short amount of time, and that lingering gaze is less likely to occur in some cases, meaning that a long total lingering time is not necessarily undesirable.

[0184] In other words, when the area is divided into four sections, it has become clear that even if the total dwell time for hair tip A4 is shorter compared to the other areas, it may still be perceived as undesirable (there is a high correlation with the rating).

[0185] Furthermore, it has become clear that, for hair tip A4 and similar materials, evaluating them using the movement speed (saccade speed) explained earlier tends to yield results that better suit preferences. Specifically, for hair tip A4 and similar materials, the movement speed (saccade speed) tended to be slower when the material was undesirable than when it was desirable.

[0186] From the above, if the presentation step (S102) is a step in which one strand of hair is presented to the subject, then in S104, the evaluation processing unit 140 divides the hair into multiple locations and, based on gaze data including the gaze position and the time spent at the gaze position, can evaluate the total time spent at each location as a single evaluation, indicating that locations with long dwell times are undesirable.

[0187] On the other hand, for example, with hair tip A4, it is also possible to evaluate whether a slower movement speed is undesirable, using the movement speed (saccade speed) as an indicator rather than the dwell time.

[0188] In the case of the second embodiment, it is thought that, as a general trend, if a single strand of hair is presented, the total retention time will be longer if the user or other target person potentially perceives the entire strand of hair as undesirable. For this reason, it is thought that the evaluation device 1 can perform an evaluation of the entire strand of hair even if the condition presentation step (S101) for presenting observation conditions is omitted and the process starts from the presentation step (S102).

[0189] Furthermore, with respect to hair tips A4, etc., if the target person, such as a user, potentially perceives them as undesirable, the movement speed (saccade speed) slows down. Therefore, it is considered that the evaluation device 1 can perform evaluation of hair tips A4, etc., even if the condition presentation step (S101) for presenting observation conditions is omitted and the process starts from the presentation step (S102).

[0190] Thus, the evaluation method for evaluating hair according to the present invention is not limited to comprising a condition presentation step for presenting observation conditions.

[0191] Although the above has been explained based on specific embodiments, this disclosure is not limited to the embodiments described above.

[0192] For example, in the case of hair, there may be situations where you want to evaluate areas that the subject is concerned about. In such cases, it is possible to evaluate based on the initial gaze position in the eye-tracking data.

[0193] Specifically, it is conceivable that the gaze would first be drawn to a particularly noticeable area within the entire head of hair, and that the gaze would then linger at that noticeable area, becoming the initial gaze position. Therefore, as described above, it is thought that the evaluation device 1 can evaluate the areas that the subject was interested in based on the initial gaze position of the gaze data.

[0194] Furthermore, as mentioned above, the tendency to dwell on undesirable aspects for a long time can be seen as a tendency to not dwell on desirable aspects for very long.

[0195] Therefore, in the case of hair, areas where the speed of movement from one viewpoint to the next viewpoint is fast are considered to be areas that the subject potentially finds desirable. For this reason, evaluation device 1 can be used to evaluate which part of the entire hair is perceived as desirable.

[0196] Furthermore, depending on the condition of the hair, specifically the hairstyle, the order in which the gaze moves may also be useful in the evaluation.

[0197] For example, when the hair on the head is divided into multiple sections (top of the head A1, above the ears A2, above the shoulders A3, and the ends of the hair A4), it has been found that, generally, subjects tend to look at the hair in the order of above the ears A2 → above the shoulders A3 → ends of the hair A4 → top of the head A1.

[0198] However, as mentioned above, the most noticeable parts of the hair are likely to be the first points of focus, so the initial point of focus may differ from the general tendency of the viewing order.

[0199] Therefore, by evaluating the viewing order, including whether it deviates from the usual viewing order, it may be possible to more accurately assess the aspects that the subjects found interesting.

[0200] Thus, the eye-tracking data of the hair evaluation method according to the present invention is not limited to those specifically described through test examples, etc.

[0201] Furthermore, in the above embodiment, the hair presented to the subject was viewed from the rear, but the presented hair does not need to be limited to a view from the rear; it may be viewed from the side, as if viewing the profile, or from the front, as if viewing the face from the front.

[0202] Therefore, any modifications or improvements made to the embodiments described herein are also included within the technical scope of the present invention, which will be clear to those skilled in the art from the claims.

[0203] The following additional notes are disclosed regarding the above embodiments. [Note 1] An evaluation method for evaluating hair, the evaluation method comprising: a presentation step of presenting the entire hair of a subject as seen from at least one direction; a data acquisition step of tracking the movement of the subject's gaze toward the hair and acquiring gaze data; and an evaluation step of performing an evaluation of the hair based on the gaze data. [Note 2] The evaluation method according to Note 1, further comprising a condition presentation step of presenting observation conditions relating to the hair to the subject before performing the data acquisition step. [Note 3] The evaluation method according to Note 1 or Note 2, wherein the gaze data includes one of the following: the position of the subject's gaze toward the hair, the time spent at the gaze position, the order of movement of the gaze positions, the speed of movement from one gaze position to the next gaze position, the distance of movement from one gaze position to the next gaze position, or the initial gaze position. [Note 4] The evaluation method according to Note 3, wherein the presentation step is a step of simultaneously presenting a plurality of the hairs of the subject to the subject. [Note 5] The evaluation method according to Note 3 or Note 4, wherein the gaze data includes the gaze position and the dwell time at the gaze position, and the evaluation step is a step in which evaluation is performed based on the total dwell time for each hair based on the gaze data. [Note 6] The evaluation method according to Note 3, wherein the presentation step is a step in which one of the hairs is presented to the subject. [Note 7] The evaluation method according to Note 3 or Note 6, wherein the gaze data includes the gaze position and the dwell time at the gaze position, and the evaluation step is a step in which the hair is divided into multiple locations and evaluation is performed based on the total dwell time for each location based on the gaze data.

[0204] Although the present invention has been described in detail and with reference to specific embodiments, it will be apparent to those skilled in the art that various changes and modifications can be made without departing from the spirit and scope of the invention.

[0205] This application is based on Japanese Patent Application No. 2024-155500, filed on September 10, 2024, the contents of which are incorporated herein by reference.

[0206] According to the present invention, it is possible to provide a method for evaluating hair with enhanced objectivity. This present invention, which achieves this effect, is useful in relation to evaluation methods.

[0207] 1...Evaluation device, 10...CPU, 20...ROM, 30...RAM, 40...Storage unit, 50...Input unit, 51...Wireless keyboard, 51A...First input area, 51B...Second input unit, 52...Wireless mouse, 53...Imaging unit, 60...Output unit, 61...Output screen, 70...Communication unit, 110...Condition presentation unit, 120...Image presentation unit, 130...Tracking processing unit, 140...Evaluation processing unit, 150...Storage unit, BS...Bus

Claims

1. An evaluation method for evaluating hair, the evaluation method comprising: a presentation step of presenting the entire hair of a subject as seen from at least one direction; a data acquisition step of tracking the movement of the subject's gaze toward the hair and acquiring gaze data; and an evaluation step of performing an evaluation of the hair based on the gaze data.

2. The evaluation method according to claim 1, further comprising a condition presentation step of presenting observation conditions regarding the hair to the subject before performing the data acquisition step.

3. The evaluation method according to claim 1 or claim 2, wherein the gaze data includes one of the following: the position of the gaze on the subject's hair, the time spent at the gaze position, the order of movement of the gaze positions, the speed of movement from one gaze position to the next gaze position, the distance of movement from one gaze position to the next gaze position, and the initial gaze position.

4. The evaluation method according to claim 3, wherein the presentation step is a step of simultaneously presenting a plurality of the hairs to the subject.

5. The evaluation method according to claim 4, wherein the gaze data includes the gaze position and the dwell time at the gaze position, and the evaluation step is a step of performing an evaluation based on the total dwell time for each hair, based on the gaze data.

6. The evaluation method according to claim 3, wherein the presentation step is a step of presenting one of the hairs to the subject.

7. The evaluation method according to claim 6, wherein the gaze data includes the gaze position and the time spent at the gaze position, and the evaluation step is a step of dividing the hair into a plurality of locations and performing an evaluation based on the total time spent at each location, according to the gaze data.

Images