Information processing device, information processing method, and program

Abstract

To provide an information processing device capable of acquiring biological information of a subject with high accuracy.SOLUTION: An information processing device includes a generating unit 11 that generates a first histogram based on color information contained in a captured image acquired by imaging a subject, a processing unit 12 that generates a second histogram by executing flattening processing on the first histogram, a setting unit 14 that sets the subject's skin area in the captured image on the basis of the second histogram, and an acquisition unit 15 that acquires biological information of the subject on the basis of the luminance value of the skin area.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program for acquiring biological information of a subject. [Background technology]

[0002] In order to obtain bioinformation of a subject without contacting the subject, a technique is known for detecting a biosignal of the subject based on a moving image obtained by imaging the subject. For example, when measuring a pulse rate as bioinformation, a pulse waveform is detected as a biosignal. Then, the pulse rate can be obtained from the number of peaks in the pulse waveform within a certain period of time. In order to detect a biosignal of the subject based on a moving image, it is necessary to extract the subject's skin region in the moving image and obtain the change in luminance value of the skin region over time. For example, the moving image can be converted into an HSV color space represented by hue (H), saturation (S), and brightness (V), and the skin region can be extracted based on the range (upper limit and lower limit) of each value (color information) of the HSV.

[0003] Patent Document 1 discloses a method of using a plurality of preset ranges of color information in order to detect the skin region of a subject. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-178055 Summary of the Invention [Problem to be solved by the invention]

[0005] When acquiring biometric information from a subject without contact, the contrast of the subject's skin region may vary significantly due to the subject's movement or changes in the light source. In this case, the method of Patent Document 1 may cause the luminance value of the skin region in the moving image to be too high or too low, and thus not be included in the range of multiple preset color information. If a skin region of sufficient size (number of pixels) cannot be extracted, the biometric information cannot be acquired with high accuracy.

[0006] SUMMARY OF THE PRESENT EMBODIMENTS Accordingly, an object of the present invention is to provide an information processing apparatus capable of acquiring biological information of a subject with high accuracy. [Means for solving the problem]

[0007] The imaging device is characterized by comprising a generation unit that generates a first histogram based on color information contained in an image obtained by imaging the subject, a processing unit that generates a second histogram by performing an equalization process on the first histogram, a setting unit that sets a skin region of the subject in the image based on the second histogram, and an acquisition unit that acquires biometric information of the subject based on the luminance value of the skin region. Effect of the Invention

[0008] According to the present invention, it is possible to provide an information processing apparatus capable of acquiring biological information of a subject with high accuracy. [Brief description of the drawings]

[0009] [Figure 1] FIG. 2 is a diagram showing the relationship between a region of interest and a skin region in a subject. [Diagram 2] FIG. 11 is a diagram showing frequency characteristics obtained by performing frequency analysis on time-series data of average luminance values ​​of a skin region. [Diagram 3] FIG. 13 is a diagram showing the distribution of hue H and lightness V contained in the entire image before the illumination change. [Figure 4] FIG. 13 is a diagram showing the distribution of hue H and lightness V contained in the entire image after the illumination is changed. [Diagram 5]FIG. 13 is a diagram showing the distribution of luminosity V obtained by executing a flattening process. [Figure 6] FIG. 1 is a block diagram of an information processing apparatus according to a first embodiment. [Figure 7] 4 is a flowchart showing a processing operation of the information processing device according to the first embodiment. [Figure 8] FIG. 11 is a block diagram of an information processing apparatus according to a second embodiment. [Figure 9] 11 is a flowchart showing a processing operation of an information processing apparatus according to a second embodiment. [Figure 10] FIG. 13 is a diagram showing the distribution of a second color difference signal contained in an entire image. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. Note that each drawing may be drawn at a scale different from the actual scale for convenience. Also, as shown in each drawing, the same reference numerals are given to the same components, and duplicated descriptions are omitted. Note that the following embodiments do not limit the invention according to the claims. Although multiple features are described in the embodiments, not all of these multiple features are necessarily essential to the invention, and multiple features may be combined in any manner.

[0011] There is a technology that detects time series data of reflected light from the skin surface of a subject as a biosignal in order to obtain bioinformation of the subject without contacting the subject. The blood flow rate of the blood vessels of a living subject periodically increases and decreases according to the pulse and breathing. This is due to the characteristics of the light absorption rate of hemoglobin contained in blood.

[0012] Hemoglobin in blood has a high absorptivity for light of 495 to 570 [nm] (green wavelength) and 800 to 1000 [nm] (infrared wavelength). Therefore, by acquiring the change over time in the amount of light (especially green wavelength or infrared wavelength) reflected from a part of the skin surface including the blood vessels of the subject, it is possible to detect the subject's biosignal. In this embodiment, any one of pulse rate, blood pressure, respiratory rate, heart rate, and oxygen saturation is acquired as the subject's bioinformation.

[0013] In order to detect the biological information of a subject with high accuracy, it is necessary to obtain the biological information from the light reflected from the subject's skin area. When detecting biological information without contact, for example, an area that satisfies the range (upper and lower limits) of each value of color information in the HSV color space is extracted as the skin area.

[0014] In this embodiment, the color information is the value of an element constituting a color space component. For example, the elements of the RGB color space are red R, green G, and blue B, the elements of the HSV color space are hue H, saturation S, and brightness V, and the elements of the YCbCr color space are luminance Y, the first color difference signal Cb, and the first color difference signal Cr. It may also be expressed using the YUV color space or the YPbPr color space. The element value (color information) is expressed, for example, as a value from 0 to 255. It is not limited to this, and the element value may be expressed as 0 to 360, 0 to 100, etc., as long as it is a standardized value or signal value.

[0015] The ranges of the values ​​of hue H, saturation S, and brightness V when detecting a skin region using the HSV color space can be expressed by, for example, equations (1) to (3). 0 <H<25···(1) 58 <S<173···(2) 88 <V<229···(3)

[0016] When detecting a skin region using the HSV color space, a region that satisfies each of the above formulas (1) to (3) can be determined as a skin region. The more pixels in the skin region of the subject in the moving image, the more accurately the subject's biological information can be acquired.

[0017] When acquiring biometric information of a subject without contacting the subject, the environmental light for the subject may change (illumination change) due to changes in the direction of sunlight due to weather or time. In this case, the luminance value of the subject's skin area in the moving image may change, which may exceed the range of color information set in advance. As a result, the number of pixels corresponding to the skin area of ​​the subject becomes smaller, making it difficult to monitor the biometric information.

[0018] The effect of illumination changes will be described with reference to FIGS.

[0019] FIG. 1(a) shows an example of a region of interest 30 and a skin region 31 (parts painted in gray) on a subject before a change in illumination, and FIG. 1(b) shows an example of a region of interest 30 and a skin region 32 on a subject after a change in illumination. In this embodiment, the skin region is a region in a moving image that satisfies the above expressions (1) to (3). Moreover, the region of interest in FIG. 1 is set to a region that includes the subject's face region. In FIG. 1(b), there are fewer regions detected as skin regions (smaller number of pixels) compared to FIG. 1(a).

[0020] The skin region includes the subject's body region. The subject's body region is a face region including facial parts such as the eyes, nose, mouth, forehead, cheeks, and facial contour, a hand region, a foot region, and the like. The face region is not limited to the entire face defined based on feature points of the types of face regions such as the eyes, nose, mouth, and facial contour, but may be a partial region such as the cheeks or forehead. The hand region is not limited to the entire hand or arm, but may be a partial region such as the palm, wrist, and forearm. The foot region is not limited to the foot region, but may be a partial region such as the sole of the foot.

[0021] Fig. 2(a) shows the frequency characteristics obtained by Fourier transforming the time series data of the average luminance value obtained from skin region 31 before the illumination change, and Fig. 2(b) shows the frequency characteristics obtained by Fourier transforming the time series data of the average luminance value obtained from skin region 32 before the illumination change. The vertical axis of the graph shown in Fig. 2 indicates the intensity of the bioinformation signal, and the horizontal axis indicates the frequency [Hz].

[0022] As shown in Figure 2, the intensity of the detected biometric signal differs due to changes in the size of the skin area caused by changes in illumination. Figure 2(a) shows that the signal intensity peaks around 1.25 Hz. On the other hand, Figure 2(b) contains a lot of noise and the peak is not clear. In other words, when the skin area narrows due to changes in illumination, it becomes difficult to detect biometric information accurately.

[0023] In this embodiment, even if the subject's skin region cannot be sufficiently detected based on the preset range of color information due to the influence of changes in illumination, an equalization process is performed on the histogram generated from the color information in order to acquire biometric information with high accuracy. The equalization process on the histogram is a process of converting the histogram, which is the frequency of color information contained in the entire image, so that it becomes flat overall.

[0024] In this embodiment, for example, contrast limited adaptive histogram equalization (CLAHE) can be executed as the equalization process for the histogram. Here, the contrast limited adaptive histogram equalization process is a process in which an image is divided into small regions, and histogram equalization is applied while imposing a constraint value for each region. For example, when the occurrence frequency of a bin exceeds the constraint value, pixels exceeding the constraint value are evenly distributed to other bins, and then histogram equalization is applied. Also, the method of the equalization process for the histogram is not limited to this.

[0025] The effect of the flattening process in this embodiment will be described with reference to Figures 3 to 5. Figures 3 to 5 are histograms of color information in an image, showing the frequency of pixel values ​​(signal values) contained in the image, with the horizontal axis showing signal values ​​in the range of 0 to 255.

[0026] Fig. 3 shows the distribution of color information in the HSV color space over the entire image when detecting the subject's skin region 31. Fig. 3(a) is a histogram of the hue H of the entire image, and Fig. 3(b) is a histogram of the lightness V of the entire image.

[0027] Fig. 4 shows the distribution of color information in the HSV color space of the entire image when detecting the subject's skin region 32. Fig. 4(a) is a histogram of the hue H of the entire image, and Fig. 4(b) is a histogram of the lightness V of the entire image.

[0028] FIG. 5 is a histogram of the luminance V obtained by performing an equalization process on the histogram of FIG.

[0029] Comparing FIG. 3(a) with FIG. 4(a), it can be seen that there is no significant difference in the distribution of signal values ​​within the range of formula (1). In other words, the color information of hue H does not change significantly due to changes in illumination. On the other hand, comparing FIG. 3(b) with FIG. 4(b), it can be seen that while there are more pixels near a signal value of 100 in FIG. 3(b) than in FIG. 4(b), there are fewer pixels with a signal value of 200 or more in FIG. 3(b) than in FIG. 4(b). It can be seen from FIG. 3(b) and FIG. 4(b) that the color information of lightness V changes significantly due to changes in illumination. In FIG. 4(b), the number of pixels that satisfy formula (3) has decreased due to changes in illumination, so the skin region 32 is smaller than the skin region 31 (the total number of pixels has decreased).

[0030] Next, comparing Fig. 4(b) with Fig. 5, there are more pixels near a signal value of 100 in Fig. 4(b) than in Fig. 5, but there are also more pixels with a signal value of 200 or more in Fig. 4(b) than in Fig. 5. In Fig. 5, the distribution of signal values ​​in Fig. 4(b) is flattened to approach the distribution in Fig. 3(b). Therefore, from the image of the distribution in Fig. 5, a skin region larger than skin region 32 can be detected based on equations (1) to (3).

[0031] The color information for which the histogram is flattened is not limited to lightness V, but may be, for example, saturation S or luminance Y, as long as the histogram distribution changes significantly before and after a change in illumination.

[0032] Even if the skin region of the subject cannot be adequately detected based on the preset range of color information due to the influence of a change in illumination, the reduction in the number of pixels in the skin region can be suppressed by flattening the histogram. In other words, the skin region of the subject can be detected with high accuracy without changing the range of color information of the skin region, such as that expressed by equations (1) to (3), before and after a change in illumination.

[0033] In this way, even when the lighting changes, biometric information can be detected with a high degree of accuracy by obtaining the skin area based on the histogram (second histogram) obtained by performing an equalization process on the histogram (first histogram) generated from the color information.

[0034] [Example 1] Next, an information processing system 1 according to a first embodiment will be described with reference to Fig. 6. Fig. 6 is a block diagram of the information processing system 1 according to the first embodiment. The information processing system 1 is a system including an information processing device 10 and an imaging device 100, and acquires biological information from a moving image obtained by imaging a subject with the imaging device 100. The information processing device 10 and the imaging device 100 are connected to each other so that they can communicate with each other. The connection method may be wired or wireless.

[0035] The information processing system 1 may be configured as an integrated device of the information processing device 10 and the imaging device 100. That is, the imaging device 100 may be provided as an imaging unit inside the information processing device 10, or the information processing device 10 may be provided as an inspection unit inside the imaging device 100. The imaging device 100 in this embodiment includes a transmission unit that transmits a captured image to the information processing device 10. The imaging device 100 may transmit imaging conditions and the like as necessary in addition to the captured image.

[0036] The information processing device 10 has a generating unit 11, a processing unit 12, a converting unit 13, a setting unit 14, and an acquiring unit 15, and acquires biometric information of a subject imaged by the imaging device 100. The information processing device 10 can acquire the biometric information of a subject by implementing its functions using one or more processors (processing means) such as CPUs.

[0037] The imaging device 100 includes an optical system and an imaging element. The optical system collects light incident on the imaging element from the subject space. The imaging element receives an optical image of the subject formed via the optical system to obtain a moving image. The imaging element is a charge coupled device (CCD) sensor or a complementary metal oxide semiconductor (CMOS) sensor. It is preferable that the imaging element has pixels sensitive to two or more wavelengths, such as an imaging element having color filters of three colors (RGB).

[0038] The imaging device 100 according to this embodiment can capture an image of a subject at 30 fps (frames per second). That is, a moving image can be obtained by continuously recording 30 images per second. Note that the frame rate of the imaging device 100 is not limited to 30 fps.

[0039] The information processing device 10 according to the first embodiment of the present invention will be described below with reference to the flowchart shown in FIG.

[0040] In step S100, the imaging device 100 captures an image of a subject. The imaging element included in the imaging device 100 according to this embodiment is an RGB color sensor having sensitivity to red, green, and blue wavelength regions.

[0041] Since the imaging device 100 acquires captured images by capturing images of the subject continuously in time, information related to time may be acquired. The information related to time is the time from the start of imaging or the number of captured images (number of frames) captured from the start of imaging. By adopting such a configuration, it is possible to acquire biological information of the subject at a specific timing during imaging.

[0042] In step S101, the generation unit 11 generates a first histogram based on color information contained in the captured image. It is preferable to generate the first histogram from color information contained in the entire image, not from a partial region of the image. With this configuration, a histogram for the entire image can be generated, and the color information of the entire image can be corrected in the subsequent steps. As a result, even if the subject's skin area cannot be adequately detected based on a preset range of color information due to the influence of lighting changes, the skin area can be obtained with high accuracy.

[0043] In step S102, the processing unit 12 generates a second histogram by performing an equalization process on the first histogram.

[0044] An example of the equalization process in this embodiment will be described with reference to Figures 4(b) and 5. The second histogram in Figure 5 is generated by performing contrast-limited adaptive histogram equalization, which is one type of histogram equalization process, on the first histogram in Figure 4(b).

[0045] As shown in FIG. 4(b) and FIG. 5, a flattened distribution (second histogram) can be obtained by performing flattening on a biased distribution (first histogram) in which the frequency of occurrence of luminance V is high in the signal value range of 100 to 150. Note that the color information is not limited to luminance V. For example, it may be green G in the RGB color space, saturation S in the HSV color space, or luminance Y in a color space composed of a luminance signal, a first color difference signal, and a second color difference signal. It is preferable that the histogram to be subjected to the flattening process is color information whose distribution changes significantly before and after a change in illumination. Also, the flattening process is not limited to one color information, and may be performed on multiple color information.

[0046] In step S103, the conversion unit 13 converts the captured image based on the second histogram as necessary to generate a converted image.

[0047] By generating a converted image, it is possible to obtain the luminance change of the reflected light from the subject with high accuracy. As a result, it is preferable because the biological information of the subject can be obtained with high accuracy. For example, when the distribution of the signal values ​​of the luminance Y, which is the color information of the YCbCr color space in the image, is taken as a first histogram, if the first histogram is concentrated in a certain range (or value), the contrast in the image is low. In this case, the luminance change of the reflected light from the subject becomes small, and the accuracy of the biological information may decrease.

[0048] By performing the flattening process, a second histogram with higher contrast than the first histogram is generated. The converted image obtained based on the second histogram with higher contrast can accurately capture the luminance change of the reflected light from the subject.

[0049] In step S104, the setting unit 14 sets the skin region of the subject based on the second histogram. In this embodiment, the setting unit 14 sets the skin region in the converted image to a region corresponding to the skin region in the captured image. If the process of step S103 has not been performed, the setting unit 14 may set the skin region from the captured image instead of the converted image.

[0050] Moreover, it is preferable that the setting unit 14 has a function of setting a region including a part of the subject's body region from the converted image or image as the region of interest. With such a configuration, the skin region of the subject can be detected with high accuracy. The region of interest may be of any size (number of pixels) and shape as long as it includes a part of the subject's body region. A known image processing method or image recognition method can be used as a method for setting the region of interest.

[0051] In this embodiment, the setting unit 14 detects the skin region based on whether or not each pixel in the region of interest satisfies a preset range of color information for the skin region (e.g., expressions (1) to (3)). Note that multiple ranges of color information may be prepared in advance. In this embodiment, the change in illumination can be determined from the ratio or difference between the number of pixels in the region of interest and the number of pixels in the skin region detected by expressions (1) to (3), or from a change in the shape of the first histogram and the second histogram.

[0052] In step S105, the acquisition unit 15 acquires biometric information of the subject based on the luminance value of the skin region. Note that the acquisition unit 15 in this embodiment acquires biometric information based on the luminance value of the skin region in the converted image. If the conversion unit 13 does not generate a converted image, the acquisition unit 15 may acquire biometric information based on the skin region in the image.

[0053] The acquisition unit 15 acquires the biometric information based on time-series data obtained by continuously acquiring luminance values ​​corresponding to the skin region set by the setting unit 14. The time-series data may be acquired based on an average luminance value obtained for each color of the skin region. This configuration can reduce the influence of noise contained in the captured image. It is preferable that the acquisition unit 15 acquires the biometric information after performing a moving average process or other noise reduction process on the acquired time-series data. It is to be noted that the present embodiment is not limited to a method of acquiring the biometric information from the time-series data.

[0054] In addition, methods for acquiring biological information include a moving average of the interval between peaks in time series data, a frequency analysis, and a principal component analysis, and the present invention does not limit the method for acquiring biological information. Examples of biological information acquired include the subject's pulse, respiratory rate, blood pressure, and oxygen saturation. Depending on the biological information of interest, second-order differentiation and noise reduction processing may be performed.

[0055] As a result, the information processing device 10 in this embodiment can accurately acquire the skin area even when the skin area of ​​the subject cannot be adequately detected based on the preset range of color information due to the influence of changes in illumination.

[0056] [Example 2] Next, an information processing system 2 according to a second embodiment will be described with reference to Fig. 8. Fig. 6 is a block diagram of the information processing system 2 according to the second embodiment. The information processing system 2 includes an information processing device 20 and an imaging device 200, and is a system that acquires biological information based on a moving image obtained by imaging a subject with the imaging device 200. The information processing device 20 in the second embodiment includes a generating unit 21, a storage unit 22, a processing unit 23, a setting unit 24, and an acquiring unit 25.

[0057] The storage unit 22 in this embodiment stores a histogram (stored histogram) of color information included in an image from which biometric information was previously acquired.

[0058] As the shape of the histogram (third histogram) stored in the storage unit 22, for example, the most frequent value or the second most frequent value in a histogram of the brightness V of the entire image when biometric information was previously acquired based on the skin region of the subject is stored. In addition, the minimum and maximum values ​​of the histogram (the range in which the variables of the histogram are distributed) or the total number of pixels corresponding to an arbitrary range of signal values ​​may also be stored.

[0059] For example, when comparing Figure 3(b) with Figure 4(b), the mode value and its frequency are different. In addition, as a method for comparing similarity in the shape of histograms, commonly known methods such as Euclidean distance and Pearson's product moment correlation coefficient may be used.

[0060] In this way, the shape of the first histogram is compared with the shape of the stored histogram, and it is determined whether or not to perform a flattening process on the first histogram based on the degree of similarity between the shape of the first histogram and the shape of the stored histogram. By adopting such a configuration, it is possible to reduce the load of calculation processing.

[0061] The stored histogram in this embodiment is a histogram used when acquiring biological information of the subject before generating a first histogram in step S201 described later. The stored histogram may be a histogram based on the same elements as the first histogram. For example, it may be a histogram based on an image obtained by imaging a subject different from the subject in step S200.

[0062] In addition, the stored histogram is preferably a histogram based on a captured image captured in an environment similar to the environment in which the captured image corresponding to the first histogram was captured. With this configuration, it is possible to improve the accuracy of the determination as to whether or not to perform the flattening process.

[0063] Note that a similar environment means that at least one of the time and weather when the image was captured, or the image capturing conditions of the image capturing device used for the image capturing, is close or similar. The captured image corresponding to the stored histogram may be an image captured using an image capturing device other than the image capturing device 200. Also, a configuration may be adopted in which a previously obtained histogram is stored in an external server or storage medium, rather than in the storage unit 22 in the information processing device 20.

[0064] An information processing device 20 according to a second embodiment of the present invention will be described below with reference to the flowchart shown in Fig. 9. Steps S200, S201, S204, S205, and S206 in Fig. 9 are the same as those in the first embodiment.

[0065] In step S202, the processing unit 23 compares the shape of the first histogram with the shape of the stored histogram to determine whether or not to perform a flattening process on the first histogram. Note that the stored histogram in this embodiment is stored in the storage unit 22.

[0066] If it is determined in step S202 that the flattening process is to be performed, then in step S203 the flattening process is performed on the first histogram. On the other hand, if it is determined in step S202 that the flattening process is not to be performed, then the process proceeds to step S204, where a region of interest in the captured image is set.

[0067] In step S203, the processing unit 23 generates a second histogram by performing a flattening process on the first histogram. When generating the second histogram, the processing unit 23 in this embodiment performs a flattening process on the first histogram based on the stored histogram (third histogram). In this way, by performing a flattening process based on the shape of a histogram of an image that was previously obtained as biometric information from the skin region of a subject, a second histogram that can accurately detect the skin region in a captured image can be generated. Note that the histogram stored in the storage unit 22 may be a histogram that was generated by a flattening process before generating the first histogram.

[0068] Here, the effect of using the stored histogram will be described with reference to Fig. 10. Fig. 10 is a histogram of color information in an image, showing the frequency of signal values ​​contained in the image, with the horizontal axis showing signal values ​​in the range of 0 to 255. Note that the color information in this embodiment is the signal value of the Cr signal in the YCbCr color space.

[0069] Fig. 10(a) is a histogram of the Cr signal stored in the storage unit 22. Fig. 10(b) is a histogram (first histogram) of the Cr signal in an image captured by imaging using the imaging device 200. Fig. 10(c) is a histogram (second histogram) obtained by performing an equalization process on the first histogram.

[0070] In the histogram of Fig. 10(a), the minimum signal value is 57 and the maximum signal value is 215. In addition, in the histogram of Fig. 10(b), the minimum signal value is 71 and the maximum signal value is 200. In other words, the histogram of Fig. 10(b) has lower contrast than the histogram of Fig. 10(a).

[0071] At this time, the processing unit 23 in this embodiment performs an equalization process on the first histogram based on the minimum signal value of 57 and the maximum signal value of 215 in Fig. 10(a). The histogram (Fig. 10(c)) obtained by performing the equalization process has a higher contrast than the histogram in Fig. 10(b). In this way, by performing an equalization process on the histogram based on the range (distribution width) of the maximum and minimum values ​​of the histogram stored in the storage unit 22, it is possible to make the shape of the histogram closer to that of an image previously obtained as biometric information from the skin region of the subject.

[0072] As a result, the information processing device 20 in this embodiment can accurately acquire the skin area even when the skin area of ​​the subject cannot be adequately detected based on the preset range of color information due to the influence of changes in illumination.

[0073] (Other Examples) This embodiment can also be realized by a process in which a program for realizing one or more functions of the above-mentioned embodiment is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) for realizing one or more functions.

[0074] Although the preferred embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist of the present invention.

[0075] The embodiments of the present invention include the following configurations, methods, and programs.

[0076] [Configuration 1] a generation unit that generates a first histogram based on color information included in an image obtained by imaging the subject; a processor for performing an equalization process on the first histogram to generate a second histogram; a setting unit that sets a skin region of the subject in the captured image based on the second histogram; and an acquisition unit that acquires biological information of the subject based on a luminance value of the skin region.

[0077] [Configuration 2] The information processing device according to configuration 1, characterized in that the processing unit determines whether or not to perform the flattening process by comparing a shape of the first histogram with a shape of a third histogram used to acquire biometric information before generating the first histogram.

[0078] [Configuration 3] 3. The information processing device according to configuration 2, further comprising a storage unit that stores the third histogram.

[0079] [Configuration 4] 4. The information processing device according to configuration 2 or 3, wherein the processing unit performs the equalization process on the first histogram based on a distribution range of the variable of the third histogram.

[0080] [Configuration 5] 5. The information processing device according to any one of configurations 1 to 4, further comprising a conversion unit that converts the captured image into a converted image based on the second histogram.

[0081] [Configuration 6] 6. The information processing apparatus according to configuration 5, wherein the acquisition unit acquires biological information of the subject based on a luminance value of a region corresponding to the skin region in the converted image.

[0082] [Configuration 7] 7. The information processing device according to any one of configurations 1 to 6, wherein the color information is a value of an element included in any one of an RGB color space, an HSV color space, and a YCbCr color space.

[0083] [Configuration 8] 8. The information processing device according to any one of configurations 1 to 7, wherein the biological information includes at least one of pulse rate, respiratory rate, blood pressure, and oxygen saturation.

[0084] [Configuration 9] An information processing system including the information processing device according to any one of configurations 1 to 8 and an imaging device capable of communicating with the information processing device, The information processing system is characterized in that the imaging device includes a transmission unit that transmits a captured image to the information processing device.

[0085] [Method 1] generating a first histogram based on color information included in an image obtained by imaging the subject; generating a second histogram by performing an equalization operation on the first histogram; setting a skin region of the subject in the captured image based on the second histogram; and acquiring biological information of the subject based on the luminance value of the skin region.

[0086] [Program 1] A program for causing a computer to execute the information processing method according to Method 1. [Explanation of symbols]

[0087] 11 Generation part 12 Processing section 14 Setting section 15 Acquisition Department

Claims

1. a generation unit that generates a first histogram based on color information included in an image obtained by imaging the subject; a processor for performing an equalization process on the first histogram to generate a second histogram; a setting unit that sets a skin region of the subject in the captured image based on the second histogram; and an acquisition unit that acquires biological information of the subject based on a luminance value of the skin region.

2. The information processing device according to claim 1, characterized in that the processing unit determines whether to perform the flattening process by comparing a shape of the first histogram with a shape of a third histogram used to acquire biometric information before generating the first histogram.

3. The information processing apparatus according to claim 2 , further comprising a storage unit for storing the third histogram.

4. The information processing apparatus according to claim 2 , wherein the processing unit performs the equalization process on the first histogram based on a distribution range of the variable of the third histogram.

5. 5. The information processing apparatus according to claim 1, further comprising a conversion unit that converts the captured image into a converted image based on the second histogram.

6. The information processing apparatus according to claim 5 , wherein the acquisition unit acquires biological information of the subject based on a luminance value of a region in the converted image that corresponds to the skin region.

7. 5. The information processing apparatus according to claim 1, wherein the color information is a value of an element included in any one of an RGB color space, an HSV color space, and a YCbCr color space.

8. 5. The information processing apparatus according to claim 1, wherein the biological information includes at least one of a pulse rate, a respiratory rate, a blood pressure, and an oxygen saturation level.

9. 5. An information processing system comprising: an information processing device according to claim 1; and an imaging device capable of communicating with the information processing device, The information processing system is characterized in that the imaging device includes a transmission unit that transmits a captured image to the information processing device.

10. generating a first histogram based on color information included in an image obtained by imaging the subject; generating a second histogram by performing an equalization operation on the first histogram; setting a skin region of the subject in the captured image based on the second histogram; and acquiring biological information of the subject based on the luminance value of the skin region.

11. A program for causing a computer to execute the information processing method according to claim 10.

Images