JP6483782B2 - Image processing apparatus, method, and program - Google Patents

Description

  Embodiments described herein relate generally to an image processing apparatus, a method, and a program.

  Various techniques for displaying a virtual image indicating a state of wearing a clothing to be tried on have been disclosed. For example, the feature point of the image of the subject to be tried on and the feature point of the clothing image are extracted, and the clothing image is deformed so that these feature points match. A technique for displaying a composite image obtained by combining a deformed clothing image and a subject image has been proposed.

Japanese Patent Laid-Open No. 2005-216094

  However, in the prior art, if the posture of the worn clothes and the posture of the subject are different from each other, there is a difference between the image of the clothing to be tried on and the image of the subject, and a natural-looking composite image is presented. Was difficult.

  The problem to be solved by the present invention is to provide an image processing apparatus, method, and program capable of presenting a synthetic image that looks natural.

  An image processing apparatus according to an embodiment is an image processing apparatus that synthesizes a second image with a first image, and that extracts a first feature from the first image and extracts a second feature from the second image And determining the first transparency of the second image corresponding to the first region in accordance with a deviation between the first feature corresponding to the first region and the second feature corresponding to the first region. Determining a second transparency of the second image corresponding to the second region according to a deviation between the first feature corresponding to the second region and the second feature corresponding to the second region; A synthesis unit that synthesizes the second image with the first image using the first transparency and the second transparency.

1 is a block diagram of an image processing apparatus according to a first embodiment. FIG. 6 is an example of a table storing second image information according to the first embodiment. FIG. 6 is a diagram illustrating an example of a second image according to the first embodiment. FIG. 4 is a diagram illustrating an example of a composite image according to the first embodiment. 3 is a flowchart of image processing according to the first embodiment. FIG. 4 is a diagram illustrating an example of a composite image according to the first embodiment. FIG. 4 is a diagram illustrating an example of a composite image according to the first embodiment. FIG. 3 is a block diagram illustrating an image processing apparatus according to a second embodiment. 10 is a flowchart of image processing according to the second embodiment. FIG. 10 illustrates an example of a composite image according to the second embodiment. FIG. 4 is a block diagram illustrating an image processing apparatus according to a third embodiment. 10 is a flowchart of clothes information generation processing according to the third embodiment. FIG. 16 is a diagram illustrating an example of a second image according to the third embodiment. FIG. 6 is a block diagram of an image processing apparatus according to a fourth embodiment. 10 is a flowchart of image processing according to the fourth embodiment. FIG. 10 is a diagram illustrating an example of a composite image according to the fourth embodiment. The figure of the hardware constitutions of an embodiment.

  Hereinafter, an embodiment of an image processing device, a method, and a program will be described in detail with reference to the accompanying drawings.

(Embodiment 1)
FIG. 1 is a block diagram showing a functional configuration of an image processing apparatus 10 according to the present embodiment. The image processing apparatus 10 includes a storage unit 12 (storage unit), an imaging unit 14 (imaging unit), a selection unit 16 (selection unit), a first calculation unit 18 (first calculation unit), an extraction unit 20 (extraction unit), A second calculation unit 22 (second calculation unit), a determination unit 24 (determination unit), a generation unit 26 (generation unit), and a presentation unit 28 (presentation unit) are provided.

  The imaging unit 14 images a subject to be tried on. Examples of the imaging unit 14 include known digital cameras and digital video cameras. The imaging unit 14 acquires a first image including the subject by imaging the subject. The imaging unit 14 outputs the first image to the first calculation unit 18, the extraction unit 20, and the generation unit 26.

  The subject to be tried on is not limited to a person, but also includes pets such as dogs and cats, and mannequins that imitate the shape of human bodies and pets. Also, clothes are items that can be worn by a subject. Examples of the clothes include a jacket, a skirt, trousers, shoes, a hat, and the like.

  The first calculator 18 calculates the posture information of the subject from the first image obtained by the imaging unit 14. The posture information indicates how to hold the body of the subject, and indicates the orientation and movement of the subject. The direction of the subject indicates the direction of the subject at the time of imaging with respect to the imaging unit 14. For example, as the direction of the subject, the front direction in which the face and the body face the front with respect to the imaging unit 14, the side direction in which the face and the body face the side with respect to the imaging unit 14, other than the front direction and the side direction There are other directions. The movement of the subject's body refers to the shape of the body determined by the set of joint angles of the subject.

  In the present embodiment, the first calculation unit 18 describes a case where the posture information indicating the direction of the subject is calculated as the posture information, but the present invention is not limited to this.

  A known method can be applied to the calculation of the posture information by the first calculation unit 18. For example, the posture information is calculated by extracting the face area in the first image by a known method and determining the orientation of the face area by a known method, thereby calculating the posture information indicating the direction of the subject. be able to. In addition, posture information is stored in advance in association with information indicating the size and shape of the contour of the subject in the first image. Then, the first calculation unit 18 may calculate the posture information by extracting the contour of the first image by a known method and reading the posture information corresponding to the information indicating the size and shape of the contour. In addition, the imaging unit 14 captures an image of a subject in a state in which a clothes with a mark is worn for each of the divided areas. Then, posture information may be calculated using a calculation result obtained by calculating each position of the mark image indicating the mark in the first image obtained by imaging.

  Further, posture information may be calculated using a posture estimation method disclosed in Japanese Patent Application Laid-Open No. 2006-249618. Specifically, posture information is stored in advance in association with information indicating the three-dimensional shape of the subject. Then, the contour of the first image obtained by imaging by the imaging unit 14 is extracted by a known method. Then, a subject model is generated for each piece of information indicating a three-dimensional body shape corresponding to each posture information, and the subject model is projected onto a two-dimensional image to extract a contour. Then, a method of calculating posture information by reading posture information corresponding to a subject model having a contour that matches or is most similar to the contour of the first image may be used.

  The storage unit 12 stores second image information indicating the second image. It is preferable that the second image information indicates an image of the clothing imaged in a state of being tried on a doll such as a subject to be tried on or a mannequin having a shape imitating the subject.

  In the present embodiment, the case where the storage unit 12 stores a table storing the second image information will be described. FIG. 2 shows an example of the data structure of a table storing the second image information stored in the storage unit 12.

  As illustrated in FIG. 2, the table storing the second image information stores, for example, clothing numbers, posture information, second image information, and clothing information in association with each other. The clothing number is information such as a number uniquely assigned to each clothing. For this reason, even if the posture information is different, the same clothes will be described as being assigned the same clothes number. Since the posture information has been described above, the description thereof will be omitted. The second image information is image information indicating the second image. The clothing information is information indicating clothing and includes, for example, information such as clothing name, color, size, material, and price.

  The storage unit 12 may store a plurality of types of posture information with different postures and second image information and clothing information corresponding to each posture information for one type of clothing (clothing number). For clothes, posture information of one kind of posture may be stored.

  When the storage unit 12 stores a plurality of types of posture information having different postures for one type of clothing and second image information corresponding to each piece of posture information, for example, the storage unit 12 is illustrated in FIG. As described above, the second image 31A captured from the side surface of the same clothes and the posture information indicating the side direction are stored in association with the clothes number indicating the clothes. Further, as shown in FIG. 3B, the storage unit 12 associates the second image 31B captured from the front side with respect to the same clothing and the posture information indicating the front direction with the clothing number associated with the clothing number. Store.

  Note that the table storing the second image information in the storage unit 12 may store at least the clothing number for identifying the clothing, the posture information, and the second image information, and does not store the clothing information. It may be.

  Returning to FIG. 1, the description will be continued. The selection unit 16 selects second image information corresponding to the posture information received from the first calculation unit 18 from the storage unit 12. When a plurality of second image information corresponding to the posture information is stored in the storage unit 12, that is, when different types of clothes corresponding to the same posture information are stored in the storage unit 12, the selection unit 16 selects one second image information among the plurality of second image information.

  The image processing apparatus 10 is provided with an operation unit (not shown), and the selection unit 16 includes a first calculation unit in the second image information of the clothing number selected by the user's operation instruction on the operation unit. The second image information corresponding to the posture information received from 18 may be selected. In addition, as an operation part, the well-known input device which inputs various information is mentioned, For example, a keyboard, a touch panel, etc. are mentioned.

  The selection unit 16 outputs the selected second image information to the extraction unit 20 and the generation unit 26.

  The extraction unit 20 extracts a contour (referred to as a first contour) of the first image, and extracts a first feature of the subject from the first contour. Further, the extraction unit 20 extracts a contour (referred to as a second contour) of the second image, and extracts a second feature from the second contour.

  The first feature and the second feature indicate portions that characterize the subject. Specifically, the first feature and the second feature indicate at least one of the shoulder portion and the waist portion of the subject. The first feature and the second feature may be any part that characterizes the subject, and include, for example, the neck, chest, side, knee, thigh, head, ankle, and toe. But you can. Hereinafter, when the first feature and the second feature are collectively referred to, they may be simply referred to as features.

  The extraction unit 20 extracts the first contour of the first image and the second contour of the second image using an edge extraction method using a known edge extraction method. Specifically, examples of the edge extraction method include a Canny method, a Sobel operator method, a Prewitt operator method, and a Roberts cross method, but are not limited thereto.

  The following methods are used as a method for extracting the first feature from the first contour and a method for extracting the second feature from the second contour. For example, the extraction unit 20 stores in advance identification information for identifying a line image portion indicating a feature in the contour. Examples of the identification information include, but are not limited to, information indicating curvature.

  An example of a method for extracting the first feature and the second feature using the curvature as identification information will be described. For example, the extraction unit 20 stores in advance information indicating the range of curvature corresponding to each feature for each feature such as a shoulder and a waist. Specifically, the extraction unit 20 stores a range that can be taken by the curvature of the curve corresponding to the shoulder in association with information indicating the shoulder. The extraction unit 20 stores the curvature range in advance in the same manner for the waist and other parts.

  Then, the extraction unit 20 calculates a curvature for each region obtained by dividing the first feature and the second feature into a plurality of regions, and indicates the curvature when information indicating a feature corresponding to the calculated curvature is stored. The region is extracted as a line image (first feature, second feature).

  A known method is used for calculating the curvature. For example, the extraction unit 20 calculates the curvature by the following method. Specifically, the extraction unit 20 first obtains a covariance matrix M (formula (1)) of the contours (first contour, second contour) of the neighborhood region S (p) of the target pixel.

  In Equation (1), M represents a covariance matrix of contours (first contour and second contour), and S (p) represents a neighborhood region of the target pixel. In the formula (1), dI / dx represents a horizontal differential operator, and dI / dy represents a vertical differential operator.

  Then, the extraction unit 20 uses the eigenvalues (λ1, λ2) of the covariance matrix M to calculate the curvature according to the following equation (2).

  Curvature = αλ1 + βλ2 Equation (2)

  In the formula (2), α is a constant and represents the importance of the eigenvalue λ1. Moreover, in formula (2), β is a constant and represents the importance of the eigenvalue λ2.

  In addition to the curvature described above, depth information indicating the depth of the subject or color information of the image may be used as identification information for identifying the line image portion indicating the feature in the contour.

  When using depth information in addition to the curvature as the identification information, the imaging unit 14 is configured to further acquire depth information indicating the depth of the subject. In this case, the imaging unit 14 is configured to include a known device that acquires the depth. Known devices for acquiring the depth include an active sensor and a stereo camera. In this case, the imaging unit 14 outputs the depth information together with the first image to the extraction unit 20.

  In this case, the extraction unit 20 stores in advance information indicating a range of curvature corresponding to each feature and depth information for each feature such as a shoulder and a waist. Then, the extraction unit 20 calculates the curvature for each region obtained by dividing the first feature and the second feature into a plurality of regions, reads the depth information, and stores information indicating the calculated curvature and the feature corresponding to the read depth information. If it is, the region indicating the curvature and depth is extracted as a feature (first feature, second feature).

  When color information is used as the identification information in addition to the curvature, the extraction unit 20 uses a range of curvature corresponding to each feature and a color value between adjacent pixels for each feature such as a shoulder and a waist. Information indicating the difference range is stored in advance. Specifically, the extraction unit 20 stores the range of the curvature of the curve corresponding to the shoulder and the range of the color value difference corresponding to the shoulder in association with the information indicating the shoulder. The extraction unit 20 stores in advance the curvature range and the color value difference range in the same manner for the waist and other parts. Then, the extraction unit 20 calculates a curvature for each region obtained by dividing the first feature and the second feature into a plurality of regions, and calculates a color value difference between adjacent pixels. Then, when information indicating a feature corresponding to the calculated curvature and color value difference is stored, the extraction unit 20 features a region indicating the difference between the curvature and the color value (first feature, second feature). ).

  Other methods may be used as the process of extracting the first feature and the second feature. For example, the imaging unit 14 captures an image of a subject wearing a garment with a first mark on a feature such as a shoulder and a belt-like garment with a second mark. Then, the extraction unit 20 extracts the shoulder portion based on the first position of the first mark in the first image information obtained by imaging, and extracts the waist portion based on the second position of the second mark. Thus, the first feature and the second feature may be extracted.

  FIG. 4 shows an example of image synthesis in the image processing apparatus 10 of the present embodiment. For example, as illustrated in FIG. 4A, the first image captured by the imaging unit 14 is the first image 30, and the second image information selected by the selection unit 16 is the second image illustrated in FIG. Assume that the image 36 is displayed. In this case, for example, the extraction unit 20 extracts, for example, the first contour 32 illustrated in FIG. 4B as the first contour of the first image 30. Moreover, the extraction part 20 extracts the 2nd outline 38 shown to FIG.4 (E) as a 2nd outline of the 2nd image 36, for example.

  Then, the extraction unit 20 extracts a first feature 34 corresponding to, for example, the shoulder 32A, which is a feature point in the first contour 32 (see FIG. 4C). Similarly, the extraction unit 20 extracts the second feature 40 corresponding to the shoulder portion 38A in the second contour 38 (see FIG. 4F). And the production | generation part 26 mentioned later produces | generates the synthesized image 42 which synthesize | combined the 1st image and the 2nd image in which the transparency was changed (refer FIG.4 (G)).

  Returning to FIG. 1, the description will be continued. The extraction unit 20 outputs the first feature extracted from the first contour of the first image and the second feature extracted from the second contour of the second image to the second calculation unit 22.

  The second calculation unit 22 calculates a shift amount between the first feature and the second feature received from the extraction unit 20 (hereinafter referred to as a first shift amount).

  A known calculation method is used to calculate the amount of deviation between the first feature and the second feature. For example, as a method of calculating the amount of deviation between the first feature and the second feature, a Champion Matching method, a level set method, a simple similarity method, or the like is used.

  More specifically, for example, the second calculation unit 22 calculates the total value of the differences between the pixel positions of the pixels constituting the first feature and the pixel positions of the pixels constituting the second feature as the first value. Calculated as the amount of deviation.

  In addition, it is preferable that the 2nd calculation part 22 performs the alignment of a 1st feature and a 2nd feature first at the time of calculation of this 1st deviation | shift amount. Specifically, the second calculation unit 22 enlarges, reduces, or changes the position of any one of the first feature and the second feature, and changes the first feature after each change. A deviation amount between the one feature and the second feature is calculated. Then, the change process and the shift amount calculation process are repeated a predetermined number of times, and the minimum value of the calculated shift amounts is calculated as the first shift amount of the first feature and the second feature. Note that the number of repetitions of the change process and the deviation amount calculation process may be determined in advance and stored in the second calculation unit 22 in advance.

  The second calculation unit 22 outputs the calculated first deviation amount to the determination unit 24.

  The determining unit 24 determines the higher transmittance as the second image transparency as the first shift amount is larger. For example, the determination unit 24 stores in advance a calculation formula for calculating a higher degree of transparency as the first deviation amount is larger or a table in which the first deviation amount and the transparency are determined as the permeability with respect to the first deviation amount. Then, the determination unit 24 calculates the transparency by substituting the first deviation amount received from the second calculation unit 22 into the calculation formula, or reads the transparency corresponding to the first deviation amount, thereby determining the transparency. To decide.

  Note that the determination unit 24 only needs to determine a higher transmittance as the first shift amount is larger, and determines the transmittance using an expression or a table in which the relationship between the first shift amount and the transmittance is indicated by a linear line. Alternatively, the transmittance may be determined using an expression or a table in which the relationship is indicated by a quadratic curve. Moreover, the determination part 24 may determine a high transmittance | permeability continuously, so that the 1st deviation | shift amount is large, and may determine a high transparency in steps, so that a 1st deviation | shift amount is large.

  The determination unit 24 outputs the transparency determined as the transparency of the second image to the generation unit 26.

  The generation unit 26 receives the transparency information indicating the transparency from the determination unit 24. Further, the generation unit 26 receives the second image information from the selection unit 16. Further, the generation unit 26 receives the first image from the imaging unit 14.

  Then, the generation unit 26 changes the transparency of the second image information received from the selection unit 16 to the transparency received from the determination unit 24. And the production | generation part 26 synthesize | combines the 2nd image of the 2nd image information of the changed transparency with the 1st image of the 1st image information received from the imaging part 14, and produces | generates a synthesized image.

  Specifically, the generation unit 26 generates a composite image by calculating a pixel value of a region where the second image and the first image overlap in the composite image using the following equation (3).

  Io = α · β · Ih + (1−α) (1−β) · Ic (3)

  In Expression (3), Io represents a pixel value of a region where the second image and the first image overlap in the composite image. Ih represents the pixel value of the overlapping area in the first image. Ic indicates the pixel value of the overlapping area in the second image. In Expression (3), α represents the transmittance determined by the determination unit 24. In Expression (3), β represents the transparency (transparency before synthesis) of the second image to be synthesized.

  In Equation (3), α and β indicate the transmittance when the maximum value of the transmittance is “1” and the minimum value of the transmittance is “0”.

  Then, the generation unit 26 outputs the composite image information of the generated composite image to the presentation unit 28.

  The presentation unit 28 receives the composite image information from the generation unit 26. The presentation unit 28 is a device that presents a composite image. In the present embodiment, “presentation” indicates display, printing, transmission, and the like. Examples of the presentation unit 28 include a display device such as a liquid crystal display device, a printing device that prints an image, and a known communication device that transmits information to an external device by wired communication or wireless communication. When the presentation unit 28 is a display device, the presentation unit 28 displays a composite image of the received composite image information. When the presentation unit 28 is a communication device, the presentation unit 28 transmits the composite image information to the external device. If the presentation unit 28 is a printing device, the presentation unit 28 prints a composite image of the composite image information.

  Next, image processing executed by the image processing apparatus 10 according to the present embodiment will be described.

  FIG. 5 is a flowchart illustrating a procedure of image processing executed by the image processing apparatus 10 according to the present embodiment.

  First, the imaging unit 14 acquires a first image by imaging a subject (step S100). Next, the first calculation unit 18 calculates the posture information of the subject from the first image information of the first image obtained by imaging by the imaging unit 14 (step S102).

  Next, the extraction unit 20 extracts the first contour of the first image information obtained by the imaging in step S100, and extracts the first feature from the first contour (step S104, step S106).

  Next, the selection unit 16 selects one second image information corresponding to the posture information calculated in step S102 from the storage unit 12 (step S108).

  Next, the extraction unit 20 extracts the second contour of the second image information selected in Step S108, and extracts the second feature from the second contour (Step S110, Step S112).

  Next, the second calculation unit 22 performs alignment of the first feature extracted in step S106 and the second feature extracted in step S112, and performs alignment (expansion / reduction of the first feature and the second feature). The minimum value of the deviation amounts calculated by the position change) is calculated (steps S114 and S116).

  Next, the second calculation unit 22 uses the same clothing number as the clothing number of the second image information used for the extraction of the second contour in step S110, and corresponds to different posture information and the second image for which the deviation amount has not been calculated. It is determined whether or not information is stored in the storage unit 12 (step S118). When the second image information corresponding to different posture information and not calculated for the deviation amount is stored in the same clothing number, the second calculation unit 22 makes an affirmative determination (step S118: Yes). Then, the second calculation unit 22 corresponds to the second image information corresponding to the posture information different from the second image information corresponding to the clothing number of the second image information used for the extraction of the second contour in step S110. Is selected from the storage unit 12, and then the process returns to step S110 (step S120).

  On the other hand, if a negative determination is made in step S118 (step S118: No), the second calculation unit 22 calculates the minimum value of the deviation amounts calculated in the processes of steps S110 to S120 as the first deviation amount (step S118). S122).

  Next, the determination unit 24 determines a higher transmittance as the first deviation amount is larger based on the first deviation amount calculated in Step S122 (Step S124).

  Next, the generation unit 26 changes the transparency of the second image information corresponding to the second feature used when calculating the first deviation amount calculated by the process of step S122 to the transparency determined in step S124. Then, a synthesized image obtained by synthesizing the second image information with the changed transparency and the first image information is generated (step S126).

  Next, the presentation unit 28 presents the composite image generated in step S126 (step S128).

  In addition, you may perform the process of said step S108-step S112 as an interruption process interrupted every predetermined time at the time of the process of said step S100-step 106.

  By performing the image processing shown in steps S100 to S128, for example, the image processing apparatus 10 generates a composite image shown in FIG.

  FIG. 6 shows an example of image synthesis in the image processing apparatus 10 of the present embodiment. For example, as illustrated in FIG. 6C, the first image captured by the imaging unit 14 is the first image 50 obtained by capturing the subject from the front direction, and the second image information selected by the selection unit 16 is illustrated in FIG. Assume that the second image 46 is obtained by photographing the second image from the front direction as shown in FIG. Then, it is assumed that the first deviation amount calculated by the second calculation unit 22 is a value corresponding to the transparency “0” (the minimum value of the transparency). It is assumed that the transparency of the first image obtained by imaging by the imaging unit 14 is the transparency “0”. In this case, the image processing apparatus 10 performs the above image processing, for example, a composite image in which the second image 46 with transparency “0” is superimposed on the first image 50 with transparency “0”. 52 is generated and presented to the presentation unit 28 (see FIG. 6E).

  On the other hand, as shown in FIG. 6A, the first image captured by the imaging unit 14 is the first image 44 obtained by capturing the subject from the side surface direction, and the second image information selected by the selection unit 16 is FIG. Assume that the second image 46 is obtained by photographing the second image from the front direction as shown in FIG. In this case, the first deviation amount between the first feature and the second feature is larger than the first deviation amount used at the time of generating the composite image shown in FIG. For example, in this case, it is assumed that the first shift amount calculated by the second calculator 22 is a value corresponding to the transparency “1” (the maximum value of the transparency). It is assumed that the transparency of the first image obtained by imaging by the imaging unit 14 is the transparency “0”. In this case, the image processing apparatus 10 performs the above-described image processing, for example, a composite image in which the second image 46A having the transparency “1” is superimposed on the first image 44 having the transparency “0”. 48 is generated and presented to the presentation unit 28 (see FIG. 6D). Therefore, as shown in FIG. 6D, the second image 46A is presented in a transparent state in the composite image 48.

  Further, although illustration is omitted, since the transparency of the second image to be combined with the first image increases as the first shift amount increases, the composite image 52 is combined with the composite image 52 as the first shift amount increases. The second image having a high transparency toward 48 is combined with the first image.

  As described above, in the image processing apparatus 10 according to the present embodiment, the shift amount between the first feature extracted from the first contour of the first image and the second feature extracted from the second contour of the second image. The greater the first deviation amount indicating is, the higher the transparency is determined, and the synthesized image obtained by synthesizing the first image and the second image changed to the determined transparency is presented.

  Therefore, in the image processing apparatus 10 according to the present embodiment, when the posture of the worn clothes and the posture of the subject are different, the transmission of the second image is increased as the posture is different, that is, as the first shift amount is larger. Since the image is combined with the first image at a high degree, it is possible to present a combined image that looks natural.

  In the present embodiment, the case has been described in which the second calculation unit 22 calculates the first shift amount between the first feature and the second feature. However, the second calculation unit 22 may divide each of the first feature and the second feature into a plurality of line regions and calculate the first shift amount for each line region. Then, the determination unit 24 determines, for each of the plurality of regions including each of the line regions in the second image, a higher transmittance for each region as the first shift amount of the line region included in each region is larger. Then, the generation unit 26 may generate a composite image in which the second image obtained by changing the transparency of each region of the second image to the determined transparency is combined with the first image.

  FIG. 7 shows an example of image synthesis in the image processing apparatus 10 of the present embodiment. Assume that the extraction unit 20 extracts, for example, the first contour 53 illustrated in FIG. 7A and the first feature 54 illustrated in FIG. 7B as the first contour of the first image. In addition, it is assumed that the extraction unit 20 extracts, for example, the second contour 56 illustrated in FIG. 7D and the second feature 57 illustrated in FIG. 7E as the second contour of the second image.

  Then, the second calculator 22 divides the first feature 54 into a plurality of line regions 55 (see FIG. 7C), and divides the second feature 57 into a plurality of line regions 58 (FIG. 7F). reference). Then, the determination unit 24 determines, for each of the plurality of regions including each of the line regions in the second image, a higher transmittance for each region as the first shift amount of the line region included in each region is larger.

  Then, for example, when the first shift amount of each line region obtained by dividing the first feature and the second feature into a plurality of line regions is a shift amount corresponding to the minimum value “0” of the transparency, the generation unit 26 Then, a synthesized image 59 is generated by synthesizing the second image with transparency “0” with the first image with transparency “0” (see FIG. 7G). On the other hand, of each line area obtained by dividing the first feature and the second feature into a plurality of line areas, the first shift amount of the line area corresponding to the part from the elbow of the subject corresponds to the maximum transparency value “1”. Suppose that the amount of deviation is. The other line regions are assumed to have a deviation corresponding to the minimum transparency value “0”. In this case, the generation unit 26 changes the transparency of the area including the line area corresponding to the tip of the elbow in the second image to the transparency “1”, and changes the transparency of the other areas to the transparency “ A composite image 60 is generated by combining the second image with “0” with the first image with transparency “0” (see FIG. 7H). For this reason, for example, when the first shift amount from the second image of the portion beyond the elbow of the subject is large, the second image having a high transparency according to the first shift amount is changed to the first image. It becomes the synthesized image. For this reason, it is possible to present a composite image that looks natural.

  In the present embodiment, as described above, the extraction unit 20 uses the edge extraction method using a known edge extraction method to extract the first contour of the first image and the second contour of the second image. Extract. Then, the extraction unit 20 has been described as extracting the first feature based on the curvature of the first contour and extracting the second feature based on the curvature of the second contour.

  The filter size used at the time of edge extraction and the neighborhood region used at the time of curvature calculation may be fixed, but are preferably adjusted according to the following ratio. Specifically, in the extraction unit 20, at least one of the filter size and the size of the neighboring region is increased as the proportion of the first image indicating the subject in the captured image obtained by the imaging of the imaging unit 14 increases. Is preferred.

  The larger the proportion of the first image in the captured image, the larger the ratio of the first image in the captured image due to movement of the subject or the like by increasing at least one of the filter size and the size of the neighboring region. However, each of the first contour, the second contour, the first feature, and the second feature can be extracted with high accuracy.

(Embodiment 2)
In the present embodiment, when a plurality of first images having different imaging times are acquired and it is determined that there is a motion in the subject, the transparency is further increased according to the shift amount of the first feature between successive first images. adjust.

  FIG. 8 is a block diagram showing a functional configuration of the image processing apparatus 10B of the present embodiment. The image processing apparatus 10B includes a storage unit 12 (storage unit), an imaging unit 14B (imaging unit), a selection unit 16 (selection unit), a first calculation unit 18 (first calculation unit), a detection unit 19B (detection unit), An extraction unit 20 (extraction unit), a second calculation unit 22 (second calculation unit), a determination unit 24B (determination unit), a generation unit 26B (generation unit), and a presentation unit 28 (presentation unit) are provided.

  In addition, the same code | symbol is provided to the part of the same function as the image processing apparatus 10 in Embodiment 1, and detailed description is abbreviate | omitted. The image processing apparatus 10B is different from the first embodiment in that the imaging unit 14B, the detection unit 19B, the determination unit 24B, and the generation unit 26B are provided.

  The imaging unit 14B images a subject to be tried on and obtains a plurality of first images having different imaging times. The plurality of first images may be a plurality of still images captured by the imaging unit 14B according to time, or may be each frame constituting a moving image captured by the imaging unit 14B. .

  The imaging unit 14B sequentially outputs the obtained first images to the first calculation unit 18, the extraction unit 20, the detection unit 19B, and the generation unit 26B every time the first image is acquired by imaging.

  The detection unit 19B detects from the first image sequentially received from the imaging unit 14B that the subject has moved since the previous imaging. The detection of the movement of the subject is performed by the following method. Specifically, the detection unit 19B calculates the first feature from the first contour of the first image for each of the first images that are continuous in time series in the same manner as the extraction unit 20 in the first embodiment. . Then, the detection unit 19B further calculates a second shift amount indicating a shift between the first features of the first image that is continuous in time series. When the second shift amount is equal to or greater than a predetermined value indicating that the subject has moved, the detection unit 19B detects that the subject has moved.

  Then, when detecting that the subject has moved, the detection unit 19B transmits the calculated second shift amount to the determination unit 24B. Further, the detection unit 19B obtains a signal indicating that the subject has moved and the latest first image (the latest first image used for calculating the second shift amount) from which the movement has been detected. It outputs to the production | generation part 26B.

  The determination unit 24B performs the same process as the determination unit 24 of the first embodiment, and further determines a higher transmittance as the second deviation amount is larger. Specifically, the determination unit 24B stores in advance a calculation formula for calculating higher transparency as the second deviation amount is larger, or a table that defines the second deviation amount and the transparency. Then, the determining unit 24B calculates the transparency by substituting the second deviation amount into the calculation formula, or determines the transparency by reading the transparency corresponding to the second deviation amount. Then, the determined transparency is output to the generation unit 26B.

  The generation unit 26B performs the same process as the generation unit 26 of the first embodiment. In addition, when the second shift amount is received from the detection unit 19B, the generation unit 26B changes the transparency of the second image information received from the selection unit 16 to the transparency received from the determination unit 24B. Then, the generation unit 26B uses the second image of the second image information with the changed transparency as the latest first image (the latest first image used for calculating the second shift amount) that is detected to have moved. Image) to generate a composite image. Then, the generated composite image is output to the presentation unit 28.

  Next, image processing executed by the image processing apparatus 10B according to the present embodiment will be described.

  The image processing apparatus 10B performs the same process as the image process in the first embodiment (see FIG. 5). Further, the interruption process shown in FIG. 9 is executed at predetermined time intervals. FIG. 9 is a flowchart illustrating a procedure of interrupt processing executed by the image processing apparatus 10B.

  The detection unit 19B determines whether the subject has moved (step S200). If it is not detected that the subject has moved (step S200: No), this routine ends. On the other hand, when the detection unit 19B detects that the subject has moved (step S200: Yes), the detection unit 19B detects the presence of movement between the first features of the first images that are continuous in time series. The second shift amount indicating the shift is output to the determination unit 24B (step S204).

  Next, the determination unit 24B determines a higher transmittance as the second deviation amount is larger (step S206). When the generation unit 26B receives the second shift amount from the detection unit 19B, the generation unit 26B changes the transparency of the second image information received from the selection unit 16 to the transparency received from the determination unit 24B. Then, the generation unit 26B uses the second image of the second image information with the changed transparency as the latest first image (the latest first image used for calculating the second shift amount) that is detected to have moved. Image) to generate a composite image (step S208).

  The presentation unit 28 presents the composite image generated in step S208 (step S210).

  FIG. 10 shows an example of a composite image in the image processing apparatus 10B of the present embodiment.

  For example, as shown in FIG. 10A, the first image first captured by the imaging unit 14B is the first image 62A obtained by capturing the subject from the front direction, and the second image information selected by the selection unit 16 is As shown in FIG. 10A, it is assumed that the second image 62B is obtained by photographing the second image from the front direction. Then, it is assumed that the first deviation amount calculated by the second calculation unit 22 is a value corresponding to the transparency “0” (the minimum value of the transparency). It is assumed that the transparency of the first image obtained by imaging by the imaging unit 14B is the transparency “0”. In this case, the image processing apparatus 10B executes the above-described image processing, for example, a composite image 62 in which the second image with the transparency “0” is superimposed on the first image with the transparency “0”. It produces | generates and shows to the presentation part 28 (refer FIG. 10 (A)).

  When the detection unit 19B detects that the subject has moved, the first image 62A (see FIG. 10A) and the first image 62D (see FIG. 10B) that are continuous in time series. The higher the second deviation amount calculated from the above, the higher the transmittance. For example, it is assumed that the subject instantaneously moves from a state facing the front (first image 62A) to a state facing the side (first image 62D). Then, it is assumed that the second shift amount is a value corresponding to the transparency “1” (the maximum value of the transparency). In this case, the image processing apparatus 10B performs the interrupt process shown in FIG. 9 to superimpose the second image 62C with the transparency “1” on the first image 62D with the transparency “0”. A composite image 68 is generated and presented to the presentation unit 28 (see FIG. 10B). Therefore, as shown in FIG. 10B, the second image 62C is not presented in the composite image 68, and the first image 62D is presented.

  As described above, in the image processing apparatus 10B according to the present embodiment, when a plurality of first images having different imaging times are acquired and it is determined that there is a motion in the subject, the first feature between successive first images is obtained. The transparency of the second image information is further adjusted according to the second deviation amount.

  Therefore, in addition to the effects of the first embodiment, a composite image that looks natural can be presented.

(Embodiment 3)
In the present embodiment, a case will be described in which a second image information is created and a creation unit for creating a second feature is further provided.

  FIG. 11 is a block diagram illustrating a functional configuration of the image processing apparatus 10C according to the present embodiment. The image processing apparatus 10C includes a storage unit 12 (storage unit), an imaging unit 14 (imaging unit), a selection unit 16 (selection unit), a first calculation unit 18 (first calculation unit), an extraction unit 20C (extraction unit), A second calculation unit 22 (second calculation unit), a determination unit 24 (determination unit), a generation unit 26 (generation unit), and a presentation unit 28 (presentation unit) are provided. Further, the image processing apparatus 10 </ b> C includes an imaging unit 11 and a creation unit 13.

  In addition, the same code | symbol is provided to the part of the same function as the image processing apparatus 10 in Embodiment 1, and detailed description is abbreviate | omitted. The image processing apparatus 10 </ b> C is different from the first embodiment in that in addition to the configuration of the image processing apparatus 10 (see FIG. 1) of the first embodiment, the image processing apparatus 10 </ b> C further includes an imaging unit 11 and a creation unit 13. The image processing apparatus 10 </ b> C is different from the image processing apparatus 10 in that an extraction unit 20 </ b> C is provided instead of the extraction unit 20.

  The imaging unit 11 captures clothes and acquires image information including the second image. The imaging unit 11 outputs the acquired image information to the creation unit 13.

  Examples of the imaging unit 11 include known digital cameras and digital video cameras. In the present embodiment, a case is described in which the imaging unit 11 that captures clothes and the imaging unit 14 that captures a subject are provided separately. However, these imaging units are provided integrally. It is good also as a structure. In other words, the imaging unit 14 may further capture clothing and output image information including the second image to the creation unit 13.

  The creation unit 13 extracts a second image included in the image of the image information received from the imaging unit 11, and generates second image information of the second image. In addition, the creation unit 13 extracts the second contour of the second image, and extracts the second feature from the second contour. The extraction of the second contour and the extraction of the second feature are performed in the same manner as the extraction unit 20 described in the first embodiment. In addition, the creation unit 13 calculates posture information from the second image information in the same manner as the first calculation unit 18.

  The creation unit 13 stores the second image information, the clothing information including the second feature, and the posture information in the table of the storage unit 12 in association with the clothing number (see also FIG. 2).

  For this reason, the memory | storage part 12 memorize | stores the table which matched and stored clothing number, attitude | position information, 2nd image information, and clothing information. Then, in addition to the information such as the clothing name, color, size, material, and price described in the first embodiment, the second feature is stored as the clothing information.

  Here, it is assumed that the clothes have a shape that does not cover the entire shoulder portion of the subject when worn on the subject. That is, it is assumed that the clothes have a shape that covers a part of the shoulder of the subject. In this case, it is preferable that the imaging unit 11 captures an image of a garment in a state where the garment is being tried on by a doll such as a subject to be tried on or a mannequin having a shape imitating the subject. In this case, the creation unit 13 extracts the second image and the image (referred to as the first image) indicating the subject or the doll included in the image of the image information received from the imaging unit 11, and extracts the second image and the second image. A second contour is extracted from one image, and a second feature is extracted from the second contour.

  The extraction unit 20C performs a process similar to the process of the extraction unit 20 described in the first embodiment. Note that the extraction unit 20C extracts the second feature of the second image information by reading the second feature corresponding to the second image information selected by the selection unit 16 from the storage unit 12. Different from 20.

  Next, clothing information generation processing executed by the image processing apparatus 10C according to the present embodiment will be described.

  The image processing apparatus 10C performs the same processing as the image processing in the first embodiment (see FIG. 5). Then, before executing this image processing or as an interrupt processing during the image processing, the clothing information generation processing shown in FIG. 12 is executed.

  FIG. 12 is a flowchart illustrating a procedure of clothing information generation processing executed by the image processing apparatus 10C.

  The imaging unit 11 captures clothes and acquires image information including the second image (steps S300 and S302). Next, the creation unit 13 generates clothes information and posture information (step S304). Next, the creation unit 13 stores the second image information, the clothing information including the second feature, and the posture information in the table of the storage unit 12 in association with the clothing number (step S306).

  As described above, the image processing apparatus 10 </ b> C according to the present embodiment includes the creation unit 13 that creates the second feature while creating the second image information. For this reason, image processing can be performed efficiently.

  Therefore, in addition to the effects of the first embodiment, a composite image that looks natural can be presented.

  Further, as described above, the creation unit 13 of the image processing apparatus 10C according to the present embodiment uses the second image from the image obtained by imaging the clothing in a state of being tried on a subject or a doll shaped like the subject. A first image showing the image and the subject or doll is extracted. Then, the creation unit 13 extracts a second contour from the second image and the first image, and extracts a second feature from the second contour.

  Therefore, even if the second image to be tried on is a second image 70 having a shape that does not cover the entire shoulder as shown in FIG. 13A, as shown in FIG. 13B. In addition, the first feature including the shoulder 72 can be extracted from the second image 70 and the first image 73 showing the subject. For this reason, it can suppress that an error arises at the time of calculation of the 1st gap amount.

  In the image processing apparatus 10 </ b> C, the case where the creation unit 13 also generates the second feature has been described. However, the creation unit 13 may create the second image information and the feature information and store them in the storage unit 12. Further, the creation unit 13 may store the first image information of the first image in the storage unit 12. In this case, the extraction unit 20C extracts the second feature from the second image information and the first image information selected by the selection unit 16 in the same manner as the extraction unit 20.

(Embodiment 4)
In the present embodiment, the aspect ratio of at least one of the second image and the first image is adjusted in accordance with the aspect ratio of the mirror that is the target for projecting the subject.

  FIG. 14 is a block diagram showing a functional configuration of the image processing apparatus 10D of the present embodiment. The image processing apparatus 10D includes a storage unit 12 (storage unit), an imaging unit 14 (imaging unit), a selection unit 16 (selection unit), a first calculation unit 18 (first calculation unit), an adjustment unit 21D (adjustment unit), An extraction unit 20 (extraction unit), a second calculation unit 22 (second calculation unit), a determination unit 24 (determination unit), a generation unit 26D (generation unit), and a presentation unit 28 (presentation unit) are provided.

  In addition, the same code | symbol is provided to the part of the same function as the image processing apparatus 10 in Embodiment 1, and detailed description is abbreviate | omitted. The image processing apparatus 10 </ b> D is different from the first embodiment in that the image processing apparatus 10 </ b> D further includes an adjustment unit 21 </ b> D and includes a generation unit 26 </ b> D instead of the generation unit 26.

  The adjustment unit 21D stores in advance the aspect ratio of the target mirror that reflects the subject. Further, the adjustment unit 21D adjusts at least one of the aspect ratio of the first image received from the imaging unit 14 and the aspect ratio of the second image received from the selection unit 16 to the aspect ratio of the mirror.

  The mirror aspect ratio indicates the ratio between the maximum length of the mirror in the vertical direction (vertical direction) and the maximum length of the mirror in the horizontal direction (horizontal direction). The aspect ratio of the first image is a ratio between the maximum length of the subject in the vertical direction (gravity direction) in the first image and the maximum length of the subject in the horizontal direction (horizontal direction) in the first image. Further, the aspect ratio of the second image indicates a ratio between the maximum length in the vertical direction of the clothes in the second image and the maximum length in the horizontal direction of the clothes in the second image. In addition, the vertical direction of the clothes in the second image matches the vertical direction (the direction of gravity) of the clothes in a state of being tried on by the subject. In addition, the lateral direction of the clothes in the second image matches the horizontal direction of the clothes that are tried on the subject.

  Note that the image processing apparatus 10D may be configured to include an operation unit (not shown). In addition, as an operation part, the well-known input device which inputs various information is mentioned, For example, a keyboard, a touch panel, etc. are mentioned. Then, in accordance with an operation instruction from the operation unit by the user, information indicating the presence / absence of adjustment of the aspect ratio of the first image and the second image and the aspect ratio may be output from the operation unit to the adjustment unit 21D. .

  Then, the adjustment unit 21D may adjust the aspect ratio so that the aspect ratio received from the operation unit is obtained when the adjustment of the aspect ratio is instructed by the operation of the operation unit by the user.

  The adjustment unit 21 </ b> D outputs the first image and the second image with the adjusted aspect ratio to the extraction unit 20.

  The generation unit 26D combines the first image whose aspect ratio is adjusted by the adjustment unit 21D and the second image whose aspect ratio is adjusted by the adjustment unit 21D and changed to the transparency determined by the determination unit 24. An image is generated and output to the presentation unit 28. The generation of the composite image by the generation unit 26D is performed in the same manner as the generation unit 26 described in the first embodiment.

  Next, image processing executed by the image processing apparatus 10D according to the present embodiment will be described.

  FIG. 15 is a flowchart showing a procedure of image processing executed by the image processing apparatus 10D of the present embodiment. In FIG. 15, it is assumed that the adjustment unit 21D stores in advance information indicating the mirror aspect ratio and information indicating execution of adjustment of the aspect ratio of both the first image and the second image. . As described above, these pieces of information can be changed by an operation instruction from a user of an operation unit (not shown).

  First, the imaging unit 14 acquires a first image by imaging a subject (step S400). Next, the first calculation unit 18 calculates the posture information of the subject from the first image information of the first image obtained by imaging by the imaging unit 14 (step S402).

  Next, the adjusting unit 21D adjusts the aspect ratio of the first image acquired in step S400 to the aspect ratio of the mirror that is the object to be projected (step S403).

  Next, the extraction unit 20 extracts the first contour of the first image information whose aspect ratio has been adjusted by the process of step S403 by the adjustment unit 21D, and extracts the first feature from the first contour (step S404, step S404). S406).

  Next, the selection unit 16 selects one second image information corresponding to the posture information calculated in step S402 from the storage unit 12 (step S408).

  Next, the adjustment unit 21D adjusts the aspect ratio of the second image information selected in step S408 to the aspect ratio of the mirror that is the target for projecting the subject (step S409).

  Next, the extraction unit 20 extracts the second contour of the second image information whose aspect ratio has been adjusted, and extracts the second feature from the second contour (steps S410 and S412).

  Next, the second calculation unit 22 performs alignment of the first feature extracted in step S406 and the second feature extracted in step S412 and performs alignment (expansion / reduction of the first feature and the second feature). The minimum value of the deviation amounts calculated by the position change) is calculated (steps S414 and S416).

  Next, the second calculation unit 22 uses the same clothing number as the clothing number of the second image information used for extracting the second contour in step S410, and corresponds to different posture information, and the second image for which the deviation amount has not been calculated. It is determined whether or not information is stored in the storage unit 12 (step S418). In the case where second image information corresponding to different posture information and having not been calculated is stored in the same clothing number, the second calculation unit 22 makes an affirmative determination (step S418: Yes). Then, the second calculation unit 22 corresponds to the second image information corresponding to the posture information different from the second image information corresponding to the clothing number of the second image information used for the extraction of the second contour in step S410. Is selected from the storage unit 12 (step S420).

  Next, the adjustment unit 21D adjusts the aspect ratio of the second image information selected in step S420 to the aspect ratio of the mirror that is the target for projecting the subject (step S421). Then, the process returns to step S410.

  On the other hand, if a negative determination is made in step S418 (step S418: No), the second calculation unit 22 calculates the minimum value of the deviation amounts calculated in the processes of steps S410 to S421 as the first deviation amount ( Step S422).

  Next, the determination unit 24 determines a higher transmittance as the first deviation amount is larger based on the first deviation amount calculated in Step S422 (Step S424).

  Next, in step S424, the generation unit 26D determines the transparency of the second image information after the aspect ratio adjustment corresponding to the second feature used when calculating the first deviation amount calculated by the process in step S422. Change to the transparency. Then, a synthesized image is generated by synthesizing the second image information whose aspect ratio and transparency are changed and the first image information whose aspect ratio is adjusted (step S426).

  Next, the presentation unit 28 presents the composite image generated in step S426 (step S428).

  Note that the processing in steps S408 to S412 may be executed as interrupt processing that interrupts at predetermined intervals during the processing in steps S400 to S406.

  By performing the image processing shown in steps S400 to S428, the image processing apparatus 10D generates, for example, a composite image shown in FIG.

  FIG. 16 shows an example of image composition in the image processing apparatus 10D of the present embodiment. When the aspect ratio is not adjusted, for example, as shown in FIG. 16A, the aspect ratio (Y2: X2) of the subject 74 and the presentation unit 28 stacked on the mirror that reflects the subject 74 are used. A composite image 78 in which the aspect ratio (Y1: X1) of the display unit (mirror) is different is presented.

  On the other hand, when adjusting the aspect ratio, for example, as shown in FIG. 16B, the aspect ratio (Y2: X2) of the subject 74 and the presentation unit 28 stacked on the mirror that reflects the subject 74 are used. A composite image 80 having the same aspect ratio (Y1: X1) of the display unit (mirror) is presented.

  Therefore, in addition to the effects of the first embodiment, the image processing apparatus 10D of the present embodiment can present a more natural-looking composite image.

  Next, the hardware configuration of the image processing device 10, the image processing device 10B, the image processing device 10C, and the image processing device 10D according to the first to fourth embodiments will be described. FIG. 17 is a block diagram illustrating a hardware configuration example of the image processing apparatus 10 according to the present embodiment.

  The image processing device 10, the image processing device 10B, the image processing device 10C, and the image processing device 10D according to the first to fourth embodiments include a presentation unit 80, a communication I / F unit 82, an imaging unit 84, and a CPU (Central A processing unit (86), a ROM (Read Only Memory) 88, a RAM (Random Access Memory) 90, an HDD 92, and the like are connected to each other by a bus 94 and have a hardware configuration using a normal computer.

  The CPU 86 is an arithmetic device that controls the overall processing of the image processing device 10, the image processing device 10B, the image processing device 10C, and the image processing device 10D. The RAM 90 stores data necessary for various processes by the CPU 86. The ROM 88 stores a program for realizing various processes by the CPU 86 and the like. The HDD 92 stores data stored in each storage unit described above. The communication I / F unit 82 is an interface for connecting to an external device or an external terminal via a communication line or the like and transmitting / receiving data to / from the connected external device or external terminal. The presentation unit 80 corresponds to the presentation unit 28 described above. The imaging unit 84 corresponds to the imaging unit 14, the imaging unit 11, and the imaging unit 14B described above.

  A program for executing the various processes executed by the image processing apparatus 10, the image processing apparatus 10B, the image processing apparatus 10C, and the image processing apparatus 10D according to the first to fourth embodiments is stored in advance in the ROM 88 or the like. Provided with built-in.

  The programs executed in the image processing apparatus 10, the image processing apparatus 10B, the image processing apparatus 10C, and the image processing apparatus 10D according to the first to fourth embodiments are in a format that can be installed in these apparatuses or executed. The file may be recorded in a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, or a DVD (Digital Versatile Disk).

  In addition, the programs executed by the image processing apparatus 10, the image processing apparatus 10B, the image processing apparatus 10C, and the image processing apparatus 10D according to the first to fourth embodiments are executed on a computer connected to a network such as the Internet. And may be provided by being downloaded via a network. In addition, a program for executing each of the processes in the image processing apparatus 10, the image processing apparatus 10B, the image processing apparatus 10C, and the image processing apparatus 10D according to the first to fourth embodiments is transmitted via a network such as the Internet. It may be configured to be provided or distributed on.

  The programs for executing the various processes executed by the image processing apparatus 10, the image processing apparatus 10B, the image processing apparatus 10C, and the image processing apparatus 10D according to the first to fourth embodiments are the above-described units (selection). Unit 16, first calculation unit 18, extraction unit 20 (extraction unit 20C), second calculation unit 22, determination unit 24 (determination unit 24B), generation unit 26 (generation unit 26B, generation unit 26D), detection unit 19B, The module configuration includes the adjustment unit 21D). As actual hardware, a CPU (processor) reads out each program from a storage medium such as the ROM 88 and executes the program, so that the respective units are loaded onto the main storage device, and the selection unit 16, the first calculation unit 18, and the extraction unit. 20 (extraction unit 20C), second calculation unit 22, determination unit 24 (determination unit 24B), generation unit 26 (generation unit 26B, generation unit 26D), detection unit 19B, and adjustment unit 21D are generated on the main storage device. It has become so.

  Various information stored in the HDD 92, that is, various information stored in the storage unit 12, may be stored in an external device (for example, a server). In this case, the external device and the CPU 86 may be connected via a network or the like.

  In addition, although several embodiment of this invention was described above, these embodiment is shown as an example and is not intending limiting the range of invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

10, 10B, 10C, 10D Image processing apparatus 11, 14, 14B Image pickup unit 16 Selection unit 18 First calculation unit 20, 20C Extraction unit 22 Second calculation unit 24, 24B Determination unit 26, 26B, 26D Generation unit 19B Detection unit 21D adjustment unit

Claims (9)

An image processing device that combines a second image with a first image,
An extraction unit for extracting a first feature from the first image and extracting a second feature from the second image;
Determining a first transparency of the second image corresponding to the first region according to a deviation between the first feature corresponding to the first region and the second feature corresponding to the first region; A second transparency of the second image corresponding to the second region is determined according to a deviation between the first feature corresponding to the second region and the second feature corresponding to the second region; A synthesizing unit that synthesizes the second image with the first image using 1 transparency and the second transparency;
An image processing apparatus comprising: An image processing device that combines a second image with a first image,
An extraction unit for extracting a first feature from the first image and extracting a second feature from the second image;
In accordance with the difference between the first feature and the second feature, the transparency of the region corresponding to the portion from the elbow part to the tip of the second image is determined, and the transparency is used to determine the first image. A combining unit that combines the second images;
An image processing apparatus comprising: An image processing method for combining a second image with a first image,
Extracting a first feature from the first image and extracting a second feature from the second image;
Determining a first transparency of the second image corresponding to the first region according to a deviation between the first feature corresponding to the first region and the second feature corresponding to the first region; A second transparency of the second image corresponding to the second region is determined according to a deviation between the first feature corresponding to the second region and the second feature corresponding to the second region; Combining the second image with the first image using 1 transparency and the second transparency;
An image processing method including: An image processing method for combining a second image with a first image,
Extracting a first feature from the first image and extracting a second feature from the second image;
In accordance with the difference between the first feature and the second feature, the transparency of the region corresponding to the portion from the elbow part to the tip of the second image is determined, and the transparency is used to determine the first image. Combining the second image;
An image processing method including: An image processing device for combining a second image with a first image including a subject and a third image including the subject,
A synthesizing unit that synthesizes the second image with the first image using a transparency determined according to a deviation between the first feature extracted from the first image and the second feature extracted from the second image. With
The combining unit updates the transparency according to the movement of the subject, and combines the second image with the third image using the updated transparency;
Image processing device. A detection unit for detecting movement of the subject from the first image and the third image;
The image processing apparatus according to claim 5, further comprising: The permeability of the updated, according to claim 5 or claim 6 third those which are updated in accordance with the deviation of the features extracted from the first feature and the third image extracted from the first image Image processing device. An image processing method for combining a second image with a first image including a subject and a third image including the subject,
The second image is synthesized with the first image using the transparency determined according to the deviation between the first feature extracted from the first image and the second feature extracted from the second image, and Updating the transparency according to the movement of the subject, and using the updated transparency, combining the second image with the third image;
Image processing method. An image processing program for causing a computer to synthesize a second image to a first image including a subject and a third image including the subject,
Synthesizing the second image with the first image using the transparency determined according to the deviation between the first feature extracted from the first image and the second feature extracted from the second image. Including
The step updates the transparency according to the movement of the subject, and uses the updated transparency to synthesize the second image with the third image.
Image processing program.

Images