COMPUTER IMPLEMENTED METHODS AND DEVICES FOR DETERMINING DIMENSIONS AND DISTANCES OF HEAD FEATURES

Abstract

Computer implemented methods and devices for determining dimensions or distances of head features are provided. The method includes identifying a plurality of features in an image of a head of a person. A real dimension of at least one target feature of the plurality of features or a real distance between at least one target feature of the plurality features and a camera device used for capturing the image is estimated based on probability distributions for real dimensions of at least one feature of the plurality of features and a pixel dimension of the at least one feature of the plurality of features.

Claims

1. A computer implemented method for estimating or determining dimensions or distances of head features, the method comprising: providing an image of a head of a person; identifying a plurality of features in the image; and estimating at least one of a real dimension of at least one target feature of the plurality of features or a real distance between at least one target feature of the plurality of features and a camera device used for capturing the image based on a probability distribution for a real dimension of at least one feature of the plurality of features and a pixel dimension of the at least one feature of the plurality of features, wherein the estimating includes calculating a probability distribution P(pix per mm|d, θ) for the number of pixels per millimeter pix per mm for the image according to $P\left(\mathrm{pix}\mathrm{per}\mathrm{mm}.Math.d,\theta \right)\propto \underset{i=1}{\overset{N}{.Math.}}P\left(d_i.Math.\mathrm{pix}\mathrm{per}\mathrm{mm},{\theta }_i\right)\pi \left({\theta }_i\right)$ where d.sub.i is the number of pixels spanning an i=1, 2, . . . , Nth feature, π(θ.sub.i) represents the probability distribution of a real dimension θ.sub.i of feature i and/or its covariances with other measured pixel dimensions, and P(d.sub.i|pixel per mm, θ.sub.i) is an operator yielding the likelihood of measuring d, based on pix per mm and θ.sub.i for given π(θ.sub.i).

2. The method of claim 1, wherein the at least one feature of the plurality of features comprises at least two features of the plurality of features.

3. The method of claim 1, wherein calculating the probability distribution for the number of pixels per millimeter for the image is based on a Monte Carlo Markov Chain type exploration of probability space.

4-6. (canceled)

7. The method of claim 1, wherein the plurality of features includes one or more features taken from the group consisting of: an interpupillary distance, an iris diameter, a pupil diameter, a vertical ear length, a Menton-Sellion distance, a bizygomatic breadth, an Euryon breadth, an eye width, and a head height.

8. The method of claim 1, further comprising providing additional information regarding the person, and selecting the probability distributions based on the additional information.

9. The method of claim 8, wherein providing the additional information comprises receiving the additional information as a user input, and/or comprises determining the additional information based on the image.

10. The method of claim 8, wherein the additional information comprises one or more of a sex of the person, an age of the person, an ethnicity of the person or a size of the person.

11. The method of claim 1, wherein estimating a real dimension of at least one of the plurality of features comprises estimating an interpupillary distance of the person.

12. The method of claim 1, wherein providing an image comprises providing a plurality of images, and wherein the estimating is done based on the plurality of images.

13. The method of claim 1, further comprising: fitting a spectacle frame to the head of the person based on the estimating; manufacturing spectacle glasses based on the estimating; or performing an eye examination based on the estimating.

14. A device, comprising: means for providing an image of a head of a person; means for identifying a plurality of features in the image; and means for estimating at least one of a real dimension of at least one of the plurality of features or a real distance between at least one of the plurality of features from a means used for capturing the image based on a probability distribution for a real dimension of at least one feature of the plurality of features and a pixel dimension of the plurality of features, the estimating comprising including calculating a probability distribution P(pix per mm|d, θ) for the number of pixels per millimeter pix per mm for the image according to $P\left(\mathrm{pix}\mathrm{per}\mathrm{mm}.Math.d,\theta \right)\propto \underset{i=1}{\overset{N}{.Math.}}P\left(d_i.Math.\mathrm{pix}\mathrm{per}\mathrm{mm},{\theta }_i\right)\pi \left({\theta }_i\right)$ where d.sub.i is the number of pixels spanning an i=1, 2, . . . , Nth feature, π(θ.sub.i) represents the probability distribution of a real dimension θ.sub.i of feature i and/or its covariances with other measured pixel dimensions, and P(d.sub.i|pixel per mm, θ.sub.i) is an operator yielding the likelihood of measuring d.sub.i based on pix per mm and θ.sub.i for given π(θ.sub.i).

15. (canceled)

16. The device of claim 14, wherein the device is configured to carry out a computer implemented method for estimating or determining dimensions or distances of head features, the method comprising: providing an image of a head of a person; identifying a plurality of features in the image; and estimating at least one of a real dimension of at least one target feature of the plurality of features or a real distance between at least one target feature of the plurality of features and a camera device used for capturing the image based on a probability distribution for a real dimension of at least one feature of the plurality of features and a pixel dimension of the at least one feature of the plurality of features, wherein the estimating includes calculating a probability distribution P(pix per mm|d, θ) for the number of pixels per millimeter pix per mm for the image according to $P\left(\mathrm{pix}\mathrm{per}\mathrm{mm}.Math.d,\theta \right)\propto \underset{i=1}{\overset{N}{.Math.}}P\left(d_i.Math.\mathrm{pix}\mathrm{per}\mathrm{mm},{\theta }_i\right)\pi \left({\theta }_i\right)$ where d.sub.i is the number of pixels spanning an i=1, 2, . . . , Nth feature, π(θ.sub.i) represents the probability distribution of a real dimension θ.sub.i; of feature i and/or its covariances with other measured pixel dimensions, and P(d.sub.i|pixel per mm, θ.sub.i) is an operator yielding the likelihood of measuring d.sub.i based on pix per mm and θ.sub.i for given π(θ.sub.i).

17. A computer program comprising instructions which, when carried out on one or more processors, cause execution of the method of claim 1.

18. A data carrier comprising the computer program of claim 17.

19. (canceled)

20. A device comprising at least one processor and the computer program of claim 17 stored for execution on the at least one processor.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0085] The disclosure will now be described with reference to the drawings wherein:

[0086] FIG. 1 is a block diagram of a device according to an exemplary embodiment;

[0087] FIG. 2 is a flowchart illustrating a method according to an exemplary embodiment;

[0088] FIG. 3 is a diagram illustrating various features of a head of a person; and

[0089] FIG. 4 illustrates various features in a landscape image.

DESCRIPTION OF EXEMPLARY EMBODIMENTS

[0090] FIG. 1 is a block diagram of a device according to an exemplary embodiment. The device of FIG. 1 comprises a camera device 10 and a computing device 11. Camera device 10 comprises one or more optical elements and an image sensor to capture an image of a head of a person. The image is provided to computing device 11. Computing device 11 includes one or more processors. Computing device 11 may be a personal computer, or may also comprise a plurality of separate entities communicating with each other to perform the method as will be described further below with respect to FIG. 2. In some exemplary embodiments, camera device 10 and computing device 11 may be integrated in a single device, for example, a smartphone or a tablet computer. For executing the method of FIG. 2 which will be described next, computing device 11 is programmed accordingly.

[0091] FIG. 2 is a schematic block diagram of one exemplary embodiment of the method of the present disclosure. At 20, an image of a head of a person is provided. In the exemplary embodiment of FIG. 1, the image is provided by camera device 10.

[0092] At 21, a plurality of features in the image are identified. Some examples for features are shown in FIG. 3. The features shown in FIG. 3 include the interpupillary distance 30, diameter of the iris 33, width of the eyes 31, vertical length of the ears 36, Menton-Sellion distance 34, bizygomatic breadth 35, Euryon breadth 38 or height of the head 37.

[0093] Returning to FIG. 2, at 22, additional information regarding the person is provided. As explained above, examples for such additional information include size, gender, age, ethnicity and the like.

[0094] At 23, at least one of a real dimension of at least one target feature of the plurality of features or a real distance between at least one target feature of the plurality of features from the camera device 10 based on probability distributions for real dimensions of at least one, typically at least two features of the plurality of features and pixel dimensions of at least one, typically at least two of the plurality of features, as described above, is estimated.

[0095] As mentioned above, techniques discussed herein may be extended from head features as shown in FIG. 3 to dimension estimation of other features in images. An example is shown in FIG. 4. Here, a scene comprising a tree 40, a car 41, traffic signs 42, a person 45, a dog 46, and a street 47 are provided. For all these kinds of objects, typical dimensions or size probability distributions for dimensions exist. The pixel dimensions of these features or objects in an image 43 depend on their real dimension and a distance in z-direction from a camera device 44 taking the image 43. Using probability distributions and additional information, for example, species of tree 40, gender, ethnicity or age of person 45, race of dog 46, brand or type of car 41 etc., such real dimensions and/or distances in z-direction may be determined.

[0096] Some exemplary embodiments are defined by the following examples:

[0097] Example 1. A computer implemented method for estimating or determining dimensions or distances of head features, comprising: [0098] providing (20) an image of a head of a person, [0099] identifying (21) a plurality of features (30-38) in the image, [0100] characterized by [0101] estimating (23) at least one of a real dimension of at least one target feature of the plurality of features (30-38) or a real distance between at least one target feature of the plurality of features (30-38) and a camera device (10) used for capturing the image based on a probability distribution for a real dimension of at least one feature of the plurality of features (30-38) and a pixel dimension of the at least one feature of the plurality of features (30-38).

[0102] Example 2. The method of example 1, characterized in that the at least one feature of the plurality of features comprises at least two features of the plurality of features.

[0103] Example 3. The method of example 1 or 2, characterized in that the features (30-38) comprise one or more features taken from, the group consisting of: [0104] an interpupillary distance (30), [0105] an iris diameter (33), [0106] a pupil diameter, [0107] a vertical ear length (36), [0108] a Menton-Sellion distance (34), [0109] a bizygomatic breadth (35), [0110] an Euryon breadth (38), [0111] an eye width (31), and [0112] a head height (37).

[0113] Example 4. The method of any one of examples 1 to 3, characterized in that the estimating comprises calculating a probability distribution P(pix per mm|d, θ) for the number of pixels per millimeter pix per mm for the image according to [0114] i) P(pix per mm|d, θ) ∝Π.sub.i=1.sup.NP(d.sub.i|pix per mm, θ.sub.i)π(θ.sub.i [0115] ii) where d.sub.i is the number of pixels spanning an i=1, 2, . . . , Nth feature, π(θ.sub.i) represents the probability distribution of a real dimension θ.sub.i of feature i and/or its covariances with other measured pixel dimensions, and P(d.sub.i|pixel per mm, θ.sub.i) is an operation giving the probability of the real dimension θ.sub.i for d, for a value pix per mm given the probability distribution π(θ.sub.i.

[0116] Example 5. The method of any one of examples 1-4, further comprising providing additional information regarding the person, and selecting the probability distributions based on the additional information.

[0117] Example 6. The method of example 5, characterized in that providing the additional information comprises receiving the additional information as a user input, and/or comprises determining the additional information based on the image.

[0118] Example 7. The method of example 5 or 6, characterized in that the additional information comprises one or more of a sex of the person, an age of the person, an ethnicity of the person or a size of the person.

[0119] Example 8. The method of any one of examples 1-7, wherein estimating at least one of a real dimension of at least one of the features (30-38) comprises estimating an interpupillary distance of the person.

[0120] Example 9. The method of any one of examples 1-8, characterized in that providing an image comprises providing a plurality of images, wherein the estimating (23) is done based on the plurality of images.

[0121] Example 10. The method of any one of examples 1-9, characterized by one or more of: [0122] fitting a spectacle frame to the head of the person based on the estimating (23), [0123] manufacturing spectacle glasses based on the estimating (23) or [0124] performing an eye examination based on the estimating (23).

[0125] Example 11. A device, comprising: [0126] means (10) for providing an image of a head of a person, [0127] means for identifying a plurality of features (30-38) in the image, [0128] characterized by [0129] means for estimating at least one of a real dimension of at least one of the features (30-38) or a real distance between at least one of the features (30-38) from a means (10) used for capturing the image based on a probability distribution for a real dimension of at least one feature of the plurality of features (30-38) and a pixel dimension of the plurality of features (30-38).

[0130] Example 12. A computer program comprising instructions which, when carried out on one or more processors, cause execution of the method of any one of examples 1-10.

[0131] Example 13. A data carrier comprising the computer program of example 12.

[0132] Example 14. A data signal carrying the computer program of example 12.

[0133] Example 15. A device (11) comprising at least one processor and the computer program of example 12 stored for execution on the at least one processor.

[0134] The foregoing description of the exemplary embodiments of the disclosure illustrates and describes the present invention. Additionally, the disclosure shows and describes only the exemplary embodiments but, as mentioned above, it is to be understood that the disclosure is capable of use in various other combinations, modifications, and environments and is capable of changes or modifications within the scope of the concept as expressed herein, commensurate with the above teachings and/or the skill or knowledge of the relevant art.

[0135] The term “comprising” (and its grammatical variations) as used herein is used in the inclusive sense of “having” or “including” and not in the exclusive sense of “consisting only of” The terms “a” and “the” as used herein are understood to encompass the plural as well as the singular.

[0136] All publications, patents and patent applications cited in this specification are herein incorporated by reference, and for any and all purposes, as if each individual publication, patent or patent application were specifically and individually indicated to be incorporated by reference. In the case of inconsistencies, the present disclosure will prevail.