Method for generating customized/personalized head related transfer function
There is provided a method for generating a personalized Head Related Transfer Function (HRTF). The method can include capturing an image of an ear using a portable device, auto-scaling the captured image to determine physical geometries of the ear and obtaining a personalized HRTF based on the determined physical geometries of the ear.
1 . A method comprising:
changing a template of control points to match a shape model with a captured image of an ear of the individual to form a template of control points of the shape model, wherein the template of control points of the shape model is a visual guide overlaid onto a display of an image capturing device;
extracting image-based properties of the ear of the individual from the template of control points of the shape model conformed to the captured image of the ear of the individual;
scaling the image-based properties of the ear corresponding to the captured image of the ear of the individual,
wherein the scaling uses from the captured image at least one of focal distance data and focal length associated with focusing of the captured image, or a tragus length for the ear in the captured image; and
displaying a preliminary version of the captured image on the display screen.
2 . The method of claim 1 , further comprising enhancing audio rendering by generating a customized Head Related Transfer Function (HRTF) dataset, based on the image-based properties of the ear.
3 . The method of claim 1 , further comprising generating an indication of alignment, in response to the shape model being conformed to the captured image of the ear of the individual within an acceptable tolerance.
4 . The method of claim 1 , further comprising generating the template of control points that is the visual guide overlaid onto the display of the image capturing device.
5 . The method of claim 1 , wherein the scaling further uses from the captured image a conventionally sized reference object.
6 . The method of claim 1 , further comprising applying the shape model to a preliminary image and the captured image of the ear of the individual to obtain the shape model conformed to the preliminary image and the captured image of the ear of the individual, the shape model being conformable to an object by being deformed based on the template of control points.
7 . The method of claim 1 , further comprising acquiring the captured image by determining a presence of the ear and deformation of the shape model.
8 . The method of claim 1 , wherein the shape model is an Active Shape Model and the Active Shape Model was previously trained on at least a plurality of ear images of individuals.
9 . The method of claim 1 , further comprising iteratively processing several preliminary images by deforming the shape model to match a preliminary image of the ear.
10 . The method of claim 1 , wherein a customized HRTF dataset from a plurality of HRTF datasets is selected based on matching most closely the image-based properties to corresponding image-based properties associated with each of the HRTF datasets in the plurality of HRTF datasets.
11 . The method of claim 1 , wherein multiple HRTF datasets are selected from a plurality of HRTF datasets by matching one or more of the image-based properties and a customized HRTF is generated by at least one of interpolation or perturbation relating to at least one of the multiple HRTF datasets, and wherein the image-based properties comprise one or more of distances of control points in the template of control points, arcs of the control points, angles of the control points, geometric relationships of the control points, a concha length, width of the ear, height of the ear, general physical dimensions of the ear, and a three dimensional representation of the ear.
12 . An article of manufacture including a non-transitory, tangible computer readable storage medium having instructions stored thereon that, in response to execution by one or more processors, cause the one or more processors to perform operations comprising:
changing a template of control points to match a shape model with a captured image of an ear of the individual to form a template of control points of the shape model, wherein the template of control points of the shape model is a visual guide overlaid onto a display of an image capturing device;
extracting image-based properties of the ear of the individual from the template of control points of the shape model conformed to the captured image of the ear of the individual;
scaling the image-based properties of the ear corresponding to the captured image of the ear of the individual,
wherein the scaling uses from the captured image at least one of focal distance data and focal length associated with focusing of the captured image, or a tragus length for the ear in the captured image; and
displaying a preliminary version of the captured image on the display screen.
13 . The article of claim 12 , wherein the shape model is an Active Shape Model and the Active Shape Model was previously trained on at least a plurality of images of individuals.
14 . The article of claim 12 , wherein multiple HRTF datasets are selected from a plurality of HRTF datasets by matching one or more of the image-based properties and a customized HRTF is generated by at least one of interpolation or perturbation relating to at least one of the multiple HRTF datasets, and wherein the image-based properties comprise one or more of distances of control points in the template of control points, arcs of control points, angles of the control points, geometric relationships of the control points, a concha length, width of the ear, height of the ear, general physical dimensions of the ear, and a three dimensional representation of the ear.
15 . A system comprising
one or more processors; and
a tangible, non-transitory memory configured to communicate with the one or more processors, the tangible, non-transitory memory having instructions stored thereon that, in response to execution by the one or more processors, cause the one or more processors to perform operations comprising:
changing a template of control points to match a shape model with a captured image of an ear of the individual to form a template of control points of the shape model, wherein the template of control points of the shape model is a visual guide overlaid onto a display of an image capturing device;
extracting image-based properties of the ear of the individual from the template of control points of the shape model conformed to the captured image of the ear of the individual;
scaling the image-based properties of the ear corresponding to the captured image of the ear of the individual,
wherein the scaling uses from the captured image at least one of focal distance data and focal length associated with focusing of the captured image, or a tragus length for the ear in the captured image; and
displaying a preliminary version of the captured image on the display screen.
16 . The system of claim 15 , wherein the plurality of HRTF datasets is indexed by image-based properties corresponding to an ear represented by each HRTF dataset in the plurality of HRTF datasets.
17 . The system of claim 15 , further comprising applying the shape model to a preliminary image and the captured image of the ear of the individual to obtain the shape model conformed to the preliminary image and the captured image of the ear of the individual, the shape model being conformable to an object by being deformed based on the template of control points.
18 . The system of claim 15 , wherein a customized HRTF dataset from a plurality of HRTF datasets is selected based on matching most closely the image-based properties to corresponding image-based properties associated with each of HRTF datasets in the plurality of HRTF datasets.
19 . The system of claim 1 , further comprising selecting, based on the image-based properties of the ear, a customized HRTF dataset from a plurality of HRTF datasets that have been determined for a plurality of individuals.