초록 ▼

Systems and methods are provided for automatic identification of a person based on an analysis of the person's skin. In one embodiment, a method for automatically identifying a person comprises acquiring white-light and UV images of a portion of the person's skin, generating a skin mask from the whi

Systems and methods are provided for automatic identification of a person based on an analysis of the person's skin. In one embodiment, a method for automatically identifying a person comprises acquiring white-light and UV images of a portion of the person's skin, generating a skin mask from the white-light image, and comparing the skin mask with a pre-stored skin mask of the person. If a substantial match is not found between the two skin masks, the person is not identified, and an error message such as “wrong person” or “person unknown” is returned. Otherwise, the method proceeds to obtain results associated with certain skin conditions using at least the UV image. The results are compared with pre-stored results to determine if the person is the right person or the wrong person.

대표청구항 ▼

1. A method for automatically identifying a person, comprising: applying white-light radiation to at least a portion of a body surface and acquiring a first white-light image at a portable image acquisition device;applying UV radiation to said portion of said body surface and acquiring a first UV im

1. A method for automatically identifying a person, comprising: applying white-light radiation to at least a portion of a body surface and acquiring a first white-light image at a portable image acquisition device;applying UV radiation to said portion of said body surface and acquiring a first UV image at said portable image acquisition device;generating a skin mask from the first white-light image and the first UV image;comparing the skin mask with a pre-stored skin mask for a known person to determine whether the two skin masks substantially match, and if there is a substantial match;obtaining results related to at least one skin condition from at least the first UV image; andcomparing the results with pre-stored data associated with the at least one skin condition for the known person to determine if the person to be identified is the known person. 2. The method of claim 1, wherein the portable image acquisition device is selected from the group consisting of: a film-based camera; a digital camera; a wireless phone; a personal digital appliance; a desktop computer; a notebook computer; a digital music player; a set-top box; a video game unit; and an entertainment unit. 3. The method of claim 1, further comprising sending the first white-light image and the UV image to a computing device for identification. 4. The method of claim 1, wherein the skin mask comprises a plurality of elements corresponding to a pixel in the at least one white-light image or the UV image. 5. The method of claim 4, further comprising identifying skin pixels and non-skin pixels in the skin mask. 6. The method of claim 5, wherein identifying skin pixels comprises determining if a pixel in the skin mask is a skin pixel by examining properties of the pixel with reference to criteria for skin pixels associated with at least one color space. 7. The method of claim 6, further comprising extracting pixels corresponding to non-skin features from the UV image before obtaining the results. 8. The method of claim 7, wherein identifying skin pixels comprises identifying a pixel in the first white-light image and the UV image that corresponds to an element having a first value in the skin mask as a skin pixel. 9. The method of claim 6, wherein generating the skin mask comprises, for an element in the skin-mask: examining the corresponding pixel in the first white-light image to determine if values in the corresponding pixel in the first white-light image satisfy predetermined criteria for skin pixels;assigning a first value to the element in the skin mask if the corresponding pixel in the first white-light image satisfy the criteria; andassigning a second value to the element in the skin mask if the corresponding pixel in the first white-light image does not satisfy the criteria. 10. The method of claim 9, wherein the first white-light image is of a first color space and the step of generating comprises: converting the first white-light image into at least one second white-light image of at least one second color space; andfor an element in the skin-mask, determining if the corresponding pixel in the first and at least one second white-light images is a skin pixel or a non-skin pixel;assigning a first value to the element if the corresponding pixel in the first and at least one second white-light images is determined to be a skin pixel; andassigning a second value to the element if the corresponding pixel in any of the white-light images is determined to be a non-skin-pixel. 11. The method of claim 10, wherein the step of determining comprises: determining if values in the corresponding pixels in the first white-light image satisfy predetermined criteria for skin pixels associated with the first color space; anddetermining if values in a corresponding pixel in the at least one second white-light images satisfy criteria for skin pixels associated with a respective one of the at least one second color space. 12. The method of claim 10, wherein some of the elements in the skin mask have coordinates that are predefined as coordinates associated with non-skin features. 13. The method of claim 12, wherein the step of assigning the first value comprises assigning the first value to the pixel in the skin-mask image if the corresponding pixel in the white-light images is determined to be a skin pixel and coordinates of the pixel in the skin-mask are not predefined to be coordinates associated with a non-skin feature. 14. The method of claim 13, wherein the at least one skin condition is selected from a group consisting of: skin tone; UV damage; pores; wrinkles; hydration levels; collagen content; skin type; topical inflammation; ablation; keratosis; deep inflammation; sun spots; pigmentation; moles; scars; acne; fungi; and erythema. 15. The method of claim 13, wherein the step of obtaining comprises measuring features in the person to quantify their size and volume. 16. The method of claim 15, wherein the step of obtaining comprises using information in the skin pixels of one or both of the first white-light and UV images to obtain UV damage results that locate and quantify UV damage associated with the person. 17. The method of claim 16, wherein the information in skin pixels of the white-light and UV images includes values associated with three color channels, and the UV damage results are computed based on values associated with one of the three color channels in the skin pixels of the UV image. 18. The method of claim 15, wherein a skin pixel of the first white-light image includes values associated with three color channels, and the step of obtaining comprises using values associated with all of the three channels in the skin pixels of the first white-light image to obtain results for skin tone that indicates an evenness of skin-tone associated with the person. 19. The method of claim 18, wherein the step of obtaining further comprises computing a standard deviation for each of the three color channels from values associated with a respective one of the three color channels. 20. The method of claim 15, wherein the step of obtaining comprises: computing a color value and an intensity value associated with a skin pixel in the first UV image; anddetermining if the color and intensity values fall within predetermined ranges for at least one skin condition. 21. The method of claim 20, wherein the step of obtaining further comprises, for a skin pixel in the UV image that has color and intensity values falling within predetermined ranges for a specified skin condition, determining a size of a skin area adjacent the skin pixel and having the specified skin condition by examining surrounding skin pixels for the specified skin condition. 22. The method of claim 21, wherein the specified skin condition is related to a specific type of pores, and the step of obtaining further comprises counting skin areas having the specified skin condition to obtain a number of the specific type of pores. 23. The method of claim 22, wherein the at least one skin condition includes a plurality of types of pores, and the step of obtaining further comprises, for a skin pixel in the UV image that has color and intensity values falling within predetermined ranges for each of the plurality of types of pores, determining a size of a pore by examining surrounding skin pixels to determine if they belong to a same pore; andcounting the pores to obtain a pore count. 24. A non-transitory computer readable medium storing therein program instructions that when executed by a processor cause the processor to perform a method for automatically identifying a person, the program instructions comprising: instructions for acquiring a first white-light image by applying white light radiation to a portion of the body surface and for acquiring a first UV image by applying UV radiation to the body surface at a portable image acquisition device, the first white-light and UV images including a plurality of pixels, the pixels in the UV image corresponding to respective pixels in the first white-light image; instructions for generating a skin mask from said first white-light and UV images; instructions for comparing the skin mask with a pre-stored skin mask for the known person; and instructions for identifying skin pixels in at least the UV image related to at least one skin condition from a UV image of at least a portion of a body surface of the person; instructions for comparing the results with pre-stored data associated with the at least one skin condition for a known person to determine if the person to be identified is the known person. 25. The computer readable medium of claim 24, further comprising: instructions for extracting pixels corresponding to non-skin features from the UV image before obtaining the results. 26. The computer readable medium of claim 24, wherein the instructions for identifying comprise instructions for determining, for a pixel in the first white-light image, if the pixel is a skin pixel by examining properties of the pixel with reference to criteria for skin pixels associated with at least one color space. 27. The computer readable medium of claim 24, wherein the instructions for identifying comprise identifying a pixel in the first white-light and UV images that corresponds to an element having a first value in the skin mask as a skin pixel. 28. The computer readable medium of claim 24, further comprising instructions for comparing the results with previous results associated with the at least one skin condition of a known person, the previous results generated from an image of the person in an identification card, to determine if the person to be identified is the known person. 29. A computer system including the computer readable medium of claim 24. 30. A system for automatically identifying a person, comprising: a portable image acquisition device (a) configured to apply white light radiation to at least a portion of a body surface of the person and to acquire a white-light image and (b) configured to apply UV radiation to said portion of said body surface and to acquire a UV image of said body surface of the person, the white-light and UV images having a plurality of pixels, the pixels in the UV image corresponding to respective pixels in the white-light image;a computer system coupled to the portable image acquisition device and configured to identify, on a pixel by pixel basis, skin pixels in the white-light and UV images to generate a skin maska database storing skin mask data associated with a known person;a database storing skin condition data associated with a known person; wherein the computer system is further configured to compare the skin mask to the stored skin mask data of said known person to determine whether the two skin masks substantially match and if there is a substantial match comparing the skin condition data of said skin mask with the stored skin condition data of said known person to determine if the person to be identified is the known person. 31. The system of claim 30, wherein the image acquisition device has a sensor that can be rotated to adjust an aspect ratio of the white-light or UV image according to control signals from the computer system. 32. The system of claim 31, wherein the image acquisition device comprises: an optical assembly configured to form images of the person on the sensor; anda plurality of flash light sources attached thereto, including two flash light sources on two sides of the optical assembly, and one on top of the optical assembly, at least a portion of the flash light sources having UV transmission filters installed thereon, and at least a portion of the flash light sources having infrared absorption filters installed thereon. 33. The system of claim 30, wherein the computer system is connected to the image acquisition device via a network. 34. The system of claim 33 wherein the computer system is connected to the image acquisition device via a wireless network. 35. The system of claim 30 wherein said at least one skin condition is selected from a group consisting of: skin tone; UV damage; pores; wrinkles; hydration levels; collagen content; skin type; topical inflammation; ablation; keratosis; deep inflammation; sun spots; pigmentation; moles; scars; acne; fungi; and erythema. 36. The system of claim 30 wherein said body surface is the face of said person. 37. The method of claim 1 further comprising sending said first white light image and said first UV image to a computing device. 38. The method of claim 37 wherein said sending is via a network. 39. The method of claim 37 wherein said sending is via a wireless network. 40. The method of claim 1 wherein said body surface is the face of said person. 41. The computer readable memory of claim 24 wherein said body surface is the face of said person. 42. The system of claim 30 wherein said skin mask data associated with a known person and said skin condition data associated with a known person are stored on the same database. 43. The system of claim 30 further comprising sending the results said determining to a user of the portable image acquisition device. 44. The computer readable medium of claim 24 further comprising instructions for forwarding the results to a user of the portable image acquisition device.