Method for unlocking mobile device using authentication based on ear recognition and mobile device performing the same

Patent metadata

Field	Value
Publication number	US-11558197-B2
Application number	US-202016845362-A
Country	US
Kind code	B2
Filing date	Apr 10, 2020
Priority date	Apr 10, 2019
Publication date	Jan 17, 2023
Grant date	Jan 17, 2023

Abstract

Exemplary embodiments relate to a method for unlocking a mobile device using authentication based on ear recognition including obtaining an image of a target showing at least part of the target's body in a lock state, extracting a set of ear features of the target from the image of the target, when the image of the target includes at least part of the target's ear, and determining if the extracted set of ear features of the target satisfies a preset condition, and a mobile device performing the same.

First claim

What is claimed is:

1. A method for unlocking a mobile device using authentication based on ear recognition, performed by the mobile device including an imaging unit, a display unit and a processor, the method comprising:
sensing an unlock attempt in a lock state;
obtaining an image of a target showing at least part of the target's body in the lock state;
providing the target with a notification to adjust a distance between the mobile device and the target, based on a determination that a brightness level of the mobile device is equal to or lower than a threshold;
extracting a set of ear features of the target from the image of the target, when the image of the target includes at least part of the target's ear; and
determining if the extracted set of ear features of the target satisfies a preset condition.

2. The method for unlocking a mobile device according to claim 1 , wherein extracting the set of ear features of the target comprises:
applying the detected ear region to a global feature analysis model configured to extract a set of first features for a global feature of the ear; and
applying the detected ear region to a local feature analysis model configured to extract a set of second features for a local feature of the ear.

3. The method for unlocking a mobile device according to claim 2 , wherein the global feature analysis model or the local feature analysis model is configured to extract the set of first features or the set of second features using multiple images obtained from a same training target as a training image, and
the multiple images share at least part of the training target's ear.

4. The method for unlocking a mobile device according to claim 2 , wherein the global feature of the ear includes at least one of a contour of the ear and a structure of the ear, and
the local feature of the ear includes a local pattern present in the ear.

5. The method for unlocking a mobile device according to claim 2 , wherein determining if the extracted set of ear features of the target satisfies the preset condition comprises:
calculating similarity of the ear features between the target and a user of the mobile device by comparing the set of first features and the set of second features with stored set of first features and set of second features of the user; and
changing a first interface state to a second interface state when a similarity match level is higher than a predetermined threshold.

6. The method for unlocking a mobile device according to claim 5 , wherein calculating the similarity of the ear features between the target and the user comprises:
calculating a first similarity representing a similarity level of the global features of the ear between the target and the user of the mobile device by comparing the set of first features of the target with the stored set of first features of the user;
calculating a second similarity representing a similarity level of the local features of the ear between the target and the user of the mobile device by comparing the set of second features of the target with the stored set of second features of the user; and
calculating the similarity of the ear features between the target and the user by concatenating the first similarity and the second similarity.

7. The method for unlocking a mobile device according to claim 2 , further comprising:
correcting a shooting angle of the target image or the image of the ear region based on a motion change of the mobile device, when the motion change of the mobile device is sensed, before applying to the global feature analysis model or the local feature analysis model.

8. The method for unlocking a mobile device according to claim 1 , wherein the lock state includes a normal lock state, and
the method for unlocking a mobile device further comprises:
displaying a screen showing at least one application interface object, when the extracted set of ear features of the target is determined to satisfy the preset condition.

9. The method for unlocking a mobile device according to claim 8 , wherein the lock state further includes an unlock state, and
the method for unlocking a mobile device further comprises:
changing from the normal lock state to the unlock state, and notifying the state change, before displaying the screen showing the at least one application interface object.

10. The method for unlocking a mobile device according to claim 1 , wherein the lock state includes a normal lock state and an application lock state, and the method for unlocking a mobile device comprises:
displaying an interface screen corresponding to an occurred event, when the event occurs in the normal lock state; and
performing an operation of an application corresponding to the event, after the extracted set of ear features of the target is determined to satisfy the preset condition.

11. The method for unlocking a mobile device according to claim 10 , wherein the event includes an incoming call, and
connection of the incoming call is performed, after the extracted set of ear features of the target is determined to satisfy the preset condition.

12. The method for unlocking a mobile device according to claim 1 , wherein the lock state includes a normal lock state, an unlock state and an application lock state, and
the method for unlocking a mobile device further comprises:
receiving an unlock input that is different from ear recognition and displaying a screen showing at least one application interface object;
displaying an interface screen corresponding to an occurred event, when the event occurs in the unlock state; and
performing an operation of an application corresponding to the event, after the extracted set of ear features of the target is determined to satisfy the preset condition,
wherein the image of the target is obtained after the event occurs.

13. The method for unlocking a mobile device according to claim 12 , wherein the different unlock input includes at least one of touch, a non-touch gesture, typing, voice, and imaging of a different body part from the ear.

14. The method for unlocking a mobile device according to claim 12 , wherein the event includes an incoming call, and
acceptance of reception of the incoming call is performed, after the extracted set of ear features of the target is determined to satisfy the preset condition.

15. The method for unlocking a mobile device according to claim 1 , further comprising:
determining if the detected ear region includes at least part of the target's ear, before extracting the set of ear features;
determining if a size of the detected ear region falls inside a predetermined size range, when the detected ear region includes the at least part of the target's ear; and
providing the target with a notification to adjust a distance between the mobile device and the target to obtain the ear region falling inside the predetermined size range, when the size of the detected ear region is outside of the predetermined size range.

16. The method for unlocking a mobile device according to claim 1 , wherein sensing the unlock attempt in the lock state comprises:
determining that the unlock attempt is sensed, when sensing at least one of a change in rotation angle of the mobile device within a preset range for a preset unit time, and brightness maintained within the preset range for the preset unit time; and
activating ear recognition for unlocking.

17. A non-transitory computer-readable recording medium that is readable by a computing device including a processor and storing program instructions executable by the computi

Assignees

• Korea Inst Sci & Tech

Inventors

• Kim Ig Jae
• Nam Gi Pyo
• Cho Junghyun
• Choi Heeseung

Classifications

• G06V10/82

  using neural networks · CPC title

• G06V10/50

  by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F3/0488

  using a touch-screen or digitiser, e.g. input of commands through traced gestures · CPC title

• H04M1/64

  Automatic arrangements for answering calls; Automatic arrangements for recording messages for absent subscribers; Arrangements for recording conversations (centralised dictation systems H04M11/10) · CPC title