Method and device for enhancing accuracy of voice control with image characteristic

• US 20070200912A1
• Filed: 02/13/2006
• Published: 08/30/2007
• Est. Priority Date: 02/13/2006
• Status: Active Grant

• Current Assignee: Hon Hai Precision Industry Co., Ltd.
• Original Assignee: Premier Image Technology Corp (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Hung, Chin-Fu
• Granted Patent: US 7,792,678 B2
• Time in Patent Office: Days
• US Class Current: 348/14.10
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04N 23/60 Control of cameras or camera modules

Abstract

A method and device for enhancing the accuracy of voice control with checking a real-time image characteristics while it is captured from the scene. Such a method and device are much suitable for using in so-called digital camera, digital camcorder and also for camera mobile phone, to perform a remote control via some verbal instructions which may utter by an operator. The method includes a step (a) to receive a verbal instruction to check its character with a voice character memory unit, to look out all of the related voice commands from a voice command unit, and to form those related voice commands as a voice command set; a step (b) to take a real-time image from the scene via a image captruing unit, and to use the character of the real-time image to compare with an image characteristic memory unit; a step (c) to use the result of the step (b) to find out a most reasonable voice command from the voice command set of step (a); and a step (d) to perform the most reasonable voice command of step (c). The method provided above can improve the accuracy of the voice control and may avoid some of the unexpected wrong response of the voice control in such a device.

Claims

1. A device for enhancing the accuracy of voice control with image characteristic comprising an image capturing device which is provided with a voice recognition device to perform a remote control via some verbal instructions which may utter by an operator and receive by a receiving device;

said voice recognition device includes

a voice command unit which saves plural voice commands for a operator to manipulate the image capturing device

a voice character memory unit which saves a plurality of voice characteristics for corresponding to the voice command unit, whereby looking out the commands to conform to the voice characteristics and to form a voice command set; and

a image character memory unit which saves a plurality of image characteristics and corresponds to the voice commands of the voice command set.

2. The device of claim 1, wherein the image capturing device includes a lens module, an image sensor module, an image processing device and a processor unit, to use the image sensor module to transfer a light captured by the lens module into an image, and to use the image processing device which provides a real-time image characteristic to check with the image characteristic memory unit, thereby a command is selected from the command set by comparing with the above checking result and executed by the processor unit.

3. The device of claim 1, wherein the receiving device is a microphone.

4. The device of claim 1, wherein the image capturing device can be either a digital camera, a digital camcorder or a camera mobile phone.

5. The device of claim 1, wherein the voice command unit includes a command for moving the focus while taking an images.

6. The device of claim 1, wherein the image characteristic memory unit includes the characteristics for checking brightness sufficiency, and the voice command unit including at least one command corresponding to the images.

7. The device of claim 1, wherein the voice command unit includes a commands of “

up”

for increasing ISO value upon insufficient brightness and “

down”

for reducing ISO value upon exceeding brightness.

8. The device of claim 1, wherein the voice command unit includes the remote voice commands of “

on”

for opening the flashlight, “

up”

for increasing brightness of flashlight and “

down”

for reducing brightness of flashlight etc.

9. A method for enhancing accuracy of voice control with image characteristic comprising a manipulation of an image capturing device which is provided with a voice recognition device and to perform a remote control via some verbal instructions which may utter by an operator and receive by a receiving device;

said voice recognition device includes a voice character memory unit, an image characteristic memory unit and a voice command unit, said method comprising the steps of;

(a) receiving a verbal instruction via a receiving device and using the character of the verbal instruction to check with a voice character memory unit, whereby looking out all the commands related to said character from a command set corresponding to the voice character memory unit and collecting those commands as a command set;

(b) taking a real-time image via the image capturing device, and checking said image with a image characteristic memory unit;

(c) selecting a most reasonable command from the command set according to the compared result from the image characteristic memory unit; and

(d) executing the most reasonable command.

10. The method of claim 9, wherein the image captruing device includes a lens module, a image sensor module, a image processing device and a processor unit to use the image sensor module to transfer the light captured by the lens module into an image, and to use the image processing device which provides a real-time image character to check with the image characteristic memory unit.

11. The method of claim 9, wherein the image capturing devide is select from digital camera, digital camcorder and camera mobile phone.

12. The method of claim 9, wherein the voice command unit includes a command for moving the focus while taking images.

13. The method of claim 9, wherein the image characteristic memory unit includes the characteristics for checking brightness sufficiency, and the voice command unit including at least one command corresponding to the images.

14. The method of claim 9, wherein the voice command unit includes a commands of “

up”

for increasing ISO value upon insufficient brightness and “

down”

for reducing ISO value upon exceeding brightness.

15. The method of claim 9, wherein the voice command unit includes a remote voice commands of “

on”

for opening the flashlight, “

up”

for increasing brightness of flashlight and “

down”

for reducing brightness of flashlight etc.

17. The method of claim 15, wherein the image captruing device includes a lens module, a image sensor module, a image processing device and a processor unit to use the image sensor module to turn the light beams captured by the lens module into an image, and to use the image processing device which provides a real-time image character to check with the image characteristic memory unit.

16. A method for enhancing accuracy of voice control with image characteristic consists of an image capturing device which is provided with a voice recognition device and to perform a remote control via some verbal instructions which may utter by an operator and receive by a receiving device;

said voice recognition device includes a voice character memory unit, an image characteristic memory unit and a voice command unit, said method comprising the steps of;

(a) receiving a verbal instruction via a receiving device and using the character of the verbal instruction to check with a voice character memory unit, whereby looking out all the commands related to said character from a command set correspond to the voice character memory unit and collecting those commands as a command set;

(b) taking a real-time image via the image capturing device, and checking said image with a image characteristic memory unit;

(c1) picking the most reasonable commands from the command set according to the search result from the image characteristic memory unit;

(c2) providing the operator to choose a command by showing those reasonable commands on a screen; and

(d1) performing the command chosen by the operator.

18. The method of claim 16, wherein the image capturing devide can be either a digital camera, a digital camcorder or a camera mobile phone.