TW201407538A - Image capturing device and method for image processing by voice recognition - Google Patents

Abstract

An image capturing device includes a memory module, an image capturing module, a voice recognition module, and a controller. The memory module stores a plurality of image special effects. The image capturing module is used for capturing and generating an image and then storing the image in the memory module. The voice recognition module is used for receiving a voice signal. The controller is respectively electronically connected to the memory module, the image capturing module, and the voice recognition module. The controller analyzes the voice signal by the voice recognition module. Then the controller is connected to the memory module and searches at least one corresponding image special effect according to the analysis result, and one desired image special effect is selected from the corresponding image special effects. Then the controller is connected to the memory module, and the controller integrates the selected image special effect and the image.

Description

Image capturing device and method for image processing using voice recognition

The present invention relates to an image capturing device, and more particularly to an image capturing device having a voice recognition function.

In addition to the basic camera functions, traditional camera phones or digital cameras also have an effect editor for post-processing of images, such as changing the color to grayscale mode, nostalgic mode, etc., to create a unique photo. , highlighting the individual style.

The conventional effect editor displays a series of options on the screen. The user selects the favorite styles according to the mood at that time to perform the setting. The operation process is cumbersome, and it is necessary to filter out the favorite styles from the huge database. In the case of travel or gatherings, such operations will become extremely inappropriate. Therefore, how to design a method and related products that can improve the search efficiency and allow users to quickly find the preferred mode for image post-production is one of the development goals of the camera industry.

In addition, if it is a camera phone or a digital camera with a recently developed portable photo printer, users can carry these devices, travel or gather In the occasion, photos will be printed immediately after the photo is taken, but the entire process from photographing to printing will become more complicated. Therefore, it will become more important to be able to provide users with the best convenience in such a complicated process and reduce the cumbersome operation process.

One aspect of the present invention provides an image capture device that reduces the operation process by voice recognition function and increases convenience.

According to an embodiment of the invention, an image capturing device includes a memory module, an image capturing module, a voice recognition module, and a controller. The memory module stores a plurality of image special effects. The image capture module is used to capture and generate images and store them in the memory module. The voice recognition module is used to receive voice signals. The controller is electrically connected to the image capturing module, the voice recognition module and the memory module. The controller analyzes the voice signal through the voice recognition module, and connects to the memory module, searches for at least one image special effect according to the analysis result, and selects the desired image special effect in the search result, and then the controller Connect to the memory module and select the image, the controller synthesizes the selected image special effects and images.

In one or more embodiments of the present invention, the controller is configured to synthesize the selected image special effects and images by means of layer stacking.

In one or more embodiments of the present invention, the controller is configured to synthesize the selected image special effects and images in a manner of image special effects as a special mark to form a composite image.

According to another embodiment of the present invention, an image processing system includes The image capturing device and the image output device described above. When the image capturing device instructs the image output device to output a composite image, the image output device outputs a composite image comprising a picture substrate printed according to the image and a picture special effect printed according to the special mark.

According to still another embodiment of the present invention, a method for performing image processing by using voice recognition includes a voice recognition module receiving a voice signal, and the controller parses the voice signal through the voice recognition module, and then, according to the analysis result, the controller is connected to The memory module searches for at least one image special effect, and then selects a desired image special effect in the search result, and then the controller connects to the memory module and selects at least one image, and finally the controller synthesizes the selected image special effect. With images.

In one or more embodiments of the present invention, the controller synthesizes the selected image special effects and images in a layered manner.

In one or more embodiments of the present invention, the controller synthesizes the selected image special effects and images by displaying the image special effects as special marks on the image to form a composite image.

In one or more embodiments of the present invention, the method for performing image processing by using voice recognition further includes providing an image output device. When the image capturing device instructs the image output device to output a composite image, the image output device outputs a composite image, and the composite image is output. Contains image bases that are printed from images and special effects that are printed according to special marks.

In one or more embodiments of the present invention, the color of the picture special effect is metallic.

The above embodiment of the present invention integrates speech recognition and image The capture device allows the user to perform image post-production very easily and conveniently after taking photos, even when using a photo printer, the process from photographing to printing is more complicated. In the case, it still gives the user the best convenience.

10‧‧‧Image capture device

12‧‧‧Image capture module

14‧‧‧Voice recognition module

16‧‧‧Memory Module

18‧‧‧ Controller

20‧‧‧Image output device

200~212‧‧‧Steps

FIG. 1 is a block diagram of an image capturing device according to an embodiment of the invention.

FIG. 2 is a schematic flow chart of an embodiment of a method for performing image processing using voice recognition according to the present invention.

FIG. 3 is a block diagram of an image capturing device according to another embodiment of the present invention.

FIG. 4 is a schematic flow chart showing another embodiment of a method for performing image processing using voice recognition according to the present invention.

The embodiments of the present invention are disclosed in the following drawings, and the details of However, it should be understood that these practical details are not intended to limit the invention. That is, in some embodiments of the invention, these practical details are not necessary. In addition, some of the conventional structures and elements are shown in the drawings in a simplified schematic manner in order to simplify the drawings.

FIG. 1 is a diagram of an image capture device according to an embodiment of the invention. Set the block diagram. The image capturing device 10 of the present embodiment may be a camera phone or a digital camera. That is to say, the image capturing device 10 is an image capturing device having the capability of processing electronic information, and the image capturing device 10 is mainly applicable to a portable device.

As shown in FIG. 1 , the image capturing device 10 includes an image capturing module 12 , a voice recognition module 14 , a memory module 16 , and a controller 18 . The memory module 16 stores a plurality of image special effects. The image capturing module 12 is configured to capture and generate images and store them in the memory module 16 . The voice recognition module 14 is configured to receive voice signals. The controller 18 is electrically connected to the image capturing module 12, the voice recognition module 14, and the memory module 16, respectively. The controller 18 analyzes the voice signal through the voice recognition module 14, and connects to the memory module 16, searches for the corresponding image special effect according to the analysis result, and selects the desired image special effect in the search result. The controller 18 then connects to the memory module 16 and selects an image, and the controller 18 synthesizes the selected image special effects and images.

The image capturing device 10 further includes a display module, an input module, and an information transmission and receiving module. The display module is used to display information provided by the image capturing device 10 to the user, such as a pattern, a photo or a text message. The display module can be a liquid crystal display. The input module is used to provide a user input control command, and the input module can be a keyboard or a touch screen. The information transmission and receiving module is used to transmit image or synthesized image special effects and images to other electronic devices, or to receive information such as firmware update files of the image capturing device 10. The information transmission and receiving module can be a wired module, such as a universal serial bus (USB) connection module, or wireless Modules, such as Bluetooth modules or modems that use RF radios.

The image capturing module 12 can include a lens, a shutter, a body, and an image sensor, and the detailed structural configuration thereof will not be described in detail. The image sensor can be a Charge-coupled Device (CCD) or a Complementary Metal-Oxide-Semiconductor (CMOS). The image can be a photo or any electronic image.

The voice recognition module 14 can have a receiver, the receiver can be used to receive voice signals from the external environment, and can selectively filter and analyze the voice signals, wherein the filtering is a function of filtering out noise, and is analyzed to be amplified. The function of the main signal. For example, the voice recognition module 14 can perform filtering, and determine a part of the voice signal as noise by a judgment criterion, delete the unnecessary noise, and then amplify the signal, and then repeat the above steps. Several times. With the above functions, the control commands included in the voice signal can be effectively recognized. The speech recognition module 14 can be a hardware or a firmware. The receiver can be a microphone.

The memory module 16 can be a random access memory. It should be understood that the specific implementation of the above-mentioned memory module 16 is merely illustrative and not intended to limit the present invention, and those having ordinary knowledge in the technical field of the present invention. The specific implementation manner of the memory module 16 can be flexibly selected according to actual needs.

The image special effects stored in the memory module 16 can be a special effect for post-production of the photos. Specifically, the image special effect may be a color conversion effect, such as a grayscale mode, a nostalgic effect, a negative film effect, an exposure effect, a color separation effect, etc., and the image special effect may also be a border image, a graffiti text on the image, or Is to overlay a special map on the image As such, the image special effects are not limited to the foregoing list. The image special effects can be built into the memory module 16 , stored in the memory module 16 through the external memory or downloaded to the memory module 16 through the Internet through the information transmission and receiving module. The source of the image special effects is not limited to the foregoing.

The controller 18 can be a central processing unit (CPU) or an application processor. It should be understood that the specific implementation of the controller 18 is merely illustrative and not limiting. Those skilled in the art to which the present invention pertains can flexibly select a specific embodiment of the controller 18 according to actual needs.

FIG. 2 is a schematic flow chart of an embodiment of a method for performing image processing by using voice recognition according to the present invention. For the image capturing device 10 described above, the operation steps are as follows. In step 200, the voice recognition module 14 receives the voice signal. The voice recognition module 14 can receive the voice signal from the external environment by using the receiver. The receiving function can be triggered by a mechanism, for example, inputting a specific instruction through the input module or The image capture module 12 captures the image and stores it in the memory module 16.

Step 202 is to analyze the voice signal by the controller 18 through the voice recognition module 14. After the voice recognition module 14 receives the voice signal, the voice recognition module 14 can selectively filter and analyze the voice signal and obtain the main signal that can be used as the command, and then determine the main signal as a specific control command. This is the result of the analysis. For example, when the user says "love", the voice recognition module 14 first filters out the background noise of the user's speech, then enlarges the "love" voice signal, and then "love" The voice signal is determined as the control command "Love".

Step 204 is based on the analysis result, and the controller 18 connects to the memory module 16 to search for at least one image special effect. For example, when the analysis result is the control command "love", the controller 18 connects to the memory module 16 to find the "love" type displayed in the text or the "love" pattern displayed in the pattern. Then, the controller 18 can display the names of the special effects of the images on the display module in a list.

Step 206 is to select a desired image special effect in the search result. For example, when the controller 18 displays the name of the "love" in the text or the name of the "love" pattern displayed in the form on the display module, the user can use the voice control or the input mode. The group selects the desired image for special effects.

After the user selects the desired image special effect, for the specific image special effects, such as graffiti text on the image or superimposed "love" pattern on the image, the user can use the voice recognition module 14 or Input module input commands, such as inputting text messages or adjusting the position of the pattern, to complete the setting of the special effects of the image.

Steps 202-206 can be repeated, so the user can select a plurality of desired image special effects. For example, the user can overlay the "love" pattern on the image while graffitiing the text on the image.

Step 208 connects the controller 18 to the memory module 16 and selects at least one image. For example, the controller 18 can just capture a photo in the image capturing module 14 and store it in the memory module 16 to select the photo. Alternatively, the controller 18 may select an image previously stored in the memory module 16 in accordance with a user's instruction.

Step 210 is for the controller 18 to synthesize the selected image special effects and images. The controller 18 synthesizes the selected image special effects and images by more than one. Specifically, if the image special effect is a color conversion effect, the controller 18 can convert the color information of the image according to a color conversion formula. For example, if the image special effect is a grayscale mode, the controller 18 can change the color of the image. Information is removed, leaving only brightness information. If the image has a special effect of graffitiing the image on the image or overlaying the special pattern on the image, the controller 18 can use the selected image as the base layer and use the selected image special effect as the overlay layer, and then layer the image. In a manner, the overlay is layered on the base layer to form a composite image; or the controller 18 can mark the selected image special effect as a special mark and mark the special mark on the selected image to form a composite image. It should be noted here that the composite image synthesized by the layer stacking method can completely display the information of the composite image on the display module, but by synthesizing the image special effect as a special mark on the image. The composite image, the information of the composite image cannot be completely displayed on the display module in a pattern.

FIG. 3 is a block diagram of an image capturing device according to another embodiment of the present invention. The image capturing device 10 can be further matched with the image output device 20, and the image capturing device 10 transmits commands to the image output device 20 through the information transmission and receiving module. When the image capturing device 10 instructs the image output device 20 to output a composite image, the image output device 20 outputs a composite image. The composite image can include a picture base printed from the image and a picture special effect printed according to the special mark. The image capturing device 10 and the image output device 20 may constitute an image processing system.

The image output device 20 can be a laser printer, an inkjet printer, or a photo printer. When the image output device 20 is a photo printer, and the user uses the image capturing device 10 in conjunction with the image output device 20, the user can take photos, select special effects, synthesize photos, and print photos according to the above embodiments. Can be done in one go. Since both the image capturing device 10 and the image output device 20 can be mobile devices, the user can carry the two devices with them, and take photos and obtain the finished photos directly in the event of traveling or gathering, so that the user can be brought to the user. pleasure. However, in the above case, the entire process from photographing to printing photographs is very complicated. Therefore, by the above-described embodiment of the present invention, the operation process is reduced in a voice-activated manner, and the user's feeling of use can be greatly improved.

The special effect of the picture can be metallic, such as gold or silver. The special effect of the picture can be achieved by using gold foil or silver foil as the printing material. This will bring more fun in the aforementioned situation. For example, in the case of a trip or party, getting a photo with a gold or silver "love" pattern will make the photo more enjoyable. It should be noted here that gold or silver is not a category that can be rendered by a general pixel, so the display module cannot be directly displayed, and the general electronic image file will not be able to express these colors, so the output is golden or In the case of a silver-colored picture with a special effect, the image output device 20 does not print the composite image synthesized by the lamination of the images, but prints the image base according to the image and prints the special effect according to the special mark. Output a composite image.

FIG. 4 is a schematic flow chart showing another embodiment of a method for performing image processing by using voice recognition according to the present invention. Larger here than the previous embodiment The method is the same. The only difference is that the method for performing image processing by using voice recognition further includes step 211: providing an image output device 20, and when the image capturing device 10 instructs the image output device 20 to output a composite image, the image output device 20 outputs a composite image. . The composite image can include a picture base printed from the image and a picture special effect printed according to the special mark.

The above embodiment of the present invention integrates the voice recognition and image capturing device 10, so that the user can perform image post-production after the photo is taken out in a place such as a trip or a party, even when using the photo printer. The process of taking photos to printing photos becomes more complicated, and still gives users the best convenience.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention, and the present invention can be modified and modified without departing from the spirit and scope of the present invention. The scope is subject to the definition of the scope of the patent application attached.

200~212‧‧‧Steps

Claims (10)

An image capturing device includes: a memory module for storing a plurality of image special effects; an image capturing module for capturing and generating an image and storing the image in the memory module; a voice recognition module, For receiving a voice signal, and a controller electrically connected to the image capturing module, the voice recognition module, and the memory module, wherein the controller parses the voice signal through the voice recognition module And connecting to the memory module, searching for at least one of the corresponding image special effects according to the analysis result, and selecting the desired image special effect in the search result, and then the controller is connected to the memory module And selecting the image, the controller synthesizes the selected image special effect and the image. The image capturing device of claim 1, wherein the controller is configured to synthesize the selected image special effect and the image through a layer stacking manner. The image capturing device of claim 1, wherein the controller is configured to synthesize the image special effect and the image in the manner of the image special effect as a special mark to form a composite image. . An image processing system comprising: the image capturing device according to claim 3; An image output device, wherein the image capturing device instructs the image output device to output the composite image, the image output device outputs a composite image, the composite image includes a picture substrate printed according to the image, and a A special effect printed on a special mark. The image processing system of claim 4, wherein the color of the special effect of the picture is metallic. A method for performing image processing by using voice recognition includes: a voice recognition module receives a voice signal; a controller analyzes the voice signal through the voice recognition module; and according to the analysis result, the controller is connected to a memory The module searches for at least one image special effect; selects the desired image special effect in the search result; the controller connects to the memory module and selects at least one image; and the controller synthesizes the selected image Special effects and the image. The method for performing image processing by using voice recognition according to claim 6, wherein the controller synthesizes the selected image special effect and the image in a layered manner. The method for performing image processing by using voice recognition according to claim 6, wherein the controller uses the image special effect as a special mark The image special effect is combined with the image in the manner of the image to form a composite image. The method for performing image processing by using voice recognition according to claim 8, further comprising: providing an image output device, when the image capturing device instructs the image output device to output the composite image, the image output device outputs a composite image The composite picture includes a picture substrate printed according to the image and a picture special effect printed according to the special mark. The method for performing image processing by using voice recognition according to claim 9, wherein the color of the special effect of the picture is a metallic color.