KR20100076795A - Apparatus and method for recognizing flower in digital image processing device - Google Patents

Abstract

PURPOSE: An apparatus and a method for recognizing a flower in a digital image processing device are provided to recognize a subject as a flower if color information is included in a certain color. CONSTITUTION: A mode determining unit(51) judges whether or not a subject of a live view image exists in a certain distance, and a color information extraction unit(53) extracts the color information of the live view image. If the extracted color information is included in a certain color indicating a flower, a control unit(57) recognizes the subject as the flower. A region division unit(55) divides the live view image into regions, and gives the weight value to the each region.

Description

Apparatus and method for recognizing flower in digital image processing device}

The present invention relates to an apparatus and method for recognizing a flower in a digital image processor that recognizes a subject as a flower using distance information and color information of the subject.

In general, in the digital image processor, as the number of scene recognition modes increases, there is a company that seeks differentiation as a flower recognition mode. However, in the case of recognizing flowers, it is inconvenient because there are too many misperceptions of flowers because they are generally recognized as flowers when there are many colors.

The present invention has been made in an effort to provide an apparatus and method for recognizing flowers in a digital image processor that accurately recognizes a subject as a flower using distance information and color information of the subject.

The device for recognizing a flower in a digital image processor for solving the technical problem to be solved by the present invention is a digital image processor. When the subject of the live view image is located within a certain distance, it is determined as a macro mode, and determined as the macro mode. When the color information of the subject is included in any color representing the flower, it is preferable to include digital signal processing means for recognizing the subject as a flower.

In the present invention, the subject of the live view image may be the AF (auto focus) process is completed.

The digital signal processing unit may include: a macro mode determination unit determining whether a subject of the live view image is located within a predetermined distance; A color information extracting unit extracting color information of the live view image; And a controller for determining the macro mode in which the subject of the live view image is located within a predetermined distance, and recognizing the subject as a flower when the extracted color information is included in an arbitrary color representing a flower.

The color information extracting unit may further include a region dividing unit which divides the live view image into a predetermined number of regions and assigns weights to the regions, and extracts color information to which the respective region weights are applied. Can be.

A method of operating a digital image processor, the method comprising: (a) determining whether a subject of a live view image is located within a predetermined distance; (b) extracting color information of the live view image; And (c) determining that the subject of the live view image is a macro mode located within a predetermined distance, and recognizing the subject as a flower if the extracted color information is included in an arbitrary color representing a flower. Do.

In the present invention, in step (a), the subject of the live view image may have completed AF (auto focus) processing.

In the present invention, step (b) comprises: (b-1) dividing the live view image into a predetermined number of regions and assigning a weight to each region; And (b-2) extracting color information to which the weight for each region is applied.

As described above, according to the present invention, the subject can be accurately recognized as a flower using distance information and color information of the subject.

Hereinafter, the present invention will be described in detail with reference to the drawings.

1 is a block diagram showing the configuration of an apparatus for recognizing a flower in a digital image processor according to the present invention. In particular, FIG. 1 schematically illustrates a digital photographing apparatus as a kind of digital image processor. Of course, the present invention is not limited to the digital image photographing apparatus as shown in FIG. 1, and the present invention can be applied to image processing apparatuses such as personal digital assistants (PDAs) and personal multimedia players (PMPs). This also applies to the embodiments described below and variations thereof.

The overall operation of the digital photographing apparatus is integrated by the CPU 100. In addition, the digital photographing apparatus includes an operation unit 200 including a key for generating an electrical signal from a user. The electrical signal from the operation unit 200 is transmitted to the CPU 100 so that the CPU 100 can control the digital photographing apparatus according to the electrical signal.

In the photographing mode, as the electrical signal from the user is applied to the CPU 100, the CPU 100 detects the signal and controls the lens driver 11, the aperture driver 21, and the imaging device controller 31. Accordingly, the position of the lens 10, the opening degree of the diaphragm 20, the sensitivity of the imaging device 30, and the like are respectively controlled. The imaging device 30 generates data from the input light, and the analog / digital converter 40 converts the analog data output from the imaging device 30 into digital data. Of course, the analog / digital converter 40 may not be necessary depending on the characteristics of the imaging device 30.

Data from the image pickup device 30 may be input to the digital signal processing unit 50 via the memory 60, or may be input to the digital signal processing unit 50 without passing through the memory 60. It may also be input to 100. The memory 60 is a concept including a ROM or a RAM. The digital signal processing unit 50 may perform digital signal processing such as gamma correction and white balance adjustment as necessary. In addition, as illustrated in FIG. 2, the digital signal processor 50 includes components such as a macro mode determiner 51, an area divider 53, a color information extractor 55, a controller 57, and the like. You may. Of course, the mode determining unit 51, the color information extracting unit 53, the region dividing unit 55, and the control unit 57 may be separate components other than the components in the digital signal processing unit 50. This is possible. Hereinafter, the detailed operation of the digital signal processing unit 50 for discriminating flowers will be described later.

The image from the data output from the digital signal processing unit 50 is transmitted to the display control unit 81 or directly through the memory 60. The display controller 81 controls the display 80 to display a video on the display 80. The data output from the digital signal processing unit 50 is inputted through the memory 60 or directly to the storage / reading control unit 71. The storage / reading control unit 71 automatically generates an image according to a signal from a user or automatically. The data is stored in the storage medium 70. Of course, the storage / reading control unit 71 reads data from the video file stored in the storage medium 70 and inputs the data to the display control unit 81 through the memory 60 or through another path to the display unit 80. You can also have a video displayed. The storage medium 70 may be detachable or may be permanently mounted to the digital photographing apparatus.

Hereinafter, an operation of the digital signal processor 50 for flower recognition will be described with reference to FIG. 2. When the subject of the live view image is located within a certain distance, the digital signal processor 50 shown in FIG. 2 determines the macro mode, and when the color information of the subject determined in the macro mode is included in an arbitrary color representing a flower, The object is recognized as a flower, and includes a mode determiner 51, a color information extractor 53, an area divider 55, and a controller 57.

Usually flowers are not taken from a distance. If you take a picture from a long distance, it is closer to the landscape than the flower. Therefore, photographing flowers means that the subject, ie, the flowers are close, can be found using macro recognition.

The mode determination unit 51 determines whether the subject of the live view image exists within a predetermined distance, for example, 3 cm-30 cm, and determines whether the macro mode or the normal mode is present. The macro mode determination unit 51 measures the subject distance of the live view image, and determines whether the controller 57 that receives the subject distance is the macro mode or the normal mode.

FIG. 3 graphically illustrates auto focus value acquisition at all lens position points for lens positioning for auto focusing in a digital image processor. The digital photographing apparatus acquires an autofocus value by shifting the position of the lens, which is shown in the graph of FIG. 3. In this graph, the lens position point AFP corresponding to the peak is determined as the lens position point for auto focusing.

The shooting mode of the digital image processor includes a macro mode and a non-macro mode (hereinafter referred to as normal mode). The macro mode is selected when the distance from the digital image processor to the subject is, for example, 3 cm-30 cm. The normal mode is a mode selected when the distance from the digital image processor to the subject is, for example, 30 cm or more. Therefore, when the normal mode is selected, as shown in FIG. 3, the lens position is changed from the infinity corresponding point corresponding to the normal mode to the 30 cm corresponding point to obtain an autofocus value, and the lens position for auto focusing is changed. Decide When the macro mode is selected, an autofocus value is obtained by changing the lens position in a range from a 30 cm corresponding point, which is a macro mode corresponding area, to a 3 cm corresponding point.

The color information extracting unit 53 extracts color information of the live view image. Usually, the color of the flower is somewhat limited, and the red, yellow, and purple flowers are distributed at specific positions in the HSV (hue, saturation, value) space as shown in FIG. If the color space where Hue information is known, not HSV coordinate system, the color of flower can be distinguished from any coordinate system.

The area dividing unit 55 divides the display unit 80 on which the subject is displayed into a predetermined number of regions, an example of which is illustrated in FIG. 5. When the user shoots flowers, the main flower is usually placed in the center. Therefore, as shown in FIG. 5, if the size of the region is divided differently and weighted to each region, color separation becomes more secure as shown in FIG. 4. For example, as shown in FIG. 5, the region may be divided into nine, the weight of the region 5 may be 10, the weight of the regions 2 and 8 may be 8, and the weight of the remaining regions may be 2.

The controller 57 determines the macro mode when the subject of the live view image is located within a predetermined distance, for example, 3 cm-30 cm, as a result of the determination by the mode determination unit 51, and the color information extracting unit 53 extracts the extracted color. If the information is included in any color representing the flower, for example, red, yellow, and purple, the subject is recognized as a flower. However, when the color information extracted by the color information extracting unit 53 is not a color representing a flower, the subject is not recognized as a flower.

As such, the subject may be recognized as a flower accurately using distance information and color information of the subject.

Hereinafter, a method of recognizing a flower in the digital image processor according to the present invention will be described in detail with reference to FIG. 6. The scene scene determination method according to the present invention may be performed in a digital image processor as shown in FIGS. 1 and 2. According to an embodiment, a main algorithm of an operation method may be performed by assisting peripheral components in a device. It may be performed in the processor 50.

As shown in FIG. 6, when the live view image is displayed on the display unit 80 (step 610), the digital signal processor 50 determines whether the image scene is changed (step 620).

When the image scene is changed, the digital signal processing unit 50 performs auto focusing adjustment (operation 630).

After the auto focusing adjustment is completed, the digital signal processing unit 50 determines whether the subject of the live view image is a macro mode existing within a predetermined distance, for example, 3 cm-30 cm (step 640), and the subject of the live view image is a predetermined distance. For example, if present within 3cm-30cm is recognized as a macro mode (step 650) otherwise it is recognized as a normal mode. The determination of the macro mode and the normal mode has been described above and thus will be omitted.

When the macro mode determination is completed, the digital signal processor 50 divides the display area into a predetermined number (for example, nine) as shown in FIG. 5 and extracts the color for each area (step 660). Usually, the color of the flower is somewhat limited, and the red, yellow, and purple flowers are distributed at specific positions in the HSV (hue, saturation, value) space as shown in FIG. If the color space where Hue information is known, not HSV coordinate system, the color of flower can be distinguished from any coordinate system.

When the user shoots flowers, the main flower is usually placed in the center. Accordingly, as shown in FIG. 5, the digital signal processor 50 divides the area size differently and applies a weight to each area (step 670). When the weight is applied in this way, color separation is more reliably as shown in FIG. 4.

Subsequently, the digital signal processor 50 determines whether the object, that is, the flower, is the color from the weighted color information (step 680). As a result, the digital signal processor 50 determines that the flower is the color, i. If included in the yellow and purple lines, the live view image is recognized as a flower (step 690).

However, if the color information of the flower is not included in any color, for example, red, yellow, and purple, the live view image is recognized as not a flower (step 700).

1 is a block diagram showing the configuration of an apparatus for recognizing a flower in a digital image processor according to the present invention.

FIG. 2 is a detailed block diagram of the digital signal processor of FIG. 1.

FIG. 3 is a diagram for describing macro mode determination in FIG. 1.

4 is a diagram illustrating an example of dividing an area where flowers are displayed in FIG. 1.

FIG. 5 is a diagram illustrating an example of color information for each region of FIG. 4.

6 is a flowchart illustrating an operation of a method of recognizing a flower in a digital image processor according to the present invention.

Claims (7)

As a digital image processor, Digital signal processing means for determining the macro mode when the subject of the live view image is located within a certain distance, and when the color information of the subject determined in the macro mode is included in an arbitrary color representing a flower, the subject is recognized as a flower. Device for recognizing a flower comprising a. The apparatus of claim 1, wherein the subject of the live view image is AF completed. 3. The digital signal processing means according to claim 2, A mode determination unit determining whether a subject of the live view image is located within a predetermined distance; A color information extracting unit extracting color information of the live view image; And And a control unit for recognizing the subject as a flower when the subject of the live view image is determined to be a macro mode located within a predetermined distance and the extracted color information is included in an arbitrary color representing a flower. Recognize the device. The method of claim 3, wherein the color information extraction unit A region dividing unit for dividing the live view image into a predetermined number of regions and assigning weights to the regions; A device for recognizing a flower, characterized in that for extracting the color information applied to the weight for each region. As an operation method of a digital image processor, (a) determining whether a subject of the live view image is located within a predetermined distance; (b) extracting color information of the live view image; And (c) Recognizing a flower comprising the step of recognizing the subject as a flower if it is determined that the subject of the live view image is a macro mode located within a predetermined distance and the extracted color information is included in an arbitrary color representing a flower. How to. The method of claim 5, wherein in step (a) The subject of the live view image is a method for recognizing a flower, characterized in that the AF (auto focus) processing is completed. The method of claim 6, wherein step (b) (b-1) dividing the live view image into a predetermined number of regions, and assigning weights to the regions; And (b-2) extracting color information to which the weight for each region is applied.

Images