KR101579107B1 - Apparatus and method for recognizing flower in digital image processing device - Google Patents

Abstract

The present invention relates to an apparatus and method for recognizing flowers in a digital image processor for recognizing a subject as flowers using distance information and color information of a subject. A device for recognizing flowers in a digital image processor is a digital image processor. When a subject of a live view image is located within a certain distance, it is determined as a macro mode. If the color information of a subject determined as the macro mode is an arbitrary color And a digital signal processing means for recognizing the subject as a flower if the subject is included in the image.

Macro mode, color information extraction, flower recognition

Description

[0001] APPARATUS AND METHOD FOR RECOGNIZING FLOWERS IN A DIGITAL IMAGE PROCESSOR [0002]

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

Generally, in digital image processors, as the number of mode of scene recognition increases, there is a company that seeks to differentiate into a flower recognition mode. However, when recognizing a flower, it is generally inconvenient because the flower is recognized as a flower if the color is large.

SUMMARY OF THE INVENTION It is an object of the present invention to provide an apparatus and method for recognizing flowers in a digital image processor for accurately recognizing a subject as flowers using distance information and color information of a subject.

According to an aspect of the present invention, there is provided an apparatus for recognizing flowers in a digital image processor, the apparatus comprising: a digital image processor for determining a macro mode when a subject of a live view image is located within a predetermined distance; And a digital signal processing means for recognizing the subject as a flower if the color information of the subject is included in an arbitrary color representing the flower.

In the present invention, the subject of the live view image may be one in which AF (auto focus) processing has been completed.

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

In the present invention, the color information extracting unit may further include an area dividing unit dividing the live view image into a predetermined number of areas and assigning weights to the respective areas, and extracting color information to which the weight per area is applied .

According to the present invention, there is provided a method of operating a digital image processor, comprising the steps of: (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) recognizing the subject as a flower if the subject of the live view image is determined to be a macro mode positioned within a certain distance and the extracted color information is included in an arbitrary color representing a flower Do.

In the present invention, in the step (a), the subject of the live view image may be one in which AF (auto focus) processing has been completed.

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

As described above, according to the present invention, a subject can be accurately recognized as a flower by 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 a configuration of an apparatus for recognizing flowers in a digital image processor according to the present invention. 1 schematically shows a digital imaging 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 PDAs (personal digital assistants) and PMPs (personal multimedia players). This also applies to the following embodiments and modifications thereof.

The overall operation of the digital photographing apparatus is governed by the CPU 100. [ The digital photographing apparatus is provided with an operation unit 200 including a key for generating an electrical signal from the user. An electrical signal from the operation unit 200 is transmitted to the CPU 100 so that the CPU 100 can control the digital photographing apparatus in accordance with an electrical signal.

The CPU 100 recognizes the signal and controls the lens driving unit 11, the diaphragm driving unit 21, and the imaging device control unit 31 as an electrical signal from the user is applied to the CPU 100 , Thereby controlling the position of the lens 10, the degree of opening of the diaphragm 20, and the sensitivity of the imaging element 30, respectively. The image pickup element 30 generates data from the input light, and the analog / digital conversion section 40 converts the analog data output from the image pickup element 30 into digital data. Of course, the analog-to-digital conversion section 40 may not be required depending on the characteristics of the imaging element 30. [

The 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 going through the memory 60, (Not shown). Here, the memory 60 is a concept including ROM, RAM, and the like. The digital signal processing unit 50 can perform digital signal processing such as gamma correction and white balance adjustment as necessary. 2, the digital signal processing unit 50 includes components such as a macro mode determination unit 51, a region division unit 53, a color information extraction unit 55, and a control unit 57 You may. Of course, the mode determination unit 51, the color information extraction unit 53, the area division unit 55, the control unit 57, and the like may be components other than the components in the digital signal processing unit 50, This is possible. Hereinafter, detailed operation of the digital signal processor 50 for discriminating flowers will be described later.

The image from the data outputted from the digital signal processing section 50 is transmitted to the display control section 81 through the memory 60 or directly. The display control unit 81 controls the display unit 80 to display a moving image on the display unit 80. [ The data output from the digital signal processing unit 50 is input to the memory 60 or directly to the storage / read control unit 71. The storage / And stores the data in the storage medium (70). Of course, the storage / read control unit 71 reads data from the moving picture file stored in the storage medium 70 and inputs it to the display control unit 81 through the memory 60 or another path, So that the moving picture is displayed. The storage medium 70 may be removable or permanently attached to the digital photographing apparatus.

Hereinafter, the operation of the digital signal processor 50 for flower recognition will be described with reference to FIG. When the subject of the live view image is located within a certain distance, the digital signal processing unit 50 shown in FIG. 2 determines that the macro mode is selected. When the color information of the subject determined as the macro mode is included in an arbitrary color representing a flower, A color information extracting unit 53, an area dividing unit 55 and a control unit 57. The mode determining unit 51 determines whether the subject is a flower or not.

Usually, taking flowers is not done at a distance. If you shoot at a distance, it is closer to the landscape than the flowers. Therefore, photographing a flower means that the subject is close to the flower, which can be detected using macro recognition.

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

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

There are modes other than macro mode and macro mode (hereinafter referred to as normal mode) in the shooting mode of the digital image processor. The macro mode is a mode in which the distance from the digital image processor to the subject is, for example, 3 cm to 30 cm And 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. Accordingly, when the normal mode is selected, the lens position is changed in the range from the infinity corresponding point, which corresponds to the normal mode to the corresponding point 30 cm, as shown in FIG. 3, and the autofocus value is obtained. . When the macro mode is selected, the lens position is changed in a range from the corresponding point of 30 cm to the corresponding point of 3 cm corresponding to the macro mode, and the autofocus value is obtained.

The color information extracting unit 53 extracts color information on the live view image. The colors of the flowers are usually limited to a certain extent, and the flowers of the red, yellow, and purple lines are distributed at specific positions on the HSV (hue (chroma), saturation, value And it is possible to distinguish the color of flowers from any coordinate system in the case of a color space in which the Hue information can be known rather than the HSV coordinate system.

The area dividing unit 55 divides the display unit 80 on which a subject is displayed into a predetermined number of areas, and an example thereof is shown in Fig. When the user shoots a flower, the main flower is usually placed in the center. Therefore, if the area size is differently divided and the weight is given to each area as shown in FIG. 5, the color classification becomes more clear as shown in FIG. For example, as shown in FIG. 5, the region may be divided into 9 regions, the region 5 may be weighted 10, the regions 2 and 8 may be weighted 8, and the remaining regions may be weighted 2.

As a result of the determination by the mode determination unit 51, the control unit 57 determines that the macro mode is selected when the subject of the live view image is located within a predetermined distance, for example, 3 cm to 30 cm. If the color information extraction unit 53 determines that the extracted color If the information is contained in a random color representing a flower, for example, a red, a yellow, or a purple line, 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.

Thus, the subject can be accurately recognized as a flower by using the distance information and color information of the subject.

Hereinafter, a method of recognizing flowers in the digital image processor according to the present invention will be described in detail with reference to FIG. The method of determining a landscape scene according to the present invention can be performed in a digital image processor as shown in FIGS. 1 and 2. According to an exemplary embodiment, And may be performed within the processing unit 50.

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 has changed (step 620).

When the video scene changes, the digital signal processor 50 performs autofocus adjustment (step 630).

After completion of the auto focus adjustment, the digital signal processing unit 50 determines whether the subject of the live view image is in a macro mode within a predetermined distance, for example, 3 cm to 30 cm (step 640) For example, if it is within 3 cm-30 cm, it is recognized as a macro mode (step 650). Otherwise, it is recognized as a normal mode. Since the determination of the macro mode and the normal mode has been described above, it is omitted here.

After the determination of the macro mode is completed, the digital signal processor 50 divides the display area into a predetermined number (for example, nine) and extracts colors for each area as shown in FIG. 5 (step 660). The colors of the flowers are usually limited to a certain extent, and the flowers of the red, yellow, and purple lines are distributed at specific positions on the HSV (hue (chroma), saturation, value And it is possible to distinguish the color of flowers from any coordinate system in the case of a color space in which the Hue information can be known rather than the HSV coordinate system.

When the user shoots a flower, 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 the weight to each area (step 670). When the weight is applied as described above, the color classification becomes more clear as shown in FIG.

In step 680, the digital signal processor 50 determines whether the subject is a color from the color information to which the weight is applied (step 680). If it is determined that the flower is a color, that is, Yellow, and purple lines, the live view image is recognized as a flower (step 690).

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

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

2 is a detailed block diagram of the digital signal processing unit in FIG.

FIG. 3 is a diagram for explaining the determination of the macro mode in FIG.

FIG. 4 is a view showing an example in which a flower display area is divided in FIG.

FIG. 5 is a diagram showing an example of color information for each region in FIG.

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

Claims (9)

As a digital image processor, The method comprising the steps of: determining whether a subject of the live view image is located within a predetermined distance; and if the subject of the live view image is determined as a macro mode located within a predetermined distance, And assigns a weight to each of the areas, obtains color information to which the weight for each area is applied, and if the color information to which the weight for each area of the subject determined to be the macro mode is applied is included in an arbitrary color representing a flower And a digital signal processing means for recognizing the subject as a flower. The apparatus of claim 1, wherein the subject of the live view image is an AF (auto focus) processed. delete delete A method of operating a digital image processor, (a) determining whether a subject of the live view image is located within a predetermined distance; (b) if the subject of the live view image is determined to be a macro mode located within a predetermined distance, dividing the live view image into a predetermined number so as to include regions having different sizes, and assigning a weight to each of the regions; (c) obtaining color information to which the weight for each region is applied; And (d) recognizing the subject as a flower if the color information to which the weight for each region of the subject determined as the macro mode is included in an arbitrary color representing a flower. 6. The method of claim 5, wherein in step (a) Wherein the subject of the live view image is an AF (auto focus) process completed. delete The method according to claim 1, Wherein the weight for each region gives a higher weight to a region closer to the center of the live view image. 6. The method of claim 5, Wherein the weight for each region gives a higher weight to a region closer to the center of the live view image.

Images