KR20100013867A - Apparatus and method for sorting/searching image in digital image processing device - Google Patents

Abstract

PURPOSE: An apparatus and a method for sorting/searching an image in a digital image processing device are provided to output a corresponding image list searching a photographing information index corresponding to received search mode, thereby easily classifying and searching images. CONSTITUTION: A digital signal processor comprises the following units. A classifier(39-1) classifies images according to a set classifying range. A memory(39-2) stores the classified images. A searcher(39-3) searches an image corresponding to a set searching range. A controller(39-4) outputs an image list corresponding to the searching result.

Description

Apparatus and method for sorting / searching image in digital image processing device}

The present invention relates to a digital image processing apparatus and method, and more particularly, to classify and store an image by setting an image classification range, and to classify and store an image in a digital image processor that searches and outputs a stored image by setting an image search range. An apparatus and method are provided.

Due to the wide spread of digital image processing apparatuses, it is possible to easily take images using the digital image processing apparatuses. The resulting images are also generated in huge quantities. In particular, with the development of image processing, the generation of images is increasing as continuous shooting increases. Personally, starting with storing images in a storage device of a PC, there is a growing need to make it easier to find an image to be classified by searching for a more detailed classification of the image for a web service such as a portal or a search engine.

In the digital image processing apparatus, a program for classifying images by shooting date has been released. However, due to the diverse requirements of the users, it can be said that it is not enough to classify the images based on the date taken. Thus, by using GPS, the latitude and longitude of the place where the image was captured are stored in the Exif information of the image, so that the image can be retrieved by the place where the image is captured. However, this too is not a more detailed classification method.

As described above, only the prior art can have some degree of image classification function. However, the criteria of this classification are not based on photographed images, but based on the information (photographed time, photographed location) of the photographed subject, and can be easily used when the time and place are large. There is a limitation of classification when taking a large amount of images in a short time at the place.

The technical problem to be solved by the present invention is to provide an image classification / retrieval apparatus and method in a digital image processor to set the image classification range to classify and store the image, and to set the image search range to retrieve and output the stored image. have.

In the digital image processor for solving the technical problem to be achieved by the present invention is an image classification / retrieval device is a digital image processor, receives a setting signal for the classification range for image classification, and classifies the image according to the set classification range And digital signal processing means for receiving a search range setting signal for searching an image, searching for the stored image, and outputting a corresponding image list.

In the present invention, the classification range and search range may be luminance, focal length, color temperature, exposure, sensitivity, presence / absence of person, and capacity of an image file.

In the present invention, the digital signal processing means includes a storage unit for classifying the image according to the set classification range; A memory for storing the classified images; A search unit for searching for an image corresponding to the set search range from the memory; And a controller configured to receive the classification range and the search range setting signal from a user and output an image list corresponding to the search result.

According to an aspect of the present invention, there is provided a method of classifying an image in a digital image processor, the method comprising: (a) setting a classification range for classifying an image; And (b) classifying and storing the image according to the set classification range when the image is captured.

In the present invention, the classification range may be luminance, focal length, color temperature, exposure, sensitivity, presence / absence of person and capacity of an image file.

According to an aspect of the present invention, there is provided an image retrieval method in a digital image processor, including: (a) storing a classification range of a captured image; (b) setting a search range for image search; And (c) searching the stored image according to the set search range and outputting a corresponding image list.

In the present invention, the classification range and search range may be luminance, focal length, color temperature, exposure, sensitivity, presence / absence of person, and capacity of an image file.

According to the present invention, a user classification range for generating photographing information is set, a photographing information index of an image is generated and stored according to the classification range, and a photographing information index corresponding to a received search mode is searched to output a corresponding image list. Thus, images can be easily classified and searched.

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

1 is a perspective view showing the front and top appearance of a digital image processor.

The shutter-release button 11 is opened and closed to expose the CCD to light for a predetermined time, and records an image on the CCD by properly exposing the subject in conjunction with an aperture (not shown).

The shutter release button 11 generates the first and second image capturing signals by a photographer input. When the first shutter release button 11 as a half-shutter signal is input, the digital image processor focuses and adjusts the amount of light, and when the focus is achieved, a green light is turned on in the display unit (23 of FIG. 2). It becomes. When the focus is achieved by the input of the first shutter release button 11 and the amount of light is adjusted, the second shutter release button 11 as a full shutter signal is input to capture an image.

The power button 13 is input to supply power to the digital image processor for operation.

The flash 15 brightens the bright light instantly when shooting in a dark place. Flash modes include auto flash, forced flash, flash off, red-eye reduction, and slow synchro.

The auxiliary light 17 supplies light to the subject so that the digital image processor automatically focuses quickly and accurately when the amount of light is insufficient or at night.

The lens unit 19 optically processes light from a subject.

FIG. 2 is a rear view illustrating a rear shape of the digital image processor illustrated in FIG. 1, and includes a wide-angle zoom button 21w, a telephoto-zoom button 21t, a display unit 23, and a touch sensor or a contact switch. Input buttons B1 to B14 (hereinafter referred to as buttons B1 to B14).

The wide-angle zoom button 21w or the tele-zoom button 21t increases the angle of view or narrows the angle of view depending on the input, particularly when the size of the selected exposure area is to be changed. When the wide-zoom button 21w is input, the size of the selected exposure area is reduced, and when the tele-zoom button 21t is input, the size of the selected exposure area is increased.

The buttons B1 to B14 are provided in the horizontal column and the vertical column of the display unit 23. That is, the buttons B1 to B14 are provided with a touch sensor to move up / down / left / right in a state where the buttons B1 to B7 in the horizontal row or the buttons B8 to B14 in the vertical row are touched. You can select any value (eg, color or brightness) from the items, or activate the submenu icons included in the main menu icon.

In addition, the buttons B1 to B14 are provided with contact switches so that the corresponding function can be executed by directly selecting the main menu icon and the submenu icon. The touch sensor requires only a weak touch relative to the contact switch input, but the contact switch input requires a relatively strong touch compared to the touch sensor input.

3 is a block diagram showing the configuration of an image classification / search apparatus in the digital image processor according to the present invention. The display unit 23, the user input unit 31, the image capture unit 33, the image processor 35, and the storage unit are shown in FIG. 37 and a digital signal processor 39 are included.

The user input unit 31 has a shutter release button 11 that opens and closes to expose the CCD to light for a predetermined time, a power button 13 that inputs to supply power, and widens the angle of view according to the input, or changes the angle of view. A wide-angle zoom button 21w and a tele-zoom button 21t for narrowing and a touch sensor or a contact switch provided in horizontal and vertical columns around the display unit 23 for text input or menu selection and execution are provided. There are buttons B1 to B14.

The imaging unit 33 is not shown in the figure together with the zoom lens 33-1, the focus lens 33-2, the focus motor 33-3, the image sensor 33-4, and the ADC 33-5. Not shutter and aperture.

The shutter is a mechanism for adjusting the amount of light exposed together with the aperture. The zoom lens 33-1 and the focus lens 33-2 optically process light from a subject. At this time, the iris adjusts the amount of light incident (light quantity) according to the degree of opening and closing. The opening and closing degree of the iris is controlled by the digital signal processing unit 39.

The zoom lens 33-1 and the focus lens 33-2 are provided at positions where their optical axes coincide with a vertical line extending from approximately the center of the light receiving surface of the image sensor 33-4. The focus lens 33-2 is provided to be movable in a straight line back and forth on the optical axis, and changes the focus position of the image formed on the light receiving surface of the image sensor 33-4 in accordance with the movement position. The movement position of the focus lens 33-2 is controlled by the digital signal processing unit 39 via the focus motor 33-3.

The image sensor 33-4 accumulates the amount of light input through the zoom lens 33-1 and the focus lens 33-2, and according to the accumulated light amount, the zoom lens 33-1 and the focus lens 33. The image picked up by -2) is output in accordance with the vertical synchronization signal. Image acquisition of the digital image processing apparatus is performed by the image sensor 33-4 that converts light reflected from a subject into an electrical signal. To obtain a color image using the image sensor 33-4, a color filter is required, and a filter (not shown) called a CFA (Color filter array) is mostly adopted. CFA has a structure arranged regularly by passing only one color light per pixel, and has various shapes according to the arrangement structure. The ADC 33-5 converts the analog video signal output from the image sensor 33-4 into a digital video signal.

The image processor 35 performs signal processing to display the digitally converted RAW data. The image processor 35 removes the black level caused by the dark current generated by the CCD and the CFA filter that are sensitive to the temperature change. The image processor 35 performs gamma correction to encode information according to nonlinearity of human vision. The image processor 35 performs CFA interpolation to interpolate the Bayer pattern implemented by the RGRG line and the GBGB line of the gamma corrected predetermined data into the RGB line. The image processing unit 35 converts the interpolated RGB signal into a YUV signal and filters the Y signal by a high band filter to clearly process the image, and uses the standard color coordinate system to adjust the color values of the U and V signals. Perform color correction to correct and remove their noise. The image processor 35 compresses and signals the Y, U, and V signals from which the noise is removed to generate a JPEG file, and the generated JPEG file is displayed on the display unit 23 and stored in the storage unit 37. . All of the operations of the image processor 35 operate under the control of the digital signal processor 39.

The digital signal processor 39 sets a user classification range for generating photographing information, generates and stores a photographing information index of an image according to the classification range, searches for a photographing information index corresponding to a received search mode, and searches for a corresponding image. Print a list.

To this end, the digital signal processor 39 includes a classifier 39-1, a memory 39-2, a searcher 39-3, and a controller 39-4.

The controller 39-4 receives a classification range or a search range for brightness, focal length, color temperature, exposure, sensitivity, presence / absence of a person, and capacity of an image file through the user input unit 31 for image classification and retrieval. .

In the case of luminance, if the luminance information of the image indicates 0-255 on an 8-bit basis, the average luminance falls within this range for any image. The luminance is divided into several predetermined sections, and if the average luminance falls in the corresponding section, tagging is performed in the corresponding section. This may be classified and searched into a high key image, a low key image or an appropriate exposure image. In addition to the average luminance of the image, the histogram of the image enables more detailed classification and retrieval.

In the case of the focal length, the position where the barrel lens is moved is stored, and the image is classified and searched based on the division of the focal lens into sections. By using this, it is possible to classify and search by macro shooting or normal distance shooting and remote landscape image.

In the case of the color temperature, the color temperature or the white balance of the image may vary according to the movement of the sun, the shadow, and the lighting in the same place. Even if the same subject is changed by the color temperature difference, the feeling of the image is completely different. Therefore, classification and retrieval with the same subject can further classify and retrieve the image. Sort by the white balance setting set at the time of shooting or color temperature estimated by auto white balance, etc. by section.

In the case of exposure, the exposure is composed of shutter speed and aperture value. The shutter speed can be classified into a high-speed shooting of a short exposure of a large-moving subject or a night shot of a long exposure by a difference in shutter speed. The image can be searched according to the depth of the losing. The shutter speed and aperture value are divided into sections and classified and searched by sections.

In the case of sensitivity, sensitivity is information that is related to the brightness of the subject. In general, when shooting at night or indoors, it is common to increase the sensitivity, and when shooting in the middle of the day, the sensitivity is generally reduced. It also classifies and searches the sensitivity by section.

In the presence / absence of a person, face detection is performed to divide a person into a portrait when there is a person and normal photography when there is a person, thereby easily searching for a portrait. In addition to this, it is classified and searched by the number of detected faces.

In the case of the image file capacity, when the subjects with small movement in the same place are photographed continuously in a short time, the capacity of the image when each image is compressed is not significantly different. By using this, images that fall within a predetermined distance from the first reference image are classified and searched into the same group.

When the classification range is set by the user, the classification unit 39-1 classifies the image according to the set classification range with the image and the photographing information. In this case, the image may be an image captured and stored, or an image stored in the storage 37.

When the classification unit 39-1 wants to classify the luminance, the classification unit 39-1 calculates the luminance of the desired region (partial region or entire region) and classifies the luminance according to the set luminance classification range.

When the classification unit 39-1 intends to classify the focal length, the classification unit 39-1 classifies the focal length into the focal length classification range set with the distance of the subject estimated by the position of the focal lens in the photographing information.

When the classification unit 39-1 intends to classify the color temperature, the classification unit 39-1 estimates the color temperature using an algorithm such as auto white balance and classifies the color temperature according to the set color temperature classification range.

If the classification unit 39-1 is to classify the exposure, it may be divided according to the EV value, but since the exposure may be determined by the shutter speed and the aperture value, the classification unit 39-1 may classify the exposure into another shutter or aperture value within the same EV. It is also possible to classify by the aperture value or the shutter speed, and then classify the EV value.

When the classification unit 39-1 intends to classify the sensitivity, the classification unit 39-1 classifies the classification according to the sensitivity classification range set based on ISO.

If the classification unit 39-1 wants to classify the presence or absence of a person, the classification unit 39-1 first classifies whether a person is recognized or not and classifies whether it is a portrait shooting or other shooting, and if a person is detected, further classifies the number of people. do.

When the classification unit 39-1 wants to classify the image file size, the classification unit 39-1 classifies the file size according to the set capacity classification range.

The memory 39-2 stores classification information classified by the classification unit 39-1 into luminance, focal length, color temperature, exposure, sensitivity, presence / absence and image file, for example, index information. Can be stored as 4 shows index information of an image classified according to a set classification range. For example, for the image file a.jpg recorded and stored, the luminance index is 100-150, the focal length index is 0-30cm, the color temperature index is 5000-5500K, the exposure index is 10-12EV, the sensitivity index is 100-200, Without the person index, the file size index can be stored classified as 300K-400KB.

When searching for an image, the controller 39-4 receives a search range setting signal from the user through the user input unit 31, and the search range setting signal is described above and thus will be omitted.

The searcher 39-3 searches for an image corresponding to a search range set from the memory 39-2. For example, an image corresponding to a set search range is searched from the memory 39-2 in which the index information as shown in FIG. 4 is stored. The user searches an image photographed by two people under sunlight at a focal length of about 2 m. When the search range is inputted, the search unit 39-3 searches for the b.jpg and d.jpg images satisfying the search range from the memory 39-2, and the control unit 39-4 searches this list of video files. Output

In addition, re-search is possible within the above results. For example, if a user wants a high-quality image for printing among images having this condition, a search range of a file size of 1M or more may be specified to finally output a desired image b.jpg. To help.

In another embodiment, the classification range and the search range may be classified and searched using the photographing time or the motion detection amount. In addition, indexes and searches can be made easier using a database instead of index information using a file.

Hereinafter, an image classification / search method in the digital image processor according to the present invention will be described in detail with reference to FIGS. 5 and 6. In the digital image processor according to the present invention, the image classification / retrieval method may be performed inside the digital image processor as shown in FIG. 3. According to an exemplary embodiment, the main algorithm of the operation method may assist the peripheral components in the apparatus. And may be performed in the digital signal processor 39.

First, the image classification method in the digital image processor according to the present invention will be described in detail with reference to FIG. 5.

When the user selects the corresponding mode to classify the image, the digital signal processor 39 enters the digital image processor into the image classification mode (step 501).

Next, the digital signal processor 39 receives a desired classification range setting signal from the user (step 503).

When the luminance classification range is to be set (step 505), the digital signal processor 39 receives the luminance classification range setting signal from the user (step 507). In the case of luminance, if the luminance information of the image indicates 0-255 on an 8-bit basis, the average luminance falls within this range for any image. The luminance is divided into several predetermined sections, and when the average luminance falls in the corresponding section, tagging is performed in the corresponding section. This may be classified into a high key image, a low key image, or an appropriate exposure image. In addition to the average luminance of the image, the histogram of the image enables more detailed classification.

When the focal length classification range is set (step 509), the digital signal processor 39 receives the focal length classification range setting signal from the user (step 511). In the case of the focal length, the image is classified based on the position where the focal lens of the barrel is moved and divided into sections. By using this, it is possible to classify macro photography or normal distance photography and remote landscape images.

When the color temperature classification range is to be set (step 513), the digital signal processor 39 receives the color temperature classification range setting signal from the user (step 515). In the case of the color temperature, the color temperature or the white balance of the image may vary according to the movement of the sun, the shadow, and the lighting in the same place. Even if the same subject is different due to the color temperature difference, the image may be classified at all. Divide according to the white balance setting set at the time of shooting, or classify color temperature estimated by auto white balance.

When the exposure classification range is to be set (step 517), the digital signal processor 39 receives an exposure classification range setting signal from the user (step 519). In the case of exposure, the exposure is composed of shutter speed and aperture value. The shutter speed can be classified into a high-speed shooting of a short exposure of a large-moving subject or a night shot of a long exposure by a difference in shutter speed. The image can be searched according to the depth of the losing. The shutter speed and aperture value are divided into sections and classified by sections.

If the sensitivity classification range is to be set (step 521), the digital signal processor 39 receives a sensitivity classification range setting signal from the user (step 523). In the case of sensitivity, sensitivity is information that is related to the brightness of the subject. In general, when shooting at night or indoors, it is common to increase the sensitivity, and when shooting in the middle of the day, the sensitivity is generally reduced. This also classifies the sensitivity by division.

When setting a person's presence / absence classification range (step 525), the digital signal processor 39 receives a person's presence / absence classification range setting signal (step 527). In the presence / absence of a person, face detection is performed to divide a person into a portrait when there is a person and normal photography when there is a person, thereby easily searching for a portrait. Furthermore, it is classified by the number of detected faces.

When the video file capacity classification range is to be set (step 529), the digital signal processor 39 receives an image file capacity classification range setting signal from the user (step 531). In the case of the image file capacity, when the subjects with small movement in the same place are photographed continuously in a short time, the capacity of the image when each image is compressed is not significantly different. By using this, images that fall within a predetermined distance from the first reference image are classified into the same group.

When the classification range setting for the luminance, focal length, color temperature, exposure, sensitivity, presence / absence and the size of the image file is completed by the user, the digital signal processor 39 stores it (step 533).

Subsequently, when the image is captured (step 535), the digital signal processor 39 classifies and stores the image according to the classification range set for the captured image (step 537). 4 shows index information of an image classified according to a set classification range. For example, if an image file (for example, f.jpg) is taken, the luminance index is 0-50, the focal length index is 30tsu-1m, the color temperature index is 5000-5500K, and the exposure index is 0-5EV, the sensitivity index is 1200-1600, the person index is included, one person, and the file size index may be classified and stored as 1M-1.5M.

Next, an image retrieval method in the digital image processor according to the present invention will be described in detail with reference to FIG. For the processing of FIG. 6, the digital signal processing unit 39 should store classification information according to the image classification disclosed in FIG. 5.

When the user selects a corresponding mode to search for an image, the digital signal processor 39 enters the digital image processor into an image search mode (step 601).

Next, the digital signal processor 39 receives a desired search range setting signal from the user (step 603). Herein, the search range setting is the same as the classification range setting, and the content thereof is disclosed above, and thus will be omitted.

The digital signal processor 39 determines whether to search by luminance (step 605), receives a luminance search range setting signal from the user (step 607), and then retrieves the corresponding image file list (step 609).

The digital signal processor 39 determines whether to search by the focal length (step 611), receives a focal length search range setting signal from the user (step 613), and then retrieves the corresponding video file list (step 615).

The digital signal processor 39 determines whether to search by the color temperature (step 617), receives a color temperature search range setting signal from the user (step 619), and then searches the corresponding video file list (step 621).

The digital signal processor 39 determines whether to search by exposure (step 623), receives an exposure search range setting signal from the user (step 625), and then searches the corresponding image file list (step 627).

The digital signal processor 39 determines whether to search by the sensitivity (step 629), receives a luminance search range setting signal from the user (step 631), and then searches the corresponding video file list (step 633).

The digital signal processor 39 determines whether to search by person or not (step 635), receives a luminance search range setting signal from the user (step 637), and then searches for a corresponding video file list (step 639).

The digital signal processor 39 determines whether to search by the image file capacity (step 641), receives a luminance search range setting signal from the user (step 643), and then searches the corresponding video file list (step 645).

When the search is completed, the digital signal processor 39 outputs an overlapped image file list (step 647). For example, when index information as shown in FIG. 4 is stored, an image corresponding to a set search range is searched, and a user inputs a search range to search an image photographed by two people under sunlight at a focal length of about 2 m. Then, the digital signal processing unit 39 searches and outputs b.jpg and d.jpg images satisfying the search range. In addition, re-search is possible within the above results. For example, if a user wants a high-quality image for printing among images having this condition, a search range of a file size of 1M or more may be specified to finally output a desired image b.jpg. To help.

1 is a perspective view showing the front and top appearance of a digital image processor.

FIG. 2 is a rear view illustrating a rear shape of the digital image processor illustrated in FIG. 1.

3 is a block diagram showing the configuration of an image classification / search apparatus in a digital image processor according to the present invention.

4 is a diagram illustrating an embodiment of index information of an image classified according to a classification range set in the apparatus of FIG. 3.

5 is a flowchart illustrating an operation of an image classification method in a digital image processor according to the present invention.

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

Claims (7)

As a digital image processor, Receiving a classification signal for setting a classification range for image classification, classifying and storing images according to the set classification range, receiving a search range setting signal for image retrieval, searching the stored image and outputting a corresponding image list An image classification / retrieval device comprising digital signal processing means. The method of claim 1, wherein the classification range and the search range is Image sorting and retrieval apparatus, characterized in that the brightness, focal length, color temperature, exposure, sensitivity, the presence / absence of people and the capacity of the image file. 3. The digital signal processing means according to claim 2, A storage unit for classifying the image according to the set classification range; A memory for storing the classified images; A search unit for searching for an image corresponding to the set search range from the memory; And And a controller configured to receive the classification range and the search range setting signal from a user and output a list of images corresponding to the search results. As an operation method of a digital image processor, (a) setting a classification range for image classification; And (b) classifying and storing the image according to the set classification range when the image is captured. The method of claim 4, wherein the classification range is Image classification method characterized in that the brightness, focal length, color temperature, exposure, sensitivity, the presence / absence of people and the capacity of the image file. As an operation method of a digital image processor, (a) storing the classification range of the photographed image; (b) setting a search range for image search; And (c) searching for the stored image according to the set search range and outputting a corresponding image list. The method of claim 6, wherein the classification range and the search range is Image retrieval method, characterized in that the luminance, focal length, color temperature, exposure, sensitivity, presence / absence of people, and the capacity of the image file.

Images