JP5124312B2 - Image processing program, image processing method, and electronic camera - Google Patents

Description

  The present invention relates to an image processing program for realizing image processing on an image to be processed by a computer, an image processing method for performing image processing on an image to be processed, and an electronic camera for performing image processing on an image generated by imaging. .

Conventionally, various techniques for performing image processing according to an image to be processed have been considered. For example, in the invention of Patent Document 1, image processing corresponding to a sensitivity word is performed using a sensitivity word that expresses an image processing effect sensuously. By using such sensitivity words, an image processing apparatus that can be easily operated by the user is realized.
JP 2006-93757 A

  However, the sensitivity words used in the invention of Japanese Patent Application Laid-Open No. H10-228707 are for the finish of the image processing result such as “brightness”, “contrast”, “overexposure, blackout (saturation)”, “priority”, etc. A phrase that expresses a subjective impression. Therefore, these sensitivity words have properties close to the image quality evaluation language. In the invention of Patent Document 1, local image processing is performed on a partial region of an image. Therefore, it is not possible to perform image processing according to the emotional impression of the entire image.

  An object of the present invention is to make it possible to easily and appropriately realize image processing according to the emotional impression of the entire image.

  An image processing program of the present invention is an image processing program for realizing image processing on a processing target image by a computer, and includes an acquisition step of acquiring the processing target image, and a color arrangement in the entire processing target image. An analysis step for analyzing, an extraction step for extracting at least one image display representing an image of the image to be processed from a plurality of predetermined image displays based on an analysis result obtained by the analysis step, and the extraction step Realizing a computer with a designation step for designating the degree of contribution to the image processing of the image display extracted in step and an image processing step for performing image processing on the image to be processed based on the designation by the designation step. Features.

  Preferably, in the analyzing step and the extracting step, for each of the plurality of predetermined image displays, the color arrangement analysis and the color information are based on a table in which color information including the color arrangement is associated in advance. Image display extraction may be performed.

  Preferably, in the image processing step, the image processing according to the color information obtained by the analysis may be performed.

  Preferably, the specifying step includes a selection step of selecting an image display to be contributed to the image processing among the image displays extracted in the extraction step, and the image for each of the image displays extracted in the extraction step. You may have at least one of the determination step which determines the degree of contribution in a process.

  Preferably, in the image processing step, the image processing including at least saturation correction may be performed.

  Also, a specific aspect of the present invention is a representation of the configuration related to the invention converted to an image processing method for performing image processing on an image to be processed and an electronic camera for performing image processing on an image generated by imaging. It is valid.

  According to the present invention, it is possible to easily and appropriately realize image processing according to the emotional impression of the entire image.

<First Embodiment>
Hereinafter, a first embodiment of the present invention will be described with reference to the drawings. In the first embodiment, a computer shown in the block diagram of FIG. 1 will be described as an example.

  As shown in FIG. 1, the computer 1 includes an image analysis unit 10, an image processing unit 11, an operation unit 12, a display unit 13, a recording unit 14, and a communication unit 15, and a control unit 16 that controls each unit. Prepare. The computer 1 also includes a table storage unit 17 that stores an image color table described later in advance. Details of the image analysis unit 10 and the image processing unit 11 will be described later. The operation unit 12 includes operation devices such as a keyboard and a mouse, and receives instructions from the user. The operation state of the operation unit 12 is detected by the control unit 16. The display unit 13 includes a display device such as a liquid crystal monitor, and displays various images and menu screens. The recording unit 14 records various data including images. The communication unit 15 is connected to the outside of the computer 1 by wire or wireless to exchange various data.

  Next, the table storage unit 17 will be described. Table 1 is an example of an image color table stored in the table storage unit 17.

イメージカラーテーブルには、色情報とイメージ語（イメージ表示）ＩＤとが予め対応づけて記憶される。色情報は、表１の例では、Ｒ値，Ｇ値，Ｂ値からなる色情報である。表１の例では、２５６階調である場合の例を示し、２５６³通りの色情報のそれぞれにイメージ語ＩＤ（イメージ表示ＩＤ）が対応づけられている。なお、色情報の数は、必ずしも階調数および色の数の全ての組み合わせである必要はない。例えば、階調に適宜幅を持たせて、組み合わせの数を減らしても良い。また、色情報はＲＧＢ形式以外の形式であっても良い。

In the image color table, color information and an image word (image display) ID are stored in association with each other in advance. In the example of Table 1, the color information is color information including an R value, a G value, and a B value. The example of Table 1 shows an example in the case of 256 gradations, and an image word ID (image display ID) is associated with each of 256 ³ types of color information. The number of color information does not necessarily need to be all combinations of the number of gradations and the number of colors. For example, the number of combinations may be reduced by giving a suitable width to the gradation. Further, the color information may be in a format other than the RGB format.

  The image word ID is an identification number for a plurality of image words prepared in advance. In the example of Table 1, the image words shown in Table 2 are associated with the identification numbers 1 to N, respectively.

イメージ語とは、画像についての情緒的な印象を示す抽象的概念のキーワードであり、表２に示すように、「鮮やかな」、「爽やかな」、「清潔な」、「フレッシュな」などがある。これらのイメージ語は、色情報と結びつく性質を有する。そして、これらのイメージ語は、予め複数（例えば、Ｎ＝３０〜５０程度）用意され、それぞれが上述した色情報と応づけられる。例えば、表１において、（Ｒ値，Ｇ値，Ｂ値）＝（６０，１２０，１８０）の色情報には、イメージ語ＩＤ＝２（「爽やかな」）およびイメージ語ＩＤ＝Ｎ（「フレッシュな」）について、「１」が記憶されている。これは、（Ｒ値，Ｇ値，Ｂ値）＝（６０，１２０，１８０）の色情報が、イメージ語として「爽やかな」および「フレッシュな」に対応づけられている（関連がある）ことを意味する。逆に、「０」が記憶されているイメージ語については、その色情報が対応づけられていない（関連がない）ことを意味する。また、表１に示すように、色情報とイメージ語とは１対１対応ではなく、ある色情報に１以上のイメージ語が対応づけられる。

An image word is an abstract concept keyword that represents an emotional impression of an image. is there. These image words have a property associated with color information. A plurality of these image words (for example, N = about 30 to 50) are prepared in advance, and each is associated with the color information described above. For example, in Table 1, the color information of (R value, G value, B value) = (60, 120, 180) includes image word ID = 2 (“fresh”) and image word ID = N (“fresh” “1” is stored for “na”). This is because (R value, G value, B value) = (60, 120, 180) color information is associated with (relevant) as “fresh” and “fresh” as image words. Means. Conversely, an image word in which “0” is stored means that the color information is not associated (not related). As shown in Table 1, color information and image words are not in a one-to-one correspondence, and one or more image words are associated with certain color information.

  The table storage unit 17 stores the image color table described above in advance. This image color table is preferably updatable as needed based on user operations.

  Next, details of image processing using image words will be described using the flowchart shown in FIG.

  In step S1, the control unit 16 acquires an image to be processed. The image to be processed may be an image recorded in the recording unit 14 or an image acquired from the outside of the computer 1 via the communication unit 15.

  In step S2, the control unit 16 controls the image analysis unit 10 to extract image word candidates. The image analysis unit 10 refers to the image color table stored in the table storage unit 17 and extracts an image word ID corresponding to the color information of the pixel for each pixel constituting the processing target image. Then, the image analysis unit 10 forms a histogram of the frequency of each image word ID extracted in all pixels. This histogram reflects information on the entire image to be processed, and the image analysis unit 10 extracts image words corresponding to image word IDs whose frequencies in the histogram exceed a certain threshold as image word candidates. To do. The threshold value may be determined for each image word, or a common threshold value may be used. The number of image words extracted as image word candidates is, for example, about 5 to 6. By extracting image word candidates in this manner, it is possible to extract an appropriate image word based on the content rate of color information.

  In step S3, the control unit 16 controls the display unit 13 to display image word candidates. FIG. 3 shows an example of display. As shown in FIG. 3, the control unit 16 displays the image word candidates extracted in step S <b> 2 on the display unit 13.

  In step S <b> 4, the control unit 16 accepts selection of an image word via the operation unit 12. For example, as shown in FIG. 3, the control unit 16 displays a message “Please select an appropriate image word” on the display unit 13 and accepts a selection by the user via the operation unit 12. By providing such a selection step, even when an image word that is not suitable in step S2 is extracted as a candidate, the image word can be eliminated.

  In step S4, a plurality of image words can be selected from a plurality of candidates. However, it is prohibited to select combinations of anti-image words (for example, “old” and “new”).

  In step S <b> 5, the control unit 16 receives the degree of image processing via the operation unit 12. For example, as shown in FIG. 4, the control unit 16 displays a message “Please specify the degree of contribution to image processing.” On the display unit 13, and is designated by the user via the operation unit 12. Accept. The designation is performed for each image word selected by the user in step S4. By providing such a designation step, the image word selected by the user in step S4 can be weighted and contributed to the image processing.

  In step S6, the control unit 16 determines whether image processing execution has been instructed. For example, when the OK button in FIG. 4 is selected, the control unit 16 determines that the image processing execution is instructed, and proceeds to step S7. When the control unit 16 determines that the image processing execution is not instructed, the control unit 16 returns to step S4.

  In step S <b> 7, the control unit 16 controls the image processing unit 11 to execute image processing. The image processing unit 11 performs image processing on the image to be processed acquired in step S1 based on the image word selected in step S4 and the degree designated in step S5 for each image word. Specifically, the image processing unit 11 refers to the image color table stored in the table storage unit 17 and extracts pixels having color information associated with the image word selected in step S4. Then, for the extracted pixel, the saturation is corrected according to the degree specified in step S5. In addition, when correcting the saturation, the pixel value of the corresponding pixel is converted from the RGB format to the HSV format and corrected by increasing or decreasing the saturation component (S), as in the known technique, and then again. Reverse conversion to RGB format replaces the original pixel value. By such replacement, the color information associated with the image word selected in step S4 can have the same effect as replacing the color information with a stronger impression and a similar color. When the upper limit value or the lower limit value is reached by increasing or decreasing the saturation component, the upper limit value or the lower limit value may be substituted. In addition, image processing relating to elements other than saturation may be performed in the same manner.

  In step S8, the control unit 16 controls the display unit 13 to display the image after image processing. Note that an image before image processing may be displayed together with an image after image processing. By performing such display, the user can compare and confirm the images before and after the image processing. Moreover, it is good also as a structure which returns to the selection step of the grade demonstrated in the selection step of the image word demonstrated in step S4, or step S5 according to a user's request.

  In step S9, the control unit 16 records the image after image processing in the recording unit 14, and ends the series of processing.

  As described above, according to the first embodiment, an image to be processed is acquired, and the color arrangement in the entire acquired image to be processed is analyzed. Then, based on the analysis result, at least one image word representing the image of the image to be processed is extracted from a plurality of predetermined image words (image display). Further, the degree of contribution of the extracted image word to the image processing is specified, and image processing is performed on the processing target image based on the specification. Therefore, it is possible to easily and appropriately realize image processing according to the emotional impression of the entire image.

  Further, according to the first embodiment, image processing corresponding to color information is performed based on the above-described table. Therefore, by performing extraction of image words (image display) and image processing based on the same table, it is possible to perform harmonious processing that is consistent as a whole.

  Further, according to the first embodiment, the above-described designation is performed by selecting an image word to be contributed to image processing from among the extracted image words (image display), and contribution of image processing for each extracted image word. This is achieved by determining the degree. Therefore, it is possible to avoid the problem of erroneous detection of image words and erroneous correction (inappropriate image processing) associated with erroneous detection, and it is possible to realize image processing according to user preferences. In addition, by performing appropriate image processing according to color information, it is possible to realize natural image processing by expanding / contracting only the color-related characteristics of the processing target image. Also, by making it possible to specify the side of the contribution to be weakened, not only emphasis is achieved, but also image processing that makes the expression calm by suppressing it as necessary.

  Note that the image words (image display) described in the first embodiment are examples, and the present invention is not limited to these examples. Any keyword can be used as an image word as long as it is an abstract concept keyword indicating an emotional impression of an image. For example, the keyword may be a color keyword such as “reddish” or “bluish”, or may be a geographical or ethnic keyword such as “American” or “African”.

  In the first embodiment, the image color table described in Table 1 and Table 2 is an example, and the present invention is not limited to this example. In the example of Table 1, an example in which “1” or “0” is stored in association with each image word ID is shown. However, for example, a configuration in which values appropriately weighted such as 0 to 5 are stored It is also good.

Second Embodiment
The second embodiment of the present invention will be described below with reference to the drawings. In the second embodiment, the electronic camera shown in the block diagram of FIG. 5 will be described as an example. In the second embodiment, only parts different from the first embodiment will be described.

  As shown in FIG. 5, the electronic camera 100 includes an imaging unit 101, an image analysis unit 110, an image processing unit 111, an operation unit 112, a display unit 113, a recording unit 114, and a communication unit 115, and controls each unit. The control part 116 to be provided is provided. The electronic camera 100 also includes a table storage unit 117 that stores in advance an image color table similar to the image color table described in the first embodiment. The imaging unit 101 includes an imaging lens (not shown), an imaging element, an A / D conversion unit, and the like, and captures a subject image to generate an image. The image analysis unit 110 and the image processing unit 111 are the same as the image analysis unit 10 and the image processing unit 11 of the first embodiment. The operation unit 112 includes operation devices such as a release button and a selection button, and receives an instruction from the user. The operation state of the operation unit 112 is detected by the control unit 116. The display unit 113 includes a display device such as a liquid crystal monitor, and displays various images and menu screens. The display unit 113 may also be used as a viewfinder by displaying a through image for composition confirmation. The recording unit 114 includes a memory card (not shown) and records various data including images. The communication unit 115 is connected to the outside of the electronic camera 100 by wire or wireless, and exchanges various data.

  In the electronic camera 100 having the configuration described above, the control unit 116 performs the same processing as the flowchart described in FIG. 2 of the first embodiment. In the second embodiment, an image to be processed can be an image generated by the imaging unit 101, an image recorded in the recording unit 114, and an image acquired from the outside of the electronic camera 100 via the communication unit 115. Any of them.

  The image generated by the imaging unit 101 includes a so-called RAW format image and a JPEG format image. Any type of image can be the image to be processed, but the image to be processed is more preferably a so-called RAW format image.

  As described above, according to the second embodiment, a subject image is captured to generate an image, and the color arrangement in the entire generated image is analyzed. Then, based on the analysis result, at least one image word representing the image of the generated image is extracted from a plurality of predetermined image words (image display). Furthermore, the degree of contribution of the extracted image word to image processing is specified, and image processing is performed on the image based on the specification. Therefore, the same effect as that of the first embodiment can be obtained also in the electronic camera.

  In each of the above-described embodiments, an example in which an image after image processing is recorded and a series of processing ends is shown. However, an image after image processing is useful when output after image processing. For example, when the technique of the present invention is applied to an output device such as a printer or an online print service, or an output service, a suitable print output can be realized by appropriately printing the image after image processing. In addition to printing, a suitable display output can be realized by displaying the image after image processing on a display such as a digital camera or a mobile phone.

It is a block diagram which shows the structure of the computer 1 of 1st Embodiment. It is a flowchart which shows operation | movement of the computer 1 of 1st Embodiment. It is a figure which shows an example of a display. It is another figure which shows the example of a display. It is a block diagram which shows the structure of the electronic camera 100 of 2nd Embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Computer, 10 ... Image analysis part, 11 ... Image processing part, 12 ... Operation part, 13 ... Display part, 14 ... Recording part, 15 ... Communication part, 16 ... Control part, 17 ... Table storage part

Claims (11)

On the computer,
An acquisition step of acquiring an image to be processed;
For each of a plurality of predetermined image displays, an analysis step for analyzing a color arrangement in the entire image to be processed based on a table in which color information including a color arrangement is associated in advance;
An extraction step of extracting at least one image display representing an image of the image to be processed from a plurality of predetermined image displays based on the analysis result of the analysis step and the table;
A designation step of designating a contribution to the image display images processing extracted in the extracting step,
Based on the color information associated with the image display extracted in the extraction step, a pixel to be processed is extracted from the processing target image, and the extracted pixel is used as a target based on designation by the designation step. An image processing program for executing an image processing step for performing image processing. In the image processing program according to claim 1,
In the analysis step, the frequency of each image display in the entire image to be processed is obtained based on the table, and the color arrangement in the entire image to be processed is analyzed according to the obtained frequency. Image processing program. The image processing program according to claim 1 or 2,
In the image processing step, the image processing according to the color information obtained by the analysis is performed. In the image processing program according to claim 1,
The specifying step includes: a selection step for selecting an image display to be contributed to the image processing among the image displays extracted in the extraction step; and a degree of contribution in the image processing for each image display extracted in the extraction step. An image processing program characterized by comprising at least one of a determination step for determining. In the image processing program according to claim 1,
In the image processing step, the image processing including at least saturation correction is performed. An acquisition procedure for acquiring an image to be processed;
For each of a plurality of predetermined image displays, an analysis procedure for analyzing the color arrangement in the entire image to be processed based on a table in which color information including the color arrangement is associated in advance ;
An extraction procedure for extracting at least one image display representing an image of the image to be processed from a plurality of predetermined image displays based on the analysis result of the analysis procedure and the table ;
A designation step for designating a contribution to the images processing of the image display extracted in the extraction procedure,
Based on the color information corresponding to the image display extracted in the extracting procedure, to extract a pixel to be processed from the image, as a target the extracted pixels, the image processing that is based on designation by the designation procedures An image processing method for causing a computer to execute an image processing procedure for performing. The image processing method according to claim 6,
In the analysis procedure, the frequency of each image display in the entire image to be processed is obtained based on the table, and the color arrangement in the entire image to be processed is analyzed according to the obtained frequency. Image processing method. The image processing method according to claim 6 or 7,
In the image processing procedure, the image processing according to the color information obtained by the analysis is performed. The image processing method according to claim 6,
The designation procedure includes a selection procedure for selecting an image display to be contributed to the image processing among the image displays extracted in the extraction procedure, and a degree of contribution in the image processing for each image display extracted in the extraction procedure. An image processing method characterized by comprising at least one of a determination procedure for determining. The image processing method according to claim 6,
In the image processing procedure, the image processing including at least saturation correction is performed. An imaging unit that captures a subject image and generates an image;
For each of a plurality of predetermined image displays, based on a table in which color information including a color scheme is associated in advance, an analysis unit that analyzes the color scheme in the entire image;
An extraction unit that extracts at least one image display representing an image of the image from a plurality of predetermined image displays based on the analysis result by the analysis unit and the table;
A designation unit for designating a degree of contribution to the image processing of the image display extracted by the extraction unit;
Based on the color information associated with the image display extracted by the extraction unit, a pixel to be processed is extracted from the image, and image processing based on designation by the designation unit is performed on the extracted pixel. An electronic camera comprising: an image processing unit for performing the operation.

Images