JP3754786B2 - Image processing apparatus and method - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image processing apparatus and method, and more particularly, to an image processing apparatus and method for detecting a desired image region from an image.
[0002]
[Prior art]
Digital image data taken with a digital camera or digital image data obtained by scanning a film taken with a silver salt camera is subjected to specific processing, for example, to identify a person in a photo, Processing such as processing an image is performed.
[0003]
[Problems to be solved by the invention]
However, the above-described technique has the following problems. When performing the above processing, it is necessary to trace the outline of the face and eyes with a pointing device such as a mouse to designate the image area of the face and eyes. However, tracing the contour of a face or the like takes time, and there is a problem that the load on the operator is heavy. Therefore, processing for accurately detecting an image region such as a face is desired.
[0004]
The present invention is for solving the above-described problems, and provides an image processing apparatus and method capable of accurately and quickly detecting a desired image area while reducing an operator's load. Objective.
[0005]
[Means for Solving the Problems]
The present invention has the following configuration as one means for achieving the above object.
[0006]
An image processing apparatus according to the present invention includes an instruction unit for indicating at least one point of a displayed image, and a point specified by the instruction unit. including, A range for searching for an image area is set, and image characteristics are set from a plurality of pixels at a position of a pixel set near the designated point and its vicinity, or a plurality of pixels included in the set search range, and the search range Detection means for detecting an image area having the image characteristics from the image data, and a determination means for determining the end or continuation of the detection of the image area based on the relationship between the image area detected by the detection means and the search range. When the determination unit determines that the detection is continued, the detection unit expands the search range, and the detection unit expands the search range, and then expands the search range to the image from a plurality of pixels included in the expanded search range. It is characterized by resetting the characteristics.
[0007]
Further, an instruction means for instructing a partial range of the displayed image, and a range instructed by the instruction means including, A detection unit for setting an image region search range, acquiring image characteristics from pixels included in the designated range, and detecting an image region having the image characteristic from the search range; and an image region detected by the detection unit And determining means for determining the end or continuation of detection of the image region based on the relationship between the search ranges, and when the determining means determines that detection is to be continued, the detecting means expands the search range, The detection means, after expanding the search range, re-acquires the image characteristics from a plurality of pixels included in the expanded search range.
[0008]
According to the image processing method of the present invention, at least one point of the displayed image is indicated, and the indication point is including, A range for searching for an image area is set, and image characteristics are set from a plurality of pixels at a position of a pixel set near the designated point and its vicinity, or a plurality of pixels included in the set search range, and the search range When detecting an image region having the image characteristics from, determining the end or continuation of the detection of the image region based on the relationship between the detected image region and the search range, and when determining to continue the detection, The search range is expanded, and after the search range is expanded, the image characteristics are reset from a plurality of pixels included in the expanded search range.
[0009]
Further, a part of the displayed image is indicated, and the indicated range including, A range for searching the image area is set, image characteristics are acquired from the pixels included in the designated range, an image area having the image characteristics is detected from the search range, and the relationship between the detected image area and the search range is determined. If it is determined that the detection of the image area is completed or continued and the detection is to be continued, the search range is expanded, and after the search range is expanded, a plurality of pixels included in the expanded search range The image characteristics are re-acquired.
[0010]
DETAILED DESCRIPTION OF THE INVENTION
As a method for detecting a face image area, there is a method in which a skin color is set in advance and an area having a color close to the set color is extracted from the image.
[0011]
However, human skin colors vary widely, and even if they are the same person, the skin color obtained as an image varies greatly depending on the surrounding environment such as lighting, physical condition, makeup, and the state of the photographing system. . Therefore, in the method of setting the skin color, it is necessary to widen the range of colors to be extracted, and as a result, regions other than the face are often detected as face image regions.
[0012]
In addition, an image photographed with a flash may have a so-called “tekari” in which the light of the flash is reflected and the skin color flies, and the color may differ depending on the portion of the face of the same person. It is difficult to collectively detect such different color areas as one face image area. Further, the above method has a problem that the calculation time becomes long because the face image area is detected for the entire image.
[0013]
Hereinafter, an image processing apparatus according to an embodiment of the present invention that solves these problems will be described in detail with reference to the drawings.
[0014]
[First Embodiment]
FIG. 8 is a block diagram illustrating a configuration example of the image processing apparatus according to the first embodiment.
[0015]
In the figure, a microprocessor (CPU) 101 executes software stored in advance in a ROM 102 or a storage unit 104 and controls the entire apparatus via a bus 109. The RAM 103 is used as a work memory for the CPU 101 or as a memory for temporarily storing image data.
[0016]
The storage unit 104 is a storage device using a storage medium such as a hard disk or a magneto-optical disk, and is used for storing image processing software and image data, which will be described later. The input / operation unit 110 is for inputting instructions and data to the CPU 101, and is, for example, a pointing device such as a keyboard, a mouse, or a digitizer. The monitor 106 is a display such as a CRT or LCD, for example, and displays an image based on image data sent via the video interface 105 by the CPU 101. The image input device 108 is a device that outputs digital image data, such as a digital camera, a film scanner, or an image reader. Image data output from the image input device 108 is stored in the RAM 103 and the storage unit 104 via the external interface 107 by the CPU 101.
[0017]
Note that the image processing apparatus shown in FIG. 9 can be configured, for example, by connecting a monitor 106 and an image input apparatus 108 to a personal computer. The external interface 107 is a general-purpose interface. For example, a parallel interface such as SCSI, GPIB, or Centronics, or a serial interface such as RS232, RS422, or IEEE1394 can be used.
[0018]
FIG. 1 is a diagram illustrating an example of a functional configuration of image processing software according to the present embodiment.
[0019]
In the figure, a detection unit 1 is a functional block that detects, for example, a face image area, and corresponds to the CPU 1 and software executed by the CPU 1. The detection unit 1 includes a reference color setting unit 5, a search range setting / enlargement unit 6, a skin region detection unit 7, an end determination unit 8, and the like, details of which will be described later.
[0020]
The image display unit 2 corresponds to the monitor 106, the coordinate input unit 3 corresponds to the input / operation unit 110, and the image storage unit 4 corresponds to the RAM 103 and the storage unit 104, respectively.
[0021]
FIG. 2 is a flowchart showing an example of image area detection processing in the present embodiment, which is processing executed by the CPU 101. From the image represented by the processing target image data stored in the image storage unit 4, the face is detected. A process for detecting an image area will be described.
[0022]
In step S101, the image data to be processed is displayed on the image display unit 2 in accordance with an instruction from the operator (FIG. 3A). In step S102, the operator uses the coordinate input unit 3 to specify one point of the face to be detected, that is, the point A shown in the figure (FIG. 3B).
[0023]
In step S103, the search range setting / enlargement unit 6 initializes the search range B of the image area. Search range B is set to include point A (FIG. 3C). Here, suddenly setting a wide range as the search range B not only takes time to search for an image area, but also searches for a useless range when the ratio of the search target image to the entire image is small. It is desirable to set the initial search range B to a relatively small range. Further, the search range B does not have to be rectangular, and may have any shape.
[0024]
In step S104, the reference color setting unit 5 sets a reference color used for detection of a skin area described later. The reference color is the basic color of the face image area to be detected, that is, the skin color. The reference color setting unit 5 determines the color of the pixels around the point A or the entire search range B. Alternatively, the reference color is set with reference to the colors of some pixels. For example, as shown in FIG. 3D, when the search range B is expanded, the distance C from the point A is within a predetermined value (for example, within a circle whose radius is centered on the point A within a predetermined value). For example, an average value of the values of these pixels is set as a reference color with reference to the included pixels. Further, as shown in FIG. 3E, the reference color may be determined with reference to the colors of the pixels included in the rectangular pixel set D centered at the point A, for example.
[0025]
The color space used to determine the reference color can be any color space, such as the RGB color space used for display on the monitor screen, the YIQ color space used for television broadcasting, and the YCbCr color space used for image compression. However, in consideration of evaluating the color difference between multiple pixels later, a color space that can represent a color difference close to human visual characteristics is desirable, for example, Lab color space or Luv color defined by CIE A uniform color space such as a space is desirable.
[0026]
Also, if the specified point A is close to the edge of the face image area, the area C or D may contain a background that is not the face image area, and the skin color due to the influence of noise etc. There is also a possibility that pixels of a different color from those in region C and region D exist. In such a case, the reference color may be different from the original skin color due to the influence of the color caused by the background color and noise. In consideration of such a deviation of the reference color, the hue of the skin color is often in the vicinity of red, and the hue of the pixel in the area C or area D is far from red. It is desirable to exclude the pixel from the reference color calculation target. In this way, it is possible to obtain a reference color that more accurately represents the skin color by reducing the influence of the background color and noise.
[0027]
Next, in step S105, the skin region detection unit 7 detects the skin region. For example, the colors of all the pixels in the search range B are compared with the reference color, and a set of pixels whose color difference is smaller than a predetermined threshold value Td is set as a pixel group constituting the skin. If the reference color is (L0, a0, b0) and the pixel color is (L1, a1, b1) in the Luv color space, the color difference d is obtained by the following calculation.
d = √ {(L1-L0) ^ 2 + (u1-u0) ^ 2 + (v1-v0) ^ 2}… (1)
Where a ^ 2 represents the square of a
[0028]
The formula difference d obtained by the formula (1) represents a value proportional to the visually perceived color difference.
[0029]
As described above, it is desirable to evaluate color differences in a uniform color space, but the original image is represented by data in another color space, and it takes time to convert from that color space to the uniform color space. May calculate the color difference d in the color space of the original image. For example, if the original image is represented in the RGB color space, assuming that the reference color is (R0, G0, B0) and the pixel color is (R1, G1, B1), the color difference d is obtained by the following calculation: It is done.
d = √ {(R1-R0) ^ 2 + (G1-G0) ^ 2 + (B1-B0) ^ 2}… (2)
[0030]
The result of equation (2) deviates from human visual characteristics as compared with the color difference d calculated in a uniform color space or the like, but is effective when it is desired to shorten the calculation time.
[0031]
FIG. 3F is an enlarged view of the search range B. In this case, the region E is detected as a skin region.
[0032]
In step S106, the end determination unit 8 determines enlargement of the skin area or the end of the process. This determination is performed by determining the overlap between the search range B and the skin region E. Taking FIG. 3F as an example, it evaluates how much the skin area E overlaps each of the four sides of the rectangular search range B. In the case of FIG. 3F, since the left side of the search range B completely overlaps the skin region E, the overlap rate is 100%. Similarly, the upper side overlap rate is 80%, the lower side overlap rate is 50%, and the right side overlap rate is 0%. Then, when an edge having a greater overlap rate than the predetermined threshold Tp is detected, the end determination unit 8 sets the end determination flag to “0” in order to instruct expansion of the skin region. In addition, when an edge having an overlap rate larger than the threshold value Tp is not detected, the end determination unit 8 sets the end determination flag to “1” in order to instruct the end of the process. The threshold value Tp is set based on a balance between detection accuracy and detection time, and is set to 5%, for example. In the example of FIG. 3F, since the overlapping ratio of the left side, the upper side, and the right side exceeds 5%, the end determination flag is set to “0”.
[0033]
Next, in step S107, an end determination flag is determined. If “1”, the process ends. If “0”, the process returns to step S103, and the search for the face image area is continued.
[0034]
When the process returns to step S103, the search range B is expanded by the following procedure. That is, information on sides having an overlapping rate exceeding the threshold value Tp is transmitted from the end determination unit 8 to the search range setting / enlargement unit 6. The search range setting / enlargement unit 6 expands the search range B in the direction of the side designated by the end determination unit 8, that is, the side where the overlap rate is larger than Tp. In the case of FIG. 3F, the search range B is expanded in the direction excluding the right side, and the region B ′ shown in FIG. 3G becomes a new search range.
[0035]
Here, there are various methods for expanding the range B to the range B ′, such as a fixed value and a value proportional to the overlap rate. For example, the width of the original search range B is W and height. Is H × S in the left and / or right direction, H × S in the upper and / or down direction, and the search range is expanded to be a region B ′. Here, S is a one-dimensional enlargement factor and has a value larger than zero. When S is 0.5, the search range is expanded by 0.5 W to the left and / or right and 0.5 H to the top and / or bottom. When the search range B is expanded by such a method, the detection time can be shortened by designating the point A near the center of the face image area to be detected. Therefore, when receiving the designation of point A in step S102, it is preferable to display a message such as “Please specify the vicinity of the center of the image to be detected” to alert the operator.
[0036]
The process then proceeds to step S104, but since the reference color has already been determined, nothing is performed and the process proceeds to step S105. In step S105, the skin area is detected for the new search range B ′. However, it is not necessary to detect the skin area for the range B in which the previous skin area was detected. In step S106, the same enlargement / end determination as in the previous time is performed. By repeating the above processing, the search range B is gradually expanded and expanded until it surrounds the face image area, and the skin area E, that is, the face image area is detected.
[0037]
Further, when the process moves to step S104 again, a reference color may be set again for the enlarged search range B ′ by the same procedure as the first time, or the detected skin region E You may set the average value of the whole pixel as a new reference color. If the reference color is updated each time the search range B is expanded, the influence of local color fluctuations in a part of the image area can be reduced, and the accurate reference color can always be maintained.
[0038]
Normally, expansion of the search range B is limited by the four sides of the entire image, but if the shooting conditions of the image are limited and it is known that the shooting magnification of the subject will not exceed the predetermined value, an upper limit can be set in the search range The image area of the face that has the largest characteristic may be set as the upper limit of the search range. In step S102, the operator may designate a rectangular area including the entire face image together with the point A, and the designated rectangular area may be set as the upper limit of the search range. In this way, if the upper limit of the search range is provided and the end determination unit 8 determines whether or not the search range has reached the upper limit, cases where the search range is expanded more than necessary can be reduced.
[0039]
As described above, according to the present embodiment, it is not necessary to search the entire image by gradually expanding the search range based on one point of the image instructed by the operator, and the desired range can be obtained in a short time. An image area can be detected.
[0040]
In addition, a reference color representing, for example, skin color is set from a pixel near one point of the designated image, and a desired image area is detected based on this reference color. For example, ambient environment such as lighting, physical condition and makeup, photography It is possible to accurately detect an image region of a person's face having various skin colors by reducing the influence of the system state and the like.
[0041]
Second Embodiment
The image processing apparatus according to the second embodiment of the present invention will be described below. Note that in the second embodiment, identical symbols are assigned to configurations similar to those in the first embodiment and detailed description thereof is omitted.
[0042]
The image region detection processing in the present embodiment is performed based on the functional configuration shown in FIG. 1 and the processing shown in FIG. 2, but the processing content in each step is different from that in the first embodiment. Therefore, in the following, only the different steps of the process will be described in detail.
[0043]
In step S102, an area R including a part of the image area detected by the operator in the vicinity of the center is designated (FIG. 4A). The operator may specify the region R so that a part of the face image enters approximately the center of the region. Further, if the region R is substantially matched with the contour of the facial skin region, the subsequent processing can be completed in a short time.
[0044]
Next, in step S103, the search range setting / enlargement unit 6 initializes the search range B of the image area. Here, the search range B may be set so as to include the region R. However, if the wide range is suddenly set as the search range B, the search of the image region not only takes time, but the search target image occupies the entire image. Since the useless range is searched when the ratio is small, the initial search range B is preferably set to a range having almost the same size as the region R. FIG. 4B shows the detection range B. In this example, the region R designated by the operator is set as the first search range B. Further, the search range B does not have to be rectangular, and may have any shape.
[0045]
In step S104, a reference color used for skin area detection is set by the same method as in the first embodiment. However, since one or both ends of the search range B may protrude from the face image area, such as when a horizontally long area R is specified, the area C or area D shown in FIGS. Changing the shape and size of the reference region according to the shape of the region R, such as reduction to the vicinity of the center, is also effective for accurately obtaining the reference color.
[0046]
Next, in step S105, a skin region within the detection range B is detected as in the first embodiment. FIG. 4C is an enlarged view of search range B. In this case, region E is detected as a skin region.
[0047]
Next, in step S106, as in the first embodiment, the enlargement of the skin area or the end of the process is determined. In the case of FIG. 4C, the search range B is expanded in the direction excluding the left side, and the new search range B ′ is as shown in FIG. 4D. In the case of the example in FIG. 4D, the enlargement factor S is 0.3.
[0048]
The upper limit of the search range B may be set based on the size of the region R. In other words, if the shooting magnification is large and the drawing area of the face is large, the size of the area R specified by the operator is large, and if the drawing area is small, the small area R is specified and the upper limit of the search range B is used. May be set to about twice the specified region R, for example.
[0049]
As described above, according to the present embodiment, the same effect as in the first embodiment can be expected, but the entire image is searched by gradually expanding the search range based on the region designated by the operator. Therefore, it is possible to detect a desired image area in a short time. In addition, an image region can be determined in a shorter time as the designated region R is closer to the contour of the desired image region.
[0050]
[Third Embodiment]
The image processing apparatus according to the third embodiment of the present invention will be described below. Note that in the third embodiment, identical symbols are assigned to configurations similar to those in the first embodiment and detailed description thereof is omitted.
[0051]
FIG. 5 is a diagram for illustrating a functional configuration example of the image processing software according to the third embodiment of the present invention, except for the color difference threshold setting unit 10 for setting the color difference threshold, which is illustrated in FIG. Same as the configuration.
[0052]
Further, the image region detection processing in the present embodiment is performed based on the functional configuration shown in FIG. 5 and the processing shown in FIG. 2, but the processing content in each step is different from that in the first embodiment. Therefore, in the following, only the different steps of the process will be described in detail.
[0053]
In step S102, the operator uses the coordinate input unit 3 to instruct the region S where the image region is to be detected (FIG. 6A). In this embodiment, as shown in FIG. 6A, an example in which an image detection area is designated by an elliptical area S including a circle will be described. The operator may specify the region S so that a part of the image region to be detected enters approximately in the center of the region S. Further, by designating the elliptical region S almost along the contour of the image such as the face, the subsequent processing can be completed in a shorter time.
[0054]
Next, in step S103, the search range setting / enlargement unit 6 initializes the search range B of the image area. Here, the search range B may be set so as to include the region R. However, if the wide range is suddenly set as the search range B, the search of the image region not only takes time, but the search target image occupies the entire image. When the ratio is small, a useless range is searched. Therefore, the initial search range B is preferably set to a range having almost the same size as the region S. FIG. 6B shows the detection range B. In this example, the region S designated by the operator is set as the first search range B. In addition, the search range B does not have to be an ellipse and may have any shape.
[0055]
In step S104, a reference color used for skin area detection is set by the same method as in the first embodiment. However, when a horizontally long area S is specified, one or both ends of the search range B may protrude from the face image area, so the area C shown in FIG. Changing the shape and size of the reference region according to the shape of the region S is also effective for accurately obtaining the reference color. Of course, the region C does not have to be an ellipse and may have any shape.
[0056]
Next, in step S105, a skin region within the detection range B is detected as in the first embodiment. FIG. 6D is an enlarged view of the search range B. In this case, the region E is detected as a skin region. In the present embodiment, all pixels in the search range B are compared with the reference color, and a set of pixels in which the color difference d is smaller than the threshold Td set by the color difference threshold setting unit 10 is determined. Set to area E.
[0057]
In order to accurately detect the skin region E, it is effective to increase the threshold value Td according to the size of the search range B. This is because when the shooting magnification is low, the color change of the skin area is small, and when the shooting magnification is high, the color variation is large even for the face image of the same person due to shadows and light. This is especially true for images taken using a flash. Therefore, it is preferable that the color difference threshold setting unit 10 sets the threshold Td to be larger as the photographing magnification becomes larger as the search range B becomes larger. As a result, separation from the background becomes accurate and easy in an image with a small shooting magnification, and an image with a large shooting magnification can be accurately detected as one image even if the color is locally different. Become.
[0058]
Next, in step S106, as in the first embodiment, the enlargement of the skin area or the end of the process is determined. However, in the present embodiment, the determination is made based on the degree of overlap between the arc of the search range B and the skin region E. That is, as shown in FIG. 6D, for the arc H of the search range B that overlaps the search area E (from point F to point G), the ratio of the circumference of the search range B to the arc H is used as the overlap ratio.
[0059]
Further, in step S106, the direction in which the ellipse should be enlarged is transmitted from the end determination unit 8 to the search range setting / enlargement unit 6. Specifically, information is transmitted so as to expand the search range in the direction of the substantially middle point of the arc H, and the search range setting / enlargement unit 6 expands the search range B in the transmitted expansion direction to search range B ′ (Figure 6F). Various methods such as a fixed value and a value proportional to the overlap rate can be considered for the enlargement rate of the search range.For example, if the overlap rate is x%, the area of the new search range B ′ is ( What is necessary is just to enlarge so that it may become 1 + x / 100) times.
[0060]
Further, the circumference of the search range B may be divided into upper, lower, left, and right arcs, and the overlap rate may be determined for each arc. In this case, for example, when the overlap ratio of the right arc is large, the eccentricity of the ellipse may be changed so that the search range B is expanded in the right direction.
[0061]
Further, the color difference threshold setting unit 10 shown in FIG. 5 can be replaced with a weight setting unit 11 shown in FIG. In this case, the basic configuration and operation are the same as in the third embodiment, but the color difference evaluation method is different.
[0062]
The weight setting unit 11 determines the weight W based on the size (area As) of the search range B and sends it to the skin region detection unit 7. Note that k is a predetermined constant.
W = k / As (3)
[0063]
The skin region detection unit 7 calculates a color difference according to the following equation using the property that local color variation is mainly caused by luminance component variation.
d = √ {W × (L1-L0) ^ 2 + (u1-u0) ^ 2 + (v1-v0) ^ 2}… (4)
[0064]
That is, by changing the weight to the term relating to the difference in lightness L, when the search range B is large, control is performed such that the weight of lightness L in the color difference evaluation is lowered. As a result, when the shooting magnification is low, the background and the skin area are clearly separated, and when the shooting magnification is high, even if the color is locally different, it can be accurately detected as one image area.
[0065]
As described above, according to each embodiment of the present invention, the image area is detected while the search range is expanded until the end determination unit 8 determines that the detection is ended. Thus, the search range may be gradually expanded to perform the detection process up to the vicinity of the edge of the image area to be detected, so that the calculation time can be shortened. Further, the operator only needs to designate one point of the image area to be detected or a range including the image area, and the load on the operator can be reduced. In addition, since the image area is detected based on the color information in the vicinity or range of the point designated by the operator, for example, when detecting a human face image, the skin color, the environment and the surrounding situation, the condition of the person and the makeup Thus, it is possible to accurately detect the face image area without being affected by the photographing system or the like. Therefore, it is possible to detect the face image area of a specific person from the natural image accurately and in a short time, and reduce the load on the operator.
[0066]
Further, the reference color setting unit 5 updates the reference color as the search range is expanded by using the pixels included in the detected image region for determining the reference color. Therefore, for example, even when there is a flash on the face due to flash photography or the like, the area of the person's face image can be accurately detected.
[0067]
In addition, since the image area is detected by determining that a pixel whose color difference from the reference color determined by the reference color determination unit 5 is a predetermined value or less is a pixel in the image area, for example, when detecting a human face image, It is possible to always detect a stable image region without being influenced by the surrounding situation, the condition of a person, makeup, a photographing system, and the like.
[0068]
Further, according to the third embodiment of the present invention, the threshold value of the color difference used when determining the pixels of the image region is changed based on the size of the search range, so that, for example, a human face image is In the case of detection, an image region can always be detected stably and accurately even when there is a large color change in the region of the face image due to the environment, surrounding conditions, the condition and makeup of a person, the influence of the photographing system, and the like.
[0069]
In addition, since the weight related to the luminance information used in the calculation for obtaining the color difference is changed based on the size of the search range, for example, when detecting a face image of a person, the environment and surrounding conditions, the condition and makeup of the person, a photographing system Even when the luminance change is large in the face image area due to the influence of the image, the image area can always be detected stably and accurately.
[0070]
[Other Embodiments]
Note that the present invention can be applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), or a device (for example, a copier, a facsimile device, etc.) including a single device. You may apply to.
[0071]
Another object of the present invention is to supply a storage medium storing software program codes for realizing the functions of the above-described embodiments to a system or apparatus, and the computer (or CPU or MPU) of the system or apparatus stores the storage medium. Needless to say, this can also be achieved by reading and executing the program code stored in the. In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the storage medium storing the program code constitutes the present invention. As a storage medium for supplying the program code, for example, a floppy disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a magnetic tape, a nonvolatile memory card, a ROM, or the like can be used.
[0072]
Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an OS (operating system) running on the computer based on the instruction of the program code. It goes without saying that a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.
[0073]
Further, after the program code read from the storage medium is written into a memory provided in a function expansion card inserted in the computer or a function expansion unit connected to the computer, the function expansion is performed based on the instruction of the program code. It goes without saying that the CPU or the like provided in the card or the function expansion unit performs part or all of the actual processing and the functions of the above-described embodiments are realized by the processing.
[0074]
When the present invention is applied to the above-described storage medium, the storage medium stores program codes corresponding to the flowcharts described above. To briefly explain, each module shown in the memory map example of FIG. Is stored in a storage medium. That is, the program codes of at least the “instruction” and “search” modules, and preferably the “image characteristic acquisition”, “search range setting / expansion”, and “search range expansion / detection end” modules are stored in the storage medium. do it.
[0075]
【The invention's effect】
As described above, according to the present invention, it is possible to provide an image processing apparatus and method for detecting a desired image area accurately and in a short time by reducing the load on the operator.
[Brief description of the drawings]
FIG. 1 is a diagram for illustrating a functional configuration example of image processing software according to a first embodiment;
FIG. 2 is a flowchart showing an example of image area detection processing in the present invention;
FIG. 3A is a diagram for explaining processing of the first embodiment;
FIG. 3B is a diagram for explaining processing of the first embodiment;
FIG. 3C is a diagram for explaining processing of the first embodiment;
FIG. 3D is a diagram for explaining processing of the first embodiment;
FIG. 3E is a diagram for explaining processing of the first embodiment;
FIG. 3F is a diagram for explaining processing of the first embodiment;
FIG. 3G is a diagram for explaining processing of the first embodiment;
FIG. 4A is a diagram for explaining processing of the second embodiment;
FIG. 4B is a diagram for explaining processing of the second embodiment;
FIG. 4C is a diagram for explaining processing of the second embodiment;
FIG. 4D is a diagram for explaining processing of the second embodiment;
FIG. 5 is a diagram for illustrating a functional configuration example of image processing software according to a third embodiment;
FIG. 6A is a diagram for explaining processing of the third embodiment;
FIG. 6B is a diagram for explaining processing of the third embodiment;
FIG. 6C is a diagram for explaining processing of the third embodiment;
FIG. 6D is a diagram for explaining processing of the third embodiment;
FIG. 6E is a diagram for explaining processing of the third embodiment;
FIG. 7 is a view for showing a modification of the functional configuration of the image processing software of the third embodiment;
FIG. 8 is a block diagram showing a configuration example of an image processing apparatus according to the present invention;
FIG. 9 is a diagram showing an example of a memory map of a storage medium storing program codes according to the present invention.

Claims (10)

Instruction means for indicating at least one point of the displayed image;
A range for searching an image area including the point indicated by the indication means is set, and a plurality of pixels at the position of the set of pixels near the indication point and its vicinity, or a plurality of pixels included in the set search range Detecting means for setting an image characteristic from a pixel and detecting an image region having the image characteristic from the search range;
Determination means for determining the end or continuation of detection of the image area based on the relationship between the image area detected by the detection means and the search range;
When the determination means determines that detection is continued, the detection means expands the search range, and the detection means expands the search range, and then extracts the image characteristics from a plurality of pixels included in the expanded search range. An image processing apparatus that is reset.   2. The image processing according to claim 1, wherein the detection unit continues detection of an image area having the reset image characteristics included in the expanded search range after the search range is expanded. apparatus.   2. The image characteristic is an image color, and the detection unit determines that a pixel whose color difference from the image color is a predetermined threshold value or less is a pixel of an image region to be detected. An image processing apparatus according to claim 2.   4. The image processing apparatus according to claim 3, further comprising a threshold setting unit configured to set a threshold used by the detection unit to determine a color difference based on a set search range size. .   4. The weight setting unit according to claim 3, further comprising a weight setting unit configured to set a weight used for calculation of a color difference when the detection unit performs a color difference determination based on a set search range size. Image processing device.   6. The image processing apparatus according to claim 5, wherein the weight setting unit changes a weight related to luminance information based on a size of the search range. Instruction means for indicating a partial range of the displayed image;
Detection that sets a range for searching an image area including a range specified by the instruction means, acquires image characteristics from pixels included in the specified range, and detects an image area having the image characteristics from the search range Means,
Determination means for determining the end or continuation of detection of the image area based on the relationship between the image area detected by the detection means and the search range;
When the determination means determines that detection is continued, the detection means expands the search range, and the detection means expands the search range, and then extracts the image characteristics from a plurality of pixels included in the expanded search range. An image processing apparatus characterized by being reacquired.   8. The image processing according to claim 7, wherein the detection unit continues detection of an image region having the re-acquired image characteristics included in the expanded search range after the search range is expanded. apparatus. Point at least one point on the displayed image,
Set a range to search the image area including the indicated point,
Set image characteristics from a plurality of pixels at a position of the set of pixels in the vicinity of the designated point or the vicinity thereof, or a plurality of pixels included in the set search range,
Detecting an image region having the image characteristics from the search range;
Based on the relationship between the detected image area and the search range, determine the end or continuation of detection of the image area,
When it is determined that the detection is to be continued, the search range is expanded, and after the search range is expanded, the image characteristics are reset from a plurality of pixels included in the expanded search range. Method. Instruct a partial range of the displayed image,
Set the range to search the image area including the indicated range,
Obtaining image characteristics from pixels included in the indicated range;
Detecting an image region having the image characteristics from the search range;
Based on the relationship between the detected image area and the search range, determine the end or continuation of detection of the image area,
When it is determined that the detection is to be continued, the search range is expanded, and after the search range is expanded, the image characteristics are re-acquired from a plurality of pixels included in the expanded search range. Method.

Images