JP2014102712A - Contour detection device, contour detection method, and contour detection program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To detect a human contour at high accuracy.SOLUTION: By an input operation, a search area 10 is set on an input image, extended from a start area 11 toward an end area 12 and having a width with a certain size or larger. Search means 3 searches for an edge from the start area 11 side toward the end area 12 side in the search area 10. In addition, the search means 3 excludes a pixel 24 determined to be positioned in an area 33 between a skin color area 31 and a skin color area 32 among pixels within the search area 10 from a pixel determined to be an edge as a result of an error detection of a contour.

Description

  The present invention relates to a contour detection device, a contour detection method, and a contour detection program.

  A technique for detecting the contour of a specific object from an image such as a photograph by image processing is known. Such a technique is used, for example, for detecting the contour of a person and erasing or replacing a background image outside the contour.

  In addition, as a technique for accurately detecting the contour of a desired object such as a person, the user can specify an area for detecting the contour using an input device such as a mouse, There is a technique for limiting to a nearby region. For example, there is a method of searching for a pixel having a high edge detection intensity toward the end point between the start point and the end point specified by the user operation. There is also a method for searching for a contour point by scanning a pixel in a width direction intersecting with the center line in a belt-like region designated by a user operation.

JP 2000-209430 A JP-A-7-92650 JP 2000-339483 A

  There are cases where the contour of a person cannot be accurately detected even by a method in which the user designates a region for detecting the contour and searches for the edge in the designated region from the start point side to the end point side. For example, in the vicinity of the ear with the face facing forward, hair may be applied to the area inside the face from the ear. In this case, the outer edge of the hair region is determined to be stronger than the outer edge of the ear, and the outer edge of the hair region inside the ear may be erroneously detected as a contour.

  In one aspect, an object of the present invention is to provide a contour detection device, a contour detection method, and a contour detection program capable of detecting a human contour with high accuracy.

  In one proposal, the following contour detection apparatus is provided. This contour detection apparatus has an input reception unit and a search unit. The input receiving unit sets a search area having a certain width or more on the input image that is extended from the start area to the end area in response to an input operation. The search means searches for an edge in the search area from the start area side to the end area side. Further, the search means excludes pixels determined to be located in an area sandwiched between the skin color area and the skin color area from the pixels determined to be edges among the pixels in the search area.

  Further, in one proposal, there are provided a contour detection method in which processing similar to that in the above contour detection device is executed, and a contour detection program for causing a computer to execute processing similar to that in the above contour detection device.

  According to one aspect, the contour of a person can be detected with high accuracy.

It is a figure which shows the structural example and processing example of the outline detection apparatus which concern on 1st Embodiment. It is a figure which shows the hardware structural example of the outline detection apparatus which concerns on 2nd Embodiment. It is a block diagram which shows the structural example of the processing function with which an outline detection apparatus is provided. It is a figure which shows the example of the state transition at the time of trace operation execution. It is a figure for demonstrating the calculation method of a trace direction angle. It is a figure which shows the example of the information registered into trace area information. It is a figure which shows the example of the classification | category of a trace direction angle. It is a figure shown about the example of the relationship between an angle range and an edge search range. It is a figure which shows the example of calculation of edge strength. It is a figure which shows the example of a setting of a trace area | region. It is a figure shown about the case where a contour line is misdetected. It is a flowchart which shows the example of the whole process sequence of the outline detection apparatus which concerns on 2nd Embodiment. It is a flowchart which shows the 1st process example of step S19. It is a figure which shows the example of a setting of the investigation direction in a 1st process example. It is a flowchart which shows the 2nd process example of step S19. It is a flowchart which shows the example of the process sequence of step S57 of FIG. It is a figure which shows the example of a setting of the investigation direction in a 2nd process example.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[First Embodiment]
FIG. 1 is a diagram illustrating a configuration example and a processing example of the contour detection apparatus according to the first embodiment. The contour detection device 1 in FIG. 1 is a device that executes a process of detecting a contour line of an object from an input image, and includes an input reception unit 2 and a search unit 3.

  Each process of the input reception unit 2 and the search unit 3 is realized by, for example, a processor included in the contour detection device 1 executing a predetermined program. Alternatively, at least a part of the processing of the input reception unit 2 and the search unit 3 may be realized by a dedicated circuit.

  The input receiving unit 2 sets a search area for searching for an edge on the input image in accordance with a user input operation. The search area is an area having a certain width or more that extends from the start area toward the end area. FIG. 1 shows an example of the search area 10 that is gently curved from the start area 11 toward the end area 12.

  It is desirable that the search area can be set by a simple operation as much as possible. As an example of the search area setting method, a method in which a search area having a certain width is set along the movement locus when the user performs an operation of continuously moving the designated position on the screen may be considered. In this case, the designated position can be, for example, the position of the mouse cursor or the touch position on the touch panel. As a similar example, a method in which when the user performs an operation of moving an icon image having a certain size, a region where the icon image has moved can be set as a search region.

The search means 3 searches for an edge from the start area side to the end area side in the set search area.
For example, the search unit 3 sets a target pixel in the search region starting from any pixel in the start region, and includes a predetermined direction including the extension direction of the search region at the position of the target pixel among the surrounding pixels of the target pixel. Pixels included in the edge search range are determined as edge candidate pixels. The search means 3 determines a pixel that is highly likely to be an edge from the edge candidate pixels, sets it as the next pixel of interest, and performs the same processing. The search means 3 repeats such edge search processing until the target pixel reaches the end region. Thereby, the set pixel group of interest is detected as a contour line.

  FIG. 1 illustrates the case where the pixel 21 is set as the pixel of interest, and at this time, an edge search range B1 including the extending direction A1 of the search region 10 at the position of the pixel 21 is set. For example, the search unit 3 sets pixels included in the edge search range B1 among the peripheral pixels of the pixel 21 as edge candidate pixels. The edge search range B1 is set, for example, as a range of a predetermined angle with the angle in the extending direction A1 being substantially the center. When the search unit 3 determines that the pixel 22 having the highest possibility of being an edge among the edge candidate pixels is the pixel 22, the search unit 3 sets the pixel 22 as the next pixel of interest.

  Thus, by searching for an edge from the start area side to the end area side in the search area, it is difficult to detect a contour line extending in a direction greatly deviating from the extending direction of the search area. For this reason, it is possible to accurately detect the contour line extending along the search region, that is, the contour line intended by the user, by the user's operation so that the search region is set along the desired contour line. Become.

  By the way, it is not usually considered that the contour line of a person, particularly the contour line of the human head, is located in a region sandwiched between the skin color region and the skin color region. Therefore, the search means 3 excludes pixels determined to be located in an area sandwiched between the skin color area and the skin color area from the pixels determined to be edges from among the pixels in the search area. Thereby, the possibility that a human outline is erroneously detected is reduced, and the detection accuracy is improved.

  For example, it is assumed that the search unit 3 sets the pixel 23 in FIG. Further, the edge search range B2 corresponding to the pixel 23 is set so as to include the extending direction A2 of the search region 10 in the pixel 23, and the pixel 24 that is one of the pixels located in the edge search range B2 It is assumed that it is located in a region 33 sandwiched between the region 31 and the skin color region 32. In this case, the search means 3 excludes the pixel 24 from the edge search candidates even if the pixel 24 is most likely an edge among the edge search pixels. That is, the pixel 24 is not set as the next pixel of interest.

  As described above, it is not normally considered that a person's outline is located in a region sandwiched between a skin color region and a skin color region. For this reason, if the search means 3 sets a region sandwiched between the skin color region and the skin color region as the next pixel of interest, it is unlikely that the set pixel of interest is along the contour of the person. Is likely to have occurred. Therefore, the search means 3 can reduce the possibility of erroneous detection of the human outline by excluding the pixels located in such a region from the edge candidate pixels, and improve the detection accuracy of the human outline. Can be made.

  As a case where the area between the flesh color area and the flesh color area is erroneously set as the next pixel of interest, for example, when the face is facing the front, the ear is exposed and the area between the ear and the face is There are cases where the area is covered with hair. Alternatively, there may be a case where a part of the hair is on the inner side of the outer edge of the face. According to the contour detection apparatus 1 described above, the possibility of erroneous detection of a human contour line in such a case can be reduced.

  Also, instead of excluding the pixel from the pixel that is determined to be an edge as described above, the user can operate the search area so that the search area is set along the shape of the outline of the person, so that the edge detection accuracy is improves. However, for example, if the user operates the search area so as to be set along the shape of the outer edge of the ear, a large amount of labor is required and the user's work efficiency is reduced.

  According to the contour detection device 1 of the present embodiment, even in the region near the ear, the search region does not exactly follow the shape of the outer edge of the ear, but extends along the rough contour line of the entire head. By setting, the outer edge of the ear is detected as a contour line. That is, human contour detection can be performed with high accuracy and high efficiency.

  Note that the search unit 3 may perform the process of determining whether a pixel is located in an area sandwiched between the skin color area and the skin color area based on, for example, color information on both sides of the pixel. As another method, for example, the following may be performed based on the detection result of the face from the input image. The search means 3 determines whether a skin color area exists in the outward direction of the detected face relative to the determination target pixel based on the positional relationship between the detected face position and the determination target pixel. When the search means 3 determines that a skin color area exists in the outward direction, the search target pixel is regarded as being located in an area sandwiched between the skin color area and the skin color area, and the pixel is excluded from the edge candidate pixels.

[Second Embodiment]
Next, an example of a contour detection apparatus having a function of detecting a human face from an input image will be described. FIG. 2 is a diagram illustrating a hardware configuration example of the contour detection apparatus according to the second embodiment. The contour detection apparatus 100 is realized as a computer as shown in FIG. 2, for example.

  The entire contour detection apparatus 100 is controlled by a processor 101. A RAM (Random Access Memory) 102 and a plurality of peripheral devices are connected to the processor 101 via a bus 109. The processor 101 may be a multiprocessor. The processor 101 is, for example, a central processing unit (CPU), a micro processing unit (MPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), or a programmable logic device (PLD). The processor 101 may be a combination of two or more elements among CPU, MPU, DSP, ASIC, and PLD.

  The RAM 102 is used as a main storage device of the contour detection device 100. The RAM 102 temporarily stores at least part of an OS (Operating System) program and application programs to be executed by the processor 101. The RAM 102 stores various data necessary for processing by the processor 101.

  Examples of peripheral devices connected to the bus 109 include an HDD (Hard Disk Drive) 103, a graphic processing device 104, an input interface 105, an optical drive device 106, a device connection interface 107, and a network interface 108.

  The HDD 103 magnetically writes and reads data to and from the built-in disk. The HDD 103 is used as an auxiliary storage device of the contour detection apparatus 100. The HDD 103 stores an OS program, application programs, and various data. As the auxiliary storage device, other types of nonvolatile storage devices such as SSD (Solid State Drive) can be used.

  A monitor 104 a is connected to the graphic processing device 104. The graphic processing device 104 displays an image on the screen of the monitor 104a in accordance with an instruction from the processor 101. Examples of the monitor 104a include a display device using a CRT (Cathode Ray Tube) and a liquid crystal display device.

  A keyboard 105 a and a mouse 105 b are connected to the input interface 105. The input interface 105 transmits signals sent from the keyboard 105a and the mouse 105b to the processor 101. Note that the mouse 105b is an example of a pointing device, and other pointing devices can also be used. Examples of other pointing devices include a touch panel, a tablet, a touch pad, and a trackball.

  The optical drive device 106 reads data recorded on the optical disc 106a using laser light or the like. The optical disk 106a is a portable recording medium on which data is recorded so that it can be read by reflection of light. The optical disk 106a includes a DVD (Digital Versatile Disc), a DVD-RAM, a CD-ROM (Compact Disc Read Only Memory), a CD-R (Recordable) / RW (ReWritable), and the like.

  The device connection interface 107 is a communication interface for connecting peripheral devices to the contour detection apparatus 100. For example, a memory device 107 a and a memory reader / writer 107 b can be connected to the device connection interface 107. The memory device 107a is a recording medium equipped with a communication function with the device connection interface 107. The memory reader / writer 107b is a device that writes data to the memory card 107c or reads data from the memory card 107c. The memory card 107c is a card type recording medium.

  The network interface 108 is connected to the network 108a. The network interface 108 transmits / receives data to / from other computers or communication devices via the network 108a.

  With the hardware configuration described above, the processing functions of the second embodiment can be realized. Note that the contour detection apparatus 1 shown in the first embodiment can also be realized by the same hardware as the contour detection apparatus 100 shown in FIG.

  FIG. 3 is a block diagram illustrating a configuration example of processing functions included in the contour detection apparatus. The contour detection apparatus 100 sequentially searches for pixels having a large edge strength with respect to the extending direction of the search region in a search region set on the input image in accordance with the input operation of the user and having a certain width or more. As a result, the outline of the person on the input image is detected. In particular, the contour detection apparatus 100 is capable of detecting a contour line near the head of a person whose face is facing the front with high accuracy. The search area is set as an area where the icon image has moved when the user performs an operation of moving an icon image of a predetermined size by a drag operation.

  The contour detection apparatus 100 includes an image reading unit 111, a face detection unit 112, a trace input unit 113, and a contour detection unit 114. Each process of the image reading unit 111, the face detection unit 112, the trace input unit 113, and the contour detection unit 114 is realized by the processor 101 executing a predetermined program. However, at least a part of these processes may be realized by a dedicated circuit such as a circuit in the graphic processing device 104, for example.

  The storage device of the contour detection apparatus 100 stores face position information 121, trace area information 122, search range information 123, and a coordinate list 124. Among these pieces of information, the search range information 123 is stored in advance in a nonvolatile storage device such as the HDD 103. On the other hand, the face position information 121, the trace area information 122, and the coordinate list 124 are temporarily stored at least in a volatile storage device such as the RAM 102.

  The image reading unit 111 reads an input image showing a person into the RAM 102 from a nonvolatile storage device connected to the contour detection device 100 such as the HDD 103 or an information processing device on the network 108a. In the present embodiment, it is assumed that at least the head of a person whose face is substantially in front is reflected in the input image.

  The face detection unit 112 detects a human face from the input image, and sets face position information 121 indicating the position of the detected face. The face position information 121 is information for determining whether the pixel of interest is located on the right side or the left side of the face. For example, coordinates indicating the center of the face with respect to the horizontal direction (y direction) are set.

  When the user performs a “trace operation” in which an icon image of a predetermined size is moved by a drag operation, the trace input unit 113 sets the area where the icon image has moved as a search area. Hereinafter, an area where the icon image has moved is referred to as a “trace area”. Information indicating the trace area is stored in the RAM 102 as the trace area information 122.

  The trace input unit 113 calculates a “trace direction angle” for each pixel in the set trace area, and registers the calculated trace direction angle in the trace area information 122 in association with each pixel. The trace direction angle is a reference angle for determining a travelable direction for edge search for each pixel. Details of the trace direction angle will be described later.

The search range information 123 stores an edge search range indicating a range in which an edge search is performed for each trace direction angle in association with each other.
The contour detection unit 114 detects a contour line by sequentially tracing pixels with high edge strength from the start region to the end region in the trace region. In such edge search processing, the contour detection unit 114 refers to the face position information 121, the trace area information 122, and the search range information 123. The contour detection unit 114 registers the coordinates of the target pixel in the coordinate list 124 every time the target pixel is set. When the edge search process ends, the coordinate list 124 is output as information indicating the detected contour line.

  In addition, when the contour detection unit 114 selects a pixel having the highest edge intensity from the surrounding pixels of the target pixel, the contour detection unit 114 is based on the trace direction at the position of the selected pixel and the positional relationship between the selected pixel and the face. For the selected pixel, it is determined whether there is a skin color region in a direction that should not be present. If there is a skin color region in a direction that should not be present, the contour detection unit 114 excludes the selected pixel from the pixel determined as an edge without setting it as the next pixel of interest. Thus, it is possible to accurately detect a human contour even in a region near the ear or a region including hair.

Next, a basic contour detection processing procedure of the contour detection apparatus 100 will be described. The basic contour detection process includes the following processing steps.
(1) Set the trace area according to the trace operation.

(2) The trace direction angle is calculated for each pixel in the trace area.
(3) Any pixel in the start area of the trace area is set as the target pixel, and the following (3-1) to (3-3) are repeated until the target pixel reaches the end area of the trace area.

(3-1) The edge search range corresponding to the trace direction angle for the target pixel is determined based on the search range information 123.
(3-2) The pixels included in the edge search range among the surrounding pixels of the target pixel are set as edge candidate pixels, and the edge strength of each edge candidate pixel is calculated.

(3-3) The edge candidate pixel having the highest edge strength is set as the next pixel of interest.
The calculation of the trace direction angle is not performed for all the pixels in the trace area at the time (2), but may be performed for the set target pixel at the time (3-1).

Hereinafter, the processes (1) to (3) will be described with reference to FIGS.
First, FIG. 4 is a diagram illustrating an example of state transition at the time of executing a trace operation. The trace operation and the trace area will be described with reference to FIG.

  In this embodiment, as an example, it is assumed that the user performs a trace operation for designating a trace area using a mouse. Then, it is assumed that the trace area 210 is set by the user moving the rectangular icon image 201 by a drag operation.

  In FIG. 4, a trace area 210 is an area surrounded by a broken line. In addition, a dotted line arrow in FIG. 4 indicates a trajectory in which the center point of the icon image 201 has moved, and this trajectory is hereinafter referred to as a “trace area center line”.

  When the user presses the mouse button with the mouse cursor placed at a desired position on the input image 200 as in state 1 in FIG. 4, an icon image 201 is displayed at the position of the mouse cursor. The icon image 201 may be displayed at the position of the mouse cursor before the mouse button is pressed.

  When the user moves the designated position on the screen by moving the mouse while holding down the mouse button, the icon image 201 is also moved along with the movement. At this time, as in state 2 in FIG. 4, the area where the icon image 201 has moved is set as the trace area 210 and the set trace area 210 is displayed in an identifiable state on the screen. Thereafter, when the user finishes pressing the mouse button at a desired position, the setting of the trace area 210 is completed as shown in state 3 of FIG.

  When detecting the outline of the human head, the user may move the icon image 201 so that the outline of the human head on the input image 200 is always included in the icon image 201.

  When the touch panel is used, for example, the user touches the finger at a desired position on the input image 200, moves the touch position while keeping the finger touched, and then moves the finger at the desired position. The trace area 210 can be designated by the operation of releasing.

  In the example of FIG. 4, the area where the icon image 201 has been moved is set as the trace area 210. However, for example, there is an area having a certain width centered on the locus of the mouse cursor or the locus of the finger contact position. The trace area 210 may be set.

Further, the shape of the icon image 201 is not limited to a rectangle as shown in FIG.
By the way, as will be described later, a start area and an end area of the trace area 210 are set in order to determine the start point and end point of the edge search. As the start region, a plurality of pixels adjacent to the end on the start point side of the trace region 210 are set, and as the end region, a plurality of pixels adjacent to the end on the end point side of the trace region 210 are set.

  When the rectangular icon image 201 is used as shown in FIG. 4, for example, as the start area, one or two sides facing the end of the area where the icon image 201 is first arranged in the trace area 210 are used. Pixel is set. When the icon image 201 moves from the initial position in the left-right direction (x-axis direction) or the up-down direction (y-axis direction), a pixel on one side facing the end is set as the start area. On the other hand, when the icon image 201 is moved obliquely from the initial position, pixels on two sides facing the end are set as the start area. FIG. 4 shows the latter example, and a pixel adjacent to the sides 211 and 212 is set as a start region.

  The same applies to the end region. Among the regions where the icon image 201 is finally arranged in the trace region 210, pixels on one or two sides facing the end are set. When the icon image 201 moves in the horizontal direction (x-axis direction) or the vertical direction (y-axis direction) with respect to the final position, a pixel on one side facing the end is set as the end region. On the other hand, when the icon image 201 moves obliquely with respect to the final position, pixels on two sides facing the end are set as the end region. FIG. 4 shows the latter example, and a pixel adjacent to the sides 213 and 214 is set as an end region.

  FIG. 5 is a diagram for explaining a method of calculating the trace direction angle. In FIG. 5, as in FIG. 4, the area surrounded by the broken line indicates the trace area 210, and the dotted arrow indicates the center line of the trace area 210.

  When the trace area 210 is set as shown in FIG. 4, the trace input unit 113 calculates the trace direction angle for each pixel in the trace area 210 and registers it in the trace area information 122. The trace direction angle indicates an angle in the extending direction of the trace region 210 at the position of each pixel. The trace direction angle is a reference angle for determining which of the surrounding pixels is a search target when focusing on the corresponding pixel.

  An example of a specific calculation method will be described using the pixel 221 in FIG. 5 as an example. The trace direction angle θ1 is set as an angle with respect to a predetermined reference direction (vertical direction in the present embodiment) on the screen. The trace direction angle θ1 for the pixel 221 can be calculated as the slope θ2 of the tangent line 223 of the center line at the intersection 222 between the perpendicular line and the center line drawn from the pixel 221 with respect to the center line.

  The slope θ2 of the tangent 223 may be approximately calculated by a simpler calculation method for the purpose of reducing the calculation load and improving the processing speed. For example, the angle of a straight line connecting the coordinates of the intersection point 222 and the coordinates on the center line that is separated from the end point side by a predetermined distance from the intersection point 222 may be calculated as an approximate value of the slope θ2 of the tangent line 223.

  FIG. 6 is a diagram illustrating an example of information registered in the trace area information. When the trace area 210 is set by the user's operation input, the trace input unit 113 creates a record for each pixel included in the trace area 210 in the trace area information 122. Each record is provided with columns of, for example, coordinates, trace direction angle, start area flag, and end area flag.

  The coordinates of each pixel are registered in the coordinate column. In the column of the trace direction angle, the trace direction angle for each pixel described in FIG. 5 is registered. The start area flag is a flag indicating whether or not the corresponding pixel belongs to the start area described with reference to FIG. 4. If the start area flag belongs to the start area, “1” is registered, and if not, “0” is registered. The The end region flag is a flag indicating whether or not the corresponding pixel belongs to the end region described with reference to FIG. 4. If the end region flag belongs to the end region, “1” is registered, and if not, “0” is registered. The It should be noted that for the pixel belonging to the end region, no further edge search is performed when the pixel is set as the pixel of interest, and therefore the trace direction angle need not be registered for that pixel.

  FIG. 7 is a diagram illustrating an example of classification of trace direction angles. As described above, the search range information 123 stores an edge search range indicating a range in which edge search is performed for each trace direction angle in association with each other. In the present embodiment, the trace direction angle is classified into eight angle ranges D0 to D7 shown in FIG. 7, and an edge search range is associated with each classified angle range.

  Here, the reason why the trace direction angle is classified into the eight angle ranges D0 to D7 is related to the presence of eight pixels around the pixel of interest in the trace region. The angle ranges D0 to D7 may be set so as to have substantially equal angles with respect to the upper side, upper right side, right side, lower right side, lower side, lower left side, left side, and upper left side of the target pixel, respectively. .

  In the example of FIG. 7, the upper side of the display screen is the angle reference direction, the range of 338 ° to less than 360 ° and the range of 0 ° to less than 24 ° is the angle range D0, and the range of 24 ° to less than 68 ° is the angle range D1. The range from 68 ° to less than 114 ° is the angle range D2, the range from 114 ° to less than 158 ° is the angle range D3, the range from 158 ° to less than 204 ° is the angle range D4, and the range is from 204 ° to less than 248 °. Is set to an angle range D5, a range of 248 ° to less than 294 ° is set to an angle range D6, and a range of 294 ° to less than 338 ° is set to an angle range D7.

  FIG. 8 is a diagram illustrating an example of the relationship between the angle range and the edge search range. In FIG. 8, with respect to the surrounding pixels of the pixel of interest, N0, N1, N2, N3, N4, N5, N6, N0, N1, N2, N3, N4, N5, N6 in the order of upper side, upper right side, right side, lower right side, lower side, lower left side, left side, upper left side. The reference numeral N7 is attached.

  The “edge candidate pixel” shown in FIG. 8 indicates a pixel to be subjected to edge search, more specifically, a pixel to be subjected to edge strength calculation. The edge search range indicates a range in which edge candidate pixels are included among the surrounding pixels of the target pixel. The edge search range by the contour detection unit 114 is limited to the vicinity range of the direction indicated by the trace direction angle calculated for the pixel of interest. In other words, the pixels that can be set as the next target pixel are limited to the pixels included in the edge search range among the peripheral pixels of the current target pixel. Thereby, the edge located in the direction largely deviated from the extending direction of the trace area is not detected, and the contour line intended by the user is easily detected.

  In the present embodiment, as an example, as shown in FIG. 8, the edge search range is set for each angle range shown in FIG. When the trace direction angle is included in the angle range D0, the edge search range is set in the vicinity of the upward direction of the pixel of interest, and the pixels N7, N0, and N1 are edge candidate pixels. When the trace direction angle is included in the angle range D1, the edge search range is set near the upper right direction of the pixel of interest, and the pixels N0, N1, and N2 are edge candidate pixels. When the trace direction angle is included in the angle range D2, the edge search range is set near the right direction of the target pixel, and the pixels N1, N2, and N3 are edge candidate pixels. When the trace direction angle is included in the angle range D3, the edge search range is set in the vicinity of the lower right direction of the pixel of interest, and the pixels N2, N3, and N4 are edge candidate pixels.

  When the trace direction angle is included in the angle range D4, the edge search range is set near the lower direction of the pixel of interest, and the pixels N3, N4, and N5 are edge candidate pixels. When the trace direction angle is included in the angle range D5, the edge search range is set near the lower left direction of the target pixel, and the pixels N4, N5, and N6 are edge candidate pixels. When the trace direction angle is included in the angle range D6, the edge search range is set in the vicinity of the target pixel in the left direction, and the pixels N5, N6, and N7 are edge candidate pixels. When the trace direction angle is included in the angle range D7, the edge search range is set near the upper left direction of the target pixel, and the pixels N6, N7, and N0 are edge candidate pixels.

In the example of FIG. 8, the edge candidate pixel is set in the range of one pixel around the target pixel, but the edge candidate pixel may be set in the range of a plurality of pixels around the target pixel.
In the search range information 123, information indicating the positions of edge candidate pixels (for example, N0 to N7 shown in FIG. 8) is registered in advance for each angle range. When the target pixel is set, the contour detection unit 114 determines edge candidate pixels corresponding to the trace angle range for the target pixel based on the search range information 123. The contour detection unit 114 calculates the edge strength for each of the determined edge candidate pixels, and sets the pixel having the highest edge strength as the next pixel of interest.

  FIG. 9 is a diagram illustrating an example of calculating the edge strength. The edge strength is an index indicating the high possibility that the target pixel is an edge. FIG. 9 shows an example in which edge strength of edge candidate pixels is calculated using a Sobel filter.

  In the method using the Sobel filter, filter coefficients are prepared for each of the x direction and the y direction. Using each filter coefficient, the x component and the y component of the edge strength are calculated. Then, the edge strength is calculated by combining the x component and the y component.

  In the filter operation in each of the x and y directions, filter coefficients are set for a total of nine pixels including the edge candidate pixel and its surrounding pixels. In the example of FIG. 9, the filter calculation in the x direction for the edge candidate pixel is “brightness value of upper left pixel × (−1) + brightness value of upper pixel × 0 + brightness value of upper right pixel × 1 + brightness value of left pixel”. × (−2) + Brightness value of edge candidate pixel × 0 + Brightness value of right pixel × 2 + Brightness value of lower left pixel × (−1) + Brightness value of lower pixel × 0 + Brightness value of lower right pixel × 1 The x-component of the edge strength is thereby calculated.

  In the example of FIG. 9, the y-direction filter operation for the edge candidate pixel is “brightness value of upper left pixel × (−1) + brightness value of upper pixel × (−2) + brightness value of upper right side pixel × (-1) + Luminance value of left pixel × 0 + Luminance value of edge candidate pixel × 0 + Brightness value of right pixel × 0 + Luminance value of lower left pixel × 1 + Luminance value of lower pixel × 2 + Luminance value of lower right pixel This is performed by the formula “× 1”, and thereby the y component of the edge strength is calculated.

Then, the edge strength E is calculated by taking the square root of the value obtained by adding the square value of the x component and the square value of the y component.
FIG. 10 is a diagram illustrating an example of setting a trace area. As shown in FIG. 10, the user moves the icon image so that the outline of the person is always included in the icon image. Thereby, the trace area 210 is set in the area including the outline of the person. According to the contour detection procedure described above with reference to FIGS. 4 to 9, the contour line located in a direction greatly deviating from the extending direction of the trace area 210 (that is, the moving direction of the icon image) is not detected, and the user intends The contour line to be detected is easily detected.

  In addition, by setting the icon image to a certain size or more, the user can accurately detect the outline of the head simply by moving the icon image so as to roughly follow the outline of the head. become able to. For example, the left and right widths of the icon image are set larger than the horizontal range of the ear. In this case, the user moves the icon image roughly along the outline of the head as shown in FIG. At this time, it is not necessary to change the moving direction of the icon image along the shape of the ear, and the icon image may be moved so that the horizontal range of the ear is included in the icon image. With such a simple operation, a contour line can be accurately detected even in the vicinity of the ear.

  However, for example, when hair is present in a region near the ear, an erroneous contour line may be detected as follows. FIG. 11 is a diagram illustrating a case where a contour line is erroneously detected.

  In the region 301 of FIG. 11, a hair region exists between the ear region and the face region. The edge strength is relatively large at the boundary between the hair region and the skin color region of the ear or face. For this reason, the contour detection unit 114 may erroneously detect the outer edge of the region of the hair existing in the inner side of the face rather than the outer edge of the ear as a human contour. In addition, when the trace area is set so as to roughly follow the outline of the head as shown in FIG. 10, the trace direction angle for the pixels in the vicinity area of the ear substantially coincides with the vertical direction. Thus, once the outer edge of the hair region is erroneously detected as a human contour line, the contour detection unit 114 continues the edge search in the vertical direction while maintaining the erroneous detection state, and the other end of the ear region is detected. There is also a possibility of progressing to.

Further, the erroneous detection as described above may occur not only in the vicinity of the ear, but also in an area where the hair is flowing inside the outer edge of the face.
Accordingly, when the contour detection unit 114 selects a pixel having the highest edge intensity from among the edge candidate pixels, if the selected pixel is located in a region between the skin color region and the skin color region, the contour detection unit 114 selects the selected pixel. Instead of setting the next pixel of interest, it is excluded from the edge candidate pixels. As a specific example of this method, the contour detection unit 114 determines the skin color in the direction that should not be originally for the selected pixel based on the trace direction at the position of the selected pixel and the positional relationship between the selected pixel and the face. Determine if there is an area. If there is a skin color region in a direction that should not be present, the contour detection unit 114 excludes the selected pixel from the pixel determined as an edge without setting it as the next pixel of interest. Thereby, it becomes possible to accurately detect the outline of a person even in a region near the ear or a region including hair.

  Next, the processing procedure of the contour detection apparatus 100 will be described using a flowchart. First, FIG. 12 is a flowchart illustrating an example of the entire processing procedure of the contour detection apparatus according to the second embodiment.

[Step S <b> 11] The image reading unit 111 reads image data of an input image into the RAM 102.
[Step S12] The face detection unit 112 performs face detection from the input image, and stores information indicating the position of the detected face in the RAM 102 as face position information 121.

[Step S13] The trace input unit 113 accepts a trace operation by the user.
[Step S14] The trace input unit 113 sets a trace area based on the trace operation. The trace input unit 113 creates a record corresponding to each pixel in the trace area in the trace area information 122 and registers the coordinates of each pixel. Further, the trace input unit 113 calculates the trace direction angle for each pixel and registers it in the trace area information 122. Further, the trace input unit 113 discriminates the start area and the end area in the trace area, and sets the start area flag and the end area flag of the trace area information 122 based on the discrimination result.

  [Step S15] The contour detection unit 114 calculates the edge strength of each pixel in the start region in the trace region, and sets the pixel having the highest edge strength as the first pixel of interest. In addition, the contour detection unit 114 registers the coordinates of the set target pixel in the coordinate list 124.

  [Step S16] The contour detection unit 114 reads the trace direction angle associated with the current pixel of interest from the trace area information 122. The contour detection unit 114 refers to the search range information 123 and determines the position of the edge candidate pixel corresponding to the angle range to which the read trace direction angle belongs.

[Step S17] The contour detection unit 114 calculates edge strength for each of the edge candidate pixels.
[Step S18] The contour detection unit 114 selects a pixel having the maximum edge strength from among the unselected edge candidate pixels.

  [Step S19] The contour detection unit 114 determines the selected pixel based on the trace direction of the pixel selected in Step S18 and the relationship between the selected pixel and the face position registered in the face position information 121. It is determined whether there is a flesh-colored area in a direction that should not be. If there is a skin color area in a direction that should not be, it is determined that there is a false detection and the process of step S20 is executed. On the other hand, if there is no skin color area in the direction that should not be, it is determined that there is no false detection, and the process of step S21 is executed.

  [Step S20] The contour detection unit 114 excludes the pixel selected in step S18 from the edge candidate pixels. For example, the contour detection unit 114 temporarily stores the position of the pixel selected in step S18 in the RAM 102.

  Thereafter, the process of step S18 is re-executed, but the pixels excluded from the edge candidate pixels by the process of step S20 are selected pixels in the next step S18 and are selected as the pixels having the maximum edge strength. Not.

  [Step S21] The contour detection unit 114 determines whether or not the selected pixel is included in the end region based on the end region flag for the selected pixel in step S18 registered in the trace region information 122. If the selected pixel is not included in the end region, the process of step S22 is executed. If included, the process of step S23 is executed.

  [Step S22] The contour detection unit 114 updates the pixel of interest to the pixel selected in step S18, and registers the coordinates of this pixel in the coordinate list 124. Thereafter, step S16 is executed, and the process for the updated target pixel is performed.

  [Step S23] The contour detection unit 114 registers the coordinates of the pixel selected in step S18 in the coordinate list 124, and then outputs the coordinate list 124 as information indicating the detected contour line.

  According to the processing in FIG. 12 described above, the contour of the human head can be accurately detected even in the vicinity of the ear and the region including the hair. Moreover, even if the user does not faithfully move the icon image along the shape of the outer edge of the ear or the outer edge of the hair region, the outline of the head is accurately detected in these regions. Therefore, the contour line can be efficiently detected by a simple operation. For example, even when there are a large number of input images to be detected as contour lines, the work time can be shortened while maintaining the contour line detection accuracy.

  In the process of FIG. 12, the trace direction angles of all the pixels in the trace area are calculated in advance in step S14 before the edge search process is started. However, as another example, the trace direction angle of the pixel of interest may be calculated at the time of step S16 without calculating the trace direction angle at the time of step S14.

  In the process of FIG. 12, the edge strength is calculated at the time of step S15 and step S17. However, as another example, after setting the trace area in step S14 and before executing the process of step S15, the edge strengths of all the pixels in the trace area are calculated in advance, similarly to the trace direction angle, It may be registered in the trace area information 122. In this case, in step S15 and step S17, the edge intensity of the corresponding pixel is read from the trace area information 122.

  Further, either or both of the trace direction angle and the edge intensity for all the pixels on the input image may be calculated and temporarily stored in the storage device before the trace operation is accepted in step S13. Good.

Next, two processing examples will be given for the determination processing procedure in step S19. First, FIG. 13 is a flowchart showing a first processing example of step S19.
[Step S31] Based on the face position information 121, the contour detection unit 114 determines whether the pixel selected in step S18 in FIG. 12 is located on the right side or the left side of the face. When it is located on the right side of the face, the process of step S32 is executed, and when it is located on the left side, the process of step S33 is executed.

  [Step S32] The contour detection unit 114 determines whether the trace direction at the position of the selected pixel is downward or upward. Specifically, the contour detection unit 114 reads the trace direction angle for the selected pixel from the trace area information 122. The contour detector 114 determines that the trace direction is downward when the vertical component (y component) of the read trace direction angle indicates a downward direction, and determines that the trace direction is upward when it indicates an upward direction. .

If the trace direction is downward, the process of step S34 is executed. If the trace direction is upward, the process of step S35 is executed.
[Step S33] The contour detection unit 114 determines whether the trace direction at the position of the selected pixel is downward or upward. The specific processing procedure is the same as that in step S32. When the trace direction is downward, the process of step S35 is executed. When the trace direction is upward, the process of step S34 is executed.

  [Step S <b> 34] The contour detection unit 114 sets the direction in which the skin color region is examined to the direction of the pixel located on the left side of the trace direction angle for the selected pixel among the surrounding pixels of the selected pixel.

  For example, the contour detection unit 114 determines which of the angle ranges D0 to D7 illustrated in FIG. 7 the trace direction angle for the selected pixel belongs to, and the left side of the surrounding pixels depending on which angle range it belongs to The pixel located at is determined. Here, the surrounding pixels of the selected pixel are indicated by using the reference numerals (N0 to N7) shown in FIG.

  When the trace direction angle belongs to the angle range D0, the contour detection unit 114 determines the pixel N6 among the surrounding pixels as a pixel located on the left side. In addition, when the trace direction angle belongs to the angle range D1, the contour detection unit 114 determines the pixel N7 among the surrounding pixels as a pixel located on the left side. In addition, when the trace direction angle belongs to the angle range D2, the contour detection unit 114 determines the pixel N0 among the surrounding pixels as a pixel located on the left side. In addition, when the trace direction angle belongs to the angle range D3, the contour detection unit 114 determines the pixel N1 among the surrounding pixels as a pixel located on the left side.

  In addition, when the trace direction angle belongs to the angle range D4, the contour detection unit 114 determines the pixel N2 among the surrounding pixels as a pixel located on the left side. In addition, when the trace direction angle belongs to the angle range D5, the contour detection unit 114 determines the pixel N3 among the surrounding pixels as a pixel located on the left side. In addition, when the trace direction angle belongs to the angle range D6, the contour detection unit 114 determines the pixel N4 among the surrounding pixels as a pixel located on the left side. Further, when the trace direction angle belongs to the angle range D7, the contour detection unit 114 determines the pixel N5 among the surrounding pixels as a pixel located on the left side.

  The contour detection unit 114 sets the direction from the selected pixel to the pixel located on the left side as the skin color region investigation direction. Thereby, the investigation direction of the skin color region is set in a direction rotated approximately 90 ° to the left with respect to the trace direction angle for the selected pixel. This investigation direction is a direction toward the outside of the face. That is, if the selected pixel is correctly along the outline of the head, it is usually a direction in which no skin color region exists.

  [Step S <b> 35] The contour detection unit 114 sets the investigation direction for investigating the skin color region to the direction of the pixel located on the right side with respect to the trace direction angle for the selected pixel among the surrounding pixels of the selected pixel.

  For example, as in step S34, the contour detection unit 114 determines which of the angle ranges D0 to D7 in FIG. 7 the trace direction angle for the selected pixel belongs to, and depending on which angle range the surrounding pixels belong to The pixel located on the right side is determined.

  When the trace direction angle belongs to the angle range D0, the contour detection unit 114 determines the pixel N2 among the surrounding pixels as a pixel located on the right side. In addition, when the trace direction angle belongs to the angle range D1, the contour detection unit 114 determines the pixel N3 among the surrounding pixels as a pixel located on the right side. In addition, when the trace direction angle belongs to the angle range D2, the contour detection unit 114 determines the pixel N4 among the surrounding pixels as a pixel located on the right side. In addition, when the trace direction angle belongs to the angle range D3, the contour detection unit 114 determines the pixel N5 among the surrounding pixels as a pixel located on the right side.

  Further, when the trace direction angle belongs to the angle range D4, the contour detection unit 114 determines the pixel N6 among the surrounding pixels as a pixel located on the right side. In addition, when the trace direction angle belongs to the angle range D5, the contour detection unit 114 determines the pixel N7 among the surrounding pixels as a pixel located on the right side. In addition, when the trace direction angle belongs to the angle range D6, the contour detection unit 114 determines the pixel N0 as the pixel located on the right side among the surrounding pixels. In addition, when the trace direction angle belongs to the angle range D7, the contour detection unit 114 determines the pixel N1 among the surrounding pixels as a pixel located on the right side.

  The contour detection unit 114 sets the direction from the selected pixel to the pixel located on the right side as the skin color region investigation direction. Thereby, the investigation direction of the skin color region is set in a direction rotated approximately 90 ° to the right with respect to the trace direction angle for the selected pixel. This investigation direction is a direction toward the outside of the face. That is, if the selected pixel is correctly along the outline of the head, it is usually a direction in which no skin color region exists.

[Step S <b> 36] The contour detection unit 114 sets the first pixel located in the set survey direction as a survey pixel to be determined as a skin color region.
[Step S37] Based on the trace area information 122, the contour detection unit 114 determines whether the current examination pixel is outside the trace area. When the investigation pixel is outside the trace area, the process of step S41 is executed. When the investigation pixel is inside the trace area, the process of step S38 is executed.

  [Step S38] The contour detection unit 114 determines whether the current investigation pixel is a skin color. This determination is performed based on, for example, whether the color information value of the investigation pixel is included in a predetermined range. If the survey image is a skin color, the process of step S39 is executed, and if it is not the skin color, the process of step S40 is executed.

[Step S39] The contour detection unit 114 determines that there is a skin color region in a direction that should not be present, and that erroneous detection has occurred. That is, “Yes” is determined in step S19.
[Step S40] The contour detection unit 114 moves the survey pixel by one pixel with respect to the set survey direction. Thereafter, the process of step S37 is performed again for the survey pixel after movement.

  [Step S <b> 41] The case where “Yes” is determined in Step S <b> 37 is a case where the investigation pixel is set outside the trace area without detecting the skin color pixel in the investigation direction. In this case, the contour detection unit 114 determines that the pixel selected in step S18 is correctly detected along the contour of the head because there is no skin color region in a direction that should not be present. That is, “No” is determined in step S19.

FIG. 14 is a diagram illustrating an example of setting the investigation direction in the first processing example. In the following description, a pixel having coordinates (n, m) is referred to as “pixel (n, m)”.
In FIG. 14, as an example, it is assumed that the pixel (12, 12) is set as the pixel of interest, and it is determined that the edge strength of the pixel (13, 13) is the highest among the edge candidate pixels in this case. Further, it is assumed that the trace direction angle for the pixel (13, 13) belongs to the angle range D4 in FIG. The center position of the face is assumed to be in the left direction (−x direction) of the pixels (13, 13).

  In this case, the contour detection unit 114 determines the pixel located on the left side of the pixel (13, 13) as the pixel (14, 13), and the direction from the pixel (13, 13) toward the pixel (14, 13) (that is, (Right direction) is the skin color area survey direction. Here, it is assumed that the right end of the trace area is at the position of the x coordinate “17”. At this time, the contour detection unit 114 uses the pixel (14, 13), the pixel (15, 13), the pixel (16, 13), and the pixel (17, 13) existing in the survey direction as the survey pixels, and at least If it is determined that one is skin color, it is determined that there is a skin color region in a direction that should not be.

  In this case, the contour detection unit 114 determines that the pixel (13, 13) is not along the contour of the head, and excludes the pixel (13, 13) from the edge candidate pixel. Then, of the edge candidate pixels for the pixel (12, 12), the pixel having the next highest edge intensity after the pixel (13, 13) is selected, and the skin color region determination similar to the above is performed.

  According to the first processing example described above, the skin color region is examined in a direction rotated by approximately 90 ° with respect to the outer direction of the face with respect to the trace direction angle for the pixel determined to have a high edge strength. The This makes it possible to determine whether there is a skin color region in a direction that should not be present.

  Next, FIG. 15 is a flowchart showing a second processing example of step S19. In the second processing example, as compared with the first processing example, the skin color region examination direction can be set to a more accurate angle corresponding to the trace direction angle.

  In the process of FIG. 15, the coordinates of the pixel selected in step S18 of FIG. 12 are (X2, Y2), and the coordinates of the pixel of interest set a predetermined number before are (X1, Y1). The pixels (X1, Y1) can be, for example, the pixel of interest set by the number corresponding to ½ of the width of the icon image (however, the fractional part is discarded).

[Step S51] The contour detection unit 114 calculates XD = X2-X1 and YD = Y2-Y1.
[Step S52] Based on the face position information 121, the contour detection unit 114 determines whether the pixel (X2, Y2) is located on the right side or the left side of the face. If it is located on the right side of the face, the process of step S53 is executed. If it is located on the left side, the process of step S54 is executed.

  [Step S53] The contour detection unit 114 determines whether the trace direction at the position of the pixel (X2, Y2) is downward or upward. When the trace direction is downward, the process of step S55 is executed. When the trace direction is upward, the process of step S56 is executed.

  [Step S54] The contour detection unit 114 determines whether the trace direction at the position of the pixel (X2, Y2) is downward or upward. When the trace direction is downward, the process of step S56 is executed. When the trace direction is upward, the process of step S55 is executed.

Steps S53 and S54 can be executed by the same processing procedure as step S32 in FIG.
[Step S55] The contour detection unit 114 sets the coordinates (XS, YS) for determining the direction of investigation of the skin color region to the left of the slope of the straight line from the coordinates (X1, Y1) to the coordinates (X2, Y2). Set the position in the direction rotated 90 °. These coordinates are calculated as XS = X2 + YD, YS = Y2-XD. XS and YS need not be integers.

  [Step S56] The contour detection unit 114 sets the coordinates (XS, YS) for determining the investigation direction of the skin color region to the right with the inclination of the straight line from the coordinates (X1, Y1) to the coordinates (X2, Y2). Set the position in the direction rotated 90 °. These coordinates are calculated as XS = X2-YD, YS = Y2 + XD. XS and YS need not be integers.

  In steps S55 and S56, the coordinates (XS, YS) are determined based on the slope of the straight line from the coordinates (X1, Y1) to the coordinates (X2, Y2). However, as another method, the coordinates (XS, YS) may be determined on the basis of the trace direction angle for the coordinates (X2, Y2) read from the trace area information 122.

  [Step S57] The contour detection unit 114 calculates x increments and y increments respectively indicating the x component and the y component of the coordinate change amount from the pixel (X2, Y2) to the coordinate (XS, YS). In this process, the calculation is performed so that at least one of the x increment and the y increment is 1. The calculation process in step S57 will be described in detail later with reference to FIG.

  [Step S58] The contour detection unit 114 sets a pixel located at a distance of the calculated x increment and y increment from the pixel (X2, Y2) as an investigation pixel in the skin color region. Since at least one of the x increment and the y increment is 1, one of the surrounding pixels adjacent to the pixel (X2, Y2) is set as the investigation pixel in this process.

  [Step S <b> 59] The contour detection unit 114 determines whether the current examination pixel is outside the trace area based on the trace area information 122. When the investigation pixel is outside the trace area, the process of step S63 is executed, and when the investigation pixel is inside the trace area, the process of step S60 is executed.

  [Step S60] The contour detection unit 114 determines whether the current investigation pixel is a skin color. This determination is performed based on, for example, whether the color information value of the investigation pixel is included in a predetermined range. If the survey image is a skin color, the process of step S61 is executed, and if it is not the skin color, the process of step S62 is executed.

[Step S61] The contour detection unit 114 determines that there is a skin color region in a direction that should not be present, and that erroneous detection has occurred. That is, “Yes” is determined in step S19.
[Step S62] The contour detection unit 114 moves the survey pixel to a position away from the current survey pixel by a distance of x increment and y increment. Here, since the value of at least one of the x increment and the y increment is 1, one of the surrounding pixels of the current survey pixel is set as a new survey pixel in this process. Thereafter, the process of step S59 is performed again for the survey pixel after movement.

  [Step S <b> 63] The case where “Yes” is determined in Step S <b> 59 is a case in which the skin pixel is not detected in the survey direction and the survey pixel is set outside the trace area. In this case, the contour detection unit 114 determines that the pixel (X2, Y2) selected in step S18 is correctly detected along the contour of the head because there is no skin color region in the direction that should not be. . That is, “No” is determined in step S19.

FIG. 16 is a flowchart showing an example of the processing procedure of step S57 of FIG.
[Step S71] The contour detection unit 114 calculates x difference = XS−X2 and y difference = YS−Y2.

  [Step S72] The contour detection unit 114 determines whether the absolute value of the x difference is smaller than the absolute value of the y difference. If the absolute value of the x difference is smaller than the absolute value of the y difference, the process of step S73 is executed. If the absolute value of the x difference is equal to or larger than the absolute value of the y difference, the process of step S77 is executed.

[Step S73] The contour detection unit 114 calculates a value obtained by dividing the x difference by the absolute value of the y difference as an x increment.
[Step S74] The contour detection unit 114 determines whether the y difference is 0 or more. When the y difference is 0 or more, the process of step S75 is executed. When the y difference is less than 0, the process of step S76 is executed.

[Step S75] The contour detection unit 114 sets the y increment to 1.
[Step S76] The contour detection unit 114 sets the y increment to -1.
The x increment and the y increment calculated by the processes in steps S73 to S76 are 1 in the y direction with respect to the direction from the coordinate (X2, Y2) to the coordinate (XS, YS) (that is, the skin color region survey direction). The x component and y component of the change amount in pixel units are shown. When the x increment and the y increment are calculated by the processes in steps S73 to S76, the y coordinate is sequentially shifted one pixel at a time when the investigation pixel is set in step S58 of FIG. 15 and the subsequent step S62. Will go.

[Step S77] The contour detection unit 114 calculates a value obtained by dividing the y difference by the absolute value of the x difference as an y increment.
[Step S78] The contour detection unit 114 determines whether the x difference is 0 or more. When the x difference is 0 or more, the process of step S79 is executed. When the x difference is less than 0, the process of step S80 is executed.

[Step S79] The contour detection unit 114 sets the x increment to 1.
[Step S80] The contour detection unit 114 sets the x increment to -1.
The x increment and the y increment calculated by the processes in steps S77 to S80 are 1 in the x direction with respect to the direction from the coordinate (X2, Y2) to the coordinate (XS, YS) (that is, the skin color region examination direction). The x component and y component of the change amount in pixel units are shown. When the x increment and the y increment are calculated by the processes in steps S77 to S80, when the investigation pixel is set in step S58 in FIG. 15 and the subsequent step S62, the x coordinate is sequentially shifted pixel by pixel. Will go.

  FIG. 17 is a diagram illustrating an example of setting the investigation direction in the second processing example. In FIG. 17, as an example, it is assumed that pixel (10, 10) (= pixel (X2, Y2)) is selected as a pixel having a high edge strength among the edge candidate pixels for the pixel of interest. Further, the pixel of interest set a predetermined number of times before is assumed to be a pixel (9, 7) (= pixel (X1, Y1)). The pixel (10, 10) is assumed to be on the right side of the face.

  In this case, in step S53 of FIG. 15, it is determined that the trace direction is downward. Also, in step S55, the coordinates (XS, YS) for determining the skin color region investigation direction C are rotated 90 degrees to the left with respect to the slope of the straight line from the coordinates (9, 7) to the coordinates (10, 10). The coordinate (13, 9) along the direction is set. Then, x increment = 1 and y increment = − (1/3) are calculated.

  At this time, the contour detection unit 114 selects the investigation pixel starting from the pixel (10, 10) while adding the x coordinate to the investigation direction C by one pixel corresponding to the x increment. Similarly, the y coordinate is incremented for each y increment, but since the absolute value of the y increment is less than 1, the y coordinate of the investigation pixel may have a value after the decimal point. When the y coordinate has a value after the decimal point, for example, both the pixel when the value after the decimal point of the y coordinate is rounded down and the pixel when the value is rounded up are set as the investigation pixel.

  For example, in FIG. 17, in the first survey pixel setting, the pixel (11, 9) and the pixel (11, 10) are set as the survey pixel, and in the second survey pixel setting, the pixel (12, 9) and the pixel (12, 10) are set as the investigation pixel. In the third survey pixel setting, since the y coordinate of the survey pixel is an integer, one pixel (13, 9) is set as the survey pixel.

If the y coordinate of the survey pixel has a value after the decimal point, only one pixel may be set as the survey pixel by rounding down or rounding up the y coordinate.
In the above-described first processing example, the skin color area examination direction is set in the direction of one of the eight pixels located around the pixel from the starting pixel. For this reason, the investigation direction of the skin color area is set in units of 45 °. On the other hand, in the second processing example, it is possible to set the angle in the investigation direction of the skin color area more finely. As a result, it is possible to accurately set an area that needs to be investigated, and it is possible to improve the accuracy of determining whether the skin color area is in a direction that should not exist.

  The processing functions of the devices (contour detection devices 1 and 100) shown in the above embodiments can be realized by a computer. In that case, a program describing the processing contents of the functions that each device should have is provided, and the processing functions are realized on the computer by executing the program on the computer. The program describing the processing contents can be recorded on a computer-readable recording medium. Examples of the computer-readable recording medium include a magnetic storage device, an optical disk, a magneto-optical recording medium, and a semiconductor memory. Examples of the magnetic storage device include a hard disk device (HDD), a flexible disk (FD), and a magnetic tape. Examples of the optical disc include a DVD, a DVD-RAM, a CD-ROM, and a CD-R / RW. Magneto-optical recording media include MO (Magneto-Optical disk).

  When distributing the program, for example, a portable recording medium such as a DVD or a CD-ROM in which the program is recorded is sold. It is also possible to store the program in a storage device of a server computer and transfer the program from the server computer to another computer via a network.

  The computer that executes the program stores, for example, the program recorded on the portable recording medium or the program transferred from the server computer in its own storage device. Then, the computer reads the program from its own storage device and executes processing according to the program. The computer can also read the program directly from the portable recording medium and execute processing according to the program. In addition, each time a program is transferred from a server computer connected via a network, the computer can sequentially execute processing according to the received program.

DESCRIPTION OF SYMBOLS 1 Contour detection apparatus 2 Input acceptance means 3 Search means 10 Search area 11 Start area 12 End area 21-24 Pixel 31, 32 Skin color area 33 Area A1, A2 Stretch direction B1, B2 Edge search range

Claims (8)

In response to an input operation, an input receiving means for setting a search area having a certain width or more extended from the start area toward the end area on the input image;
Search means for searching for an edge in the search area from the start area side toward the end area side, and determined to be located in an area sandwiched between the skin color area and the skin color area among the pixels in the search area Search means for excluding selected pixels from pixels determined as edges;
A contour detection apparatus comprising: Further comprising face detection means for detecting a human face from the input image;
The search means determines that, of the pixels in the search area, a pixel in which a skin color area exists outside the face detected from the pixel is located in an area sandwiched between the skin color area and the skin color area. ,
The contour detection apparatus according to claim 1. The search means includes
Among the surrounding pixels of the target pixel set from the search region, pixels included in a predetermined range including the extension direction of the search region at the position of the target pixel are set as edge candidate pixels, and the edge candidate pixel to the edge The edge search process for determining a pixel having a high possibility and setting the next target pixel is repeated until the target pixel reaches the end region from the start region,
Among the surrounding pixels of the set pixel of interest, a pixel having a skin color area in the outward direction of the face detected from the pixel is determined to be located in an area sandwiched between the skin color area and the skin color area, and the edge Exclude from candidate pixels,
The contour detection apparatus according to claim 2.   For the pixel selected from the surrounding pixels of the set target pixel, the search means is based on the positional relationship between the pixel and the detected face, and the extension direction of the search region at the position of the pixel, A determination is made as to whether the direction of investigation of the flesh color region is rightward or leftward with respect to the extending direction of the search region at the position of the pixel, and the presence or absence of the flesh color region is investigated with respect to the determined direction Item 4. The contour detection apparatus according to item 3.   The search means rotates a predetermined number of pixels in the determined direction with reference to a first pixel located in the extending direction of the search region at the pixel position among the surrounding pixels of the selected pixel. The contour detection apparatus according to claim 4, wherein a second pixel at a position is selected, and whether a pixel located in a direction from the selected pixel to the second pixel is a skin color is checked.   The search means determines a direction in which the inclination from the target pixel set a predetermined number before the set target pixel to the selected pixel is rotated by 90 ° in the determined direction, and the selected pixel determines the direction from the selected pixel. The contour detection apparatus according to claim 4, wherein a pixel adjacent to the determined direction is examined for skin color. Contour detection device
In accordance with the input operation, a search area having a certain width or more extended from the start area to the end area is set on the input image,
In the search area, an edge is searched from the start area side toward the end area side.
Including processing,
In the process of searching for the edge, out of the pixels in the search region, the pixel determined to be located in the region sandwiched between the skin color region and the skin color region is excluded from the pixel determined as the edge.
A contour detection method characterized by the above. On the computer,
In accordance with the input operation, a search area having a certain width or more extended from the start area to the end area is set on the input image,
In the search area, an edge is searched from the start area side toward the end area side.
Execute the process,
In the process of searching for the edge, out of the pixels in the search region, the pixel determined to be located in the region sandwiched between the skin color region and the skin color region is excluded from the pixel determined as the edge.
A contour detection program.

Images