JP6116916B2 - Image detection apparatus, control program, and image detection method - Google Patents

Description

  The present invention relates to a technique for detecting a detection target image from a processing target image.

  Patent Documents 1 to 3 disclose techniques for detecting a detection target image from a processing target image.

JP 2008-27058 A JP 2009-175821 A JP 2011-221791 A

  Now, when detecting a detection target image from a processing target image, improvement of the detection accuracy is desired.

  Therefore, the present invention has been made in view of the above points, and an object thereof is to provide a technique capable of improving the detection accuracy of a detection target image.

In order to solve the above-described problem, one aspect of an image detection device according to the present invention is an image detection device that detects a detection target image from a processing target image, and a plurality of detections whose positions differ from each other with respect to the processing target image A detection unit configured to detect a detection target image with respect to an image in the detection frame for each of the plurality of detection frames, and the detection target based on a detection result of the detection unit. A map generating unit that generates a map indicating a distribution in the processing target image with respect to a detection accuracy value indicating the certainty as an image; a search unit that searches for a maximum point of the detection accuracy value in the map; and a predetermined reference one performs integration processing to integrate into, pixels in the same position and the maximum point after the integration processing in the processing target image a plurality of said local maximum points close to each other in the map based on And a determining section that determines to be the detection target image a predetermined region including the Le, the determination unit, in the map, the detection of the maximum point in a direction away from the maximum point after the integration process When the accuracy value is viewed, the processing target is the same as the position where the detection accuracy value is initially (1 / Z) times or less (Z> 1) with respect to the detection accuracy value at the local maximum point. The position in the image is defined as the end of the predetermined area that is determined to be the detection target image, and the detection accuracy value is viewed from the local maximum point along the direction away from the local maximum point after the integration process in the map. The change in the detection accuracy value is not monotonously reduced before the position at which the detection accuracy value is less than (1 / Z) times the detection accuracy value at the maximum point appears. The change is not monotonically decreasing. The position determining that became, the end of the predetermined area to determine that the to be detected image.

  In the image detection device according to the aspect of the invention, the search unit may include a plurality of the detections included in a processing target region using the detection accuracy value as a weighting factor in the map arranged in two-dimensional coordinates. By calculating a weighted average value of coordinate values for a plurality of positions each having an accuracy value, and repeating the process of moving the processing target region so that the center position of the processing target region becomes the weighted average value, Search for local maxima.

  In the image detection device according to the aspect of the invention, the search unit may determine that the image within the detection frame is likely to be the detection target image as a result of the detection unit performing the detection process. The search for the maximum point is started with the position on the map that is the same as the predetermined position in the detection frame as the center position of the processing target region.

  In the aspect of the image detection apparatus according to the present invention, when the weighting average value is calculated, the search unit is included in the processing target region in the map in which the detection accuracy value is thinned out. Coordinate values for a plurality of positions each having a plurality of detection accuracy values are used.

  In one aspect of the image detection apparatus according to the present invention, the detection target image is a human face image.

One aspect of the control program according to the present invention is a control program for controlling an image detection device that detects a detection target image from a processing target image. The control program includes (a) the processing target image. A plurality of detection frames whose positions are different from each other, and for each of the plurality of detection frames, a process of detecting the detection target image with respect to an image in the detection frame; and (b) the step Generating a map indicating a distribution in the processing target image with respect to a detection accuracy value indicating the certainty as the detection target image based on the detection result in (a), and (c) detecting the detection in the map A step of searching for a local maximum point of the accuracy value; (d) a step of performing integration processing for integrating the plurality of local maximum points close to each other in the map based on a predetermined criterion; and ( e ) before A predetermined region including a pixel at the same position as the maximum point after the integration processing in the processing target image is executed, and in the map, the maximum point after the integration processing When the detection accuracy value is viewed from the local maximum point along the direction away from the detection point, the detection accuracy value is initially less than (1 / Z) times the detection accuracy value at the local maximum point ( The position in the processing target image that is the same as the position where Z> 1) is set as the end of the predetermined region that is determined to be the detection target image, and in the direction away from the maximum point after the integration processing in the map When the detection accuracy value is viewed from the local maximum point along the line, before the position at which the detection accuracy value is less than (1 / Z) times the detection accuracy value at the local maximum point appears. The change of the detection accuracy value is monotonous If it is determined that no longer small, the position determination with the change is no longer monotonically decreases, the process of the end of the predetermined area to determine said a detection target image, the order is executed in the step (e) Is.

An aspect of the image detection method according to the present invention is an image detection method for detecting a detection target image from a processing target image, wherein: (a) a plurality of detection frames whose positions are different from each other with respect to the processing target image; Setting, for each of the plurality of detection frames, a step of performing detection processing of the detection target image on an image in the detection frame, and (b) based on the detection result in the step (a), generating a map showing the distribution in the processing target image of detection accuracy value indicating the likelihood of a detection target image, a step of searching a maximum point of the detection accuracy value in (c) the map, ( d) performing an integration process of integrating a plurality of local maximum points close to each other in the map based on a predetermined criterion; and ( e ) the same as the local maximum point after the integration process in the processing target image. A predetermined region including a pixel at the same position is determined as the detection target image, and in the step (e), in the map, the local maximum along the direction away from the local maximum after the integration process. When the detection accuracy value is viewed from a point, the detection accuracy value is initially (1 / Z) times or less (Z> 1) with respect to the detection accuracy value at the local maximum point; The position in the same processing target image is set as an end of the predetermined region that is determined to be the detection target image, and the detection is performed from the local maximum point along the direction away from the local maximum point after the integration processing in the map. When looking at the accuracy value, the detection accuracy value changes before the position where the detection accuracy value becomes (1 / Z) times or less than the detection accuracy value at the maximum point appears. If it is determined that the monotonic decrease is no longer The position is determined to no longer monotonically decreases and the end of the predetermined area to determine that the to be detected image.

  According to the present invention, it is possible to improve detection accuracy for a detection target image.

It is a figure which shows the structure of an image detection apparatus. It is a figure which shows the structure of the several functional block with which an image detection apparatus is provided. It is a figure which shows the structure of a detection part. It is a figure for demonstrating operation | movement of a detection part. It is a figure for demonstrating operation | movement of a detection part. It is a figure for demonstrating operation | movement of a detection part. It is a figure for demonstrating operation | movement of a detection part. It is a figure for demonstrating operation | movement of a detection part. It is a figure for demonstrating operation | movement of a detection part. It is a figure which overlaps and shows a detection result frame on a process target image. It is a figure for demonstrating the production | generation method of an output value map. It is a figure for demonstrating the production | generation method of an output value map. It is a figure which shows an output value map. It is a figure for demonstrating the search method of a local maximum point. It is a figure for demonstrating the search method of a local maximum point. It is a figure which shows distribution of the detection accuracy value vicinity of the maximum point in an output value map. It is a figure for demonstrating the determination method of a detection image area | region. It is a flowchart which shows operation | movement of a detection target image determination part. It is a figure which overlaps and shows a detection image area | region and the detection result frame after integration on a process target image.

  FIG. 1 is a diagram illustrating a configuration of an image detection apparatus 1 according to an embodiment. The image detection apparatus 1 according to the present embodiment detects a detection target image from an image indicated by input image data. The image detection apparatus 1 is used, for example, in a surveillance camera system, a digital camera system, or the like. In the present embodiment, the detection target image is, for example, a human face image. Hereinafter, simply speaking “face image” means a human face image. An image to be subjected to detection processing of a detection target image is referred to as a “processing target image”. The detection target image in the image detection apparatus 1 may be an image other than a face image.

  As shown in FIG. 1, the image detection apparatus 1 includes a CPU (Central Processing Unit) 10 and a storage unit 11. The storage unit 11 includes a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. The storage unit 11 stores a control program 12 for controlling the operation of the image detection apparatus 1 and the like. Various functions of the image detection apparatus 1 are realized by the CPU 10 executing the control program 12 in the storage unit 11. In the image detection apparatus 1, a plurality of functional blocks as shown in FIG. 2 are formed by executing the control program 12.

  As shown in FIG. 2, the image detection apparatus 1 includes an image input unit 2, a detection unit 3, a map generation unit 4, a maximum point search unit 5, and a detection target image determination unit 6 as functional blocks. I have. Hereinafter, after describing the schematic operation of each functional block included in the image detection apparatus 1, the detailed operation of each functional block will be described. Note that each functional block included in the image detection apparatus 1 may be realized by a hardware circuit.

<Overview of operation of image detection apparatus>
The image input unit 2 is sequentially input with a plurality of image data respectively indicating a plurality of images sequentially captured by an imaging unit (camera) included in the surveillance camera system or the like. The image input unit 2 outputs image data indicating the processing target image. The image input unit 2 may use each image obtained by the imaging unit as a processing target image, or may use an image obtained every few seconds among images obtained by the imaging unit as a processing target image. In the imaging unit, for example, L (L ≧ 2) images are captured per second. That is, the imaging frame rate at the imaging unit is Lfps (frame per second). In the image captured by the imaging unit, M (M ≧ 2) pixels are arranged in the row direction, and N (N ≧ 2) pixels are arranged in the column direction. The resolution of the image picked up by the image pickup unit is, for example, VGA (Video Graphics Array), and M = 640 and N = 480.

  Hereinafter, the size of an area in which m (m ≧ 1) pixels are arranged in the row direction and n (n ≧ 1) pixels are arranged in the column direction is represented by mp × np (p is a meaning of a pixel). In addition, among a plurality of values arranged in a matrix, a value located in the m-th row and the n-th column with reference to the upper left may be referred to as an m × n-th value.

  The detection unit 3 uses the image data output from the image input unit 2 to detect a face image for the processing target image. The map generation unit 4 generates an output value map indicating the distribution in the processing target image with respect to the detection accuracy value indicating the likelihood as the face image based on the detection result of the detection unit 3. The maximum point search unit 5 searches for a maximum point of the detection accuracy value in the output value map generated by the map generation unit 4. The detection target image determination unit 6 determines that a predetermined area including a pixel at the same position as the maximum point obtained by the maximum point search unit 5 in the processing target image is a face image. As a result, the image detection apparatus 1 detects a face image from the processing target image.

<Detailed operation description of image detection apparatus>
<Face detection processing>
The detection unit 3 detects a face image for a partial image within the detection frame while moving the detection frame with respect to the processed image. In other words, the detection unit 3 sets a plurality of detection frames whose positions are different from each other with respect to the processing target image, and for each of the plurality of detection frames, a face image detection process is performed on a partial image in the detection frame. I do.

  In this embodiment, in order to detect face images of various sizes in the processing target image, the detection unit 3 uses a plurality of types of detection frames having different sizes. Hereinafter, among the plurality of types of detection frames, the detection frame having the smallest size may be referred to as a “reference detection frame”, and other types of detection frames may be referred to as “non-reference detection frames”. In the present embodiment, the plurality of types of detection frames include a plurality of types of non-reference detection frames having different sizes. The size of the reference detection frame is, for example, 16p × 16p. The plurality of types of non-reference detection frames include, for example, a non-reference detection frame having a size of 18p × 18p and a non-reference detection frame having a size of 20p × 20p.

  FIG. 3 is a diagram illustrating a configuration of the detection unit 3. As illustrated in FIG. 3, the detection unit 3 includes a detection frame setting unit 30, a feature amount extraction unit 31, a discriminator 32, and a determination unit 33.

  The detection frame setting unit 30 sets a detection frame for the processing target image. The feature amount extraction unit 31 extracts feature amounts such as Haar-like feature amounts and LBP (Local Binary Pattern) feature amounts from the partial images within the detection frame set by the detection frame setting unit 30 in the processing target image. To do. The discriminator 32 performs face detection on the partial image within the set detection frame based on the feature amount extracted by the feature amount extraction unit 31 and the learning data, and as a result, the partial image is a face image. A detection accuracy value indicating a certain probability is output as a real value. That is, it can be said that the detection accuracy value output from the discriminator 32 indicates the likelihood of a face image (the likelihood of a face) for a partial image within the detection frame. As the discriminator 32, for example, SVM (Support Vector Machine) or Adaboost is used.

  If the detection accuracy value output from the discriminator 22 is greater than or equal to the threshold value, the determination unit 33 determines that there is a high possibility that the partial image in the detection frame is a face image. On the other hand, if the detection accuracy value output from the discriminator 22 is less than the threshold, the determination unit 33 determines that there is a high possibility that the partial image in the detection frame is not a face image. Hereinafter, the detection frame in which the determination unit 33 determines that the partial image in the detection frame is likely to be a face image, that is, the detection frame in which the face image is detected is referred to as a “detection result frame”. .

  Next, a series of operations of the detection unit 3 when the detection unit 3 detects a face image for a partial image in the detection frame while moving the detection frame with respect to the processing target image will be described. 4-7 is a figure for demonstrating the said operation | movement of the detection part 3. FIG. The detection unit 3 detects a face image for a partial image in the detection frame while performing raster scanning of the detection frame.

  As shown in FIG. 4, the detection frame setting unit 30 first sets the detection frame 100 at the upper left of the processing target image 20. Thereafter, the feature amount extraction unit 31 extracts a feature amount from the partial image in the upper left detection frame 100. Then, the classifier 32 obtains a detection accuracy value for the partial image in the detection frame 100 based on the feature amount extracted by the feature amount extraction unit 31 and the learning data. When the detection accuracy value obtained by the discriminator 32 is equal to or greater than the threshold value, the determination unit 33 determines that the partial image in the detection frame 100 is likely to be a face image and determines the detection frame 100. Is a detection result frame.

  Next, the detection frame setting unit 30 moves the detection frame 100 slightly to the right in the processing target image 20 to set a new detection frame 100 for the processing target image 20. For example, the detection frame setting unit 30 moves the detection frame 100 to the right by one pixel or several pixels. Thereafter, the feature amount extraction unit 31 extracts a feature amount from the newly set partial image in the detection frame 100, and the discriminator 32 newly sets the detection frame 100 based on the feature amount and the learning data. A detection accuracy value for the partial image is obtained. The determination unit 33 determines that there is a high possibility that the newly set partial image in the detection frame 100 is a face image when the detection accuracy value obtained by the classifier 32 is equal to or greater than the threshold value. Thus, the newly set detection frame 100 is set as a detection result frame.

  Thereafter, the detection unit 3 operates in the same manner, and as illustrated in FIG. 5, when the detection frame 100 moves to the right end of the processing target image, the detection unit 3 detects the partial image in the detection frame 100 at the right end. Find the accuracy value. And the detection part 3 will make the detection frame 100 of a right end into a detection result frame, if the calculated | required detection accuracy value is more than a threshold value.

  Next, as shown in FIG. 6, the detection frame setting unit 30 moves the detection frame 100 to the left end of the processing target image 20 while slightly lowering the detection frame 100, and sets a new detection frame 100 for the processing target image 20. To do. The detection frame setting unit 30 moves the detection frame 100 downward by, for example, one pixel or several pixels in the vertical direction (column direction). Thereafter, the feature amount extraction unit 31 extracts a feature amount from the newly set partial image in the detection frame 100, and the discriminator 32 newly sets the detection frame 100 based on the feature amount and the learning data. The detection accuracy value for the partial image is obtained and output. When the detection accuracy value output from the discriminator 32 is greater than or equal to the threshold value, the determination unit 33 determines that there is a high possibility that the newly set partial image within the detection frame 100 is a face image. Thus, the newly set detection frame 100 is set as a detection result frame.

  Thereafter, the detection unit 3 operates in the same manner, and as shown in FIG. 7, when the detection frame 100 moves to the lower right of the processing target image 20, the detection unit 3 moves to the lower right part of the detection frame 100. A detection accuracy value for the image is obtained. And the detection part 3 will make the detection frame 100 of a right end into a detection result frame, if the calculated | required detection accuracy value is more than a threshold value.

  The detection unit 3 performs the face detection process as described above using each of a plurality of types of detection frames having different sizes. In the present embodiment, when using the reference detection frame, the detection unit 3 moves the reference detection frame with respect to the processing target image as described above, while moving the reference detection frame with respect to the partial image in the reference detection frame. To detect face images. Then, the detection unit 3 performs at least one detection result frame obtained as a result of detecting the face image on the partial image in the reference detection frame while performing raster scanning of the reference detection frame on the processing target image. And stored as a face detection result using the reference detection frame.

  On the other hand, when using the non-reference detection frame, the detection unit 3 does not use the non-reference detection frame as it is, but the size of the non-reference detection frame matches the size of the reference detection frame. Thus, the non-reference detection frame is reduced and used. Then, the detection unit 3 uses the processing target image by reducing the non-reference detection frame.

  For example, when using a non-reference detection frame having a size of Rp × Rp (R> 16), the detection unit 3 has a width in the vertical direction (column direction) and a horizontal direction (row direction) of the non-reference detection frame. ) Are respectively multiplied by (16 / R) to reduce the non-reference detection frame. Hereinafter, the non-reference detection frame reduced in this way is referred to as a “reduced non-reference detection frame”. The detection unit 3 reduces the processing target image by multiplying the vertical width (number of pixels) and the horizontal width (number of pixels) of the processing target image by (16 / R), respectively. Hereinafter, the processing target image thus reduced is referred to as a “reduction processing target image”. Then, the detection unit 3 moves the reduced non-reference detection frame with respect to the reduction target image while moving the reduced non-reference detection frame with respect to the reduction processing target image, as in the face detection process described with reference to FIGS. The face image is detected for the partial image. Thereafter, the detection result frame corresponding to the reduction target image obtained as a result of the face image detection process using the reduced non-reference detection frame, that is, the partial image in the reduced non-reference detection frame is a face image. The reduced non-reference detection frame determined to have a high possibility is particularly referred to as a “reduction detection result frame”.

  The detection unit 3 performs face image detection processing on the reduction target image using the reduced non-reference detection frame, and as a result, when at least one reduced detection result frame is obtained, the at least one reduced detection result is obtained. The frame is converted into a detection result frame corresponding to the processing target image.

  Specifically, the detection unit 3 first sets at least one obtained reduction detection result frame for the reduction processing target image. FIG. 8 is a diagram illustrating a state in which a reduction detection result frame 130 is set for the reduction processing target image 120. In the example of FIG. 8, a plurality of reduction detection result frames 130 are set for the reduction processing target image 120.

  Next, the detection unit 3 converts the reduction processing target image 120 into the processing target image 20 as shown in FIG. 9 by enlarging the reduction processing target image 120 in which the reduction detection result frame 130 is set. As a result, the reduction detection result frame 130 set in the reduction processing target image 120 is also enlarged, and the reduction detection result frame 130 is converted into a detection result frame 150 corresponding to the processing target image 20, as shown in FIG. Is done. The detection unit 3 stores the detection result frame 150 thus obtained for each non-reference detection frame as a face detection result using the non-reference detection frame.

  As described above, when the detection unit 3 performs face detection using each of a plurality of types of detection frames, the detection unit 3 performs a plurality of detection frames corresponding to the detection frames for each of the plurality of types of detection frames. A detection accuracy value is obtained. The detection unit 3 obtains at least one detection result frame for one type of detection frame as the face detection result.

  FIG. 10 is a diagram showing a plurality of detection result frames 150 obtained by performing face image detection processing on a certain processing target image 20 using a plurality of types of detection frames, overlaid on the processing target image 20. is there. As shown in FIG. 10, detection result frames 150 of various sizes are obtained by performing face image detection processing using a plurality of types of detection frames. This means that face images of various sizes included in the processing target image 20 are detected. As shown in FIG. 10, when the obtained detection result frame 150 is superimposed on the processing target image 20, a plurality of detection result frames 150 are concentrated in the vicinity of one face image. That is, a plurality of detection result frames 150 are obtained for one face image.

<Output value map generation processing>
As described above, it is possible to detect a face image from the processing target image by performing the face detection process using the detection frame.

  However, as shown in FIG. 10, since a plurality of detection result frames 150 are obtained for one face image, it is difficult to specify the number of face images included in the processing target image. Further, when the processing target image 20 with the detection result frames 150 superimposed thereon is displayed on the display device as shown in FIG. 10, the face image included in the processing target images 20 may be hidden by the plurality of detection result frames 150. And it is difficult to identify the face image.

  Therefore, an integrated detection result frame is generated by integrating a plurality of detection result frames 150 concentrated near the face image into one detection result frame, and one integrated detection result frame corresponds to one face image. Is desirable.

  On the other hand, if the plurality of detection result frames 150 are not properly integrated, the face image does not fit properly in the integrated detection result frame, and as a result, the detection accuracy of the face image may be lowered.

  In the present embodiment, the output value map generated by the map generation unit 4 is used to identify a region that is a face image in the processing target image, and the outline frame of the region is used as an integrated detection result frame, thereby improving accuracy. A good integrated detection result frame, that is, an integrated detection result frame in which a face image is appropriately contained inside is generated.

  Here, a method for generating an output value map will be described.

  The map generation unit 4 generates an output value map indicating the distribution in the processing target image with respect to the detection accuracy value indicating the likelihood (face image likelihood) as the face image based on the detection result of the detection unit 3.

  Specifically, the map generation unit 4 is a map composed of a total of (M × N) values in which M values are arranged in the row direction and N values are arranged in the column direction, similarly to the processing target image. Think about 200. Then, the map generation unit 4 sets one detection result frame included in at least one detection result frame obtained as a face detection result using the reference detection frame as a target detection result frame, and is located at the same position as the target detection result frame. A frame 210 having the same size as the target detection result frame is set for the map 200. FIG. 11 is a diagram illustrating a state in which a frame 210 is set for the map 200.

  Next, the map generation unit 4 sets “0” for each value outside the frame 210 in the map 200, and for each value within the frame 210, a detection accuracy value corresponding to the target detection result frame (the target detection result frame and The detection accuracy value obtained as a result of performing the face image detection process on the partial image within the detection frame is determined. In the present embodiment, since the size of the reference detection frame is 16p × 16p, there are a total of 256 values in the frame 210, 16 in the row direction and 16 in the column direction. FIG. 12 is a diagram for explaining a method for determining each value in the frame 210.

  The map generation unit 4 sets the value of the center 211 in the frame 210 as the detection accuracy value corresponding to the target detection result frame obtained by the detection unit 3. Then, the map generation unit 4 gradually increases the values of the other values in the frame 210 from the center 211 in the frame 210 to the outside according to a normal distribution curve with the value at the center 211 of the frame 210 as the maximum value. To be smaller. Thereby, each of a plurality of values constituting the map 200 is determined, and the map 200 corresponding to the target detection result frame is completed. The map generation unit 4 generates at least one map 200 corresponding to each of at least one detection result frame obtained as a face detection result using the reference detection frame. As a result, the map generation unit 4 generates at least one map 200 corresponding to the reference detection frame.

  Similarly to the above, the map generation unit 4 at least corresponds to at least one detection result frame obtained as a face detection result using the non-reference detection frame for each of a plurality of types of non-reference detection frames. One map 200 is generated. Here, assuming that the size of at least one detection result frame obtained as a face detection result using the non-reference detection frame is, for example, 18p × 18p, there are 18 columns in the frame 210 in the row direction. There are 18 values in the direction, a total of 324 values. Also, assuming that the size of at least one detection result frame obtained as a face detection result using a non-reference detection frame is, for example, 20p × 20p, there are 20 in the frame 210 in the row direction and in the column direction. There are 20 values in total, for a total of 400 values.

  As described above, when at least one map 200 corresponding to each detection frame is generated for each of a plurality of types of detection frames, the map generation unit 4 combines these maps 200 to generate an output value map. Generate. Specifically, the map generation unit 4 adds the m × n-th values of the plurality of generated maps 200, and uses the obtained addition value as the m × n-th detection accuracy value of the output value map. . In this way, the map generation unit 4 obtains each detection accuracy value constituting the output value map. Thereby, an output value map indicating the distribution of detection accuracy values in the processing target image is completed. By referring to the output value map, it is possible to specify a region having a high likelihood of a face image in the processing target image. That is, the face image included in the processing target image can be specified by referring to the output value map.

  FIG. 13 is a diagram showing an output value map for the processing target image 20 shown in FIG. In FIG. 13, for easy understanding, the output value map is shown by dividing the magnitude of the detection accuracy value into, for example, five stages from the first stage to the fifth stage. In the output value map shown in FIG. 13, vertical line hatching is shown for the area belonging to the fifth stage where the detection accuracy value is the largest, and sand area is shown for the area belonging to the second largest fourth stage. Hatching is shown. Further, in the output value map in FIG. 13, the area belonging to the third stage where the detection accuracy value is the third largest shows hatching upward to the right, and the area belonging to the fourth largest second stage. Indicates a hatching that goes up to the left. In the output value map shown in FIG. 13, hatching is not shown for the region belonging to the first stage having the smallest detection accuracy value.

  Referring to FIG. 13, it can be understood that in the output value map, the detection accuracy value in the region corresponding to each face image included in the processing target image 20 is high.

<Maximum point search processing>
As shown in FIG. 13, in the output value map, there is a high possibility that the detection accuracy value in the region corresponding to the face image in the processing target image is large. Then, looking at the output value map from a micro viewpoint, in the output value map, the detection accuracy value in the region corresponding to the face image in the processing target image is the same as the center position of the face image. There is a high possibility that the detection accuracy value will be the largest. Therefore, the center position of the face image can be specified by searching for the maximum point of the detection accuracy value in the output value map. Then, by determining that a predetermined area including a pixel at the same position as the identified maximum point (corresponding to the center position of the face image) in the processing target image is a face image, the face image in the processing target image is accurately Can be specified. Therefore, an accurate integrated detection result frame can be obtained by using the outer frame of the predetermined area as the integrated detection result frame.

  Here, a method for searching for the maximum point of the detection accuracy value in the output value map will be described. In the present embodiment, the maximum point search unit 5 searches for the maximum point of the detection accuracy value in the output value map using, for example, the Mean-Shift method. The operation of the maximum point search unit 5 will be described in detail below. Hereinafter, simply speaking, “maximum point” means “maximum point of detection accuracy value in output value map”.

  In the output value map arranged in the two-dimensional coordinates, the local maximum point search unit 5 uses the detection accuracy value as a weighting factor, and coordinates values for a plurality of positions each having a plurality of detection accuracy values included in the processing target region. The maximum point is searched by repeating the process of moving the processing target region so that the center position of the processing target region becomes the weighted average value. In the present embodiment, the maximum points are obtained by the same number as the number of the plurality of detection result frames 150 obtained as a result of the face image detection process performed by the detection unit 3 using a plurality of types of detection frames.

  FIG. 14 is a diagram for explaining a search method for local maximum points. In FIG. 14, an output value map 300 is arranged at XY coordinates that are two-dimensional coordinates. In the present embodiment, for example, the upper left of the output value map 300 is the origin O of the XY coordinates, the row direction is the X axis direction, and the column direction is the Y axis direction. The shape of the processing target area 400 that is moved when searching for the maximum value is, for example, circular.

  The local maximum point search unit 5 performs target detection on one detection result frame 150 among the plurality of detection result frames 150 obtained as a result of the detection unit 3 performing face image detection processing using a plurality of types of detection frames. Let it be a result frame 150a.

  Next, the local maximum point search unit 5 determines the movement start position of the processing target area 400 to be moved on the output value map 300. Here, since the partial image in the detection result frame 150 in the processing target image is highly likely to be a face image, the center of the face image in the processing target image is likely to exist in the detection result frame 150. Therefore, in the output value map 300, there is a high possibility that a local maximum point exists in the region at the same position as the target detection result frame 150a. In particular, in the present embodiment, when the above-described map 200 used for generating the output value map 300 is completed, the value of the center 211 in the frame 210 is used as the detection accuracy value. Is likely to have a local maximum near the same position as the center position in the object detection result frame 150a.

  Therefore, as illustrated in FIG. 14, the local maximum point search unit 5 uses a predetermined position in the target detection result frame 150 a, for example, a position 410 in the output value map 300 that is the same as the center position, as the center position of the processing target region 400. The initial position. That is, when starting the search for the maximum point, the local maximum point search unit 5 sets the processing target region 400 so that the center position of the processing target region 400 is the same as the central position in the target detection result frame 150a. 400 is placed in the output value map 300. Thereby, the local maximum point can be searched immediately.

  Note that the size of the processing target area 400 is, for example, such that 50 to 60 detection accuracy values are arranged along the radial direction from the center in the processing target area 400 arranged on the output value map 300. It is a size.

  Next, the maximal point search unit 5 uses the detection accuracy value as a weighting factor in the output value map 300 arranged in the XY coordinates, and a plurality of positions where a plurality of detection accuracy values included in the processing target region 400 exist. A weighted average value (XM, YM) of coordinate values is calculated. The maximum point search unit 5 calculates a weighted average value (XM, YM) using the following equation (1).

  Here, J in Expression (1) indicates the number of a plurality of detection accuracy values existing in the processing target area 400. In addition, i indicates a number assigned to each of a plurality of detection accuracy values in the processing target area 400. And vi means the i-th detection accuracy value, and (Xi, Yi) is the XY coordinate value for the position where the i-th detection accuracy value exists in the output value map 300 arranged in the XY coordinates. Is shown.

  When the maximum point search unit 5 obtains the weighted average value (XM, YM), the processing target region 400 is moved so that the XY coordinates of the center position of the processing target region 400 become the weighted average value (XM, YM). . The arrows in FIG. 14 indicate how the processing target area 400 moves.

  Next, the local maximum point search unit 5 determines whether the moving distance (shift amount) of the processing target area 400 is less than a threshold value. The movement distance of the processing target area 400 is obtained by calculating the distance between the center position of the processing target area 400 before the movement and the center position of the processing target area 400 after the movement. When the local maximum point search unit 5 determines that the movement distance of the processing target area 400 is equal to or greater than the threshold value, the local maximum point searching unit 5 has a plurality of detection accuracy values included in the processing target area 400 after the movement. A weighted average value (XM, YM) of coordinate values is calculated using equation (1). Then, the local maximum point search unit 5 further moves the processing target region 400 so that the XY coordinates of the center position of the processing target region 400 become the newly obtained weighted average value (XM, YM).

  On the other hand, when the local maximum point search unit 5 determines that the movement amount of the processing target region 400 is less than the threshold value, the local maximum point searching unit 5 determines that the movement amount of the processing target region 400 has converged, and moves the processing target region 400. finish. Then, the local maximum point search unit 5 sets the current center position of the processing target region 400 as the local maximum point. From this, the local maximum point in the vicinity of the position of the target detection result frame 150 is obtained.

  The local maximum point search unit 5 is located near the position of the detection result frame 150 for each of the plurality of detection result frames 150 obtained as a result of the detection unit 3 performing face image detection processing using a plurality of types of detection frames. Find the local maximum in the same way.

  In addition, when calculating the weighted average value (XM, YM), the maximum point search unit 5 may use the output value map 300 from which the detection accuracy value is thinned out. In other words, when calculating the weighted average value (XM, YM), the local maximum point search unit 5 does not have to use all of the plurality of detection accuracy values included in the processing target area 400 in the output value map 300. good.

  FIG. 15 is a diagram illustrating an example of an output value map 300 in which detection accuracy values are thinned out. In the example of FIG. 15, the output value map 300 is latticed by a plurality of dividing lines 500 arranged at equal intervals in the row direction (X-axis direction) and a plurality of dividing lines 510 arranged at equal intervals in the column direction (Y-axis direction). It is divided into shapes. In the output value map 300, detection accuracy values other than the detection accuracy values existing at the grid intersections (intersections of the dividing lines 500 and 510) are deleted. Thereby, in the output value map 300, (P-1) pieces of detection accuracy values are thinned out every P (P ≧ 2) in the column direction, and every Q pieces (Q ≧ 2) in the row direction ( Q-1) Thinned out. The circles in FIG. 15 indicate the detection accuracy values existing in the output value map 300 from which the detection accuracy values are thinned out.

  In the output value map 300 shown in FIG. 15, as in the output value map in FIG. 13, the magnitude of the detection accuracy value is divided into, for example, five stages from the first stage to the fifth stage to indicate each detection accuracy value. Has been. In the output value map 300 in FIG. 15, a circle indicating a detection accuracy value belonging to the fifth highest stage is indicated by a horizontal line hatching, and a circle indicating a detection accuracy value belonging to the second highest fourth stage. The mark shows vertical hatching. In addition, in the output value map 300 in FIG. 15, the circle indicating the detection accuracy value belonging to the third largest third stage indicates a right-up hatching, and the detection belonging to the fourth largest second stage. The circle indicating the accuracy value indicates a left-upward hatching. In the output value map 300 shown in FIG. 15, the circle indicating the detection accuracy value belonging to the smallest first stage is not hatched.

  When calculating the weighted average value (XM, YM), the maximum point search unit 5 uses the output value map 300 in which the detection accuracy value is thinned as shown in FIG. In the map 300, the XY coordinate values and the plurality of detection accuracy values for a plurality of positions where the plurality of detection accuracy values included in the processing target area 400 respectively exist are substituted into the above equation (1). This reduces the number of detection accuracy values used when calculating the weighted average value (XM, YM). Furthermore, the number of times of calculating the weighted average value (XM, YM) required until the movement amount of the processing target area 400 converges is also reduced. Therefore, the processing load for searching for the maximum point is reduced.

<Maximum point integration processing>
As can be understood from the above description, the maximum point search unit 5 may require a plurality of maximum points having different positions. In the output value map, a plurality of local maximum points located close to each other is likely to indicate the center of the same face image. On the other hand, there is a high possibility that the plurality of local maximum points located apart from each other indicate the centers of different face images.

  Therefore, the detection target image determination unit 6 uses the local maximum point obtained by the local maximum point search unit 5 to specify a region that is a face image in the processing target image. A plurality of local maximum points located close to each other are integrated into one local maximum point. Hereinafter, an example of a method for integrating a plurality of local maximum points located close to each other will be described.

  Similar to the case where the detection unit 3 moves the detection frame from the upper left to the lower right of the processing target image during the face detection process, the detection target image determination unit 6 looks at the output value map from the upper left to the lower right ( When the local maximum obtained by the local maximum searching unit 5 appears, the distance between the reference point and the next maximum local point is determined with the local maximum as a reference point. Then, if the obtained distance is less than the threshold value, the detection target image determination unit 6 leaves the reference point and deletes the maximum point that appears later. On the other hand, if the obtained distance is equal to or greater than the threshold value, the detection target image determination unit 6 leaves the current reference point and sets the maximum point that appears later as a new reference point.

  The threshold value used in the integration of local maximum points is determined according to how large a face image should be detected. For example, when this image detection apparatus 1 is used in a surveillance camera system and an area relatively close to the camera is monitored, a relatively large face image is detected. A large value is used. In addition, when the image detection apparatus 1 is used in a surveillance camera system and an area relatively far from the camera is monitored, a relatively small face image is detected. A small value is used. In this example, the threshold value is set to a distance of 5 pixels in the processing target image, for example. The threshold value is preferably adjustable (rewritable) by the user.

  If the obtained distance is less than the threshold value, the detection target image determination unit 6 leaves the current reference point, deletes the maximum point that appears later, and then deletes the current reference point and the next maximum point after the deletion. The threshold value is compared with the distance between the local maximum points appearing in. Further, when the obtained distance is equal to or greater than the threshold value and the maximum point that appears later is set as a new reference point, the detection target image determination unit 6 sets the maximum point that appears next to the new reference point and the new reference point. The distance between the points is compared with the threshold value.

  Thereafter, the detection target image determination unit 6 operates in the same manner, and when the distance between the maximum point that appears last and the reference point is less than the threshold value, the maximum point that appears last is deleted, and the maximum point is deleted. This completes the integration process. On the other hand, when the distance between the maximum point that appears last and the reference point is equal to or greater than the threshold value, the detection target image determination unit 6 does not delete the maximum point that appears last, and integrates the maximum points. Exit. The detection target image determination unit 6 specifies an area that is a face image in the processing target image using at least one local maximum point remaining after the local maximum point integration process is completed.

  In the above example, if the distance between the reference point and the maximum point that appears later is less than the threshold value, only the reference point is left among the reference point and the maximum point that appears later. Of the local maximum points that appear later, only the local maximum point with the larger detection accuracy value at that position may be left. Accordingly, there is a high possibility that the maximal point remaining after the maximal point integration process ends indicates the center position of the face image.

<Face image determination process>
When the integration process of local maximum points is completed, the detection target image determination unit 6 applies a predetermined region including a pixel at the same position as the local maximum point in the processing target image for each remaining local maximum point after that. It is determined that Then, the detection target image determination unit 6 sets the outline frame of the predetermined area determined to be a face image as a post-integration detection result frame. Hereinafter, the predetermined area determined to be a face image is referred to as a “detected image area”. In addition, the maximum point to be described may be referred to as “target maximum point”.

  Here, in the region corresponding to the face image in the output value map, the detection accuracy value at the same position as the center position of the face image increases, and the detection accuracy value may decrease as the distance from the same position increases. high. In the output value map, there is a high possibility that the detection accuracy value is zero or very small in an area other than the area corresponding to the face image. Therefore, in the output value map, there is a high possibility that the detection accuracy value becomes smaller from the maximum point corresponding to the center position of a certain face image toward the position corresponding to the end of the face image. In other words, in the output value map, there is a high possibility that the detection accuracy value monotonously decreases from the maximum point corresponding to the center position of a certain face image toward the position corresponding to the end of the face image.

  FIG. 16 is a graph showing an example of the distribution of detection accuracy values near the target maximum point 700 in the output value map. FIG. 16 shows a distribution of detection accuracy values in the left-right direction with the target maximum point 700 as the center. In FIG. 16, the vertical axis indicates the detection accuracy value, and the horizontal axis indicates the position in the left-right direction on the output value map 300. As shown in FIG. 16, the detection accuracy value decreases from the target maximum point 700 in the right direction DR1 (monotonically decreases). Further, the detection accuracy value decreases from the target maximum point 700 in the left direction DR2 (monotonically decreases).

  In the present embodiment, in view of such points, the detection target image determination unit 6 looks at the detection accuracy value from the target maximum point 700 along the direction away from the target maximum point 700 in the output value map. In this case, the position in the processing target image is the same as the position where the detection accuracy value first becomes (1 / Z) times or less (Z> 1) with respect to the detection accuracy value at the target maximum point 700. By defining the edge, the edge of the face image is specified. Thereby, the edge of the face image included in the processing target image can be accurately specified.

  In addition, when a plurality of face images are in contact with each other in a processing target image because a plurality of faces exist in front and back in the imaging area of the imaging unit, the target maximum is along a direction away from the target maximum point 700. When the detection accuracy value is viewed from the point 700, before the position where the detection accuracy value is (1 / Z) times or less than the detection accuracy value at the target maximum point 700 appears, the detection accuracy value The change may not be monotonous. In such a case, there is a high possibility that the position in the processing target image that is the same as the position where the change in the detection accuracy value is not monotonously decreased is the end of the face image.

  Therefore, when the detection target image determination unit 6 looks at the detection accuracy value from the target maximum point 700 along the direction away from the target maximum point 700 in the output value map 300, the detection accuracy value is the target maximum point. If it is determined that the change in the detection accuracy value is no longer monotonically decreasing before a position that is less than (1 / Z) times the detection accuracy value in 700, the position that is determined that the change is no longer monotonically decreasing The position in the same processing target image is the end of the detected image area. Thereby, even when a plurality of face images are in contact with each other, each of the plurality of face images can be specified individually. The operation of the detection target image determination unit 6 will be described in detail below.

  FIG. 17 is a diagram for explaining a method of determining a detection image region 600 (hereinafter, referred to as “target detection image region 600”) including a pixel at the same position as the target maximum point 700 in the processing target image. In FIG. 17, the output value map 300 is shown enlarged. In FIG. 17, the outline frame 600 a of the target detection image region 600 is shown superimposed on the output value map 300.

  In the present embodiment, the shape of the detected image area is set to, for example, a quadrangle. The detection target image determination unit 6 determines the detection image region by determining the right end, left end, upper end, and lower end of the square detection image region.

  First, the operation of the detection target image determination unit 6 when the detection target image determination unit 6 determines the right end 610 of the target detection image region 600 will be described. FIG. 18 is a flowchart showing the operation.

  As shown in FIG. 17, the detection target image determination unit 6 looks at the detection accuracy value 800 (indicated by a circle) from the target maximum point 700 along the right direction DR1 in the output value map 300. Then, the two detection accuracy values 800 are compared before and after changing the pair, and the right end 610 of the target detection image region 600 is determined based on the comparison result. At this time, the detection target image determination unit 6 may view the detection accuracy values 800 one by one, every other one, or every other plurality. In this example, it is assumed that the detection target image determination unit 6 looks at the detection accuracy values 800 one by one.

  More specifically, as shown in FIG. 18, the detection target image determination unit 6 sets the detection accuracy value 800 at the target maximum point 700 (the detection accuracy value 800a shown in FIG. 17) to the first in step s1. And the detection accuracy value 800 on the right side thereof is set as the second accuracy value v2. In step s2, the detection target image determination unit 6 obtains (v1-v2) and compares the first accuracy value v1 and the second accuracy value v2.

  Next, in step s3, the detection target image determination unit 6 determines whether the comparison result between v1 and v2 is (v1-v2) <0. If the detection target image determination unit 6 determines that (v1−v2) <0 is not satisfied, the detection target image determination unit 6 determines that the detection accuracy value 800 is monotonously decreasing and executes step s4. In step s4, the detection target image determination unit 6 determines whether the second accuracy value v2 is equal to or less than (1 / Z) times the detection accuracy value 800 at the target maximum point 700. For Z, for example, 3 ≦ Z ≦ 5 is set. When the detection target image determination unit 6 determines that the second accuracy value v2 is equal to or less than (1 / Z) times the detection accuracy value 800a at the target maximum point 700, the output value map 300 in step s5. The position in the processing target image that is the same as the position 710 (see FIGS. 16 and 17) where the accuracy value v2 of 2 exists is the right end 610 of the target detection image area 600. This position 710 indicates that when the detection accuracy value 800 is viewed along the right direction DR1 from the target maximum point 700 in the output value map 300, the detection accuracy value 800 becomes the detection accuracy value 800a at the target maximum point 700. First, it is a position that becomes (1 / Z) times or less.

  On the other hand, in step s4, when the detection target image determination unit 6 determines that the second accuracy value v2 is not less than (1 / Z) times the detection accuracy value 800a at the target maximum point 700, in step s1, The current second accuracy value v2 is set as a new first accuracy value v1, and the detection accuracy value 800 on the right side thereof is set as a new second accuracy value v2. Thereafter, the detection target image determination unit 6 operates in the same manner.

  In step s3, if the detection target image determination unit 6 determines that the comparison result between v1 and v2 is (v1-v2) <0, step s6 is executed. In step s6, the detection target image determination unit 6 determines whether the comparison result of (v1-v2) <0 has been generated a predetermined number of times C (C ≧ 2) including the current comparison result. That is, when the detection target image determination unit 6 compares the two detection accuracy values 800 before and after changing the pair along the right direction DR1 from the target maximum point 700 in the output value map 300, the previous detection is performed. It is determined whether a comparison result that the accuracy value 800 is smaller than the subsequent detection accuracy value 800 has occurred a predetermined number of times C continuously. The predetermined number of times C is set to C = 2, for example.

  In step s6, when the detection target image determination unit 6 determines that the comparison result of (v1-v2) <0 has continuously occurred a predetermined number of times C, the detection accuracy value is the detection accuracy value at the target maximum point 700. Before a position that is less than (1 / Z) times appears, it is determined that the change in the detection accuracy value is no longer monotonically decreasing, and step s5 is executed, so that the current second accuracy value v2 exists. The position in the processing target image that is the same as the position 710 to be processed is set as the right end 610 of the target detection image area 600. This position 710 indicates that when the detection target image determination unit 6 looks at the detection accuracy value 800 along the right direction DR1 from the target maximum point 700 in the output value map 300, the detection accuracy value 800 is the target maximum. Before a position that is (1 / Z) times or less than the detection accuracy value 800a at the point 700 appears, the detection accuracy value is determined to be no longer monotonically decreasing.

  On the other hand, in step s6, if the detection target image determination unit 6 does not determine that the comparison result of (v1-v2) <0 has continuously occurred a predetermined number of times C, the current second image is determined in step s1. The accuracy value v2 is a new first accuracy value v1, and the detection accuracy value 800 on the right side is a new second accuracy value v2. Thereafter, the detection target image determination unit 6 operates in the same manner.

  In this way, the detection target image determination unit 6 determines the right end 610 of the target detection image region 600.

  Similarly, when the detection target image determination unit 6 determines the left end 620 of the target detection image region 600, as shown in FIG. 17, in the output value map 300, the left direction DR2 from the target maximum point 700 is displayed. , The two detection accuracy values 800 are compared before and after changing the pair, and the left end 620 of the target detection image region 600 is determined based on the comparison result. When the right end 610 and the left end 620 of the target detection image region 600 are determined, the width W1 (see FIGS. 16 and 17) in the left-right direction (row direction) of the target detection image region 600 is determined.

  Further, when the detection target image determination unit 6 determines the upper end 630 of the target detection image region 600, as shown in FIG. 17, in the output value map 300, the detection target image determination unit 6 extends from the target maximum point 700 along the upward direction DR3. Then, the two detection accuracy values 800 are compared while changing the pair, and the upper end 630 of the target detection image region 600 is determined based on the comparison result. Then, when the detection target image determination unit 6 determines the lower end 640 of the target detection image region 600, as shown in FIG. 17, in the output value map 300, the target maximum point 700 is shifted downward DR4. The two detection accuracy values 800 are compared while changing the pair, and the lower end 640 of the target detection image region 600 is determined based on the comparison result. When the upper end 630 and the lower end 640 of the target detection image region 600 are determined, the vertical width (column direction) width W2 (see FIG. 17) of the target detection image region 600 is determined.

  In this way, the detection target image determination unit 6 determines the position and size of the detection image region by determining the right end, left end, upper end, and lower end of the quadrangle detection image region. Then, the detection target image determination unit 6 sets the determined outer frame of the detected image region as a post-integration detection result frame. The partial image within the post-integration detection result frame in the processing target image area becomes a detected image area determined to be a face image.

  The detection target image determination unit 6 determines a detection image region (region that is a face image) corresponding to the local maximum point for each local maximum point remaining after the integration processing of the local maximum points is completed, and the detection image region The outline frame is set as a post-integration detection result frame. Thereby, for each face image included in the processing target image, one post-integration detection result frame is obtained for one face image.

  In addition, when the size of the obtained detection image area is too small, the detection target image determination unit 6 may delete the detection image area, assuming that the detection image area is not a face image. In other words, when the size of the obtained detection result frame after integration is too small, the detection target image determination unit 6 determines that the partial image in the detection result frame after integration is not a face image, and performs detection after integration. The result frame may be deleted.

  FIG. 19 shows a detection image region 600 and a post-integration detection result frame 900 (outer frame 600a of the detection image region 600) obtained by the detection target image determination unit 6 with respect to the processing target image 20 shown in FIGS. FIG. In FIG. 19, the detection image region 600 and the post-integration detection result frame 900 are shown superimposed on the processing target image 20.

  As shown in FIG. 19, approximately one detected image area 600 is obtained for each face image included in the processing target image 20. That is, approximately one post-integration detection result frame 900 is obtained for each face image included in the processing target image 20. This is because a plurality of detection result frames 150 (see FIG. 10) obtained for one face image are integrated, and one post-integration detection result frame 900 is obtained for the one face image. Means. In addition, the face images are appropriately contained in each post-integration detection result frame 900. Therefore, it can be said that the face image is appropriately detected in the image detection apparatus 1 according to the present embodiment.

  In the above example, step s6 is performed in order to suppress erroneous determination that the monotonous decrease is no longer caused by the influence of noise, but step s6 may not be performed. In this case, if it is determined in step s3 that (v1-v2) <0, step s5 is executed. That is, when the comparison result of (v1-v2) <0 is obtained even once, before the position where the detection accuracy value becomes (1 / Z) times or less than the detection accuracy value at the target maximum point 700 appears. In addition, it is determined that the change in the detection accuracy value is not monotonously decreased, and step s5 is executed.

  In addition, when the processing target image is displayed on the display device, the image detection device 1 displays the post-integration detection result frame 900 (the outer shape frame 600a of the detection image region 600) for the processing target image, as shown in FIG. ) May be displayed in an overlapping manner.

  In addition, the image detection apparatus 1 compares the face image registered in advance with the detection image region 600 (image in the post-integration detection result frame 900) determined to be a face image in the processing target image. It may be determined whether or not they match. If the face image registered in advance and the detected image area 600 in the processing target image do not match, the image detecting apparatus 1 performs mosaic processing on the detected image area 600 and then The processing target image may be displayed on the display device. As a result, when the image detection apparatus 1 according to the present embodiment is used in a surveillance camera system, even when a face image of a neighbor's person is photographed by the surveillance camera, the face image cannot be recognized. can do. That is, a privacy mask can be realized.

  As described above, in the present embodiment, the processing target image that is the same as the maximum point of the detection accuracy value in the output value map that indicates the distribution in the processing target image with respect to the detection accuracy value that indicates the probability as the detection target image. It is determined that the predetermined area including the pixel at the position is the detection target image. Since the maximum point of the detection accuracy value in the output value map is considered to correspond to the center position of the detection target image in the processing target image, the predetermined region including the pixel at the same position as the maximum point in the processing target image Is determined to be a detection target image, the detection target image can be accurately detected from the processing target image. That is, the detection accuracy for the detection target image can be improved.

  Although the image detection device 1 has been described in detail, the above description is illustrative in all aspects, and the present invention is not limited thereto. The various modifications described above can be applied in combination as long as they do not contradict each other. And it is understood that the countless modification which is not illustrated can be assumed without deviating from the scope of the present invention.

DESCRIPTION OF SYMBOLS 1 Image detection apparatus 3 Detection part 4 Map production | generation part 5 Maximum point search part 6 Detection object image determination part 12 Control program

Claims (7)

An image detection device for detecting a detection target image from a processing target image,
A detection unit that sets a plurality of detection frames whose positions are different from each other with respect to the processing target image, and performs detection processing of the detection target image with respect to an image in the detection frame for each of the plurality of detection frames;
A map generation unit that generates a map indicating a distribution in the processing target image with respect to a detection accuracy value indicating the certainty as the detection target image based on a detection result in the detection unit;
A search unit for searching for a maximum point of the detection accuracy value in the map;
Based on a predetermined criterion, an integration process that integrates a plurality of local maximum points that are close to each other in the map is performed, and a predetermined region that includes a pixel at the same position as the local maximum point after the integration process in the processing target image. A determination unit that determines that the image is a detection target image ,
The determination unit
In the map, when the detection accuracy value is viewed from the local maximum point along the direction away from the local maximum point after the integration process, the detection accuracy value becomes the detection accuracy value at the local maximum point. On the other hand, the position in the processing target image that is the same as the position that is first (1 / Z) times or less (Z> 1) is set as the end of the predetermined region that is determined to be the detection target image,
In the map, when the detection accuracy value is viewed from the local maximum point along the direction away from the local maximum point after the integration process, the detection accuracy value becomes the detection accuracy value at the local maximum point. On the other hand, if it is determined that the change in the detection accuracy value is no longer monotonically decreasing before a position that is (1 / Z) times or less appears, the position where the change is determined not to be monotonically decreased is determined in the detection target image. An image detection apparatus that uses an end of the predetermined area to be determined . The image detection apparatus according to claim 1,
In the map arranged at two-dimensional coordinates, the search unit uses the detection accuracy value as a weighting factor, and calculates coordinate values for a plurality of positions where a plurality of the detection accuracy values included in the processing target area respectively exist. An image detection apparatus that searches for the maximum point by calculating a weighted average value and repeating a process of moving the processing target region so that a center position of the processing target region becomes the weighted average value. The image detection apparatus according to claim 2,
The search unit determines that an image in the detection frame is highly likely to be the detection target image as a result of the detection unit performing the detection process, and the search unit is the same as the predetermined position in the detection frame. An image detection apparatus that starts searching for the maximum point with a position as a center position of the processing target region. The image detection apparatus according to any one of claims 2 and 3,
When the search unit calculates the weighted average value, the search unit includes a plurality of positions where the plurality of detection accuracy values included in the processing target region exist in the map where the detection accuracy values are thinned out. An image detection device using the coordinate values of An image detection apparatus according to any one of claims 1 to 4 , wherein
The image detection apparatus, wherein the detection target image is a human face image. A control program for controlling an image detection device that detects a detection target image from a processing target image,
In the image detection device,
(A) A step of setting a plurality of detection frames whose positions are different from each other with respect to the processing target image, and performing detection processing of the detection target image on the image in the detection frame for each of the plurality of detection frames. When,
(B) based on the detection result in the step (a), generating a map indicating a distribution in the processing target image with respect to a detection accuracy value indicating the certainty as the detection target image;
(C) searching for a maximum point of the detection accuracy value in the map;
(D) performing an integration process for integrating the plurality of local maximum points close to each other in the map based on a predetermined criterion;
( E ) performing a step of determining a predetermined region including a pixel at the same position as the maximum point after the integration processing in the processing target image as the detection target image ;
In the map, when the detection accuracy value is viewed from the local maximum point along the direction away from the local maximum point after the integration process, the detection accuracy value becomes the detection accuracy value at the local maximum point. In contrast, in the map, a position in the processing target image that is the same as a position that is initially (1 / Z) times or less (Z> 1) is set as an end of the predetermined region that is determined to be the detection target image. When the detection accuracy value is viewed from the local maximum point along the direction away from the local maximum point after the integration process, the detection accuracy value is (1) with respect to the detection accuracy value at the local maximum point. / Z) If it is determined that the change in the detection accuracy value is no longer monotonically decreasing before a position that is less than or equal to (Z) appears, the position where it is determined that the change is no longer monotonically decreased is determined as the detection target image. Work with the end of the predetermined area The control program for executing in said step (e). An image detection method for detecting a detection target image from a processing target image,
(A) A step of setting a plurality of detection frames whose positions are different from each other with respect to the processing target image, and performing detection processing of the detection target image on the image in the detection frame for each of the plurality of detection frames. When,
(B) based on the detection result in the step (a), generating a map indicating a distribution in the processing target image with respect to a detection accuracy value indicating the certainty as the detection target image;
(C) searching for a maximum point of the detection accuracy value in the map;
(D) performing an integration process for integrating the plurality of local maximum points close to each other in the map based on a predetermined criterion;
( E ) determining a predetermined region including a pixel at the same position as the maximum point after the integration processing in the processing target image as the detection target image ,
In the step (e),
In the map, when the detection accuracy value is viewed from the local maximum point along the direction away from the local maximum point after the integration process, the detection accuracy value becomes the detection accuracy value at the local maximum point. On the other hand, the position in the processing target image that is the same as the position that is first (1 / Z) times or less (Z> 1) is set as the end of the predetermined region that is determined to be the detection target image,
In the map, when the detection accuracy value is viewed from the local maximum point along the direction away from the local maximum point after the integration process, the detection accuracy value becomes the detection accuracy value at the local maximum point. On the other hand, if it is determined that the change in the detection accuracy value is no longer monotonically decreasing before a position that is (1 / Z) times or less appears, the position where the change is determined not to be monotonically decreased is determined in the detection target image. An image detection method using an end of the predetermined area to be determined .