JP5398860B2 - Image processing apparatus, image processing apparatus control method, program, and storage medium - Google Patents

Description

The present invention relates to an image processing apparatus, a control method for the image processing apparatus, a program, and a storage medium , and more particularly, to a technique suitable for performing image processing on a scene including a vivid subject.

  2. Description of the Related Art Conventionally, there has been known an image processing apparatus that discriminates image scenes and subject types and performs image processing in accordance with the discriminated subject types. For example, in Patent Document 1, it is determined whether or not an input image is a scene including a vivid subject (hereinafter, a vivid scene), and an image output for outputting a vivid scene image at high resolution is disclosed. An apparatus is disclosed.

JP 2000-259372 A

  According to the technique disclosed in Patent Document 1 described above, whether or not the scene is vivid is determined based on whether or not the number of highly saturated pixels is greater than a predetermined number. Here, as a vivid scene, there can be a scene where the background is vivid and a scene where the main subject (main subject) is vivid. Among these, in a scene with a bright background, the distribution of highly saturated pixels varies depending on the presence of a main subject other than the background, such as a person.For example, when a person enters, the amount of highly saturated pixels in the background Will fall. For this reason, in the image output apparatus described in Patent Document 1, it is difficult to distinguish a scene with a bright background in which the main subject is included, so that it is difficult to distinguish the scene as a vivid scene. There is a problem that it is not possible.

  In view of the above-described problems, the present invention enables appropriate image processing to be performed on an image including a vivid scene regardless of whether or not the input image includes a main subject. It is an object.

The image processing apparatus of the present invention includes: a calculating means for calculating an image signal or al Review value is entered, a detecting means for detecting a region of a subject of the input image signal, based on the evaluation value, the input comprising a determination unit which image signal is discriminated whether or not determine specific condition is satisfied, and output means for outputting a discrimination result by said discriminating means, and said discriminating means is detected by said detecting means There line the determination based on the evaluation value of the region other than the region of the subject that, the larger the percentage of the total image area of the subject detected by the detecting means and relieving the discrimination condition .

  According to the present invention, it is possible to determine a vivid scene regardless of whether or not the main subject is included in the input image. Thus, appropriate image processing can be performed on an image including any vivid scene.

It is a block diagram showing an example of composition of an imaging device concerning a 1st embodiment. It is a figure which shows an example of the picked-up image divided | segmented into 8x8 block. It is a flowchart which shows an example of the discrimination | determination processing procedure of a vivid scene. It is a figure which shows an example of the picked-up image containing a face area | region. It is a figure which shows an example of the discrimination | determination reference | standard of a vivid scene. It is a figure which shows an example of the relationship between a vividness and a high saturation block ratio. It is a figure which shows the discrimination | criterion reference example of a vivid scene according to the ratio of the face in an image. It is a figure which shows an example of the picked-up image from which the ratio of the face in an image differs. It is a block diagram which shows the structural example of the imaging device which concerns on 2nd Embodiment. It is a flowchart which shows an example of the discrimination | determination processing procedure of a vivid scene. It is a figure which shows a mode that evaluation value is replaced.

(First embodiment)
The imaging apparatus according to the first embodiment of the present invention will be described below with reference to FIGS.
FIG. 1 is a block diagram illustrating a configuration example of an imaging apparatus 100 that has a function of detecting a scene of a captured image and performs image correction processing according to the scene in the present embodiment.
In FIG. 1, a lens 101 is for imaging a luminous flux of a subject, and an image sensor 103 is for photoelectrically converting light incident through the lens 101 and the iris 102. The AGC amplifier 104 is for amplifying the signal output from the image sensor 103 to an appropriate level.

  The luminance / color signal generation unit 105 is for converting a signal generated in the image sensor 103 into a luminance signal (Y) and color signals (R0, G0, B0). The white balance amplification unit 106 amplifies the color signals (R0, G0, B0) output from the luminance / color signal generation unit 105 according to the white balance gain, and generates an amplified color signal (R, G, B). Is. The color difference signal generation unit 107 is for generating color difference signals (RY, BY). The color difference signal correcting unit 108 is for performing correction such as applying gain to the color difference signal, and the encoder 109 is for converting the input image signal into a standard television signal or the like.

  The signal dividing unit 110 is for dividing the luminance signal (Y) and the color difference signals (RY, BY) into predetermined small blocks. The saturation calculation unit 111 is for calculating the saturation (Chroma) from the color difference signals (RY, BY), and the camera control unit 112 is for controlling the entire imaging system. . The scene discriminating unit 113 is for discriminating the scene of the input captured image, and the face detecting unit 114 is for detecting a human face from the captured image.

  Next, the processing operation by the imaging apparatus 100 in FIG. 1 will be described. Light incident on the lens 101 is photoelectrically converted by the image sensor 103, amplified to an appropriate level by the AGC amplifier 104, and output to the luminance / color signal generator 105. The luminance / color signal generation unit 105 generates a luminance signal (Y) and color signals (R0, G0, B0) from the image signal formed on the image sensor 103, and among these, the color signals (R0, G0, B0). Is output to the white balance amplifier 106.

The white balance amplification unit 106 amplifies the color signals (R0, G0, B0) based on the white balance gain calculated by the camera control unit 112, and the amplified color signals (R, G, B) are color difference signal generation units. It outputs to 107. The color difference signal generation unit 107 generates color difference signals (RY, BY) from the amplified color signals (R, G, B), and outputs them to the color difference signal correction unit 108 and the signal division unit 110. The color difference signal correction unit 108 functions as an image processing unit, and corrects the color difference signals (RY, BY) by applying the color difference gain G (G is 1 or more) calculated by the camera control unit 112. . That is, the corrected color difference signals {(R−Y) ′ and (B−Y) ′}
(R−Y) ′ = G × (R−Y),
(B−Y) ′ = G × (B−Y),
It becomes. Then, the corrected color difference signals {(R−Y) ′, (B−Y) ′} are output to the encoder 109. The intensity of the color difference gain G will be described later. The encoder 109 generates a standard television signal such as NTSC from the luminance signal (Y) and the corrected color difference signals (RY) ′ and (BY) ′, and outputs them to the outside.

  The above is the basic processing at the time of imaging. Further, the camera control unit 112 adaptively controls the parameters used in the color difference signal correction unit 108 according to the characteristics of the image signal, and the color difference signal correction unit 108 performs image processing. Correct the signal. Hereinafter, the analysis processing of the characteristics of the image signal will be described.

  The signal dividing unit 110 divides the image signal into blocks (8 × 8 blocks) as shown in FIG. 2 and calculates the average value of the luminance signal (Y) and color difference signals (RY, BY) for each block. Calculate and output the result to the saturation calculation unit 111. The saturation calculation unit 111 calculates the saturation (Chroma) of each block from the color difference signals (RY, BY). The saturation (Chroma) is calculated based on the following equation (1).

  Then, the saturation calculation unit 111 outputs the calculated saturation (Chroma) information of each block to the scene determination unit 113. On the other hand, the face detection unit 114 detects the face of the person who is the main subject from the captured image based on the luminance signal (Y) output from the luminance / color signal generation unit 105, and the face detection result is the scene determination unit 113. Output to. If a human face is detected, the face position information is also output to the scene determination unit 113. Various methods for recognizing a person's face, such as a method for performing pattern matching of luminance signals, have been proposed in the past, and any of these methods may be used.

  The scene determination unit 113 weights the captured scene more in saturation based on the saturation (Chroma) for each block output from the saturation calculation unit 111 and the face detection result output from the face detection unit 114. It is determined whether or not the image to be added (bright scene). Hereinafter, the processing flow of the scene determination unit 113 will be described with reference to FIG.

FIG. 3 is a flowchart illustrating an example of a vivid scene discrimination processing procedure by the scene discrimination unit 113.
First, in step S301 in FIG. 3, it is checked whether or not a face is detected by the face detection unit 114. As a result of this check, if a face is detected, the process proceeds to step S302, and if a face is not detected, the process proceeds to step S307.

  In step S302, the average saturation is calculated from the area excluding the face area. This process will be described with reference to FIG. FIG. 4A is a diagram illustrating an example of a captured image including a face area. As shown in FIG. 4A, in the case of a captured image including a face, the average saturation is calculated by excluding the face area including the face. In step S302, the average saturation of the block excluding the face area 401 as shown in FIG. 4B is calculated.

  Next, in step S303, the number of blocks having a saturation equal to or higher than a predetermined threshold is calculated from the blocks excluding the face area (for example, the face area 401 shown in FIG. 4B). Then, the ratio of the number of blocks having a saturation equal to or higher than a predetermined threshold to the total number of blocks excluding the face area (52 blocks in the example of FIG. 4) (high saturation block ratio) is calculated. In step S304, the past vivid discrimination result is referred to and it is checked whether or not the vivid scene has been discriminated in the past. The scene determination unit 113 stores a determination result as to whether or not the scene is a vivid scene before a predetermined time (for example, two seconds before). In step S304, the scene determination unit 113 performs determination based on the stored past determination result. Do. If the result of this check is that the scene has been determined to be a bright scene in the past, the process proceeds to step S305. If the scene has not been determined to be a bright scene in the past, the process proceeds to step S306.

  In steps S305 and S306, the threshold value At of the high saturation block ratio calculated in step S303, which is one of the parameters for determining whether or not the scene is vivid, is determined.

FIG. 5 is a diagram illustrating an example of a bright scene discrimination criterion with respect to the average saturation and the high saturation block ratio.
As shown in FIG. 5A, the case where the average saturation calculated in step S302 is higher than the average saturation threshold Ct and the high saturation block ratio calculated in step S303 is larger than the threshold At will be described later. In step S310, it is determined that the scene is vivid. In steps S305 and S306, this threshold value At is determined.

In step S305, the threshold value At of the high saturation block ratio is lowered below the reference value At (Base), and the discrimination criterion is relaxed. This state is shown in FIG. In this way, when it is determined that the subject is vivid in the past, it is easy to discriminate it as a vivid scene even if a bright subject is hidden behind the face. On the other hand, in step S306, the threshold value At of the high saturation block ratio is raised above the reference value At (Base), and the discrimination criterion is made strict. That is, when it is determined that the scene is bright in the past, the determination criterion is relaxed compared to the case where it is not determined that the scene is bright.
This state is shown in FIG. By doing so, it is possible to prevent the scene from being determined to be a vivid scene when only a small amount of a vivid subject enters an area other than the face.

  On the other hand, if no face is detected as a result of the check in step S301, the average saturation of all blocks (8 × 8 blocks) is calculated in step S307. Next, in step S308, the number of blocks having a saturation equal to or greater than a predetermined threshold is calculated from all blocks. Then, the ratio of the number of blocks having a saturation equal to or higher than a predetermined threshold to the total number of blocks (64 blocks in the example of FIG. 4) (high saturation block ratio) is calculated. Next, in step S309, as in steps S305 and S306, a threshold value At of the high saturation block ratio, which is one of the parameters for determining whether or not the scene is vivid, is determined. In this step, since no face is detected, the reference value At (Base) shown in FIG. 5A is set as the threshold value At of the high saturation block ratio.

  In step S310, as described above, it is determined whether or not the scene is vivid according to the criteria for determining the bright scene shown in FIG. That is, the scene is vivid when the average saturation calculated in step S302 (or S307) is higher than the average saturation threshold Ct and the high saturation block ratio calculated in step S303 (or S308) is larger than the threshold At. Is determined.

  Information on whether or not the scene is a vivid scene determined by the scene determination unit 113 by the above processing procedure is output to the camera control unit 112. The camera control unit 112 controls parameters used in the color difference signal correction unit 108 based on information about whether or not the scene is a vivid scene determined by the scene determination unit 113.

  In the present embodiment, as described above, the camera control unit 112 controls the color difference gain G used in the color difference signal correction unit 108. The color difference gain G includes parameters G1 and G2, and has a relationship of G1> G2 ≧ 1. If it is determined that the scene is bright, the color difference gain G is set to G1, and if it is determined that the scene is not bright, the color difference gain G is set to G2. That is, when it is determined that the scene is vivid, the image is corrected to an image with higher saturation by increasing the gain for the color difference signal.

  As described above, according to the present embodiment, it is determined whether or not the scene is vivid, and image processing is controlled according to the determination result. Specifically, a human face is detected, and control is performed so as to limit the influence of the detected face area on scene determination as to whether the face is vivid or not. This makes it possible to properly discriminate vivid scenes regardless of whether or not a person is included in the input captured image, and enhance saturation even for images containing any vivid scene. Image processing can be performed.

  In the present embodiment, a case where a human face is detected has been described as an example, but the present invention is not limited to a human face. For example, any object such as an animal or a plant may be detected. Further, in the present embodiment, an example has been described in which information such as the average value of saturation is calculated by excluding the face area in order to determine whether or not the scene is vivid. On the other hand, any process may be performed as long as the influence of the face area is small for discrimination of a vivid scene. For example, a block corresponding to the face area (for example, the face area 401 shown in FIG. 4B) is weighted, and control is performed so that the influence of the face area is reduced when calculating the average value of saturation. You may go.

  In the present embodiment, the threshold value of the high saturation block ratio is changed according to the face detection result. However, any parameter for discriminating a vivid scene may be controlled by detecting the face. . In addition, the parameters for discriminating a vivid scene are not limited to the high chroma block ratio and the average chroma, but the conditions set for discriminating that the scene is vivid according to human perception. Any conditions, parameters, and discrimination criteria may be used.

  In the present embodiment, the color difference gain G used in the color difference signal correction unit 108 is prepared as binary values for a vivid scene and a non-vivid scene, but the present invention is not limited to this. When a person is detected as the main subject, if the color difference gain is set in the same way as when no person is detected and the saturation is emphasized, the skin color of the person may appear to be an unnatural color. Therefore, when a person is detected, the weight on saturation may be made smaller than when no person is detected, and the degree of correction that emphasizes vividness may be suppressed. That is, if the color difference gain G when a person is detected is G3, G3 may be set so that a relationship of G1> G3> G2 is established.

  In the present embodiment, the processing for increasing the saturation and enhancing the vividness of the image data determined to be a vivid scene has been described. However, the present invention is not limited to this, and conversely for the vivid scene. It can also be applied to processing that reduces saturation and suppresses vividness. In this case, for example, the gain may be set such that G1 <G2 ≦ 1. If the color difference gain G when a person is detected as described above is G3, then naturally G1 <G3 <G2.

  In the present embodiment, the color difference gain G set based on the determination result of whether or not the scene is vivid is uniformly applied to the entire image data. However, the present invention is not limited to this. It may be limited to blocks (or pixels) with high saturation in the image data, and a high color difference gain G may be applied compared to other blocks.

  Furthermore, in the present embodiment, the saturation (chroma) is calculated from the color difference signals (R−Y, B−Y) by the equation shown in Equation 1, but the method for calculating the saturation is not limited thereto. For example, the saturation may be calculated in the L * a * b * space after being once converted into another space such as the L * a * b * space. In this embodiment, the example in which the image signal is divided into 8 × 8 blocks by the signal dividing unit 110 has been described, but any number of divisions may be used.

  In the present embodiment, whether or not a scene is vivid is determined by binary, but may be calculated by multiple values such as the degree of vividness. In this case, the higher the average saturation and the higher the saturation block ratio, the higher the vividness.

FIG. 6 is a diagram illustrating an example of the relationship between the vividness and the high saturation block ratio.
In FIG. 6, reference numeral 601 denotes a reference characteristic when no face is detected. On the other hand, when a face is detected, the reference characteristic 601 is changed. For example, reference numeral 602 denotes a characteristic when a face is detected and determined to be vivid in the past. In this case, in step S305 in FIG. 3, the characteristic 602 becomes more vivid than the reference characteristic 601. On the other hand, reference numeral 603 denotes characteristics when a face is detected and has not been determined to be vivid in the past. In this case, in step S306 in FIG. 3, the characteristic 603 has a vividness lower than that of the reference characteristic 601.

  By controlling as described above, even when the discrimination result of a vivid scene is expressed not in binary but in multiple values (vividness), it becomes possible to control the ease of discrimination of vividness depending on the presence or absence of a face. Thus, a vivid scene can be discriminated more appropriately.

  Furthermore, parameters for discriminating vivid scenes may be controlled according to the area ratio of the face in the image. For example, in the present embodiment, when the face is detected, the threshold value At of the high saturation block ratio is uniformly determined according to the past determination result. However, the threshold value At is set according to the ratio of the face in the image. It may be determined dynamically. This will be described with reference to FIG.

FIG. 7A is a diagram illustrating an example of the threshold value At of the high saturation block ratio for determining a vivid scene when it has been determined to be vivid in the past.
In FIG. 7A, At (min) indicates the maximum fluctuation amount (lower threshold value) of the reference value At (Base). In the example illustrated in FIG. 7, a value between the lower limit value At (min) and the reference value At (Base) is determined as a final bright scene determination threshold value At based on the ratio of the face in the image.

FIG. 7B is a diagram illustrating an example of the relationship between the ratio of the face in the image and the threshold value At for determining a vivid scene.
As shown in FIG. 7B, for example, when the ratio of the face in the image is Fr, the threshold value At of the final high saturation block ratio is determined to be At (Fr). For example, as shown in FIG. 8A, when the ratio of the face in the image is small, even when the face is detected, the influence degree of the face is low when determining a vivid scene. On the other hand, as shown in FIG. 8B, when the proportion of the face in the image is large, the influence degree of the face is high when determining a vivid scene based on the face detection result. Therefore, the threshold value At for determining a vivid scene may be largely changed from the reference value At (Base) as the area ratio of the face to the image increases.

  In this embodiment, the scene discrimination result by the scene discrimination unit 113 is reflected and output on the image data used for the discrimination, but the invention is not particularly limited to this. That is, it is naturally possible to reflect the image processing corresponding to the determination result for a certain frame (image data) after the next frame. In addition, the scene is identified for the first time when a multi-frame vivid scene discrimination result continues, or the scene is identified when the ratio of vivid scenes is high in multiple frames. It is also possible to specify a scene. At this time, it is conceivable that the image processing according to the determination result is reflected in the plurality of frames and the subsequent frames. At this time, the discrimination result used as the past discrimination result may be a discrimination result of the frame immediately before the discrimination target frame or may be a discrimination result obtained from a plurality of frames up to immediately before.

  The situation that is specifically assumed is a situation in which processing is performed on captured image data (frames) in an imaging apparatus capable of capturing a still image or an information processing apparatus such as a PC that performs image processing on image data. is there. In addition, in an information processing apparatus such as an imaging apparatus capable of live view display or moving image shooting or a PC that performs image processing on a moving image, the above-described processing over a plurality of frames is assumed.

  In this embodiment, the saturation correction is applied to the image data using the determination result output by the scene determination unit 113. However, the method of using the determination result is not limited to this. For example, when the determination result is displayed on a display means (not shown) to inform the user or save the image data, information corresponding to the determination result is attached to a header or the like, and the image data is captured after the storage. You can also specify the scene. Even if one correction is taken, the vividness may be enhanced by correcting other than the saturation. Such processing includes, for example, correction for increasing luminance and contour enhancement processing.

(Second Embodiment)
Hereinafter, an imaging apparatus according to the second embodiment of the present invention will be described with reference to FIGS. 9 to 11. In the present embodiment, evaluation values such as saturation that are hidden by detecting a face are replaced with evaluation values detected in the past.

  FIG. 9 is a block diagram illustrating a configuration example of the imaging apparatus 900 according to the present embodiment. In FIG. 9, the same reference numerals as those in FIG. In this embodiment, an evaluation value memory 901 and a motion amount detection unit 902 are further provided in the configuration of FIG.

  Next, a processing flow of the imaging apparatus 900 illustrated in FIG. 9 will be described. The flow from capturing an image to outputting an image signal from the encoder 109 is the same as in the first embodiment. Further, the scene determination unit 113 determines whether or not the scene is a vivid scene, and the camera control unit 112 controls parameters used in the color difference signal correction unit 108 according to the result, as in the first embodiment. Therefore, detailed description is omitted. Hereinafter, differences from the first embodiment will be described.

  Similarly to the first embodiment, the signal dividing unit 110 calculates an average value of the luminance signal (Y) and the color difference signals (RY, BY) for each block, and sends the average value to the saturation calculating unit 111 as an evaluation value. Output. Similar to the first embodiment, the saturation calculation unit 111 calculates the saturation (Chroma) for each block from the color difference signals (RY, BY), and evaluates information on the calculated saturation (Chroma). The value is output to the value memory 901 and the scene determination unit 113.

  The evaluation value memory 901 functions as a storage unit, and stores information on chroma (Chroma) of all blocks output from the chroma calculation unit 111 including past ones. Here, the process of storing the saturation information in the evaluation value memory 901 is performed at predetermined time intervals. However, saturation information is not stored when a face is detected by the face detection unit 114. The motion amount detection unit 902 calculates a motion amount from the zoom and anti-shake information of the lens 101 and outputs information on the calculated motion amount to the scene determination unit 113.

  The scene determination unit 113 outputs the saturation information calculated by the saturation calculation unit 111, the saturation information stored in the evaluation value memory 901, the face detection result by the face detection unit 114, and the motion amount detection unit 902. It is determined whether or not the scene is vivid based on the information on the amount of movement.

Hereinafter, the flow of processing by the scene determination unit 113 will be described with reference to FIG.
FIG. 10 is a flowchart illustrating an example of a vivid scene discrimination processing procedure by the scene discrimination unit 113. In FIG. 10, the processes with the same reference numerals as those in FIG. 3 are the same as those described in the first embodiment, and thus the description thereof is omitted.

  In step S <b> 1001, it is determined whether the image as a whole is moving based on the movement amount information output from the movement amount detection unit 902. That is, it is determined whether or not the motion amount output from the motion amount detection unit 902 is greater than or equal to a predetermined value. If the result of this determination is that the amount of movement is greater than or equal to a predetermined value and the entire image is moving, the process proceeds to step S302. Note that the processing after step S302 is the same as in the first embodiment.

  On the other hand, if the result of determination in step S1001 is that the amount of motion is smaller than the predetermined value and the entire image is not moving, the process proceeds to step S1002. In step S1002, the saturation of the detected face area is replaced with the saturation stored in the evaluation value memory 901. This process will be described with reference to FIG.

  FIG. 11A shows a captured image that does not include a face. As described above, past saturation information when no face is included is stored in the evaluation value memory 901. FIG. 11B is a diagram illustrating the saturation distribution stored in the evaluation value memory 901 of the photographed image illustrated in FIG. FIG. 11B shows that the blocks displayed in darker colors in each block have higher saturation. FIG. 11C is a diagram illustrating an example of a scene in which a human face is included in the scene (captured image) in FIG. FIG. 11D shows the face area 1101 of the scene shown in FIG.

  In step S1002, for example, the saturation of the block included in the face area 1101 is replaced with the saturation 1102 corresponding to the face area stored in the evaluation value memory 901 shown in FIG. By replacing the evaluation value of the face area in step S1002, the influence of the face can be eliminated. Accordingly, the following processing can be handled in the same way as when there is no face, and thus the process proceeds to step S307. Since the processing after step S307 is the same as the processing described in the first embodiment, the description thereof is omitted.

  As described above, according to the present embodiment, when a face is detected, the evaluation value of the face area is replaced with the evaluation value when a past face is not detected. By replacing the evaluation value in this way, it is possible to appropriately determine whether or not the scene is vivid even when the background subject is hidden behind the person's face. As a result, image processing with higher saturation can be applied to an image including any vivid scene.

  In this embodiment, the example in which the evaluation value of the face area is replaced with the evaluation value when there is no past face has been described, but the two evaluation values may be mixed at a ratio according to the amount of motion. In this embodiment, the saturation value is described as an example of the evaluation value. However, the evaluation value to be replaced when a face enters is any parameter as long as it is an evaluation value used for distinguishing a vivid scene. May be. Further, in the present embodiment, the motion amount detection unit 902 calculates the motion amount based on information of the optical system such as the lens 101, but may be calculated in any manner as long as the motion amount can be calculated. For example, the amount of motion may be calculated using an image signal in addition to the information of the optical system. As mentioned above, although preferable embodiment of this invention was described, this invention is not limited to these embodiment, A various deformation | transformation and change are possible within the range of the summary.

(Other embodiments)
The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, or the like) of the system or apparatus reads the program. It is a process to be executed.

108 color difference signal correction unit, 111 saturation calculation unit, 112 camera control unit, 113 scene discrimination unit, 114 face detection unit

Claims (18)

A calculating means for calculating an input image signal or al Review value,
Detecting means for detecting a region of a subject of the input image signal;
A determining means on the basis of the evaluation value, the input image signal is discriminated whether or not determine another condition is satisfied,
Output means for outputting a discrimination result by the discrimination means,
Said discriminating means, have rows the determination based on the evaluation value of the region other than the region of the subject detected by said detecting means, the greater the percentage of the total image area of the subject detected by the detecting means, An image processing apparatus that relaxes the determination condition . A calculating means for calculating an input image signal or al Review value,
Detecting means for detecting a region of a subject of the input image signal;
A determining means on the basis of the evaluation value, the input image signal is discriminated whether or not determine another condition is satisfied,
Output means for outputting a discrimination result by the discrimination means,
The calculation means assigns a smaller weight to the evaluation value of the area of the subject detected by the detection means than the evaluation value of the area other than the area of the subject,
Said discriminating means, have rows the determination based on the evaluation values labeled the weight, the greater the percentage of the total image area of the subject detected by the detecting means, to mitigate the discrimination condition A featured image processing apparatus. A calculating means for calculating an input image signal or al Review value,
Detecting means for detecting a region of a subject of the input image signal;
Based on the evaluation value, and a determination means for the input image signal is discriminated whether or not determine another condition is satisfied,
Said determining means, said had row the determination based on the evaluation value that is weighted so is less affected areas of the subject detected by the detecting means, the entire image area of the subject detected by the detecting means The image processing apparatus is characterized in that the determination condition is relaxed as the proportion of the image becomes larger .   The image processing apparatus according to claim 1, further comprising a correction unit that corrects an input image signal based on a determination result obtained by the determination unit.   The correction unit corrects the saturation of the input image signal when the determination unit determines that the input image signal satisfies the determination condition. The image processing apparatus described.   The correction means performs correction for increasing the luminance of the input image signal or correction for enhancing the contour when the determination means determines that the input image signal satisfies the determination condition. The image processing apparatus according to claim 4.   5. The image processing apparatus according to claim 1, further comprising a display control unit configured to display a determination result obtained by the determination unit on a display unit.   The image processing apparatus according to claim 1, wherein the determination unit changes a determination reference according to a detection result of the subject by the detection unit.   The image processing apparatus according to claim 1, wherein the determination unit changes the determination condition according to a past determination result.   When the determination means determines that the determination condition is satisfied in the past determination, the determination means relaxes the determination condition compared to the case where the determination means does not determine that the determination condition is satisfied. The image processing apparatus according to claim 9. The image processing apparatus according to claim 1, wherein the evaluation value includes at least saturation information, and the determination condition is a condition related to saturation. Storage means for storing past evaluation values calculated by the calculation means;
12. The determination unit according to claim 1, wherein the determination unit performs the determination by replacing an evaluation value of a subject area detected by the detection unit with an evaluation value stored in the storage unit. The image processing apparatus according to item 1. A motion amount detecting means for detecting a motion amount of the input image;
13. The determination unit according to claim 12, wherein when the amount of motion detected by the motion amount detection unit is smaller than a predetermined value, the determination unit replaces the evaluation value stored in the storage unit with the evaluation value. The image processing apparatus described.   The image processing apparatus according to claim 1, wherein the subject is a person. Calculating means, a calculating step of calculating an image signal or al Review value input,
A detecting step for detecting a region of a subject of the input image signal;
Determining means, a determining step on the basis of the evaluation value, the input image signal is discriminated whether or not determine another condition is satisfied,
An output step for outputting a determination result obtained by the determination step;
The determination step may have rows the determination based on the evaluation value of the region other than the region of the subject detected by said detecting means, the greater the percentage of the total image area of the subject detected by the detecting step, A control method for an image processing apparatus, wherein the discrimination condition is relaxed . Calculating means, a calculating step of calculating an image signal or al Review value input,
A detecting step for detecting a region of a subject of the input image signal;
Determining means, a determining step on the basis of the evaluation value, the input image signal is discriminated whether or not determine another condition is satisfied,
An output step for outputting a determination result obtained by the determination step;
The determination step assigns a smaller weight to the evaluation value of the area of the subject detected by the detection means than the evaluation value of the area other than the area of the subject,
Wherein in the determination step, the weight had row the determination based on the evaluation values labeled, as percentage of total image area of the subject detected by the detecting step is larger, to mitigate the discrimination condition A control method for an image processing apparatus. A program for causing a computer to execute each step of the control method of the image processing apparatus according to claim 15 or 16 . A computer-readable storage medium storing a program for causing a computer to execute each step of the control method for an image processing apparatus according to claim 15 or 16 .

Images