JP2008276302A - Information processing apparatus, image processing method and image processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an information processing apparatus, an image processing method and an image processing program capable of enhancing quality of images by area while taking the edges of objects into consideration. <P>SOLUTION: The information processing apparatus 10 has a CPU 11, a RAM 12, a ROM 13, a network connection 14, a selected subject storage part 15, an area setting storage part 16, an EPG data storage part 17, a recorded file storage part 18, and an interface part 20. The CPU 11 loads into the RAM 12 both an image processing program stored in the ROM 13 and the data required to execute the program, and, for a recorded file that is the subject of an image enhancement process, performs the process of enhancing quality of images by area in accordance with the image processing program while taking the edges of objects into consideration. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an information processing apparatus, an image processing method, and an image processing program that perform high image processing.

  A moving image is composed of a plurality of frame images. When a single still image is extracted from a moving image, a high image can be obtained by complementing the pixels of the original image based on a plurality of frame images. In general, this high image processing often requires a long processing time. For this reason, when extracting a high-quality still image, the processing time is often shortened by dividing the still image into a plurality of regions and reducing the image quality of less important regions.

  However, if a region having different image quality exists in one still image, the frame (boundary) of the region may become conspicuous.

  Conventionally, there is a technique disclosed in Japanese Patent Laid-Open No. 2005-354124 (Patent Document 1) for smoothing the frame of this type of region.

  The image processing apparatus disclosed in Japanese Patent Laying-Open No. 2005-354124 (Patent Document 1) is an image processing apparatus that generates one high resolution frame from a plurality of low resolution frames, and becomes a high resolution frame. An area segmentation unit that divides a power area into a plurality of areas including an emphasis area, a transition area surrounding the emphasis area, and a non-emphasis area; The determined first pixel value, the pixel value in the non-weighted area as the second pixel value determined using the second number of low resolution frames smaller than the first number, and the pixel value in the transition area as the first pixel value. A resolution enhancement processing unit that is determined by adding a value obtained by adding a first weight to the pixel value and a value obtained by adding a second weight to the second pixel value.

In this image processing apparatus, by providing a transition region, it is possible to prevent the change in image quality at the region frame (boundary) from becoming excessively large, thereby preventing the region frame from being excessively conspicuous and increasing the image quality for each region. This makes it possible to alleviate the uncomfortable appearance.
JP 2005-354124 A

  When high image processing is performed, the periphery of the edge portion (edge, contour) of an object (such as a person) in the image seems to be emphasized and expanded under the influence of high image processing over several pixels. May be visible. For this reason, when the edge part of a certain object is straddling the area | region where image quality differs, an edge part becomes unnatural and will give a viewer a sense of incongruity.

  However, the conventional image processing apparatus only uses the region surrounding the frame of the priority region as a transition region in order to reduce the uncomfortable appearance associated with the improvement in image quality for each region. For this reason, when the edge of the object is located in the vicinity of the frame of the region (for example, when the edge crosses the region), it is not possible to accurately relieve the uncomfortable appearance due to the enhancement of the edge portion of the object. .

  The present invention has been made in consideration of the above-described circumstances, and an object of the present invention is to provide an information processing apparatus, an image processing method, and an image processing program capable of performing high image enhancement for each region in consideration of an edge of an object. And

  In order to solve the above-described problem, the information processing apparatus according to the present invention actually includes a region information acquisition unit that acquires information on a region to be highly imaged in a frame, and a region that is to be highly imaged. Final attention area determination means as a first area to be imaged, and edge determination for determining whether there is an end of an object drawn in the frame in the vicinity of the inside of the frame of the first area And when there is an end portion of the object in the vicinity of the inside of the frame portion of the first region, a region within a predetermined distance from the frame portion outside the frame portion of the first region is defined as the second region. A buffer area setting means for setting, and applying high image processing at a first intensity to each pixel belonging to the first area, and for each pixel belonging to the second area from the first intensity Apply high image processing at the second strength which is inferior, High image processing means for performing high image processing at a third intensity that is inferior to the second intensity with respect to a third area that does not belong to any of the first area and the second area; It is characterized by comprising.

  In addition, in order to solve the above-described problem, the information processing apparatus according to the present invention includes a selection target type acquisition unit that acquires information on a type of a target to be particularly imaged in a frame, and the above-described information in the frame. Based on the object position acquisition means for acquiring position information including the outline position of the object belonging to the type, and the position information of the object belonging to the type, within the required distance from the outline of the object belonging to the type The final attention area determination means that sets the area as the first area that should be particularly high in image, and the edge of the object drawn in the frame is located near the inside of the frame of the first area. An edge determination means for determining whether or not there is an end of the object in the vicinity of the inside of the frame portion of the first region, and a region within a predetermined distance from the frame portion outside the frame portion of the first region With the second region A buffer area setting means for setting, and applying high image processing at a first intensity to each pixel belonging to the first area, and applying the first intensity to each pixel belonging to the second area A third image that is inferior to the second intensity with respect to a third area that does not belong to any of the first area and the second area is subjected to high image processing at a second intensity that is inferior. And high image processing means for performing high image processing at high intensity.

  On the other hand, in order to solve the above-described problem, the image processing method according to the present invention obtains information on a region that should be particularly high in the frame, and the region that should be particularly high is actually high. A first region to be imaged, a step of determining whether there is an end portion of an object drawn in the frame in the vicinity of the inside of the frame portion of the first region, and the first region A step of setting a region within a predetermined distance from the frame portion outside the frame portion of the first region as a second region when the end portion of the object is near the inside of the frame portion of the region; Each pixel belonging to one region is subjected to high image processing at a first intensity, and each pixel belonging to the second region is subjected to high image processing at a second intensity inferior to the first intensity. And applying the first region and the second region A method characterized in that it comprises the steps of: applying a high image processing in a third intensity less than the second strength to the third region that does not belong to any region of the band.

  In addition, in order to solve the above-described problem, the image processing method according to the present invention obtains information on the type of an object to be particularly imaged in a frame, and an object belonging to the type in the frame. Acquiring position information including the contour position of the object, and, based on the information on the position of the object belonging to the type, the area within the required distance from the contour of the object belonging to the type A first region to be performed, a step of determining whether or not there is an end of an object drawn in the frame in the vicinity of the inside of the frame portion of the first region, When there is an end of the object in the vicinity of the inside of the frame portion, a step of setting a region within a predetermined distance from the frame portion outside the frame portion of the first region as the second region; Belonging to an area High image processing at a first intensity for each pixel, and high image processing at a second intensity inferior to the first intensity for each pixel belonging to the second region, Applying a high image processing to a third region that does not belong to any of the first region and the second region at a third intensity that is inferior to the second intensity. It is a characteristic method.

  On the other hand, in order to solve the above-described problem, the image processing program according to the present invention actually obtains a step of acquiring information on a region to be highly imaged in a frame and a region to be highly imaged in a frame. A first region to be subjected to a particularly high image quality, a step of determining whether or not there is an end of an object drawn in the frame in the vicinity of the inside of the frame portion of the first region, When there is an end of the object in the vicinity of the inside of the frame portion of the region where the image should be increased in particular, the region within the required distance from the frame portion outside the frame portion of the final attention region is set as the second region A setting step; applying a high-image-processing process with a first intensity to each pixel belonging to the first area; and a second inferior to the first intensity with respect to each pixel belonging to the second area High image quality with high intensity Performing a high image processing with a third intensity that is inferior to the second intensity with respect to a third area that does not belong to any of the first area and the second area; , Is a program for executing.

  In addition, in order to solve the above-described problem, the image processing program according to the present invention acquires, in a computer, information on the type of an object to be imaged particularly in a frame, and the type in the frame. A step of acquiring position information including a contour position of the target object, and based on the position information of the target object belonging to the type, an area within a required distance from the contour of the target object belonging to the type is actually A step of setting a first region to be image-enhanced, a step of determining whether there is an end of an object drawn in the frame in the vicinity of the inside of the frame portion of the first region, and the first A step of setting a region within a predetermined distance from the frame portion outside the frame portion of the first region as a second region when the end of the object is in the vicinity of the frame portion inside the region of Each pixel belonging to the first region is subjected to high image processing at a first intensity, and each pixel belonging to the second region is high at a second intensity that is inferior to the first intensity. An imaging process is performed, and a high imaging process is performed at a third intensity that is inferior to the second intensity with respect to a third area that does not belong to any of the first area and the second area Is a program for executing steps.

  According to the information processing apparatus, the image forming method, and the image forming program according to the present invention, it is possible to increase the image for each region in consideration of the edge of the object.

  Embodiments of an information processing apparatus, an image processing method, and an image processing program according to the present invention will be described with reference to the accompanying drawings.

  FIG. 1 is a schematic overall configuration diagram showing an embodiment of an information processing apparatus 10 according to the present invention.

  In the present embodiment, an example in which a recording / reproducing apparatus that records and reproduces data including video and audio, such as an HDD / DVD recorder or a personal computer equipped with a TV tuner, is used as the information processing apparatus 10.

  The information processing apparatus 10 includes a CPU 11, a RAM 12, a ROM 13, a network connection unit 14, a selection target storage unit 15, an area setting storage unit 16, an EPG data storage unit 17, a recording file storage unit 18, and an interface unit 20.

  The CPU 11 controls the processing operation of the information processing apparatus 10 according to a program stored in the ROM 13. The CPU 11 loads the image processing program stored in the ROM 13 and data necessary for executing the program into the RAM 12, and in accordance with the image processing program, the object edge of the recording file to be subjected to the high image processing is loaded. Considering the part (edge, contour), processing is performed to increase the image for each region.

  The RAM 12 provides a work area for temporarily storing programs executed by the CPU 11 and data.

  The ROM 13 stores a startup program for the information processing apparatus 10, an image processing program, and various data necessary for executing these programs.

  The ROM 13 has a configuration including a recording medium readable by the CPU 11 such as a magnetic or optical recording medium or a semiconductor memory, and a part or all of the programs and data in the ROM 13 are transmitted via an electronic network. It may be configured to be downloaded.

  The network connection unit 14 implements various information communication protocols according to the network form. The network connection unit 14 connects the information processing apparatus 10, the recording / reproducing apparatus, and the EPG server database 30 according to these various protocols. For this connection, an electrical connection via an electronic network can be applied. Here, the electronic network means an entire information communication network using telecommunications technology. In addition to a LAN (Local Area Network) and the Internet network, a telephone communication line network, an optical fiber communication network, a cable communication network, and a satellite communication network. Etc.

  FIG. 3 is an explanatory diagram showing the selection object types associated with the categories stored in the selection object storage unit 15.

  The selected object storage unit 15 is associated with categories such as dramas and song programs in advance for the types of objects (faces, telops (lyrics, etc.)) to be particularly high-imaged (hereinafter referred to as “target object types”). Remember the information.

  In addition, the target object type information associated with each category is displayed on the display device 22 by the CPU 11 according to the image processing program on the target type selection screen of each category, and input by the user based on this selection screen. An instruction may be received via the device 23 and stored in the selection target storage unit 15.

  The region setting storage unit 16 stores in advance information on a region that should be particularly high (hereinafter referred to as a region of interest). This attention area may be an area for which an instruction is received by the user via the input device 23. In addition, the area setting storage unit 16 stores in advance information as to whether or not to perform high image formation based on the attention area.

  The EPG data generally includes information such as a category (genre name), broadcast start date / time and end date / time, program name, program content, and performer name of the program to be broadcast. The recording / reproducing apparatus is configured to display an EPG (electronic program guide) on the display device 22 via the interface unit 20 based on the EPG data.

  The EPG data storage unit 17 stores the EPG data received by the tuner 21 via the interface unit 20 when the broadcast station multiplexes and transmits the EPG data to the television broadcast signal. When the EPG data is distributed over the Internet, the EPG data acquired from the EPG server database 30 via the network connection unit 14 is stored.

  The recorded file storage unit 18 stores video data of a broadcasted program received by the tuner 21 input via the interface unit 20 as a recorded file as necessary.

  The interface unit 20 receives a video data, EPG data, and the like of a broadcasted program and applies the data to the recording / reproducing device. The video data and EPG data received by the tuner 21, the video data output from the recording / reproducing device, and the EPG It is connected to a display device 22 such as a CRT or LCD for displaying data and an input device 23 such as a remote controller having a function of transmitting the user's intention to the recording / reproducing device. The display device 22 is configured by a general display output device such as a liquid crystal display or a CRT display.

  The EPG server database 30 stores EPG data distributed by the EPG server over the Internet.

  FIG. 2 is a schematic block diagram showing a configuration example of a function realization unit by the CPU 11 shown in FIG. In addition, this function realization part may be comprised by hardware logics, such as a circuit, without using CPU11.

  The CPU 11 executes at least a selection object information acquisition unit 11a, a selection object type determination unit 11b, an object position acquisition unit 11c, an area designation determination unit 11d, an area information acquisition unit 11e, and a final attention area determination unit 11f according to an image processing program. , Function as an intensity setting unit 11g, an edge determination unit 11h, a buffer region setting unit 11i, and a high image processing unit 11j. Each of the units 11a to 11j uses a required work area of the RAM 12 as a temporary storage location for data.

  Next, each part 11a-11j of CPU11 is demonstrated.

  The selection target information acquisition unit 11a acquires information on a target type (target target type) that should be particularly high-imaged from the selection target storage unit 15, and uses this target target type information as a selection target type determination unit. 11b.

  The selection target type determination unit 11b determines whether a face is selected as a target target type and whether a telop is selected.

  The object position acquisition unit 11c acquires the position information of the object for each target object type, and stores this position information in a required work area of the RAM 12. For example, when the target object type is a face, the object position acquisition unit 11c includes face position information (at least position information of a face outline) in each frame constituting a recording file to be subjected to high image processing. Including).

  Various techniques for identifying the position of the object in the frame are known, and any of these techniques can be applied. For example, when the object is a face, the object position acquisition unit 11c can acquire information on the position of the face in the frame by applying a conventional face recognition technique. When the object is a telop, the object position acquisition unit 11c can acquire the position of the telop in the frame by applying a conventional telop recognition technique.

  In this embodiment, an example in which a face and a telop can be selected as the target object type has been described. However, any object other than a face and a telop can be used as long as the object can acquire position information in a frame. Even if it exists, it can be set as an attention object classification.

  The region designation determination unit 11d searches the region setting storage unit 16 to determine whether or not to perform high image formation based on the region of interest.

  The area information acquisition unit 11 e acquires the information on the attention area from the area setting storage unit 16 and stores the information on the attention area in a required work area of the RAM 12.

  The final attention area determination unit 11f determines an area (hereinafter, referred to as a final attention area) that is to be actually increased in image quality based on information on the position of the object belonging to the attention object type and information on the attention area. In the case of executing high image formation based only on the target object type, the final attention area determination unit 11f sets an area within a predetermined distance from the outline of the attention object as the final attention area.

  The intensity setting unit 11g assigns the intensity of high image processing to each area in the frame. In the present embodiment, an example in which the intensity of the high image processing is set to three levels of 0, 1 and 2 will be described. The intensity setting unit 11g assigns intensity 2 to the final attention area. In addition, an intensity of 0 is assigned to areas other than the final attention area. When there is a buffer area, strength 1 is assigned to the buffer area. In the present embodiment, it is assumed that the region subjected to the high image processing with high intensity is a higher image.

  The edge determination unit 11h determines whether or not there is an edge portion (end portion or contour) of the object near the inside of the frame portion of the final attention area. Here, the case where the edge of the object is in the vicinity of the inside of the frame portion of the final attention area includes the case where the edge portion of the object crosses the frame portion of the final attention area.

  The buffer region setting unit 11i sets a region within a predetermined distance from the frame portion outside the frame portion of the final target region as a buffer region.

  The high image processing unit 11j performs high image processing on the pixels belonging to each region according to the intensity assigned to each region by the intensity setting unit 11g. For example, for an area to which intensity 2 is assigned (final attention area), a high-resolution processing such as super-resolution, which has a high sharpness but a high processing load and requires processing time, is applied to an area to which intensity 0 is assigned. In such a case, an image processing with a lower processing load such as cubic interpolation is performed.

  Next, an example of the operation of the information processing apparatus 10 according to the present embodiment will be described.

  FIG. 4 is a flowchart showing a procedure when the CPU 11 of the information processing apparatus 10 shown in FIG. 1 performs high image by region in consideration of the edge of an object for a recording file to be subjected to high image processing. is there. In FIG. 4, reference numerals with numbers added to S indicate steps in the flowchart.

  Note that FIG. 4 shows a procedure for performing image enhancement for each region in consideration of the edge of an object for one of a plurality of frames constituting a recording file to be subjected to image enhancement processing. By repeating the procedure shown in FIG. 4 for all the frames constituting the recording file, the entire recording file can be made high-image.

  In step S1, the selection target information acquisition unit 11a acquires the category of the recording file to be subjected to the high image processing from the EPG data storage unit 17, and the attention associated with this category from the selection target storage unit 15 Get information about the object type. As a result, the target object type for this recorded file is specified.

  Next, in step S2, the selection target type determination unit 11b determines whether a face is selected as the target target type. If a face has been selected, the process proceeds to step S3. On the other hand, if no face is selected, the process proceeds to step S4.

  Next, in step S <b> 3, the object position acquisition unit 11 c acquires position information of the face in the frame on which the high image processing is performed.

  Next, in step S4, the selection target type determination unit 11b determines whether a telop is selected as the target target type. If a telop is selected, the process proceeds to step S5. On the other hand, if no face is selected, the process proceeds to step S6.

  Next, in step S5, the object position acquisition unit 11c acquires the position information of the telop in the frame on which the high image processing is performed.

  Next, in step S6, the region designation determination unit 11d searches the region setting storage unit 16 to determine whether or not to perform high image formation based on the region of interest. In the case of executing the image enhancement based on the attention area, the process proceeds to step S7. On the other hand, when the high image formation based on the attention area is not executed, the process proceeds to step S8.

  By the above procedure, it is possible to determine whether or not to perform high image formation based on the target object type and the target area. When neither the target object type nor the attention area is used, the whole area of the frame is increased in image.

  Next, in step S <b> 7, the region information acquisition unit 11 e acquires information on the attention region from the region setting storage unit 16.

  Next, in step S8, the final attention area determination unit 11f determines an area (final attention area) that is to be a particularly high image based on information on the position of the object belonging to the target object type and information on the attention area. To do.

  Next, in step S9, the intensity setting unit 11g assigns intensity 2 as the high image processing intensity to the final attention area.

  Next, in step S10, the edge determination unit 11h determines whether or not there is an object edge near the inside of the frame portion of the final region of interest. If there is an edge of the object in the vicinity of the inner side of the final attention area, the process proceeds to step S11. If not, the process proceeds to step S13.

  Next, in step S11, the buffer area setting unit 11i receives a determination result that the edge of the object exists in the vicinity of the inner frame part of the final attention area from the edge determination unit 11h, and this frame outside the frame part of the final attention area. An area within a required distance from the section is set as a buffer area.

  Next, in step S12, the intensity setting unit 11g assigns intensity 1 as the high image processing intensity to the buffer area.

  Next, in step S13, the intensity setting unit 11g assigns intensity 0 as the high image processing intensity to the area other than the final target area and the buffer area.

  Here, the relationship between the edge portion of the object and the buffer region will be briefly described.

  FIG. 5 is an explanatory diagram showing an example of the final attention area in the frame when the image is increased based only on the attention area.

  In the example shown in FIG. 5, since the attention object type is not specified, the attention area acquired by the area information acquisition unit 11e is the final attention area. Higher-intensity image processing is performed on the inside of the final region of interest (intensity 2) indicated by the broken line, compared to the outside of the final region of interest (intensity 0).

  When the high image processing is performed, the periphery of the edge portion (contour) of the object in the frame may appear to be enhanced and expanded under the influence of the high image processing over several pixels. For this reason, for example, when the edge portion of a certain object extends over regions having different high image processing strength, the user receives an impression that the edge portion is discontinuous and feels unnatural. There is a fear.

  The object in this image is not limited to the target object. For example, even if the target object type is a face and the face part is in the same high image processing strength area, there are objects such as bicycles and trees in the image, and these objects have high image processing strength. In the case of straddling different areas, there is a risk that discontinuity will occur in the edge portions of these objects.

  In order not to give the user a discontinuity of the edge portion, it is preferable that the edge portion of one object exists in the region of the same high image processing intensity. It is more preferable if this edge portion does not exist in the vicinity of the inside of the frame portion of the region.

  However, when the image enhancement process is performed based on the attention area stored in advance in the area setting storage unit 16, the edge portion of one object exists in the vicinity of the inside of the frame of the area (the intensity of the image enhancement process). Etc.). In these cases, it is preferable to gradually decrease the high image processing intensity from the final attention area to the outside. By gradually decreasing the image processing intensity, it is possible to reduce the discontinuity of the edge portion that the user receives. In the present embodiment, the high image processing strength of the region (buffer region) within a required distance from the frame portion outside the frame portion of the final target region is strength 1, and the high image processing strength outside the buffer region is strength 0. An example of this is shown.

  In FIG. 5, the objects in the frame are only airplanes and mountains, both of which are present in the region of the same high image processing intensity, and the edge portion of each object is not present near the inside of the frame of the region. For this reason, although the high image processing intensity changes rapidly from intensity 2 to intensity 0 inside and outside the final attention area, there is no possibility of causing the user to feel the discontinuity of the object, and a buffer area based on the presence of the edge is provided. There is no need to provide it. Of course, a buffer region may be provided also in this case.

  FIG. 6 is an explanatory diagram showing another example of the final attention area in the frame when the image is increased based only on the attention area.

  In FIG. 6, the person who is the object in the frame exists across the frame of the final attention area. For this reason, it is necessary to provide a buffer area based on the presence of an edge.

  FIG. 7 is an explanatory diagram showing an example when a buffer area is set for the frame shown in FIG.

  As shown in FIG. 7, by providing a buffer area shown as an area surrounded by a one-dot chain line and a broken line, the change in image quality of the edge portion of a person, which is an object in the frame, is compared with the case where no buffer area is provided. Can be smoother.

  FIG. 8 is an explanatory diagram illustrating an example of a final attention area in a frame when performing high-resolution based only on the target object type (face).

  In the example shown in FIG. 8, since the attention area is not specified, an area within a predetermined distance from the face contour is the final attention area. Also in FIG. 8, since the person who is an object in the frame exists across the frame of the final attention area, a buffer area shown as an area surrounded by a one-dot chain line and a broken line is provided.

  FIG. 9 is a diagram for explaining a region setting procedure when performing high-image formation based on information on the position of an object belonging to the target object type (face) and information on the target area.

  FIG. 10 is an explanatory diagram showing an example of area setting in the frame shown in FIG.

  In the example illustrated in FIG. 9, the attention area and the area within a predetermined distance from the face outline overlap. That is, the face exists outside the attention area. However, it is necessary to perform high-intensity image processing with intensity 2 on the face.

  In this case, as shown in FIG. 10, the final attention area determination unit 11f is within a predetermined distance from the outline of the target object based on the information on the position of the target object belonging to the target object type and the information on the target area. An area composed of the area and the attention area acquired by the area information acquisition unit 11e is determined as the final attention area. Further, since the lower body of the person crosses the frame of the final attention area, a buffer area shown as an area surrounded by a dashed line and a broken line is provided.

  As described with reference to FIGS. 5 to 10, when the edge portion of the object exists in the vicinity of the inside of the frame portion of the final attention area (for example, when crossing the frame portion of the final attention area), the buffer area It is good to provide.

  Finally, in step S14, the high image processing unit 11j performs high image processing on the pixels belonging to each region according to the intensity assigned by the intensity setting unit 11g.

  By repeating the above procedure for all the frames constituting the recording file, it is possible to increase the image for each region in consideration of the edge of the object for the recording file to be subjected to the high image processing.

  When the information processing apparatus 10 according to the present embodiment performs high image processing for each image on a frame image, whether the edge portion of the object existing in the frame exists in the vicinity of the inside of the frame portion of the final target region. Determine if. For this reason, it is possible to perform high image processing in consideration of the edge portion based on the determination result.

  Therefore, according to the information processing apparatus 10 according to the present embodiment, the discontinuity can be reduced when different resolution enhancement processing is performed on continuous edge portions. Further, even when the edge portion exists in the same region, the feeling of expansion of the edge portion that can be visually recognized when the edge portion is in the vicinity of the inside of the frame portion can be reduced.

  Further, according to the information processing apparatus 10 according to the present embodiment, it is possible to increase the intensity difference between the final attention area and the area other than this area only when the edge portion does not exist near the inside of the frame portion of the area. is there. Therefore, waste of processing time can be saved as compared with the conventional technique in which the gradient of high image processing intensity is applied to the dark clouds.

  Further, the information processing apparatus 10 according to the present embodiment determines the final attention area based on the information on the position of the object belonging to the attention object type and the information on the attention area (see FIG. 10). For this reason, it is possible to increase the image without waste for both the target object and the target area desired by the user. Therefore, the information processing apparatus 10 according to the present embodiment can perform high-image processing at high speed without causing the user to feel discontinuity in image quality.

  Note that the present invention is not limited to the above-described embodiment as it is, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage.

  For example, when a method that does not require a plurality of frames is used in the image enhancement process, the image enhancement process for each frame can be performed independently of the preceding and succeeding frames. In this case, the present invention can be applied not only to moving images but also to one (one frame) still image.

  In addition, various inventions can be formed by appropriately combining a plurality of components disclosed in the embodiment. For example, some components may be deleted from all the components shown in the embodiment.

1 is a schematic overall configuration diagram showing an embodiment of an information processing apparatus according to the present invention. FIG. 2 is a schematic block diagram illustrating a configuration example of a function realizing unit by a CPU illustrated in FIG. 1. Explanatory drawing which shows the selection target type linked | related with the category memorize | stored in a selection target memory | storage part. The flowchart which shows the procedure at the time of performing the high image according to area | region considering the edge of an object about the recording file used as the object which performs the high image processing by CPU of the information processing apparatus shown in FIG. Explanatory drawing which shows an example of the last attention area | region in a flame | frame at the time of performing high-image-izing based only on attention area. Explanatory drawing which shows the other example of the final attention area | region in a flame | frame at the time of performing high-image-izing based only on attention area. FIG. 7 is an explanatory diagram showing an example when a buffer area is set for the frame shown in FIG. 6. Explanatory drawing which shows an example of the last attention area | region in a flame | frame at the time of performing high-image-izing based only on attention object classification (face). The figure for demonstrating the area | region setting procedure at the time of performing high-image-izing based on the information on the position of the target object which belongs to the target object type (face) and the information on the target area. Explanatory drawing which shows an example of the area | region setting in the flame | frame shown in FIG.

Explanation of symbols

10 Information processing apparatus 11 CPU
11a Selection target information acquisition unit 11b Selection target type determination unit 11c Target position acquisition unit 11d Region designation determination unit 11e Region information acquisition unit 11f Final attention region determination unit 11g Intensity setting unit 11h Edge determination unit 11i Buffer region setting unit 11j High image processing unit 12 RAM
13 ROM
14 Network connection unit 15 Selection object storage unit 16 Area setting storage unit 17 EPG data storage unit 18 Recording file storage unit 20 Interface unit 21 Tuner 22 Display device 23 Input device 30 EPG server database

Claims (15)

Area information acquisition means for acquiring information of an area that should be particularly high in the frame;
A final region of interest determination means that sets the region to be highly imaged as the first region to be actually imaged particularly high;
Edge determination means for determining whether or not there is an end of an object drawn in the frame in the vicinity of the inside of the frame portion of the first region;
A buffer for setting a region within a predetermined distance from the frame portion outside the frame portion of the first region as a second region when the end portion of the object is near the inside of the frame portion of the first region. Region setting means;
Each pixel belonging to the first area is subjected to high image processing with a first intensity, and each pixel belonging to the second area is subjected to a high image with a second intensity inferior to the first intensity. The third region that does not belong to any one of the first region and the second region is subjected to a high image processing with a third intensity that is inferior to the second intensity. Imaging processing means;
An information processing apparatus comprising: A selection object type acquisition means for acquiring information on the type of object to be imaged particularly in the frame;
Object position acquisition means for acquiring position information including a contour position of an object belonging to the type in the frame;
Based on the information on the position of the object belonging to the type, the final region of interest is determined as a first region in which a region within a required distance from the outline of the object belonging to the type is to be actually increased in image Means,
Edge determination means for determining whether or not there is an end of an object drawn in the frame in the vicinity of the inside of the frame portion of the first region;
A buffer for setting a region within a predetermined distance from the frame portion outside the frame portion of the first region as a second region when the end portion of the object is near the inside of the frame portion of the first region. Region setting means;
Each pixel belonging to the first area is subjected to high image processing with a first intensity, and each pixel belonging to the second area is subjected to a high image with a second intensity inferior to the first intensity. The third region that does not belong to any one of the first region and the second region is subjected to a high image processing with a third intensity that is inferior to the second intensity. Imaging processing means;
An information processing apparatus comprising: A selection object type acquisition means for acquiring information on the type of object to be imaged particularly in the frame;
Object position acquisition means for acquiring position information including a contour position of an object belonging to the type in the frame;
Further comprising
The final attention area determination means includes
Based on the information on the position of the object belonging to the type and the information on the area to be imaged in particular, the first area to be actually imaged in particular is determined.
The information processing apparatus according to claim 1. The frame is a part of image data composed of a plurality of frames including the frame.
The information processing apparatus according to claim 3. A selection object storage means for storing the information of the type of the object to be highly imaged in association with a category;
EPG data storage means for storing EPG data including at least information on the category to which the image data belongs;
Further comprising
The selection object type acquisition means includes
Based on the category to which the image data acquired from the EPG data storage means belongs, it is configured to acquire information on the type of the object to be highly imaged associated with the category from the selection target storage means. The
The information processing apparatus according to claim 4. Obtaining information of a region that should be particularly high in the frame;
Making the region to be highly imaged a first region to be actually imaged particularly high;
Determining whether there is an edge of an object drawn in the frame in the vicinity of the inside of the frame of the first region;
A step of setting a region within a predetermined distance from the frame portion outside the frame portion of the first region as a second region when the end portion of the object is near the inside of the frame portion of the first region. When,
Each pixel belonging to the first area is subjected to high image processing with a first intensity, and each pixel belonging to the second area is subjected to a high image with a second intensity inferior to the first intensity. Performing high image processing at a third intensity that is inferior to the second intensity on a third area that does not belong to any of the first area and the second area. When,
An image processing method comprising: Obtaining information of the type of the object to be particularly imaged in the frame;
Obtaining position information including a contour position of an object belonging to the type in the frame;
Based on the information on the position of the object belonging to the type, a region within a required distance from the contour of the object belonging to the type is set as a first region that should be subjected to actual high image processing,
Determining whether there is an edge of an object drawn in the frame in the vicinity of the inside of the frame of the first region;
A step of setting a region within a predetermined distance from the frame portion outside the frame portion of the first region as a second region when the end portion of the object is near the inside of the frame portion of the first region. When,
Each pixel belonging to the first area is subjected to high image processing with a first intensity, and each pixel belonging to the second area is subjected to a high image with a second intensity inferior to the first intensity. Performing high image processing at a third intensity that is inferior to the second intensity on a third area that does not belong to any of the first area and the second area. When,
An image processing method comprising: Obtaining information of the type of the object to be particularly imaged in the frame;
Obtaining position information including a contour position of an object belonging to the type in the frame;
Further comprising
The step of setting the first region includes
The step of determining the first region to be actually imaged particularly based on the information on the position of the object belonging to the type and the information on the region to be imaged in particular.
The image processing method according to claim 6. The frame is a part of image data composed of a plurality of frames including the frame.
The image processing method according to claim 8. Storing the information of the type of the object to be highly imaged in association with the category;
Storing EPG data including at least information of the category to which the image data belongs;
Further comprising
The step of acquiring the information of the type of the object to be imaged in particular,
Obtaining information on the category to which the image data belongs, and obtaining information on the type of the object to be imaged in particular associated with the category based on the category;
The image processing method according to claim 9. On the computer,
Obtaining information of a region that should be particularly high in the frame;
Making the region to be highly imaged a first region to be actually imaged particularly high;
Determining whether there is an edge of an object drawn in the frame in the vicinity of the inside of the frame of the first region;
A step of setting a region within a predetermined distance from the frame portion outside the frame portion of the first region as a second region when the end portion of the object is near the inside of the frame portion of the first region. When,
Each pixel belonging to the first area is subjected to high image processing with a first intensity, and each pixel belonging to the second area is subjected to a high image with a second intensity inferior to the first intensity. Performing high image processing at a third intensity that is inferior to the second intensity on a third area that does not belong to any of the first area and the second area. When,
An image processing program for executing On the computer,
Obtaining information of the type of the object to be particularly imaged in the frame;
Obtaining position information including a contour position of an object belonging to the type in the frame;
Based on the information on the position of the object belonging to the type, a region within a required distance from the contour of the object belonging to the type is set as a first region that should be subjected to actual high image processing,
Determining whether there is an edge of an object drawn in the frame in the vicinity of the inside of the frame of the first region;
A step of setting a region within a predetermined distance from the frame portion outside the frame portion of the first region as a second region when the end portion of the object is near the inside of the frame portion of the first region. When,
Each pixel belonging to the first area is subjected to high image processing with a first intensity, and each pixel belonging to the second area is subjected to a high image with a second intensity inferior to the first intensity. Performing high image processing at a third intensity that is inferior to the second intensity on a third area that does not belong to any of the first area and the second area. When,
An image processing program for executing Obtaining information on the type of the object to be imaged especially in the frame in the computer;
Obtaining position information including a contour position of an object belonging to the type in the frame;
And execute
The step of setting the first region includes
The step of determining the first region to be actually imaged particularly based on the information on the position of the object belonging to the type and the information on the region to be imaged in particular.
The image processing program according to claim 11. The frame is a part of image data composed of a plurality of frames including the frame.
The image processing program according to claim 13. Storing in the computer further information on the type of the object to be imaged especially in association with the category;
Storing EPG data including at least information of the category to which the image data belongs;
And execute
The step of acquiring the information of the type of the object to be imaged in particular,
Obtaining information on the category to which the image data belongs, and obtaining information on the type of the object to be imaged in particular associated with the category based on the category;
The image processing program according to claim 14.

Images