JP4940024B2 - Information processing apparatus, motion vector generation program, and interpolated image generation program - Google Patents

Description

  The present invention relates to an information processing apparatus, a motion vector generation program, and an interpolation image generation program that handle an interpolation frame interpolated between frames.

  In the field of moving image processing and the like, there is a technique for generating an interpolated frame to be interpolated between two frames (a previous frame and a subsequent frame). In generating the interpolation frame, a technique for determining a motion vector between the preceding and following frame images is very important. The interpolated frame image is generated based on a motion vector between at least two frame images in front and back. For this reason, unless an appropriate motion vector can be determined, an appropriate interpolated frame image cannot be generated.

  Conventionally, there is a technique disclosed in Japanese Patent Laid-Open No. 2002-185970 (Patent Document 1) for determining this type of motion vector.

  A moving image encoding apparatus disclosed in Japanese Patent Laid-Open No. 2002-185970 (Patent Document 1) is an apparatus that encodes an image frame using a plurality of motion compensation inter-frame prediction methods, and the motion of the image frame. In motion vector search means for searching for vectors and motion compensation inter-frame prediction processing, a plurality of prediction methods such as block movement, affine transformation and bilinear transformation are used for each small area of variable size. A prediction unit that generates and outputs a prediction image, and determines an optimal region size and prediction method based on a plurality of prediction images from the prediction unit, and various parameters (side information) such as region information and motion vectors, and a prediction image And an area prediction determining means for outputting.

This conventional technique requires a motion vector by devising a region division method and using a motion vector of an adjacent region as a motion vector of the region of interest when the prediction method of a region adjacent to the region of interest is different. The motion vector can be determined so that data is reduced.
JP 2002-185970 A

  One method for calculating motion vectors is block matching. In order to determine a motion vector by block matching, a parameter group including a plurality of parameters is required.

  This parameter group differs not only in the optimal object for calculating the motion vector between the stationary object scene and the moving object scene, but also there is an optimal parameter group particularly for a character image. Furthermore, when the character image moves, the optimum parameter group for the moving character should be applied. This is because the background image of a character is often mixed in a block containing characters, so in block matching that uses the luminance difference between blocks in the previous and next frames, parameters such as the block size are suitable for the character. Because it is necessary to make it.

  However, in the conventional technology, when calculating a motion vector, a character region and a region other than a character, a stationary object region, a moving object region, and the like are not clearly distinguished. For this reason, a trade-off is often made by using an intermediate parameter group, but it is difficult to obtain an image with sufficient accuracy for each region of the frame. In particular, when the frame image includes characters, if the accuracy of the interpolated image is poor, it is conspicuous as a major failure for human eyes. If the letters move, this failure becomes even more noticeable.

  The present invention has been made in consideration of the above-described circumstances. The frame is divided into a plurality of areas including at least a character area, and a motion vector is determined by applying a parameter group corresponding to the image of each area to each area. An information processing apparatus, a motion vector generation program, and an interpolation image generation program are provided.

  In order to solve the above-described problem, the information processing apparatus according to the present invention applies a parameter group including a plurality of parameters when determining a motion vector necessary for generating an interpolation frame from at least two frames. A character area detecting means for receiving at least two frames of data and acquiring position information of a character area, which is an area including characters, from each of the plurality of inputted frames. Static motion determining means for determining whether or not the characters in the character region move between the plurality of inputted frames when the positions of the character regions match in all of the plurality of inputted frames. A moving character region parameter group is included in the character region in the moving character region in which characters included in the character region move between the input frames. The stationary character region parameter group is applied to the stationary character region where the characters are stationary between the input frames, and the default parameter group is applied to the other region, so that the moving character region and the stationary region are applied. Motion vector determining means for determining the motion vectors between the input frames in the character region and the other region.

  On the other hand, the motion vector generation program according to the present invention is a parameter comprising a plurality of parameters when determining a motion vector necessary for generating an interpolation frame from at least two frames in order to solve the above-described problem. A program for applying a group, wherein the computer receives data of the at least two frames, and obtains position information of a character area, which is an area including characters, from each of the plurality of inputted frames Static detection for determining whether or not the characters in the character area move between the input frames when the position of the character area matches in all of the input frames. A moving character region in the moving character region in which the character included in the character region moves between the input frames; Apply the parameter group, the static character area parameter group to the static character area where the characters included in the character area are stationary between the input frames, and the default parameter group to the other areas. A program for functioning as motion vector determining means for determining the motion vectors between the plurality of inputted frames in the moving character region, the still character region, and the other region.

  Further, in order to solve the above-described problem, the interpolation image generation program according to the present invention is a parameter composed of a plurality of parameters when determining a motion vector necessary for generating an interpolation frame from at least two frames. A program for applying a group, wherein the computer receives data of the at least two frames, and obtains position information of a character area, which is an area including characters, from each of the plurality of inputted frames Static detection for determining whether or not the characters in the character area move between the input frames when the position of the character area matches in all of the input frames. A determining unit, a moving character region parameter for a moving character region in which characters included in the character region move between the plurality of input frames; Applying the static character region parameter group to the static character region where the characters included in the character region are stationary between the input frames, and applying the default parameter group to the other regions. A motion vector determining means for determining the motion vector between the plurality of input frames in the dynamic character region, the still character region, and the other region, and the plurality of input based on the motion vector It is a program for functioning as an interpolation image generation means for generating the interpolation frame image to be interpolated between frames, and an image output control means for displaying the interpolation frame image.

  According to the information processing apparatus, the motion vector generation program, and the interpolation image generation program according to the present invention, the frame is divided into a plurality of regions including at least a character region, and a parameter group corresponding to the image in each region is applied to each region. To determine a motion vector.

  Embodiments of an information processing apparatus, a motion vector generation program, and an interpolation image generation program according to the present invention will be described with reference to the accompanying drawings.

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

  The information processing apparatus 10 includes a CPU 11, a RAM 12, a ROM 13, a network connection unit 14, a frame memory unit 15, a character area information storage unit 16, a parameter group storage unit 17, an interface unit 20, a display device 21, and a tuner 22.

  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 an interpolation image generation program containing the motion vector generation program stored in the ROM 13 and data necessary for execution of the program into the RAM 12, and in accordance with the interpolation image generation program, a plurality of data including at least a character area are loaded. In a frame divided into regions, a motion vector is determined by applying a parameter group corresponding to the image of each region, and an interpolated image is generated based on the motion vector.

  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 interpolation image generation program, and various types of 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 and other electrical devices 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.

  Here, a procedure for generating an interpolation frame image will be briefly described.

  An interpolated frame image can be generated by calculating a motion vector by performing block matching between at least two frame images before and after, and using this motion vector. In the present embodiment, an example in which an interpolation frame image is generated based on two frames (the previous frame and the subsequent frame) and is interpolated between the two frames will be described.

  FIG. 2 is an explanatory diagram schematically showing an example of a block matching process between two front and rear frames.

  As shown in FIG. 2, in block matching processing, in order to evaluate the similarity between images, a region of interest (block) having a certain size (for example, 16 pixels × 16 pixels) from images to be compared (front and back frame images). Cut out. This positional relationship between the blocks is called a matching vector. Next, a matching value that is an index of the degree of matching between blocks is calculated. As the matching value, a sum of luminance differences (SAD), a square sum of luminance differences (SSD), or the like is often used. Then, the cut-out position that gives the minimum value of the matching value is searched within the search range, and the matching vector that gives the minimum value of the matching value is set as the motion vector.

  The block matching process requires various parameters including the block size as initial values. For this reason, if the parameter group consisting of these various parameters is different, the obtained motion vector is different. Examples of the various parameters include a motion vector search range, a motion vector detection block size, a motion vector allocation block size, a detected motion vector value clip amount, and a motion vector continuity guarantee threshold between adjacent blocks. Can be mentioned.

  The parameter group to be applied differs between a character image and a non-character image, or a moving object image and a stationary object image. For this reason, it is desirable to apply different parameter groups to different types of images. Therefore, it is desirable to divide the frame into regions for each type of image, and to determine a motion vector by applying a parameter group corresponding to the image in each region to each region.

  The frame memory unit 15 receives video data from the tuner 22 and stores it for each frame. The frame memory unit 15 stores the interpolation frame generated by the CPU 11.

  In the present embodiment, an example will be described in which video data of a broadcast program is received by the tuner 22 and interpolation frames are generated in real time for a plurality of frames constituting the video data. More specifically, in this embodiment, the video data received by the tuner 22 is sequentially given to the CPU 11 and the frame memory unit 15 for each frame, and the frame memory unit 15 stores the given video data for each frame. Then, the CPU 11 generates an interpolation frame based on a frame (back frame) given from the tuner 22 and a frame (previous frame) stored in the frame memory unit 15 immediately before this frame. Will be described.

  The character area information storage unit 16 is controlled by the write control unit 41 of the CPU 11, and includes character area information (information on the position of the character area of the frame) and a stationary character area in which characters included in the character area are stationary. Or information indicating whether the character is a moving character area with movement (static information) is stored in association with each other.

  The parameter group storage unit 17 stores in advance at least a parameter group suitable for moving characters (moving characters) (parameter group for moving character regions), a parameter group suitable for stationary characters (parameter group for stationary characters), and a region other than characters. A parameter group suitable for the above (default parameter group) is stored.

  The interface unit 20 receives video data of a broadcast program and supplies the video data to the CPU 11 and the frame memory unit 15, and displays video data received by the tuner 22, video data output by the CPU 11, and the like. It is connected to a display device 21 such as a CRT or LCD.

  FIG. 3 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 an image acquisition unit 31, a character area presence / absence determination unit 32, a parameter allocation unit 33, a motion vector determination unit 34, an interpolation image generation unit 35, an image output control unit 36, a write control unit 41, by an interpolation image generation program. It functions as a character region detection unit 42, a detection determination unit 43, a flag determination unit 44, a region position determination unit 45, a static movement determination unit 46, and a buffer region setting unit 51. Each of the units 31 to 36, 41 to 46 and 51 uses a required work area of the RAM 12 as a temporary storage location for data.

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

  4, the CPU 11 of the information processing apparatus 10 illustrated in FIG. 1 determines a motion vector by applying a parameter group corresponding to an image in each area to a frame divided into a plurality of areas including a character area. It is a flowchart which shows the procedure at the time of producing | generating an interpolation image based on a motion vector. In FIG. 4, reference numerals with numbers added to S indicate steps in the flowchart.

  FIG. 4 shows an example in which one interpolated frame image is generated from two frame images (front and rear frame images). By repeating the procedure shown in FIG. 4 for all the frames of the video data, an interpolation frame can be generated for the entire video data.

  The parameter group storage unit 17 previously stores a parameter group suitable for moving characters (parameter group for moving character area), a parameter group suitable for still characters (parameter group for still characters), and a parameter suitable for regions other than characters. It is assumed that a group (default parameter group) is stored.

  First, in step S <b> 1, the image acquisition unit 31 acquires a previous frame from the frame memory unit 15 and a subsequent frame from the tuner 22.

  Next, in step S <b> 2, the character area presence / absence determination unit 32 determines whether character area information exists in the character area information storage unit 16. If there is character area information, the process proceeds to step S3. If there is no character area information, the process proceeds to step S4.

  Next, in step S3, the parameter allocating unit 33 applies character group information (position of the character region of the frame) from the character region information storage unit 16 in order to determine a motion vector by applying a parameter group corresponding to the image of each region. ) And information on whether this character area associated with this character area information is a static character area or a dynamic character area (static information), and a static character area parameter group is The motion vector determination unit 34 is provided with information indicating that the dynamic character region parameter group is applied to the character region and the default parameter group is applied to the other regions, respectively.

  On the other hand, in step S <b> 4, the parameter assignment unit 33 gives the motion vector determination unit 34 information indicating that the default parameter group should be applied to all regions in the frame.

  Next, in step S <b> 5, the motion vector determination unit 34 determines a motion vector from the preceding and following frames input from the image acquisition unit 31 based on the parameter group information received from the parameter assignment unit 33.

  FIG. 5 is an explanatory diagram showing an example of a frame image including a static character region and a moving character region. In the frame image shown in FIG. 5, a static character region parameter group is applied to the static character region, a dynamic character region parameter group is applied to the dynamic character region, and a default parameter group is applied to the other regions.

  Next, in step S6, the interpolation image generation unit 35 generates an interpolation frame image based on the determined motion vector, and this interpolation frame is interpolated between the previous frame and the subsequent frame of the frame memory unit 15. As shown in FIG.

  In step S <b> 7, the image output control unit 36 reads a frame from the frame memory unit 15 and causes the display device 21 to output an image.

  With the above procedure, in a frame divided into a plurality of regions including a character region, a motion vector is determined by applying a parameter group corresponding to the image of each region, and an interpolated image is generated based on the motion vector. Can do.

  FIG. 6 is a flowchart showing a procedure for detecting character region information used when applying a parameter group corresponding to an image of each region and static information of characters included in the character region. In FIG. 6, reference numerals with numbers added to S indicate steps in the flowchart.

  In step S11, the writing control unit 41 provides a static motion determination flag indicating whether or not a character area is being detected in a required work area of the RAM 12, and this flag is used to indicate that the static motion determination is not currently being performed. Have information (invalidate static determination flag).

  Next, in step S <b> 12, the image acquisition unit 31 acquires the previous frame from the frame memory unit 15. Further, when the process has passed through step S <b> 17, the image acquisition unit 31 acquires a subsequent frame from the frame memory unit 15 or the tuner 22.

  Next, in step S <b> 13, the character region detection unit 42 detects a character region from the frame input from the image acquisition unit 31 and acquires character region information (position of the character region in the frame).

  Next, in step S <b> 14, the detection determination unit 43 determines whether a character area is detected by the image acquisition unit 31. If detected, the process proceeds to step S15. On the other hand, if not detected, the process proceeds to step S16.

  In step S15, the writing control unit 41 deletes the character region information from the character region information storage unit 16, and the series of procedures for detecting the character region information and the static information of the characters included in the character region is completed. . When the character area information is not stored, the series of procedures is finished as it is. As a result, it is assumed that there is no character area in the interpolated frame unless there is a character area in both the previous and subsequent frames, and the default parameter group is applied to the entire interpolated frame.

  Next, in step S <b> 16, the flag determination unit 44 refers to a required work area in the RAM 12 and determines whether or not the static movement determination flag is valid. If the static motion determination flag is invalid, the process proceeds to step S17. On the other hand, if it is valid, the process proceeds to step S18.

  Next, in step S17, the writing control unit 41 temporarily stores the detected character region information in the character region information storage unit 16, enables the static motion determination flag, and returns to step S12.

  On the other hand, in step S18, the region position determination unit 45 determines that the character region detected this time (character region in the subsequent frame) is a character region (character region in the previous frame) temporarily stored in the character region information storage unit 16 last time. ). If not, the process proceeds to step S19. On the other hand, if they match, the process proceeds to step S20.

  Here, the case where the character area does not match in the preceding and following frames is often the case where the character area has moved greatly within the frame (appears in a completely different location), so an error of several to several tens of pixels may occur. For example, it may be included when they match.

  Next, when the character areas of the preceding and following frames do not match, in step S19, the writing control unit 41 deletes the character area information temporarily stored in the character area information storage unit 16 last time, and the series of procedures ends. It becomes. In this step, when the character area information of the frame detected after this detection is not deleted and used, for example, the character area information is regarded as a static character area, and the character area information and the character area information include a static character. The character area information of the frame after the previous detection may be overwritten by associating with the information indicating the area.

  On the other hand, if the character areas of the preceding and following frames match, in step S20, the static motion determination unit 46 performs motion vector detection by comparing the current character area that matches the previous frame with the previous and next frames, and the characters included in this area Distinguishes whether is a stationary character or a moving character. The accuracy of the motion vector detection is sufficient if it can be distinguished from a stationary character and a moving character, and can be simply performed by using a default parameter group with relatively low accuracy.

  In step S21, the writing control unit 41 associates the character region information with information about whether the character region is a static character or a moving character, and stores it in the character region information recording unit.

  With the above procedure, it is possible to detect the character area information used when applying the parameter group corresponding to the image of each area and the static information of the characters included in the character area.

  At least before step S2 in FIG. 4, the character region information and the static information are stored in the character region information storage unit 16 by executing the procedure shown in FIG. 6 for the front and rear frames used in FIG. Note that you should keep Therefore, for example, the series of processes shown in FIG. 6 may be performed between the start of the procedure shown in FIG. 4 and step S2.

  Further, the character area information and static information used in S2 and S3 of FIG. 4 may be character area information and static information obtained from the previous frame and the previous frame. If character area information and static information obtained from the previous frame and the previous frame are used, the character area information and static information may be shifted by one frame, but this shift can be almost perceived by the user. This is not a problem in practice.

  When the character area information obtained from the previous frame and the previous frame is used in S2 and S3 of FIG. 4, for example, from step S2 in the procedure of FIG. 4 for the previous frame and the previous frame to the end of the procedure of FIG. In the meantime, a series of processing shown in FIG. 6 is performed to store the character area information of the previous frame and the previous frame in the character area information storage unit 16, and the character area information is stored for the previous frame and the subsequent frame. What is necessary is just to utilize at step S2 and S3 in the procedure of FIG. In this case, step S20 in FIG. 6 and step S4 in FIG. 4 may be synchronized.

  The information processing apparatus 10 according to the present embodiment performs static motion determination of characters inside the character area when detecting the character area from the previous and next frame images. For this reason, the character area can be distinguished into a stationary character area and a moving character area. Therefore, according to the information processing apparatus 10 according to the present embodiment, a frame image can be distinguished between a static character region and a moving character region, and an optimum parameter group can be applied to the image in each region. It is possible to acquire a simple motion vector.

  Further, the information processing apparatus 10 according to the present embodiment can generate a highly accurate interpolation frame image that does not cause the user to perceive failure even when moving characters are included based on the motion vector. .

  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. 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.

  Furthermore, although the flowcharts shown in FIGS. 4 and 6 show an example in which the processing of each step is performed in time series in the order described, parallel processing is not necessarily performed in time series. May be performed manually or individually.

  For example, in the present embodiment, an example in which video data of a broadcast program is received by the tuner 22 and interpolation frames are generated in real time for a plurality of frames constituting the video data has been described. An interpolation frame may be generated based on the video data (recording data). In this case, the interpolation frame may be generated in real time when the recorded data is reproduced, or the character area information and the static information are previously stored in the character area information storage unit 16 in association with the frame number for all the recorded data frames. The character area information and the static information may be used at the time of reproduction by using the frame number as an index.

  Further, one or more buffer areas are provided around the character area, and the buffer area is an intermediate value between the parameter group applied to the character area and the default parameter group, and gradually approaches the default parameter group as the distance from the character area increases. Such a parameter group may be applied. FIG. 7 shows an example in which three buffer areas are provided around the character area. As shown in FIG. 7, the motion vector is determined by applying the dynamic character buffer region parameter group and the static character buffer region parameter group to the buffer regions around the dynamic character region and the static character region, respectively.

  By providing a buffer area around the character area, discontinuity between the areas can be reduced. For example, when providing a three-layer buffer area, three distances from the character area to the frame portion of each buffer area are stored in advance in the ROM 13 or the like, and a parameter group for each buffer area is stored in the parameter group. Stored in the unit 17.

  In this case, between steps S2 and S3 shown in FIG. 4, the buffer area setting unit 51 of the CPU 11 reads the distance from the ROM 13 or the like to the frame part of each buffer area, and sets the buffer area around the character area. Execute. Then, in step S3 shown in FIG. 4, the parameter assigning unit 33 causes the stationary character area to include a static character area parameter group, the dynamic character area to include a dynamic character area parameter group, and each buffer area to each buffer area. For example, the motion vector determination unit 34 may be provided with information indicating that the parameter group for use and the default parameter group for the other areas should be applied.

1 is a schematic overall configuration diagram showing a first embodiment of an information processing apparatus according to the present invention. Explanatory drawing which shows roughly an example of the block matching process between two front and back frames. FIG. 2 is a schematic block diagram illustrating a configuration example of a function realizing unit by a CPU illustrated in FIG. 1. A flowchart showing a procedure for determining a motion vector for a frame divided into a plurality of regions including a character region by applying a parameter group corresponding to the image of each region and generating an interpolated image based on the motion vector. . Explanatory drawing which shows an example of the frame image containing a static character area | region and a moving character area | region. The flowchart which shows the procedure at the time of detecting the character area information utilized when applying the parameter group according to the image of each area | region, and the static motion information of the character contained in this character area. Explanatory drawing which shows an example of the frame image in the case of providing three buffer areas around a character area.

Explanation of symbols

10 Information processing apparatus 11 CPU
12 RAM
13 ROM
14 network connection unit 15 frame memory unit 16 character region information storage unit 17 parameter group storage unit 20 interface unit 21 display device 22 tuner 31 image acquisition unit 32 character region presence / absence determination unit 33 parameter allocation unit 34 motion vector determination unit 35 interpolation image generation Unit 36 image output control unit 41 writing control unit 42 character region detection unit 43 detection determination unit 44 flag determination unit 45 region position determination unit 46 static motion determination unit 51 buffer region setting unit

Claims (9)

An information processing apparatus that applies a parameter group composed of a plurality of parameters when determining a motion vector necessary for generating an interpolated frame image to be interpolated into the plurality of frames from a plurality of frame images,
Character region detection means that receives the plurality of frames and acquires position information of a character region that is a region including characters from each of the plurality of input frames;
Static decision means for determining whether or not the characters in the character region move between the plurality of inputted frames when the position of the character region matches in all of the plurality of inputted frames;
A moving character region parameter group is set in a moving character region in which characters included in the character region move between the input frames, and a character group included in the character region is stopped between the input frames. The static character region parameter group is applied to the static character region and the default parameter group is applied to the other region, and the input is performed in the dynamic character region, the static character region, and the other region. Motion vector determining means for determining the motion vector from a plurality of frames;
An information processing apparatus comprising: Interpolated image generating means for generating the interpolated frame image interpolated between the input plurality of frames based on the motion vector;
Image output control means for displaying the interpolated frame image;
The information processing apparatus according to claim 1, further comprising: Buffer area setting means for setting a buffer area around the character area;
The motion vector determining means includes
The buffer area around the dynamic character area is applied with a parameter group for a dynamic character buffer area that takes an intermediate value between the parameter group for the dynamic character area and the default parameter group, and the buffer around the static character area is applied. The area further includes a function of determining the motion vector of the buffer area by applying a static character buffer area parameter group that takes an intermediate value between the static character area parameter group and the default parameter group,
The information processing apparatus according to claim 1 or 2. The buffer area setting means is configured to set a plurality of buffer areas surrounding the character area in order.
The moving character buffer area parameter group and the stationary character buffer area parameter respectively applied when the motion vector determining means determines the motion vectors of the buffer area around the moving character area and the stationary character area. The group is different for each buffer area, and the closer to the other area, the closer to the default parameter group,
The information processing apparatus according to claim 3. The static motion determining means includes
When the position of the character area matches two frames before and after the interpolation frame is interpolated among the plurality of input frames, the characters in the character area move between the input frames. Configured to determine whether or not
The information processing apparatus according to claim 1. The plurality of input frames are only two frames before and after the interpolation frame is interpolated.
The information processing apparatus according to claim 1. The plurality of inputted frames used by the character region detecting unit and the static motion determining unit and the plurality of frames used when the motion vector determining unit determines the motion vector are at least one frame. Is different,
The information processing apparatus according to claim 1. A program for applying a parameter group consisting of a plurality of parameters when determining a motion vector necessary for generating an interpolated frame image to be interpolated into the plurality of frames from a plurality of frame images,
Computer
Character region detection means that receives data of the plurality of frames and acquires position information of a character region that is a region including characters from each of the input plurality of frames.
Static motion determining means for determining whether or not the characters in the character region move between the plurality of input frames when the position of the character region matches in all of the plurality of input frames; and ,
A moving character region parameter group is set in a moving character region in which characters included in the character region move between the input frames, and a character group included in the character region is stopped between the input frames. The static character region parameter group is applied to the static character region and the default parameter group is applied to the other region, and the input is performed in the dynamic character region, the static character region, and the other region. Motion vector determining means for determining the motion vector from a plurality of frames;
Motion vector generation program to function as A program for applying a parameter group consisting of a plurality of parameters when determining a motion vector necessary for generating an interpolated frame image to be interpolated into the plurality of frames from a plurality of frame images,
Computer
Character region detection means that receives data of the plurality of frames and acquires position information of a character region that is a region including characters from each of the input plurality of frames.
Static determination means for determining whether or not the characters in the character region move between the plurality of input frames when the position of the character region matches in all of the plurality of input frames.
A moving character region parameter group is set in a moving character region in which characters included in the character region move between the input frames, and a character group included in the character region is stopped between the input frames. The static character region parameter group is applied to the static character region and the default parameter group is applied to the other region, and the input is performed in the dynamic character region, the static character region, and the other region. Motion vector determining means for determining the motion vector from a plurality of frames;
Interpolated image generating means for generating the interpolated frame image to be interpolated between the input plurality of frames based on the motion vector, and
Image output control means for displaying the interpolated frame image;
Interpolated image generation program to function as

Images