JP2012019315A - Image processor and image processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor and an image processing method for simultaneously performing multiple kinds of processing by minimum necessary memory access times.SOLUTION: An image processor includes: an input part 11 for inputting an image; an image memory 12 for storing the image inputted by the input part 11; a parameter memory 15 for storing by pixel unit in one memory word, multiple kinds of parameters to be used for image processing to be performed on the image stored in the image memory 12; an image processing part 14 for performing the image processing on the image stored in the image memory 12 by using the multiple kinds of parameters stored in the parameter memory 15; and an output part 13 for outputting the image where the image processing is performed by the image processing part 14.

Description

  The present invention relates to an image processing apparatus and an image processing method for performing image processing on an input image (still image and moving image) and outputting the processed image.

  In general, in a projection apparatus such as a projector or a HUD (Head Up Display), the projection image may be distorted when the input image is projected as it is due to the installation angle of the projection apparatus, the screen shape to be projected, or lens distortion. . Therefore, as shown in FIG. 10, an image processing apparatus 110 has been devised that eliminates this distortion by applying electronic signal processing to an input image (see Patent Document 1).

  In order to transform an image in such an image processing apparatus 110, the following procedure is performed. First, an image for one screen input from the outside is stored in the image memory 120 in the order of scanning lines. Next, when reading the image stored in the image memory 120, pixel data reading control is performed in consideration of deformation, not the scanning line order. This read control is performed along a parameter representing the deformed shape (hereinafter referred to as a deformation processing parameter P11). When the distortion shape can be expressed by a mathematical expression such as a trapezoid, the deformation processing parameter P11 can be sequentially calculated and generated. On the other hand, when the shape of distortion cannot be expressed by a mathematical expression, a method is used in which a deformation processing parameter P11 obtained in advance is stored in a table on a memory and is referred to. In order to realize this, a parameter memory 151 for storing the deformation processing parameter P11 is required separately from the image memory 120.

  The “pixel data readout control considering deformation” specifically corresponds to an operation of “rearrangement of pixel data of an input image”. That is, a coordinate system on the input image (hereinafter referred to as “input coordinate system”) and a coordinate system on the output image (hereinafter referred to as “output coordinate system”) are considered, and each pixel of the input image and the output image is output to the input coordinate system. Corresponding to each grid point of the coordinate system. Then, a corresponding position in the input coordinate system is obtained for each grid point in the output coordinate system, and the pixel value of the output pixel is calculated based on the pixel value at that position. Here, if the grid point of the output coordinate system has a one-to-one correspondence with the grid point of the input coordinate system, the input pixel is output as it is as the output pixel. However, depending on the deformed shape, the coordinates of the corresponding position may not be an integer value, that is, the grid point of the output coordinate system may not be on the grid point of the input coordinate system. In this case, the pixel value of the output pixel is obtained by performing an interpolation operation based on the pixels existing around the position to be obtained.

  FIG. 11 is an explanatory diagram of a conventional general deformation process. First, pay attention to the point O [0, 0] in the output coordinate system, and consider the case of obtaining a point in the input coordinate system corresponding to this output point. In this case, referring to the data array (deformation processing parameter P11) describing the correspondence between the input coordinate system and the output coordinate system, the point I [[0, 0] in the output coordinate system corresponds to the point I [[ Since it is understood that the pixel value is 0,0], the pixel value at this point I [0,0] is output. On the other hand, when attention is paid to the point O [2, 1] of the output coordinate system, the position of the input coordinate system corresponding to this output point is I [2, 1.5], but this position is the grid of the input coordinate system. There is no one-to-one corresponding pixel, not a point. In this case, an interpolation operation is performed based on the pixel values of the points I [2, 1] and I [2, 2], and the pixel value of I [2, 1.5] is output.

  According to the projection apparatus 110 given as an example, in addition to the shape distortion, the problem of uneven brightness and uneven color occurs. That is, in general, the projection apparatus 130 tends to decrease the amount of transmitted light from the center to the periphery. Therefore, even when an image is projected through the projection lens, luminance or color shading (brightness unevenness or color unevenness) occurs in the projected image in accordance with the transmitted light amount characteristic. Therefore, a method has been proposed in which unevenness occurring in all the optical systems in the projection apparatus 130 including the projection lens is corrected by electronic signal processing (Patent Document 2). Specifically, in the projection device 130 in which luminance unevenness and color unevenness occur, correction is realized by reading data for correcting each unevenness (hereinafter referred to as unevenness correction processing parameter P12) from the memory and applying it to the input image. To do. In order to realize this, as shown in FIG. 12, a parameter memory 152 for storing the unevenness correction processing parameter P12 is required separately from the image memory 120.

  In general, there are many requests to perform processing for overlaying arbitrary lines, figures, characters, etc. on the input image (hereinafter, overlay processing), and an apparatus for realizing this has been developed (see Patent Document 3). ). Specifically, the overlay processing is realized by reading data (hereinafter, overlay processing parameter P13) such as lines, figures, and characters to be superimposed on the input image from the memory and applying them to the input image. In order to realize this, a parameter memory 153 for storing the overlay processing parameter P13 is required separately from the image memory 120, as shown in FIG.

JP 2002-215114 A JP 2005-150859 A JP-A-9-16151

  When an apparatus capable of performing the three image processes (deformation process, unevenness correction process, and overlay process) is to be realized, as shown in FIG. 14, a parameter memory 151 for storing the deformation process parameter P11, an unevenness correction process parameter, The parameter memory 152 for storing P12 and the parameter memory 153 for storing the overlay processing parameter P13 need to be provided separately from the image memory 120. Such a configuration requires the installation of multiple memories in the device, which not only increases costs and complicates the design, but also increases the number of memory accesses. It ’s hard.

  SUMMARY An advantage of some aspects of the invention is that it provides an image processing apparatus and an image processing method capable of simultaneously performing a plurality of types of processing with a minimum number of memory accesses. is there.

  A first feature according to an embodiment of the present invention is that in an image processing apparatus, an input unit for inputting an image, an image memory for storing an image input by the input unit, and an image stored in the image memory A parameter memory for storing a plurality of types of parameters used in image processing applied to each pixel in a single memory word, and a plurality of types of parameters stored in the parameter memory, stored in the image memory An image processing unit that performs image processing on an image, and an output unit that outputs an image subjected to image processing by the image processing unit.

  A second feature according to an embodiment of the present invention is that in the image processing apparatus having the first feature, the parameter memory stores an additional bit for designating a function of the image processing unit. is there.

  According to a third feature of an embodiment of the present invention, in the image processing apparatus having the first feature, the parameter memory indicates an additional bit indicating the contents of image processing performed on the image stored in the image memory. Is to store.

  According to a fourth feature of an embodiment of the present invention, in the image processing device having the second or third feature, when the image processing unit has a specific value, the additional bit The pixel is rearranged by regarding the value stored in the predetermined area of the same memory word as the coordinate value.

  According to a fifth feature of an embodiment of the present invention, in the image processing device having the second or third feature, when the image processing unit has a specific value, the additional bit Pixels are rearranged by considering a part of the values stored in a predetermined area of the same memory word as coordinate values, and blending processing with the rearranged pixels by considering other parts as color values Is to do.

  A sixth feature according to an embodiment of the present invention is that, in the image processing device having the second or third feature, the image processing unit, when the additional bit is a specific value, The pixel is rearranged by considering a part of the value stored in the predetermined area of the same memory word as the coordinate value, and the luminance unevenness of the pixel by considering the other part as a parameter for correcting the uneven brightness. Is to correct.

  A seventh feature according to an embodiment of the present invention is that, in the image processing device having the second or third feature, the image processing unit, when the additional bit has a specific value, The pixel is rearranged by considering a part of the value stored in the predetermined area of the same memory word as the coordinate value, and the color unevenness of the pixel considering the other part as a parameter for the uneven color correction processing. Is to correct.

  An eighth feature according to an embodiment of the present invention is that, in the image processing device having the second or third feature, when the image processing unit has a specific value, the additional bit The pixel is rearranged by considering a part of the value stored in the predetermined area of the same memory word as the coordinate value, and the luminance unevenness of the pixel by considering the other part as a parameter for correcting the uneven brightness. Is corrected, and another part is regarded as a parameter for color unevenness correction processing to correct pixel color unevenness.

  A ninth feature according to an embodiment of the present invention is that, in the image processing device having the second or third feature, the image processing unit, when the additional bit has a specific value, The pixel is rearranged by considering a part of the value stored in the predetermined area of the same memory word as the coordinate value, and the luminance unevenness of the pixel by considering the other part as a parameter for correcting the uneven brightness. Is corrected, and a blending process is performed on the rearranged pixels by regarding another part as a color value.

  According to a tenth aspect of the present invention, in the image processing method, the step of inputting an image, the step of storing the input image in an image memory, and the image stored in the image memory are performed. A step of storing a plurality of types of parameters used for image processing in one memory word of a parameter memory in units of pixels and a plurality of types of parameters stored in the parameter memory using the plurality of types of parameters stored in the image memory A step of performing image processing on the image; and a step of outputting the image subjected to the image processing.

  According to the present invention, it is possible to provide an image processing apparatus and an image processing method capable of simultaneously performing a plurality of types of processing with a minimum necessary number of memory accesses.

1 is a configuration diagram of an image processing apparatus according to an embodiment of the present invention. It is a figure which shows the usage example of the image processing apparatus in embodiment of this invention. It is a figure which shows operation | movement of the image processing apparatus in embodiment of this invention. It is explanatory drawing of the parameter memory in the 1st Embodiment of this invention. It is a figure which shows the parameter in the 2nd Embodiment of this invention. It is a figure which shows the parameter in the 3rd Embodiment of this invention. It is a figure which shows the parameter in the 4th Embodiment of this invention. It is a figure which shows the parameter in the 5th Embodiment of this invention. It is a figure which shows the parameter in the 6th Embodiment of this invention. It is a figure which shows the usage example of the conventional image processing apparatus. It is explanatory drawing of the conventional general deformation | transformation process. It is a figure which shows the usage example of the conventional image processing apparatus. It is a figure which shows the usage example of the conventional image processing apparatus. It is a figure which shows the usage example of the conventional image processing apparatus.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a configuration diagram of an image processing apparatus 10 according to an embodiment of the present invention. The image processing apparatus 10 is an apparatus that performs image processing on input images (still images and moving images) and outputs them. As illustrated in FIG. 1, an input unit 11, an image memory 12, an output unit 13, and the like. The image processing unit 14 and the parameter memory 15 are provided. The input unit 11 is an input port for inputting an image. The image memory 12 is a memory that stores an image input by the input unit 11. The parameter memory 15 is a memory that stores a plurality of types of parameters used for image processing applied to the image stored in the image memory 12 in one memory word in units of pixels. The image processing unit 14 performs image processing on the image stored in the image memory 12 using a plurality of types of parameters stored in the parameter memory 15. The output unit 13 is an output port or the like that outputs an image subjected to image processing by the image processing unit 14.

  FIG. 2 is a diagram illustrating a usage example of the image processing apparatus 10 according to the embodiment of the present invention. Here, the image input from the input port 11 is subjected to three types of image processing: deformation processing, unevenness correction processing, and overlay processing, and is output from the output port 13. The deformation process is a process of changing the shape of the input image so that the projected image is displayed in the same shape as the input image in consideration of lens distortion (a process of rearranging pixels). The unevenness correction process is a process for correcting the brightness and color of the input image so that the projected image is displayed with the same brightness and color as the input image, taking into account that the transmitted light amount of the lens differs between the central part and the peripheral part of the lens. . The overlay process is a process for overlaying an arbitrary line, figure, character, or the like on the input image.

  The parameter memory 15 stores processing parameters (for example, three types of parameters used for deformation processing, unevenness correction processing, and overlay processing) P1 required in the image processing apparatus 10 in one memory word in units of pixels. The type of parameter P1 stored in the parameter memory 15 may be changed according to the content of the image processing. For example, when only deformation processing and overlay processing are performed, the parameter memory 15 may store two types of deformation processing parameters and overlay processing parameters.

  FIG. 3 is a flowchart showing the operation of the image processing apparatus 10 according to the embodiment of the present invention. Hereinafter, the configuration of the image processing apparatus 10 will be described together with its operation. First, a plurality of types of parameters used for image processing are stored in the parameter memory 15 (step S1). Next, when an image is input from the input unit 11, this image is stored in the image memory 12 (steps S2 → S3). Accordingly, the image processing unit 14 performs image processing on the image stored in the image memory 12 using a plurality of types of parameters stored in the parameter memory 15 (step S4). Finally, the output unit 13 outputs the image subjected to the image processing by the image processing unit 14 (step S5).

(First embodiment)
FIG. 4 is an explanatory diagram of the parameter memory 15 according to the first embodiment of this invention. As shown in this figure, the parameter memory 15 is a memory having a 64-bit data width (memory word). Here, “one memory word” means a memory area that can be read by the image processing unit 14 by one access, and has 2 additional bits and 62 data bits per pixel. The two additional bits are bits for designating the function of the image processing unit 14, in other words, bits indicating the contents of image processing performed on the image stored in the image memory 12. The 62-bit data bits are a 15-bit X coordinate indicating the position on the X axis in the input coordinate system, a 15-bit Y coordinate indicating the position on the Y axis in the input coordinate system, and the function of the image processing unit 14. It consists of various parameters of 32 bits according to. The image processing unit 14 regards the lower 30 bits of data bits stored in the parameter memory 15 as deformation processing parameters (coordinate values), obtains corresponding positions in the input coordinate system for each grid point in the output coordinate system, The pixel value of the output pixel is calculated. In the case where the additional bit has a specific value, predetermined image processing is performed in addition to the deformation processing. However, in this embodiment, only the deformation processing is performed, and thus the areas corresponding to the various 32-bit parameters are empty.

  When the value of the additional bit is [00], the image processing unit 14 regards the lower 30 bits of the memory word as a pair of 15 bits for the X coordinate and 15 bits for the Y coordinate, and performs only the deformation process. As a result, an image subjected to the deformation process is output.

  As described above, according to the first embodiment, since the deformation processing parameter is stored in one memory word in units of pixels, the lens distortion of the projection device 130 is corrected with the minimum number of memory accesses. It is possible.

  In addition, although the deformation | transformation process for correct | amending the lens distortion of the projector 130 was illustrated here, this invention is not limited to this. That is, the present invention can be applied to a case where an input image is deformed into an arbitrary shape and displayed on a display.

(Second Embodiment)
In the first embodiment, the case where only the deformation process is performed on the input image has been described. In the present embodiment, only the differences from the first embodiment will be described for the configuration in which overlay processing is performed in addition to deformation processing.

  FIG. 5 is a diagram showing the parameter P1 in the second embodiment of the present invention. Here, the transformation processing parameter is stored in the lower 30 bits of the memory word, and the 32-bit overlay processing parameter and the 2 additional bits are stored in the higher order.

  When the value of the additional bit is [00], the image processing unit 14 sets the lower 30 bits of the memory word as a pair of 15 bits for the X coordinate and 15 bits for the Y coordinate as described in the first embodiment. Only the transformation process is performed. On the other hand, if the value of the additional bit is other than [00], the image processing specified by the additional bit is performed in addition to the deformation process. For example, when the value of the additional bit is [01], the 32 bits in the memory word are regarded as the RGB value (8 bits for each color, 24 bits in total) and the α value (8 bits), and after the transformation process is performed A blending process is performed on the pixel. As a result, a translucent logo mark or the like is superimposed on the image that has been subjected to the deformation process and output.

  By changing the designation of the additional bits, it is possible to designate color values in different color representation formats, and a configuration in which these are mixed according to the situation is possible. For example, when the value of the additional bits is [10], the 32 bits in the memory word are regarded as RGB values (6 bits for each color, 18 bits in total) and α values (12 bits), and after the transformation process is performed Blending processing is performed on the pixel. Further, when the value of the additional bit is [11], the 32 bits in the memory word are regarded as the YUV value (8 bits for each color, 24 bits in total) and the α value (8 bits), and after the transformation process is performed A blending process is performed on the pixel. With the same configuration, color designation by a color expression method different from RGB or YUV or color designation by index color may be performed. The blending method is not limited to addition, and logical operations such as multiplication and subtraction may be employed.

  As described above, according to the second embodiment, since the deformation processing parameter and the overlay processing parameter are stored in one memory word in units of pixels, the shape of the input image can be changed with the minimum number of memory accesses. In addition to changing, arbitrary lines, figures, characters, etc. can be superimposed. In this way, if a configuration in which two types of parameters necessary for image processing are read in one access is adopted, two types of parameters are stored in different memories, or stored in different locations in the same memory for two accesses. Compared with the case of reading with, the number of accesses to the memory is halved, and the memory bandwidth can be suppressed. Therefore, the configuration of the memory control circuit and device can be simplified as compared with the conventional device.

(Third embodiment)
In the second embodiment, the configuration in which overlay processing is performed in addition to deformation processing has been described. In the present embodiment, only the differences from the first or second embodiment will be described for the configuration in which the luminance unevenness correction process is performed in addition to the deformation process.

  FIG. 6 is a diagram showing the parameter P1 in the third embodiment of the present invention. As shown in this figure, the parameter in the present embodiment indicates the correction amount for luminance unevenness correction. For example, in the process of correcting the luminance unevenness, the luminance of the output pixel is obtained as follows with reference to two correction coefficients (a, b).

Output pixel brightness Y ′ = input pixel brightness Y × a + b
When the value of the additional bit is [00], the image processing unit 14 performs only the deformation process as in the first embodiment. On the other hand, when the value of the additional bit is [01], the luminance of the pixel is corrected by regarding 16 bits as a coefficient a and 8 bits as a coefficient b sequentially from a 32-bit predetermined area in the memory word.

  As described above, according to the third embodiment, the deformation processing parameter and the luminance unevenness correction processing parameter are stored in one memory word in units of pixels, so that the input image can be stored with the minimum number of memory accesses. In addition to changing the shape, it is possible to correct luminance unevenness.

  The expression format of the coefficients a and b is not limited to this, and a configuration of “store only parameter a” or a configuration of “store only parameter b” may be employed. Further, the expression format of the coefficient a expressed as an integer part 8 bits and a decimal part 8 bits is not limited to this, and an expression form such as an integer part 4 bits and a decimal part 12 bits is also possible.

(Fourth embodiment)
In the third embodiment, the configuration in which the luminance unevenness correction process is performed in addition to the deformation process has been described. In the present embodiment, only the differences from the first to third embodiments will be described with respect to a configuration in which color unevenness correction processing is performed in addition to deformation processing.

  FIG. 7 is a diagram showing a parameter P1 in the fourth embodiment of the present invention. As shown in this figure, the parameter in the present embodiment indicates a correction amount for color unevenness correction. For example, in the process of correcting color unevenness, the color of the output pixel is obtained as follows with reference to two correction coefficients (a, b).

Output pixel color B ′ = input pixel color B × B. a + B. b
Output pixel color G ′ = input pixel color G × G. a + G. b
Output pixel color R ′ = input pixel color R × R. a + R. b
When the value of the additional bit is [00], the image processing unit 14 performs only the deformation process as in the first embodiment. On the other hand, when the value of the additional bit is [10], 6 bits are set to “B.a”, 4 bits are set to “B.b”, and 6 bits are set to “G. .A ”, 4 bits as“ G.b ”, 6 bits as“ R.a ”, 4 bits as“ R.b ”, and color unevenness of the pixel is corrected.

  As described above, according to the fourth embodiment, since the deformation processing parameter and the color unevenness correction processing parameter are stored in one memory word in units of pixels, the input image can be stored with the minimum number of memory accesses. In addition to changing the shape, it is possible to correct color unevenness.

  The expression format of the coefficients a and b is not limited to this, and a configuration of “store only parameter a” or a configuration of “store only parameter b” may be employed. Further, although the coefficient a is 6 bits and the coefficient b is 4 bits, the expression format is not limited to this, and an expression format such that the coefficient a is 4 bits and the coefficient b is 6 bits is also possible.

(Fifth embodiment)
In the second to fourth embodiments, by storing the deformation parameter and another image processing parameter on the same memory word, the deformation process and the separate image processing can be performed simultaneously while reducing the number of memory accesses. The configuration was shown. In the present embodiment, only a difference from the first to fourth embodiments will be described with respect to a configuration that can be implemented by combining the plurality of processes.

  FIG. 8 is a diagram showing a parameter P1 in the fifth embodiment of the present invention. In parallel with the transformation of the output image, the image processing unit 14 in the present embodiment performs luminance correction for any pixel in the output image and color correction for any pixel in the output image. That is, when the value of the additional bit is [00], only the deformation process is performed as in the first embodiment. On the other hand, when the additional bit is [11], luminance unevenness correction similar to that in the third embodiment is performed, and color unevenness correction similar to that in the fourth embodiment is performed. Specifically, as shown in FIG. 8, “Ya”, “Yb”, “Ba”, “BB”, “G. Assuming “a”, “G.b”, “R.a”, and “R.b”, the luminance unevenness and the color unevenness of the pixel are corrected.

  As described above, according to the fifth embodiment, since the deformation processing parameter, the luminance unevenness correction processing parameter, and the color unevenness correction processing parameter are stored in one memory word in units of pixels, the minimum necessary memory In addition to changing the shape of the input image depending on the number of accesses, it is possible to correct luminance unevenness and color unevenness.

(Sixth embodiment)
In the fifth embodiment, the luminance unevenness correction process and the color unevenness correction process are combined with the deformation process. However, a plurality of different types of image processing can be combined. Hereinafter, only different points of the present embodiment from the first to fifth embodiments will be described.

  FIG. 9 is a diagram showing a parameter P1 in the sixth embodiment of the present invention. In parallel with transforming the output image, the image processing unit 14 according to the present embodiment performs luminance correction and overlay processing on an arbitrary pixel in the output image. That is, when the value of the additional bit is [00], only the deformation process is performed as in the first embodiment. On the other hand, when the additional bit is [01], luminance unevenness correction similar to that in the third embodiment is performed, and overlay processing similar to that in the second embodiment is performed. Specifically, as shown in FIG. 9, in order from a predetermined area of 32 bits in the memory word, 4 bits are “Ya”, 4 bits are “Yb”, 6 bits are “α”, 6 Assuming that the bit is “B”, the 6 bits are “G”, and the 6 bits are “R”, the luminance unevenness of the pixel is corrected and overlay processing is performed.

  As described above, according to the sixth embodiment, since the deformation processing parameter, the luminance unevenness correction processing parameter, and the overlay processing parameter are stored in one memory word in units of pixels, the necessary minimum number of memory accesses In addition to changing the shape of the input image, it is possible to perform luminance unevenness correction and overlay processing.

  In the first to sixth embodiments, the width of the memory word is 64 bits, and each pixel has 2 additional bits, 30 data bits, and 32 parameter bits. However, the present invention is not limited to this. For example, it is possible to adopt a configuration having 3 additional bits, 28 data bits, and 33 parameter bits per pixel. In this case, each of the X coordinate and the Y coordinate may be expressed by 14 bits. The width of the memory word is not limited to a 64-bit width, and a similar function can be realized using a 32-bit or 48-bit width memory.

  In the first to sixth embodiments, an additional bit is provided in the memory word, but the present invention is not limited to this. That is, the same effect as described above can be obtained as long as one type or a plurality of types of parameters are stored in one memory word in units of pixels.

  In the first to sixth embodiments, one parameter is assigned to one output pixel, but the present invention is not limited to this. One parameter can be assigned to two output pixels. That is, the same effect as described above can be obtained as long as one type of plural parameters or all or part of plural types are stored in one memory word in units of one pixel or in units of plural pixels.

  Further, the content of the deformation process referred to in the present invention is not limited to the content described in the first to sixth embodiments. That is, as long as it is a process of changing the coordinate value of a pixel, it is included in the deformation process in the present invention. For example, a process for enlarging or reducing an image can be adopted as the deformation process.

  Although not particularly mentioned in the above description, the deformation processing parameter, the color unevenness correction processing parameter, and the overlay processing parameter may be stored in one memory word in units of pixels. In this case, when the additional bit is a specific value, the image processing unit 14 considers a part of the value stored in a predetermined area of the same memory word as the additional bit as a coordinate value and rearranges the pixels. In addition, the other part is regarded as a parameter for the color unevenness correction process, the color unevenness of the pixel is corrected, and the other part is regarded as a color value to perform the blending process with the rearranged pixels. Become. In this way, color unevenness correction and overlay processing can be performed in addition to changing the shape of the input image with the minimum necessary number of memory accesses. Of course, if the width of the memory word is increased or the number of bits of the parameter is reduced, it is possible to further combine other types of image processing not exemplified here.

DESCRIPTION OF SYMBOLS 10 ... Image processing apparatus 11 ... Input part 12 ... Image memory 13 ... Output part 14 ... Image processing part 15 ... Parameter memory

Claims (10)

An input unit for inputting an image;
An image memory for storing an image input by the input unit;
A parameter memory for storing a plurality of types of parameters used for image processing applied to the image stored in the image memory in one memory word in units of pixels;
An image processing unit that performs image processing on an image stored in the image memory using a plurality of types of parameters stored in the parameter memory;
An output unit that outputs an image subjected to image processing by the image processing unit;
An image processing apparatus comprising:   The image processing apparatus according to claim 1, wherein the parameter memory stores additional bits for designating a function of the image processing unit.   The image processing apparatus according to claim 1, wherein the parameter memory stores an additional bit indicating a content of image processing to be performed on the image stored in the image memory.   When the additional bit is a specific value, the image processing unit considers a value stored in a predetermined area of the same memory word as the additional bit as a coordinate value, and performs pixel rearrangement. The image processing apparatus according to claim 2 or 3.   When the additional bit is a specific value, the image processing unit regards a part of a value stored in a predetermined area of the same memory word as the additional bit as a coordinate value and rearranges the pixels. 4. The image processing apparatus according to claim 2, wherein blending processing is performed on the rearranged pixels by regarding other parts as color values.   When the additional bit is a specific value, the image processing unit regards a part of a value stored in a predetermined area of the same memory word as the additional bit as a coordinate value and rearranges the pixels. 4. The image processing apparatus according to claim 2, wherein other part is regarded as a parameter for correcting the luminance unevenness and the luminance unevenness of the pixel is corrected.   When the additional bit is a specific value, the image processing unit regards a part of a value stored in a predetermined area of the same memory word as the additional bit as a coordinate value and rearranges the pixels. 4. The image processing apparatus according to claim 2, wherein other part is regarded as a parameter for color unevenness correction processing and color unevenness of a pixel is corrected.   When the additional bit is a specific value, the image processing unit regards a part of a value stored in a predetermined area of the same memory word as the additional bit as a coordinate value and rearranges the pixels. In addition, the luminance unevenness of the pixel is corrected by regarding the other part as a parameter for the uneven luminance correction process, and the color unevenness of the pixel is corrected by regarding the other part as a parameter for the uneven color correction process. The image processing apparatus according to claim 2 or 3.   When the additional bit is a specific value, the image processing unit regards a part of a value stored in a predetermined area of the same memory word as the additional bit as a coordinate value and rearranges the pixels. The other part is regarded as a parameter for correcting the luminance unevenness, the luminance unevenness of the pixel is corrected, and the other part is regarded as a color value and the blending process is performed with the rearranged pixels. The image processing apparatus according to claim 2 or 3. Inputting an image;
Storing the input image in an image memory;
Storing a plurality of types of parameters used for image processing applied to the image stored in the image memory in one memory word of the parameter memory in units of pixels;
Performing image processing on the image stored in the image memory using a plurality of types of parameters stored in the parameter memory; and
Outputting the image subjected to the image processing;
An image processing method comprising: