Image processing device and method with storage resource saving mechanism

Abstract

The invention discloses an image processing method with a storage resource saving mechanism. The method comprises the following steps of: storing an original image picture into a picture storage circuit; reading the original image pictures to an operation storage circuit line by line; the original image picture is rotated by 90 degrees in the rotation direction to form a first rotation image picture; performing first column direction image operation on the first rotation image frame column by column to generate a first operation image frame and storing the first operation image frame in an operation storage circuit; rotating the first operation image picture by 270 degrees along the rotation direction to form a second rotation image picture; storing the second rotation image picture in a picture storage circuit; reading the second rotation image frame to an operation storage circuit column by column; performing second column direction image operation on the second rotation image column by column to generate a second operation image picture; and outputting the second operation image picture.

Description

Technical Field

[0001] The present invention relates to image processing technology, and more particularly to an image processing device and method with a storage resource saving mechanism. Background Art

[0002] In image processing, some algorithms, such as debanding and filtering, use a cross-shaped algorithm. More specifically, for any pixel in the image as the center point, it is necessary to refer to the horizontal pixels on the left and right, and the vertical pixels on the top and bottom, in order to perform calculations on these pixels simultaneously.

[0003] However, in image processing circuits, image input is often scanned column by column. To perform the aforementioned calculations, the required vertical reference pixels must be accessed using static random access memory (SRAM) implemented as a line buffer. The performance of these algorithms is often dependent on the number of reference pixels, requiring a large number of pixels to achieve good results. However, a large number of vertical pixels requires a large number of line buffers, significantly increasing circuit costs. Summary of the Invention

[0004] In view of the problems in the prior art, an object of the present invention is to provide an image processing device and method with a storage resource saving mechanism to improve the prior art.

[0005] The present invention includes an image processing method with a storage resource saving mechanism, including: storing the original image frame to a frame storage circuit; reading the original image frame row by row to a calculation storage circuit; rotating the original image frame 90 degrees along the rotation direction to obtain a first rotated image frame; performing a first column direction image operation on the first rotated image frame column by column to generate a first calculation image frame and storing it in the calculation storage circuit; rotating the first calculation image frame 270 degrees along the rotation direction to obtain a second rotated image frame; storing the second rotated image frame to the frame storage circuit; reading the second rotated image frame column by column to the calculation storage circuit; performing a second column direction image operation on the second rotated image column by column to generate a second calculation image frame; and outputting the second calculation image frame.

[0006] The present invention also includes an image processing device with a storage resource saving mechanism, comprising: a screen storage circuit, an operation storage circuit, and a processing circuit. The processing circuit is electrically coupled to the screen storage circuit and the operation storage circuit, and is configured to execute an image processing method. The image processing method includes: storing the original image screen to the screen storage circuit; reading the original image screen row by row to the operation storage circuit; rotating the original image screen 90 degrees along the rotation direction to form a first rotated image screen; performing a first column direction image operation on the first rotated image screen column by column to generate a first operation image screen and storing it in the operation storage circuit; rotating the first operation image screen 270 degrees along the rotation direction to form a second rotated image screen; storing the second rotated image screen to the screen storage circuit; reading the second rotated image screen column by column to the operation storage circuit; performing a second column direction image operation on the second rotated image column by column to generate a second operation image screen; and outputting the second operation image screen.

[0007] The present invention also includes an image processing method with a storage resource saving mechanism, including: storing the original image frame to the image storage circuit; reading the original image frame column by column to the operation storage circuit; performing a first column direction image operation on the original image frame column by column to generate a first operation image frame and storing it in the operation storage circuit; rotating the first operation image frame 90 degrees along the rotation direction to obtain a first rotated image frame; storing the first rotated image frame to the image storage circuit; reading the first rotated image frame column by column to the operation storage circuit; performing a second column direction image operation on the first rotated image column by column to generate a second operation image frame and storing it in the operation storage circuit; rotating the second operation image frame 270 degrees along the rotation direction to obtain a second rotated image frame; and outputting the second rotated image frame.

[0008] The features, embodiments and technical effects of the present invention are described in detail below with reference to the accompanying drawings for a preferred embodiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A module diagram of an image processing device with a storage resource saving mechanism in one embodiment of the present invention is shown;

[0010] Figure 2 A flowchart of an image processing method with a storage resource saving mechanism in one embodiment of the present invention is shown;

[0011] Figure 3 A schematic diagram showing multiple images related to image processing performed by an image processing device in one embodiment of the present invention is shown;

[0012] Figure 4 FIG1 shows a schematic diagram of a sliding window in one embodiment of the present invention;

[0013] Figure 5 A module diagram of an image processing device with a storage resource saving mechanism in one embodiment of the present invention is shown;

[0014] Figure 6 A flowchart of an image processing method with a storage resource saving mechanism in one embodiment of the present invention is shown;

[0015] Figure 7 A flowchart showing an image processing method with a storage resource saving mechanism in one embodiment of the present invention is shown; and

[0016] Figure 8 A schematic diagram illustrating multiple images related to image processing performed by an image processing device in one embodiment of the present invention is shown.

[0017] Description of reference numerals:

[0018] 100: Image processing device 110: Image storage circuit 120: Calculation storage circuit

[0019] 130: Processing Circuit 200: Image Processing Method 400: Sliding Window

[0020] 500: Image processing device 510: First rotation operation circuit 520: Second rotation operation circuit

[0021] 600: Image processing method 700: Image processing method S210-S290: Steps

[0022] S610-S690: Steps S710-S790: Steps CD: Row Direction

[0023] DR: Rotation direction N1~N4: Peripheral pixels NT, NN1~NN4, N1~N4: Grid points

[0024] O1~O4: peripheral pixels OI: original image screen OP1: first operation image screen

[0025] PT: target pixel RD: column direction OP2: second operation image screen

[0026] RO1: First rotating image screen RO2: Second rotating image screen DETAILED DESCRIPTION

[0027] An object of the present invention is to provide an image processing device and method with a storage resource saving mechanism, which achieves the effect of reducing hardware costs and improving image processing effects by performing a two-stage rotation and column-direction image operation equivalent to a cross operation.

[0028] Please refer to Figure 1 . Figure 1 FIG2 shows a block diagram of an image processing device 100 with a storage resource saving mechanism in one embodiment of the present invention. The image processing device 100 includes a frame storage circuit 110 , a calculation storage circuit 120 , and a processing circuit 130 .

[0029] The image storage circuit 110 and the calculation storage circuit 120 are any circuits capable of storing data. In one embodiment, the image storage circuit 110 is a dynamic random-access memory (DRAM), and the calculation storage circuit 120 is a static random-access memory (SRAM) or a register.

[0030] The processing circuit 130 is electrically coupled to the image storage circuit 110 and the computational storage circuit 120 and can be configured to execute stored computer-executable instructions (not shown). The computer-executable instructions include, for example, but are not limited to, firmware / drivers and related instructions for the image storage circuit 110, the computational storage circuit 120, and other hardware modules within the electronic device 110. By executing the computer-executable instructions, the processing circuit 130 can access signals or data from the image storage circuit 110 and the computational storage circuit 120 to perform operations and thereby implement the functions of the image processing device 100.

[0031] The following will be paired Figure 2 as well as Figure 3 ,for Figure 1 The operation of the image processing device 100 is described in more detail.

[0032] Please also refer to Figure 2 as well as Figure 3 . Figure 2 FIG. 2 is a flow chart illustrating an image processing method 200 with a storage resource saving mechanism in one embodiment of the present invention. Figure 3 FIG. 1 is a schematic diagram showing a plurality of images related to image processing performed by the image processing apparatus 100 in one embodiment of the present invention.

[0033] In addition to the aforementioned apparatus, the present invention further discloses an image processing method 200 with a storage resource saving mechanism, which is applied to, for example, but not limited to Figure 1 In the image processing device 100. An embodiment of the image processing method 200 is as follows Figure 2 As shown, the following steps are included.

[0034] In step S210 , the processing circuit 130 stores the original image frame OI in the frame storage circuit 110 .

[0035] In one embodiment, the original image frame OI may be received by the image processing device 100 via, for example, but not limited to, a network, and stored in the image storage circuit 110 after decoding. In another embodiment, the original image frame OI may also be previously stored within the image processing device 100. The present invention is not limited to a specific source of the original image frame OI.

[0036] like Figure 3 As shown, the original image frame OI has a plurality of original pixels arranged in an array having a number of columns and a number of rows, where the number of rows is greater than the number of columns. That is, the original image frame OI may be an image frame having A rows and B columns, and has a size of A×B, where A is greater than B.

[0037] In step S220 , the processing circuit 130 reads the original image frame OI line by line to the calculation storage circuit 120 .

[0038] like Figure 3 As shown, the processing circuit 130 reads the original image frame OI line by line in the row direction CD. In the above embodiment, since the size of the original image frame OI is A×B, the processing circuit 130 reads the original image frame OI from the 1st row to the Ath row in sequence.

[0039] In step S230 , the processing circuit 130 rotates the original image frame OI by 90 degrees along the rotation direction DR to obtain a first rotated image frame RO1 .

[0040] In one embodiment, after the processing circuit 130 reads a row of pixels of the original image frame OI, it stores the row of pixels as a column of the first rotated image frame RO1 to achieve the effect of rotation. Figure 3 As shown, the original image frame OI with a size of A×B becomes a first rotated image frame RO1 with a size of B×A after being rotated 90 degrees.

[0041] In step S240 , the processing circuit 130 performs a first row-direction image operation on the first rotated image frame RO1 row by row to generate a first operation image frame OP1 and stores the generated first operation image frame OP1 in the operation storage circuit 120 .

[0042] In one embodiment, the first row-direction image operation performed by the processing circuit 130 is to perform a pixel averaging operation or a pixel interpolation operation on a target pixel of the first rotated image frame RO1 and a plurality of surrounding pixels in the same row and located in a peripheral range of the target pixel.

[0043] Taking a target pixel PT in the first rotated image frame RO1 as an example, the processing circuit 130 can perform operations on the target pixel PT and surrounding pixels N1-N4 located in the same column and two pixels to the left and right of the target pixel PT, respectively. The pixel values ​​of these five pixels are averaged or interpolated to obtain the resulting pixel value of the target pixel PT after the first column-wise image operation. For edge pixels of the first rotated image frame RO1 (e.g., pixels at the beginning and end of a column), even if some surrounding pixels do not exist, calculations can still be performed by, for example, but not limited to, setting redundant pixels with preset pixel values. The present invention is not limited to a specific operation method.

[0044] Therefore, after the processing circuit 130 performs the same operation on all pixels of the first rotated image frame RO1, all resulting pixel values ​​are the pixel values ​​of the pixels of the first operation image frame OP1. Figure 3 As shown, since the processing circuit 130 performs calculation on each pixel of the first rotated image frame RO1 to generate the first calculated image frame OP1 , the size of the first calculated image frame OP1 is still B×A.

[0045] In step S250 , the processing circuit 130 rotates the first operating image frame OP1 by 270 degrees along the rotation direction DR to obtain a second rotated image frame RO2 .

[0046] In one embodiment, after the processing circuit 130 completes the operation of a row of pixels corresponding to the first operation image frame OP1, it stores this row of pixels as a row of the second rotation image frame RO2 to achieve the effect of rotation. Figure 3 As shown, the first operating image frame OP1 with a size of B×A becomes the second rotated image frame RO2 with a size of A×B after being rotated 270 degrees.

[0047] It should be noted that since the first rotated image frame RO1 is generated by rotating the original image frame OI by 90 degrees along the rotation direction DR, and the first calculated image frame OP1 is generated by the first rotated image frame RO1, the pixels of the second rotated image frame RO2 generated by rotating the first calculated image frame OP1 by 270 degrees along the rotation direction DR will correspond to the pixels of the original image frame OI.

[0048] In step S260 , the processing circuit 130 stores the second rotated image frame RO2 in the image storage circuit 110 .

[0049] In one embodiment, the second rotated image frame RO2 and the original image frame OI are stored in two independent blocks of the image storage circuit 110 and do not overlap each other.

[0050] In step S270 , the processing circuit 130 reads the second rotated image frame RO2 row by row to the calculation storage circuit 120 .

[0051] like Figure 3 As shown, the processing circuit 130 reads the second rotated image frame RO2 column by column along the column direction RD. In the above embodiment, since the size of the second rotated image frame RO2 is A×B, the processing circuit 130 reads the second rotated image frame RO2 from column 1 to column B in sequence.

[0052] In step S280 , the processing circuit 130 performs a second row-direction image operation on the second rotated image RO2 row by row to generate a second operation image frame OP2 .

[0053] In one embodiment, similar to the first row direction operation, the second row direction image operation performed by the processing circuit 130 is to perform pixel averaging operation or pixel interpolation operation on a target pixel of the second rotated image frame RO2 and a plurality of surrounding pixels in the same row and located in the surrounding range of the target pixel.

[0054] Taking the target pixel PT, which also appears in the second rotated image frame RO2, as an example, the processing circuit 130 can perform operations on the target pixel PT and surrounding pixels O1-O4 located in the same column and two pixels to the left and right of the target pixel PT, respectively. The pixel values ​​of these five pixels are averaged or interpolated to form the resulting pixel value of the target pixel PT after the first column-wise image operation. For edge pixels of the second rotated image frame RO2 (e.g., pixels at the beginning and end of a column), even though some surrounding pixels do not exist, calculations can still be performed by, for example, but not limited to, setting redundant pixels with predetermined pixel values. The present invention is not limited to a specific operation method.

[0055] Therefore, after the processing circuit 130 performs the same operation on all pixels of the second rotated image frame RO2, all resulting pixel values ​​are the pixel values ​​of the pixels of the second operation image frame OP2. Figure 3 As shown, since the processing circuit 130 performs calculation on each pixel of the second rotated image frame RO2 to generate the second calculated image frame OP2 , the size of the second calculated image frame OP2 is still A×B.

[0056] In step S290 , the processing circuit 130 outputs the second operating image frame OP2 .

[0057] exist Figure 2In the figure, steps related to the processing circuit 130 reading the image storage circuit 110 (such as steps S220 and S270) are marked with bold frames, and steps related to the processing circuit 130 writing the image storage circuit 110 (such as step S260) are marked with gray frames. Therefore, it can be seen from the above that the image processing method 200 performs two read operations and one write operation on the image storage circuit 110.

[0058] Please refer to Figure 4 . Figure 4 FIG. 4 is a schematic diagram of a sliding window 400 in one embodiment of the present invention. The sliding window 400 includes grid points NT, NN1 to NN4, and ON1 to ON4 arranged in a cross shape.

[0059] In one embodiment, after Figure 2 The original image OI is rotated for the first time, image calculation is performed in the first column direction, and the second rotation and image calculation are performed in the second column direction, which is equivalent to Figure 4 The sliding window 400 is used to calculate each pixel of the original image frame OI.

[0060] by Figure 3 In the embodiment, when the center grid point NT in the sliding window 400 corresponds to the target pixel PT, the grid points NN1-NN4 within a range of two pixels above and below the grid point NT (in the vertical direction) will correspond to the surrounding pixels N1-N4 used in the first column direction image calculation because the first rotated image frame RO1 is a 90-degree rotation of the original image frame OI. The grid points ON1-ON4 within a range of two pixels to the left and right of the grid point NT will correspond to the surrounding pixels O1-O4 used in the second column direction image calculation because the pixels of the second rotated image frame RO2 will correspond to the pixels of the original image frame OI.

[0061] Since debanding or filtering operations may use a cross-type operation method in image processing, in one embodiment, the first column direction image operation and the second column direction image operation performed in the above-mentioned manner are configured to perform debanding or filtering operations on the original image frame OI.

[0062] In some technologies, cross-shaped calculations are performed by reading multiple columns of the original image OI and then directly calculating the surrounding pixels above, below, and to the left and right of the target pixel. While this approach eliminates the need for multiple reads and writes to the image storage circuit, it requires a large amount of static random access memory (SRAM) implemented as a line buffer to store multiple columns of pixels, increasing storage costs. The above embodiment only uses two pixels above, below, and to the left and right as examples. However, in actual applications, to achieve better calculation results, more pixels above, below, and to the left may be used, further increasing storage costs.

[0063] In comparison, the image processing device of the present invention can perform cross-shaped operations through two stages of rotation and column-direction image operations, eliminating the need for a large number of line buffers to store upper and lower (vertical) pixels. This can reduce hardware costs and improve image processing performance without requiring a trade-off between hardware costs and computational performance.

[0064] In some systems, after an image is stored in a frame storage circuit, it is pre-processed before subsequent image processing. Since the two image rotations and the first column-wise image operation described above in the present invention are equivalent to image pre-processing, in such a system, no additional frame storage circuit read / write cycles are actually added.

[0065] Please also refer to Figure 5 as well as Figure 6 . Figure 5 FIG. 5 shows a module diagram of an image processing device 500 with a storage resource saving mechanism in one embodiment of the present invention. Figure 6 FIG. 6 is a flowchart illustrating an image processing method 600 with a storage resource saving mechanism in one embodiment of the present invention.

[0066] Figure 5 The image processing device 500 and Figure 1 The image processing device 100 is similar to the image processing device 100, including: a picture storage circuit 110, a calculation storage circuit 120 and a processing circuit 130, and the same components are not repeated here. In this embodiment, Figure 5 The image processing device 500 further includes a first rotation operation circuit 510 and a second rotation operation circuit 520 .

[0067] In addition to the aforementioned apparatus, the present invention further discloses an image processing method 600 with a storage resource saving mechanism, which is applied to, for example, but not limited to Figure 5 In the image processing device 500. An embodiment of the image processing method 600 is as follows Figure 6 As shown, the following steps are included.

[0068] In this embodiment, steps S610, S620 and Figure 2Steps S210 and S220 are the same and will not be repeated here.

[0069] In step S630 , the first rotation calculation circuit 510 independent of the processing circuit 130 rotates the original image frame OI by 90 degrees along the rotation direction DR to obtain a first rotated image frame RO1 .

[0070] In step S635 , the first rotation calculation circuit 510 stores the first rotated image frame RO1 in the frame storage circuit 110 .

[0071] In step S640 , the processing circuit 130 reads the first rotated image frame RO1 from the frame storage circuit 110 row by row to the calculation storage circuit 120 .

[0072] In step S645 , the processing circuit 130 performs a first row-direction image operation on the first rotated image frame RO1 row by row to generate a first operation image frame OP1 and stores the generated first operation image frame OP1 in the operation storage circuit 120 .

[0073] In step S650 , the processing circuit 130 stores the first calculated image frame OP1 in the frame storage circuit 110 .

[0074] In step S655 , the processing circuit 130 reads the first computing image frame OP1 row by row to the computing storage circuit 120 .

[0075] In step S660 , the second rotation operation circuit 520 independent of the processing circuit 130 rotates the first operation image frame OP1 by 270 degrees to form a second rotated image frame RO2 .

[0076] In step S665 , the second rotation calculation circuit 520 stores the second rotated image frame RO2 in the frame storage circuit 110 .

[0077] In this embodiment, steps S670 to S690 are Figure 2 Steps S270 to S290 are the same and will not be repeated here.

[0078] In one embodiment, the original image frame OI, the first rotated image frame RO1, the first calculated image frame OP1, and the second rotated image frame RO2 are stored in four independent blocks of the image storage circuit 110 and do not overlap each other.

[0079] exist Figure 6In the figure, steps related to the processing circuit 130 reading from the image storage circuit 110 (such as steps S620, S640, S655, and S670) are marked with bold frames, and steps related to the processing circuit 130 writing to the image storage circuit 110 (such as steps S635, S650, and S665) are marked with gray frames. Therefore, it can be seen from the above that the image processing method 200 performs four read operations and three write operations on the image storage circuit 110.

[0080] Through the above method, Figure 5 The image processing device 500 can perform 90-degree and 270-degree rotations, respectively, using a first rotation calculation circuit 510 and a second rotation calculation circuit 520, which are independent of the processing circuit 130. Although this configuration increases the number of read and write operations of the image storage circuit 110 by the processing circuit 130, it reduces the usage of the calculation storage circuit 120, further reducing its storage cost.

[0081] It should be noted that in some embodiments, the first rotation operation circuit 510 and the second rotation operation circuit 520 can be configured alternatively to balance the read and write times of the image storage circuit 110 and the usage of the operation storage circuit 120. The present invention is not limited to a specific configuration.

[0082] Please also refer to Figure 7 as well as Figure 8 . Figure 7 FIG. 7 is a flow chart illustrating an image processing method 700 with a storage resource saving mechanism in one embodiment of the present invention. Figure 8 FIG. 1 is a schematic diagram showing a plurality of images related to image processing performed by the image processing apparatus 100 in one embodiment of the present invention.

[0083] In addition to the aforementioned apparatus, the present invention further discloses an image processing method 700 with a storage resource saving mechanism, which is applied to, for example, but not limited to Figure 1 In the image processing device 100. An embodiment of the image processing method 700 is as follows Figure 7 As shown, the following steps are included.

[0084] In step S710 , the processing circuit 130 stores the original image frame OI in the frame storage circuit 110 .

[0085] like Figure 8 As shown, in this embodiment, the original image frame OI has a plurality of original pixels arranged in an array having a number of columns and a number of rows, where the number of columns is greater than the number of rows. That is, the original image frame OI may be an image frame having A columns and B rows, and has a size of B×A, where A is greater than B.

[0086] In step S720 , the processing circuit 130 reads the original image frame OI row by row to the calculation storage circuit 120 .

[0087] like Figure 8 As shown, the processing circuit 130 reads the original image frame OI column by column along the column direction RD. In the above embodiment, since the size of the original image frame OI is B×A, the processing circuit 130 reads from the first column to the Ath column of the original image frame OI.

[0088] In step S730, the processing circuit 130 performs a first row-wise image operation on the original image frame OI to generate a first calculated image frame OP1, which is then stored in the operation storage circuit 120. The first row-wise image operation is performed in a manner similar to that described in the previous embodiment and will not be further described here. Since the processing circuit 130 performs an operation on each pixel of the original image frame OI to generate the first calculated image frame OP1, the size of the first calculated image frame OP1 remains B×A.

[0089] In step S740, the processing circuit 130 rotates the first operating image frame OP1 by 90 degrees along the rotation direction DR to obtain the first rotated image frame RO1. Figure 8 As shown, the first operating image frame OP1 with a size of B×A becomes the first rotated image frame RO1 with a size of A×B after being rotated 90 degrees.

[0090] In step S750 , the processing circuit 130 stores the first rotated image frame RO1 in the image storage circuit 110 .

[0091] In step S760 , the processing circuit 130 reads the first rotated image frame RO1 row by row to the calculation storage circuit 120 .

[0092] like Figure 8 As shown, the processing circuit 130 reads the first rotated image frame RO1 column by column along the column direction RD. In the above embodiment, since the size of the first rotated image frame RO1 is A×B, the processing circuit 130 reads the original image frame OI from the 1st column to the Bth column in sequence.

[0093] In step S770, the processing circuit 130 performs a second row-wise image operation on the first rotated image RO1 row by row to generate a second calculated image frame OP2, which is then stored in the calculation storage circuit 120. The second row-wise image operation is performed in a manner similar to that described in the previous embodiment and will not be further described here. Since the processing circuit 130 performs an operation on each pixel of the first rotated image RO1 to generate the second calculated image frame OP2, the size of the second calculated image frame OP2 remains A×B.

[0094] In step S780, the processing circuit 130 rotates the second operating image frame OP2 by 270 degrees along the rotation direction DR to form a second rotated image frame RO2. Figure 8 As shown, the second operating image frame OP2 with a size of A×B becomes a second rotated image frame RO2 with a size of B×A after being rotated 270 degrees.

[0095] In step S790 , the processing circuit 130 outputs the second rotated image frame RO2 .

[0096] Therefore, the image processing device of the present invention can flexibly select the order of image rotation and column-wise image operations based on the size configuration of the original image frame. The present invention is not limited to a specific execution order of rotation and column-wise image operations.

[0097] It should be noted that the above embodiment is merely one example. In other embodiments, modifications and variations may be made by those skilled in the art without departing from the spirit of the present invention. For example, the number of peripheral pixels involved in the image calculation in the first row direction and the number of peripheral pixels involved in the image calculation in the second row direction may be the same or different. Furthermore, the image rotation may be performed in either a clockwise or counterclockwise direction.

[0098] In summary, the image processing device and method with a storage resource saving mechanism of the present invention can perform cross-shaped operations equivalent to two-stage rotation and column-direction image operations, thereby reducing hardware costs and improving image processing effects.

[0099] Although the embodiments of the present invention are described above, these embodiments are not intended to limit the present invention. A person skilled in the art with ordinary knowledge in this technical field may change the technical features of the present invention based on the explicit or implicit contents of the present invention. These changes may fall within the scope of patent protection sought by the present invention. In other words, the scope of patent protection of the present invention shall be based on the definition of the claims of the present invention.

Claims

1. An image processing method with a storage resource saving mechanism, comprising: storing an original image frame in a frame storage circuit; Reading the original image frame line by line into a computing storage circuit; Rotating the original image frame 90 degrees along a rotation direction to form a first rotated image frame; Performing a first column direction image operation on the first rotated image frame row by row to generate a first operation image frame and storing the first operation image frame in the operation storage circuit; Rotating the first computing image frame by 270 degrees along the rotation direction to obtain a second rotated image frame; storing the second rotating image in the image storage circuit; Reading the second rotated image frame row by row into the calculation storage circuit; performing a second row direction image operation on the second rotated image row by row to generate a second operation image frame; and Output the second computing image screen.

2. The image processing method according to claim 1, wherein: The image storage circuit is a dynamic random access memory, and the operation storage circuit is a static random access memory or a temporary register.

3. The image processing method according to claim 1, wherein: The first column direction image operation and the second column direction image operation are configured to perform a debanding operation or a filtering operation, and the first column direction image operation and the second column direction image operation respectively perform a pixel averaging operation or a pixel interpolation operation on a target pixel and multiple surrounding pixels in the same column and located in a peripheral range of the target pixel.

4. The image processing method according to claim 1, wherein: Also includes: A first rotation operation circuit rotates the original image frame by 90 degrees to obtain the first rotated image frame.

5. The image processing method according to claim 4, wherein: Also includes: storing the first rotating image frame in the frame storage circuit; as well as The first rotated image frame is read row by row from the frame storage circuit to perform the first row direction image operation.

6. The image processing method according to claim 1, wherein: Also includes: A second rotation operation circuit rotates the first operation image frame by 270 degrees to form the second rotation image frame.

7. The image processing method according to claim 6, wherein: Also includes: storing the first computing image frame in the frame storage circuit; as well as The first computing image frame is read from the frame storage circuit so that the second rotation computing circuit rotates the first computing image frame by 270 degrees.

8. The image processing method according to claim 1, wherein: The original image frame has a plurality of original pixels arranged in an array having a number of columns and a number of rows, and the number of rows is greater than the number of columns.

9. An image processing device with a storage resource saving mechanism, comprising: a picture storage circuit; an arithmetic storage circuit; as well as A processing circuit is electrically coupled to the image storage circuit and the operation storage circuit and is configured to execute an image processing method, including: storing an original image frame in the frame storage circuit; Reading the original image frame line by line into the calculation storage circuit; Rotating the original image frame 90 degrees along a rotation direction to form a first rotated image frame; Performing a first column direction image operation on the first rotated image frame row by row to generate a first operation image frame and storing the first operation image frame in the operation storage circuit; Rotating the first computing image frame by 270 degrees along the rotation direction to obtain a second rotated image frame; storing the second rotating image in the image storage circuit; Reading the second rotated image frame row by row into the calculation storage circuit; performing a second row direction image operation on the second rotated image row by row to generate a second operation image frame; and Output the second computing image screen.

10. An image processing method with a storage resource saving mechanism, comprising: storing an original image frame in a frame storage circuit; Reading the original image frame row by row into a computing storage circuit; Performing a first row-wise image operation on the original image frame to generate a first operation image frame and storing the first operation image frame in the operation storage circuit; Rotating the first computing image frame 90 degrees along a rotation direction to obtain a first rotated image frame; storing the first rotating image frame in the frame storage circuit; Reading the first rotated image frame row by row into the calculation storage circuit; Performing a second row direction image operation on the first rotated image row by row to generate a second operation image frame and storing the second operation image frame in the operation storage circuit; Rotating the second calculated image frame by 270 degrees along the rotation direction to obtain a second rotated image frame; and Output the second rotating image.

Images