WO2017077680A1 - 画像処理システム、画像処理方法、および画像処理プログラム記録媒体 - Google Patents
画像処理システム、画像処理方法、および画像処理プログラム記録媒体 Download PDFInfo
- Publication number
- WO2017077680A1 WO2017077680A1 PCT/JP2016/004197 JP2016004197W WO2017077680A1 WO 2017077680 A1 WO2017077680 A1 WO 2017077680A1 JP 2016004197 W JP2016004197 W JP 2016004197W WO 2017077680 A1 WO2017077680 A1 WO 2017077680A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- pixel value
- instruction function
- pixel
- updated
- Prior art date
Links
- 238000003672 processing method Methods 0.000 title claims description 10
- 238000013459 approach Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 30
- 230000003044 adaptive effect Effects 0.000 claims description 17
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 60
- 238000000926 separation method Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 208000003443 Unconsciousness Diseases 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 125000001475 halogen functional group Chemical group 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/02—Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers
- G11B27/031—Electronic editing of digitised analogue information signals, e.g. audio or video signals
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
- G11B27/19—Indexing; Addressing; Timing or synchronising; Measuring tape travel by using information detectable on the record carrier
- G11B27/28—Indexing; Addressing; Timing or synchronising; Measuring tape travel by using information detectable on the record carrier by using information signals recorded by the same method as the main recording
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/40—Picture signal circuits
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/40—Picture signal circuits
- H04N1/409—Edge or detail enhancement; Noise or error suppression
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/58—Edge or detail enhancement; Noise or error suppression, e.g. colour misregistration correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Definitions
- the present invention relates to an image processing technique, and relates to an image processing system, an image processing method, and an image processing program recording medium.
- cameras using sensors that are suitable for imaging various target objects are widely used.
- a monitoring camera using a visible light sensor is widely used.
- cameras using non-visible light sensors such as a near infrared camera and a far infrared camera are widely used for nighttime monitoring.
- a near ultraviolet camera is also commercially available.
- devices for imaging wavelengths longer than the visible light wavelength region such as terahertz waves and radio waves are also commercially available as other cameras.
- Non-Patent Document 1 discloses a method of performing processing based on image gradient information (difference value between adjacent regions) as image processing useful for such applications.
- Non-Patent Document 1 a target gradient is calculated from a group of images to be referenced, and the target gradient and the gradient of the output image are calculated.
- the output image is obtained by updating the pixel value of the input image so that they match.
- Non-Patent Document 1 there is no restriction on the absolute value (pixel value) of the output image itself. For this reason, the method of Patent Document 1 has a problem in that details such as collapse of the structure, collapse of white, blackout, artifacts such as a halo effect and ringing occur.
- An object of the present invention is to provide an image processing system, an image processing method, and an image processing program recording medium that solve the above-described problems.
- the image processing system of the present invention calculates a gradient calculation unit that calculates a desired gradient from an input image, and calculates an instruction function that defines a range that an output image can take and a pixel value of a reference image for the input image.
- An instruction function calculation unit that performs the update, a pixel value update unit that updates the pixel value of the input image so as to approximate a desired gradient, and outputs an updated image, and a reference image that is within a possible range of the output image
- a pixel value restriction unit that obtains the output image by using the pixel value of the updated image so as to be close to the pixel value.
- An image processing method of the present invention is an image processing method of an image processing system that obtains an output image by analyzing input images acquired from various sensors, and a gradient calculation unit calculates a desired gradient from the input image.
- a gradient calculating step, an indicator function calculating unit that defines, for an input image, a range that the output image can take and a pixel value of a reference image, an indicator function calculating step of calculating an indicator function, and a pixel value update The pixel value updating step of updating the pixel value of the input image and outputting the updated image so that the unit approaches a desired gradient, and the pixel value constraint unit is within a range that the output image can take and A pixel value constraining step of updating the pixel value of the updated image to obtain an output image so as to be close to the pixel value of the image.
- An image processing program recording medium of the present invention is a recording medium that records an image processing program of an image processing system that causes a computer to analyze an input image acquired from various sensors and obtain an output image.
- a gradient calculation procedure for calculating a desired gradient from the input image an instruction function calculation procedure for calculating an instruction function that defines a range that the output image can take and a pixel value of a reference image for the input image,
- an image processing program for executing a pixel value restriction procedure for updating the pixel value of the updated image to obtain an output image is recorded.
- the output image in order to easily analyze input images acquired from various sensors, the output image can be improved to an image quality suitable for the user.
- FIG. 1 is a block diagram illustrating a schematic configuration of an image processing system of related technology disclosed in Non-Patent Document 1.
- FIG. It is a figure which shows the subject which should be solved by this invention.
- 1 is a block diagram showing a schematic configuration of an image processing system according to a first embodiment of the present invention.
- 3 is a flowchart for explaining the operation of the image processing system shown in FIG. 2. It is a figure which shows the effect by the image processing system shown in FIG. It is a block diagram which shows schematic structure of the image processing system which concerns on the 2nd Embodiment of this invention.
- Non-Patent Document 1 First, in order to facilitate understanding of the present invention, a related art image processing system disclosed in Non-Patent Document 1 will be described.
- FIG. 1 is a block diagram showing an image processing system of related technology described in Non-Patent Document 1.
- the image processing system described in Non-Patent Document 1 includes an image input unit 100, a gradient calculation unit 201, a pixel value update unit 202, and an image output unit 300.
- the image input unit 100 receives one or more image groups. Then, the image input unit 100 records the input image in a memory (not shown) or the like.
- the gradient calculation unit 201 calculates a target gradient from a reference image group.
- the pixel value updating unit 202 updates the pixel value of the input image so as to obtain the output image so that the target gradient matches the gradient of the output image.
- the pixel value update unit 202 updates the pixel value as shown in the following formula 2 so as to minimize the following formula 1.
- Represents the i-th pixel value of the output image Represents the gradient of the i-th pixel of the output image, Represents the gradient at pixel i of the target image, Represents parameters related to updating, which are predetermined by the user.
- the image output unit 300 outputs an output image to a display or the like.
- Non-Patent Document 1 shown in FIG. 1 has no restriction on the absolute value (pixel value) of the output image itself. For this reason, the image processing system of Patent Document 1 shown in FIG. 1 has a drawback in that details such as collapse of the structure, collapse of white, blackout, or artifacts such as a halo effect and ringing occur.
- the input image shown in FIG. 2 has a large dynamic range (difference between dark and bright areas). For this reason, when the input image of FIG. 2 is processed using the related technique disclosed in Non-Patent Document 1, overexposure and blackout occur in the output image obtained by processing.
- FIG. 3 is a block diagram showing a schematic configuration of the image processing system according to the first embodiment of the present invention.
- an image processing system includes an image input unit 100, a computer (central processing unit; processor; data processing unit) 200 that operates under program control, and an image output. Part 300.
- the illustrated image processing system is a system that obtains an output image by analyzing input images obtained from various sensors.
- the computer (central processing unit; processor; data processing unit) 200 includes a gradient calculation unit 201, a pixel value update unit 202, an instruction function calculation unit 203, and a pixel value restriction unit 204.
- the illustrated image processing system has a configuration in which an instruction function calculation unit 203 and a pixel value restriction unit 204 are further added to the related art image processing system shown in FIG.
- the image obtained by a camera or the like is input to the image input unit 100.
- images to be input color images and images acquired from other sensors may be input separately.
- the image input unit 100 records the input image in a memory (not shown) or the like.
- the red, green, and blue pixel values of the i-th pixel are represented as Ri, Gi, and Bi. Also, these ingredients are put together, It shall be expressed as Furthermore, when there is an image acquired from another sensor other than the input color image, the pixel value of the i-th pixel is also expressed by using a subscript. For example, in the case where a near-infrared image is input in addition to the input color image, the pixel value of the i-th near-infrared image may be expressed as Ni.
- the output image is represented by a matrix in which the pixel values of the pixels are arranged in the raster scan order. More specifically, when an RGB image is considered as the output color image, the red, green, and blue pixel values of the i-th pixel are represented as Ri, Gi, and Bi.
- the image output unit 300 is an output device that outputs a reconstructed image (output image).
- the image output unit 300 is realized by, for example, a display device.
- the gradient calculation unit 201 determines a desired gradient from the input image input by the image input unit 100.
- the gradient of an input image may be simply multiplied by a constant, the gradient may be normalized by some method, or the gradient is weighted from two or more images. It may be expressed as a sum.
- the gradient calculation unit 201 may multiply the gradient of the input image by a constant value to obtain a desired gradient.
- the pixel value update unit 202 updates the pixel value of the input image so that the target gradient is close to the gradient of the output image, and outputs an updated image. Specifically, as described above, the pixel value update unit 202 updates the pixel value of the input image as in the above equation 2 so as to minimize the above equation 1, for example. That is, the pixel value update unit 202 in the embodiment of the present invention may be the same as the related technology described above.
- the pixel value update unit 202 has described the method of updating the pixel value of the output image so that the target gradient and the gradient of the output image are close to each other.
- the first embodiment is not limited to this.
- a term corresponding to a reconstruction constraint (or data term or faithful term) used in super-resolution, noise removal, inpainting, etc. is adopted, and a pixel value updating method corresponding to this is adopted.
- the value update unit 202 may perform this.
- the instruction function calculation unit 203 calculates an instruction function for defining a definition area that restricts a range that the pixel value of the output image can take in order to suppress white-out, black-out, ringing, halo effect, and the like. .
- an instruction function that is uniform over the entire image may be used for the input image, as shown in the following Equation 3.
- an adaptive instruction function for each pixel which is determined from the minimum value and the maximum value of the pixel of interest with respect to the input image, as shown in Equation 4 below, is used. Also good.
- the instruction function calculation unit 203 does not need to use the same function for the entire image for the input image.
- the instruction function calculation unit 203 uses an instruction function that is uniform over the entire image for a part of the input image as the instruction function, and an adaptive instruction function for each pixel for the remaining part of the input image May be used.
- the instruction function calculated by the instruction function calculation unit 203 may be any function that defines a range that can be taken by the pixel value of the output image in any sense.
- the first embodiment the case where the same instruction function is used for the entire image or an adaptive instruction function for each pixel is described.
- the first embodiment is not limited to this.
- a range that can be taken by the pixel value may be defined using a function such as the following Expression 5.
- ⁇ is a parameter defined in advance by the user.
- Zi is an image serving as a guide.
- Zi may be calculated using an edge-preserving spatial filter.
- the pixel value restriction unit 204 updates the pixel value of the update image so that the pixel value of the output image is within the definition area according to the defined instruction function, and obtains the output image.
- the updated image may be updated using a uniform instruction function for the entire image.
- the update amount of the pixel value of the updated image is corresponding to an adaptive instruction function for each pixel determined from the minimum value and the maximum value of the target pixel, as shown in Equation 7 below. You may decide.
- the pixel value restriction unit 204 does not need to use the same instruction function for the entire image. For example, the pixel value restriction unit 204 updates the pixel value of the update image corresponding to a uniform instruction function for the entire image for a part of the input image, and for the remaining part of the input image. The pixel value of the updated image may be updated in correspondence with an adaptive instruction function for each pixel. In any case, the instruction function used in the pixel value restriction unit 204 may be any function that defines a range that the pixel value of the output image can take in some sense.
- the input image acquired from one or more sensors is input in the image input unit 100 (step S200).
- the gradient calculation unit 201 calculates a desired gradient from the input image (step S201).
- the instruction function calculation unit 203 calculates an instruction function that defines a range that can be taken by the pixel value of the output image and a reference pixel value for the input image (step S202).
- the pixel value update unit 202 updates the pixel value of the input image so as to bring the gradient of the updated image closer to a desired gradient, and outputs an updated image (step S203).
- the pixel value restriction unit 204 updates the pixel value of the update image so that the pixel value calculated by the instruction function calculation unit 203 can be obtained, thereby obtaining an output image (step S204).
- the computer 200 calculates the pixel value of the output image. It is determined whether the value of is sufficiently converged (step S205). If enough pixel value of the output image Is not converged (No in step S205), the computer 200 repeats the processing from step S203 to S204 again (step S205).
- step S205 If the pixel value of the output image Is sufficiently converged (Yes in step S205), the image output unit 300 outputs an output image consisting of the pixel value (step S206).
- the output image can be improved to an image quality suitable for the user in order to easily analyze the input image acquired from various sensors.
- the reason is that the instruction function calculation unit 203 calculates the range that the output image can take and the pixel value of the reference image, and the pixel value restriction unit 204 falls within the range that the output image can take and becomes the reference. This is because the pixel value of the updated image is updated so as to be close to the pixel value of the image.
- the input image shown in FIG. 2 is compared with the output image shown in FIG. It can be displayed as an image.
- an image processing program is expanded in RAM (random access memory), and hardware such as a control unit (CPU (central processing unit)) is operated based on the program.
- CPU central processing unit
- Each part is realized as various means.
- the program may be recorded on a recording medium and distributed.
- the program recorded on the recording medium is read into a memory via a wired, wireless, or recording medium itself, and operates a control unit or the like. Examples of the recording medium include an optical disk, a magnetic disk, a semiconductor memory device, and a hard disk.
- a computer that operates as an image processing system is based on an image processing program developed in a RAM, a gradient calculating unit 201, a pixel value updating unit 202, an instruction function calculation. It can be realized by operating as the unit 203 and the image value restriction unit 204.
- the output image can be improved to an image quality suitable for the user.
- FIG. 6 is a block diagram showing a schematic configuration of an image processing system according to the second embodiment of the present invention.
- an image processing system includes an image input unit 100, a computer (central processing unit; processor; data processing unit) 200A that operates under program control, and an image output. Part 300.
- the illustrated image processing system is a system that obtains an output image by analyzing input images obtained from various sensors.
- a computer (central processing unit; processor; data processing unit) 200A includes a gradient calculation unit 201, a pixel value update unit 202, an instruction function calculation unit 203a, a pixel value restriction unit 204, a color information separation unit 205, a color And an information adding unit 206.
- the illustrated image processing system has a configuration in which a color information separating unit 205 and a color information adding unit 206 are further added to the image processing system according to the first embodiment shown in FIG.
- the operation of the instruction function calculation unit is changed as described later.
- the gradient calculation unit 201, the pixel value update unit 202, the pixel value restriction unit 204, and the image output unit 300 are the same operations as those in the first embodiment, and thus description thereof is omitted.
- a color image is input to the image input unit 100, and the lightness component and luminance component of the image are input to the gradient calculation unit 201, the pixel value update unit 202, and the pixel value restriction unit 204.
- the image input unit 100 may input a multispectral image
- the gradient calculation unit 201, the pixel value update unit 202, and the pixel value restriction unit 204 may use other values instead of the lightness component or the luminance component of the image.
- a saturation component, a hue component, or a part of a band of a multispectral image may be processed.
- the color information separation unit 205 separates color components and brightness from the color image input by the image input unit 100. More specifically, for example, when a pixel value defined in the RGB color space is input as a color image in the image input unit 100, the color information separation unit 205 defines each color defined in the RGB color space. The pixel value of the pixel is converted into a pixel value in the YUV color space and the Lab color space. Then, the color information separation unit 205 extracts a lightness component, that is, a Y component or an L component, from pixel values defined in the YUV color space or the Lab color space. Then, the color information separation unit 205 may separate the lightness component and the color component by extracting the UV component or the ab component as the color component. Then, the color information separation unit 205 delivers the lightness component to the gradient calculation unit 201 and the color component to the instruction function calculation unit 203a and the color information addition unit 206.
- a lightness component that is, a Y component or an L component
- the instruction function calculation unit 203a calculates, as an instruction function, a range in which brightness can be obtained for each pixel under the constraint of storing the color of the input image, from the color components calculated by the color information separation unit 205. For example, when the color component is represented as an ab component in the Lab space, the instruction function calculation unit 203a calculates a range that L can take under the constraint of storing the color of the input image.
- the instruction function calculation unit 203a first sets the L value that is the brightness to all possible ranges (ie, from 0 to A plurality of pixel values are obtained by sampling N discretely within (up to 100).
- these sampled pixel values in the Lab space are represented as ⁇ (L 1 , a 0 , b 0 )... (L N , a 0 , b 0 ) ⁇ .
- the instruction function calculation unit 203a converts the pixel values represented in the Lab space into pixel values in the RGB space.
- this is expressed as ⁇ (r 1 , g 1 , b 1 )...
- the instruction function calculation unit 203a has one of the converted pixel values in the RGB space within a predetermined range (that is, a range from 0 to 255 in an 8-bit image). If not, that is, if any one of the components has a saturated pixel value (that is, 0 or less or 255 or more in an 8-bit image), the sample is rejected. Finally, the instruction function calculation unit 203a represents the minimum value and the maximum value of the brightness component among all the samples that are not rejected as R min and R max, and this range is a constraint for storing the color of the input image. In the following, it is assumed that the brightness can be taken, and the indicator function is defined based on this range. At this time, the pixel value update unit 202 updates the pixel value corresponding to the instruction function by the following equation (16).
- the instruction function calculation unit 203a has described the case where the possible range of brightness can be obtained from the sampled values under the constraint of storing the color of the input image.
- the operation of the instruction function calculation unit 203a is as follows. It is not limited to this.
- the color information adding unit 206 synthesizes a color image from the brightness obtained by the pixel value restriction unit 204 and the color component obtained by the color information separation unit 205.
- the instruction function calculation unit 203a determines the range in which the brightness can be taken under the constraint of saving the color of the input image. And calculated as an instruction function. Based on the instruction function, the lightness component is calculated by the pixel value restriction unit 204. Then, the color information adding unit 206 synthesizes the output image from the calculated brightness component and the color component of the input image.
- the second embodiment uses the output image to easily analyze the input image acquired from various sensors while preserving the color component of the input image. Image quality suitable for the user.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
Description
まず、本発明の理解を容易にするために、上記非特許文献1に開示された関連技術の画像処理システムについて説明する。
次に、発明を実施するための形態について図面を参照して詳細に説明する。
図3は、本発明の第1の実施の形態に係る画像処理システムの概略構成を示すブロック図である。
次に、図4のフローチャートを参照して、本第1の実施の形態に係る画像処理システムの全体の動作について詳細に説明する。
次に、本第1の実施の形態の効果について説明する。
図6は、本発明の第2の実施の形態に係る画像処理システムの概略構成を示すブロック図である。
次に、本第2の実施の形態の効果について説明する。
200、200A コンピュータ(中央処理装置;プロセッサ;データ処理装置)
201 勾配算出部
202 画素値更新部
203、203a 指示関数算出部
204 画素値制約部
205 色情報分離部
206 色情報付加部
300 画像出力部
Claims (12)
- 入力画像から所望の勾配を算出する勾配算出部と、
前記入力画像に対して、出力画像が取りうる範囲及び基準となる画像の画素値を規定する、指示関数を算出する指示関数算出部と、
前記所望の勾配に近づけるように、前記入力画像の画素値を更新して更新画像を出力する画素値更新部と、
前記出力画像が取りうる範囲内に収まりかつ、前記基準となる画像の画素値に近くなるように、前記更新画像の画素値を更新して前記出力画像を得る画素値制約部と、
を備える画像処理システム。 - 前記指示関数算出部は、前記指示関数として、前記入力画像に対して画像全体で一様な指示関数を算出し、
前記画素値制約部は、前記画像全体で一様な指示関数を用いて、前記更新画像の画素値を更新して前記出力画像を得る、
請求項1に記載の画像処理システム。 - 前記指示関数算出部は、前記指示関数として、前記入力画像に対して注目画素の極小値と極大値とから定まる、画素毎に適応的な指示関数を算出し、
前記画素値制約部は、前記画素毎に適応的な指示関数に対応して、前記更新画像の画素値の更新量を決定して前記出力画像を得る、
請求項1に記載の画像処理システム。 - 前記指示関数算出部は、前記指示関数として、前記入力画像の一部分に対して、画像全体で一様な指示関数を算出し、前記入力画像の残りの部分に対して、画素毎に適応的な指示関数を算出し、
前記画素値制約部は、前記入力画像の一部分に対しては、前記画像全体で一様な指示関数に対応して前記更新画像の画素値の更新を行い、前記入力画像の残りの部分に対しては、前記画素毎に適応的な指示関数に対応して前記更新画像の画素値の更新を行って、前記出力画像を得る、
請求項1に記載の画像処理システム。 - 種々のセンサより取得された入力画像を解析して、出力画像を得る画像処理システムの画像処理方法であって、
勾配算出部が、前記入力画像から所望の勾配を算出する勾配算出工程と、
指示関数算出部が、前記入力画像に対して、前記出力画像が取りうる範囲及び基準となる画像の画素値を規定する、指示関数を算出する指示関数算出工程と、
画素値更新部が、前記所望の勾配に近づけるように、前記入力画像の画素値を更新して更新画像を出力する画素値更新工程と、
画素値制約部が、前記出力画像が取りうる範囲内に収まりかつ、前記基準となる画像の画素値に近くなるように、前記更新画像の画素値を更新して前記出力画像を得る画素値制約工程と、
を含む画像処理方法。 - 前記指示関数算出工程では、前記指示関数算出部が、前記指示関数として、前記入力画像に対して画像全体で一様な指示関数を算出し、
前記画素値制約工程では、前記画素値制約部が、前記画像全体で一様な指示関数を用いて、前記更新画像の画素値を更新して前記出力画像を得る、
請求項5に記載の画像処理方法。 - 前記指示関数算出工程では、前記指示関数算出部が、前記指示関数として、前記入力画像に対して注目画素の極小値と極大値とから定まる、画素毎に適応的な指示関数を算出し、
前記画素値制約工程では、前記画素値制約部が、前記画素毎に適応的な指示関数に対応して、前記更新画像の画素値の更新量を決定して前記出力画像を得る、
請求項5に記載の画像処理方法。 - 前記指示関数算出工程では、前記指示関数算出部が、前記指示関数として、前記入力画像の一部分に対して、画像全体で一様な指示関数を算出し、前記入力画像の残りの部分に対して、画素毎に適応的な指示関数を算出し、
前記画素値制約工程では、前記画素値制約部が、前記入力画像の一部分に対しては、前記画像全体で一様な指示関数に対応して前記更新画像の画素値の更新を行い、前記入力画像の残りの部分に対しては、前記画素毎に適応的な指示関数に対応して前記更新画像の画素値の更新を行って、前記出力画像を得る、
請求項5に記載の画像処理方法。 - コンピュータに、種々のセンサより取得された入力画像を解析して、出力画像を得させる画像処理システムの画像処理プログラムを記録した記録媒体であって、前記画像処理プログラムは前記コンピュータに、
前記入力画像から所望の勾配を算出する勾配算出手順と、
前記入力画像に対して、前記出力画像が取りうる範囲及び基準となる画像の画素値を規定する、指示関数を算出する指示関数算出手順と、
前記所望の勾配に近づけるように、前記入力画像の画素値を更新して更新画像を出力する画素値更新手順と、
前記出力画像が取りうる範囲内に収まりかつ、前記基準となる画像の画素値に近くなるように、前記更新画像の画素値を更新して前記出力画像を得る画素値制約手順と、
を実行させる画像処理プログラム記録媒体。 - 前記指示関数算出手順は、前記コンピュータに、前記指示関数として、前記入力画像に対して画像全体で一様な指示関数を算出させ、
前記画素値制約手順は、前記コンピュータに、前記画像全体で一様な指示関数を用いて、前記更新画像の画素値を更新して前記出力画像を得させる、
請求項9に記載の画像処理プログラム記録媒体。 - 前記指示関数算出手順は、前記コンピュータに、前記指示関数として、前記入力画像に対して注目画素の極小値と極大値とから定まる、画素毎に適応的な指示関数を算出させ、
前記画素値制約手順は、前記コンピュータに、前記画素毎に適応的な指示関数に対応して、前記更新画像の画素値の更新量を決定して前記出力画像を得させる、
請求項9に記載の画像処理プログラム記録媒体。 - 前記指示関数算出手順は、前記コンピュータに、前記指示関数として、前記入力画像の一部分に対して、画像全体で一様な指示関数を算出させ、前記入力画像の残りの部分に対して、画素毎に適応的な指示関数を算出させ、
前記画素値制約手順は、前記コンピュータに、前記入力画像の一部分に対しては、前記画像全体で一様な指示関数に対応して前記更新画像の画素値の更新を行い、前記入力画像の残りの部分に対しては、前記画素毎に適応的な指示関数に対応して前記更新画像の画素値の更新を行って、前記出力画像を得させる、
請求項9に記載の画像処理プログラム記録媒体。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/772,239 US10699455B2 (en) | 2015-11-05 | 2016-09-14 | Image processing system, image processing method, and image processing program recording medium |
JP2017548626A JP6909979B2 (ja) | 2015-11-05 | 2016-09-14 | 画像処理システム、画像処理方法、および画像処理プログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015-217328 | 2015-11-05 | ||
JP2015217328 | 2015-11-05 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017077680A1 true WO2017077680A1 (ja) | 2017-05-11 |
Family
ID=58663146
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2016/004197 WO2017077680A1 (ja) | 2015-11-05 | 2016-09-14 | 画像処理システム、画像処理方法、および画像処理プログラム記録媒体 |
Country Status (3)
Country | Link |
---|---|
US (1) | US10699455B2 (ja) |
JP (1) | JP6909979B2 (ja) |
WO (1) | WO2017077680A1 (ja) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6825625B2 (ja) * | 2016-06-28 | 2021-02-03 | ソニー株式会社 | 画像処理装置および画像処理装置の作動方法、並びに医療用撮像システム |
CN110909750B (zh) * | 2019-11-14 | 2022-08-19 | 展讯通信(上海)有限公司 | 图像差异检测方法及装置、存储介质、终端 |
US11756210B2 (en) | 2020-03-12 | 2023-09-12 | Adobe Inc. | Video inpainting via machine-learning models with motion constraints |
US11823357B2 (en) * | 2021-03-09 | 2023-11-21 | Adobe Inc. | Corrective lighting for video inpainting |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0844863A (ja) * | 1994-07-27 | 1996-02-16 | Dainippon Printing Co Ltd | 画像拡大方法 |
JP2003060916A (ja) * | 2001-08-16 | 2003-02-28 | Minolta Co Ltd | 画像処理装置、画像処理方法、プログラム及び記録媒体 |
JP2005095328A (ja) * | 2003-09-24 | 2005-04-14 | Toshiba Corp | 超解像処理装置及び医用画像診断装置 |
JP2013218660A (ja) * | 2012-03-14 | 2013-10-24 | Fujitsu Ltd | 画像処理方法、プログラム及び装置 |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7492967B2 (en) | 2003-09-24 | 2009-02-17 | Kabushiki Kaisha Toshiba | Super-resolution processor and medical diagnostic imaging apparatus |
US7936392B2 (en) * | 2004-10-01 | 2011-05-03 | The Board Of Trustees Of The Leland Stanford Junior University | Imaging arrangements and methods therefor |
US7443443B2 (en) * | 2005-07-28 | 2008-10-28 | Mitsubishi Electric Research Laboratories, Inc. | Method and apparatus for enhancing flash and ambient images |
JP2010055487A (ja) * | 2008-08-29 | 2010-03-11 | Toshiba Corp | 画像処理方法、装置、およびプログラム |
JP5372680B2 (ja) * | 2009-09-24 | 2013-12-18 | 日立オートモティブシステムズ株式会社 | 障害物検知装置 |
JP5445363B2 (ja) * | 2010-07-08 | 2014-03-19 | 株式会社リコー | 画像処理装置、画像処理方法および画像処理プログラム |
TWI602152B (zh) * | 2013-02-06 | 2017-10-11 | 聚晶半導體股份有限公司 | 影像擷取裝置及其影像處理方法 |
US10311552B2 (en) * | 2017-04-06 | 2019-06-04 | Pixar | De-noising images using machine learning |
US10540749B2 (en) * | 2018-03-29 | 2020-01-21 | Mitsubishi Electric Research Laboratories, Inc. | System and method for learning-based image super-resolution |
-
2016
- 2016-09-14 WO PCT/JP2016/004197 patent/WO2017077680A1/ja active Application Filing
- 2016-09-14 JP JP2017548626A patent/JP6909979B2/ja active Active
- 2016-09-14 US US15/772,239 patent/US10699455B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0844863A (ja) * | 1994-07-27 | 1996-02-16 | Dainippon Printing Co Ltd | 画像拡大方法 |
JP2003060916A (ja) * | 2001-08-16 | 2003-02-28 | Minolta Co Ltd | 画像処理装置、画像処理方法、プログラム及び記録媒体 |
JP2005095328A (ja) * | 2003-09-24 | 2005-04-14 | Toshiba Corp | 超解像処理装置及び医用画像診断装置 |
JP2013218660A (ja) * | 2012-03-14 | 2013-10-24 | Fujitsu Ltd | 画像処理方法、プログラム及び装置 |
Non-Patent Citations (1)
Title |
---|
PATRICK PEREZ: "Poisson Image Editing", ACM TRANSACTIONS ON GRAPHICS (TOG, vol. 22, no. 3, 27 July 2003 (2003-07-27), pages 313 - 318, XP058249525 * |
Also Published As
Publication number | Publication date |
---|---|
JP6909979B2 (ja) | 2021-07-28 |
US20180322672A1 (en) | 2018-11-08 |
JPWO2017077680A1 (ja) | 2018-08-23 |
US10699455B2 (en) | 2020-06-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Guo et al. | Low-light image enhancement via breaking down the darkness | |
JP4410304B2 (ja) | 視覚処理装置、視覚処理方法、画像表示装置、テレビジョン、携帯情報端末、カメラおよびプロセッサ | |
JP6351903B1 (ja) | 画像処理装置、画像処理方法、及び撮影装置 | |
US11265490B2 (en) | Systems and methods of spatiotemporal image noise reduction for multispectral image data | |
WO2017077680A1 (ja) | 画像処理システム、画像処理方法、および画像処理プログラム記録媒体 | |
US20060269270A1 (en) | Photography apparatus, photography method and photography program | |
JP2008159069A5 (ja) | ||
JP2010218110A (ja) | ノイズ低減装置、ノイズ低減方法、ノイズ低減プログラム、記録媒体 | |
JP2015156615A (ja) | 画像処理装置、画像処理方法、制御プログラム、および記録媒体 | |
JP5546166B2 (ja) | 撮像装置、信号処理方法、及びプログラム | |
JP2005039460A (ja) | 画像処理方法および装置 | |
JP5771677B2 (ja) | 画像処理装置、撮像装置、プログラム及び画像処理方法 | |
JP4126297B2 (ja) | 視覚処理装置、視覚処理方法、視覚処理プログラム、集積回路、表示装置、撮影装置および携帯情報端末 | |
JP6677222B2 (ja) | 検出装置、画像処理装置、検出方法、及び画像処理方法 | |
JP6826277B2 (ja) | 画像処理システム、画像処理方法、および画像処理プログラム | |
JP5203159B2 (ja) | 画像処理方法、画像処理システムおよび画像処理プログラム | |
CN105654541B (zh) | 窗口图像处理方法和装置 | |
JP2011095110A (ja) | 光源推定装置および光源推定方法 | |
JP2008160210A (ja) | 情報処理方法および撮像装置 | |
EP3483831A1 (en) | Method and device for modifying a contrast of a visual content | |
JP7026879B2 (ja) | 画像データ表示システム、画像データ表示方法、および画像データ表示プログラム | |
JP5836878B2 (ja) | 画像処理装置、方法、及びプログラム | |
KR101359370B1 (ko) | 채도 향상을 위한 영상 처리 장치 및 방법 | |
Chen et al. | Quantitative evaluation of a new gamma correction method for endoscopic image improvement | |
JP2008312177A (ja) | 映像階調変換装置、映像階調変換方法、映像階調変換プログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16861758 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2017548626 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15772239 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16861758 Country of ref document: EP Kind code of ref document: A1 |