# US 2017/0287115 A1 · Image processing apparatus and image processing method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0287115 A1 - Document ID: US20170287115A1 - Status: Published application - Kind: A1 - Application number: 15/470,024 - Filed: 2017-03-27 - Published: 2017-10-05 - Earliest claimed: 2016-03-31 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Tomokazu Ishikawa; Wakako Tanaka; Tetsuya Suwa; Shinjiro Hori - Web page: https://patentgrep.com/patent/US20170287115A1 ## CPC - G06T 5/70: Denoising; Smoothing - B41J 2/2139: {Compensation for malfunctioning nozzles creating dot place or dot size errors (generating single droplets or particles on demand by pressure, e.g. electromechanical transducers B41J2/045)} - G06T 5/50: using two or more images, e.g. averaging or subtraction - G06T 5/73: Deblurring; Sharpening - G06T 5/80: Geometric correction - G06T 5/90: Dynamic range modification of images or parts thereof - G06T 5/94: based on local image properties, e.g. for local contrast enhancement - G06V 10/993: {Evaluation of the quality of the acquired pattern} - H04N 1/40: Picture signal circuits (H04N1/387 takes precedence) - H04N 1/58: Edge or detail enhancement; Noise or error suppression, e.g. colour misregistration correction (H04N1/62 takes precedence) - H04N 1/6041: {for controlling uniformity of color across image area} - H04N 23/951: by using two or more images to influence resolution, frame rate or aspect ratio - H04N 25/618: for random or high-frequency noise - B41J 2/2132: {Print quality control characterised by dot disposition, e.g. for reducing white stripes or banding (methods for local corrections by dot omission, image edge enhancement, or multi-pass mask selection G06K15/102; colour conversion H04N1/40)} - B41J 2/2142: {Detection of malfunctioning nozzles (generating single droplets or particles on demand by pressure, e.g. electromechanical transducers B41J2/045, B41J2/05; jet deflection sensors B41J2/125; for cleaning purposes B41J2/16579)} - G06T 2207/20076: Probabilistic image processing - G06T 2207/30144: Printing quality - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - B41J: TYPEWRITERS; SELECTIVE PRINTING MECHANISMS, i.e. MECHANISMS PRINTING OTHERWISE THAN FROM A FORME; CORRECTION OF TYPOGRAPHICAL ERRORS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract An image processing apparatus has a stochastic resonance processing unit executing a stochastic resonance processing to obtain a result. The result corresponds to a result that is calculated in a case where each of a plurality of pixel signals constituting reading image data is added noise and subjected to a binary processing and a plurality of results obtained by parallelly performing above step are synthesized and the parallel number is infinite. The stochastic resonance processing unit sets, with regard to a pixel signal as a processing target among the plurality of pixel signals, at least one of a strength of the noise and a threshold value used for the binary processing based on a pixel signal of the input image data corresponding to the pixel signal. ## Claims ### Claim 1 An image processing apparatus, comprising: a unit configured to acquire reading image data composed of a plurality of pixel signals by imaging an image that is printed by a printing unit based on input image data having a plurality of pixel signals; a stochastic resonance processing unit configured to execute a stochastic resonance processing in which each of the plurality of pixel signals constituting the reading image data is added noise and subjected to a binary processing and a plurality of results obtained by parallelly performing above step are synthesized; and an output unit configured to output the result of the stochastic resonance processing, wherein the stochastic resonance processing unit sets, with regard to a pixel signal as a processing target among the plurality of pixel signals, at least one of a strength of the noise and a threshold value used for the binary processing based on a pixel signal of the input image data corresponding to the pixel signal. ### Claim 2 An image processing apparatus, comprising: a unit configured to acquire reading image data composed of a plurality of pixel signals by imaging an image printed by a printing unit based on input image data having a plurality of pixel signals; a stochastic resonance processing unit configured to execute a stochastic resonance processing to obtain a result corresponding to a result that is calculated in a case where each of the plurality of pixel signals constituting the reading image data is added noise and subjected to a binary processing and a plurality of results obtained by parallelly performing above step are synthesized and the parallel number is infinite equivalency; and an output unit configured to output the result of the stochastic resonance processing, wherein the stochastic resonance processing unit sets, with regard to a pixel signal as a processing target among the plurality of pixel signals, at least one of a strength of the noise and a threshold value used for the binary processing based on a pixel signal of the input image data corresponding to the pixel signal. ### Claim 3 (depends on 2) The image processing apparatus according to claim 2, wherein the stochastic resonance processing unit calculates a difference between the plurality of pixel signals constituting the reading image data and the plurality of pixel signals constituting the input image data to add the noise to the difference to subject the difference to the binary processing. ### Claim 4 (depends on 2) The image processing apparatus according to claim 2, wherein the respective pixel signals constituting the input image data are composed of R, G, and B brightness signals; and the stochastic resonance processing unit sets at least one of the strength of the noise and the threshold value used in the binary processing based on a brightness signal obtained by synthesizing the R, G, and B brightness signals. ### Claim 5 (depends on 2) The image processing apparatus according to claim 2, wherein the respective pixel signals constituting the reading image data are composed of R, G, and B brightness signals; and the stochastic resonance processing unit performs the stochastic resonance processing on a brightness signal obtained by synthesizing the R, G, and B brightness signals. ### Claim 6 (depends on 2) The image processing apparatus according to claim 2, wherein the printing unit prints the image using a plurality of printing elements; and the stochastic resonance processing unit sets at least one of the strength of the noise and the threshold value based on a pixel signals of the input image data and the printing status of the printing element corresponding to a pixel signal as the processing target. ### Claim 7 (depends on 6) The image processing apparatus according to claim 6, wherein the printing unit is an inkjet printing apparatus; and the image processing apparatus further comprising a unit configured to detect an ink ejection status of the printing element as the printing status. ### Claim 8 (depends on 2) The image processing apparatus according to claim 2, wherein the printing unit is an inkjet printing apparatus including a plurality of printing elements; and the singular portion is a white stripe caused by ejection failure of the printing element. ### Claim 9 (depends on 2) The image processing apparatus according to claim 2, wherein the noise is white noise. ### Claim 10 (depends on 2) The image processing apparatus according to claim 2, wherein the predetermined stochastic resonance processing is performed by using the following formula to calculate data J(x) obtained by processing input data I(x), J  ( x ) = { 1 T < I  ( x ) 0 I  ( x ) < T - K 1 - ( T - I  ( x ) ) / K T - K ≦ I  ( x ) ≦ T where T is a threshold value to quantize the input data and K is a noise strength. ### Claim 11 (depends on 2) The image processing apparatus according to claim 2, further comprising: an extraction unit configured to extract a singular portion based on the result of the stochastic resonance processing. ### Claim 12 (depends on 2) The image processing apparatus according to claim 2, further comprising: a reading unit configured to image the image printed by the printing unit. ### Claim 13 (depends on 12) The image processing apparatus according to claim 12, further comprising the printing unit. ### Claim 14 An image processing method, comprising: a step of acquire reading image data composed of a plurality of pixel signals by imaging an image printed based on input image data composed of a plurality of pixel signals; a stochastic resonance processing step of executing a stochastic resonance processing in which each of the plurality of pixel signals constituting the reading image data is added noise and subjected to a binary processing and a plurality of results obtained by parallelly performing above step are synthesized; and an output step of outputting the result of the stochastic resonance processing, wherein the stochastic resonance processing step sets, with regard to a pixel signal as a processing target among the plurality of pixel signals, at least one of a strength of the noise and a threshold value used for the binary processing based on a pixel signal of the input image data corresponding to the pixel signal. ### Claim 15 An image processing method, comprising: a step of acquiring reading image data composed of a plurality of pixel signals by imaging an image printed based on input image data composed of a plurality of pixel signals; a stochastic resonance processing step of executing a stochastic resonance processing to obtain a result corresponding to a result that is calculated in a case where each of the plurality of pixel signals constituting the reading image data is added noise and subjected to a binary processing and a plurality of results obtained by parallelly performing above step are synthesized and the parallel number is infinite; and an output step of outputting the result of the stochastic resonance processing, wherein the stochastic resonance processing step sets, with regard to a pixel signal as a processing target among the plurality of pixel signals, at least one of a strength of the noise and a threshold value used for the binary processing based on a pixel signal of the input image data corresponding to the pixel signal. ### Claim 16 (depends on 15) The image processing method according to claim 15, wherein the stochastic resonance processing step calculates a difference between the plurality of pixel signals constituting the reading image data and the plurality of pixel signals constituting the input image data to add the noise to the difference to subject the difference to the binary processing. ### Claim 17 (depends on 15) The image processing method according to claim 15, wherein the respective pixel signals constituting the input image data are composed of R, G, and B brightness signals; and the stochastic resonance processing step sets at least one of the strength of the noise and the threshold value used in the binary processing based on a brightness signal obtained by synthesizing the R, G, and B brightness signals. ### Claim 18 (depends on 15) The image processing method according to claim 15, wherein the respective pixel signals constituting the reading image data are composed of R, G, and B brightness signals; and the stochastic resonance processing step performs the stochastic resonance processing on a brightness signal obtained by synthesizing the R, G, and B brightness signals. ### Claim 19 (depends on 15) The image processing method according to claim 15, wherein the image is printed by using a plurality of printing elements; and the stochastic resonance processing step sets at least one of the strength of the noise and the threshold value based on a pixel signals of the input image data and the printing status of the printing element corresponding to a pixel signal as the processing target. ### Claim 20 (depends on 19) The image processing method according to claim 19, wherein the image is printed by an inkjet printing apparatus; and the image processing method further comprising a step of detecting an ink ejection status of the printing element as the printing status. ### Claim 21 (depends on 15) The image processing method according to claim 15, wherein the image is printed by an inkjet printing apparatus including a plurality of printing elements; and the singular portion is a white stripe caused by ejection failure of the printing element. ### Claim 22 (depends on 15) The image processing method according to claim 15, wherein the noise is white noise. ### Claim 23 (depends on 15) The image processing method according to claim 15, wherein the predetermined stochastic resonance processing is performed by using the following formula to calculate data J(x) obtained by processing input data I(x), J  ( x ) = { 1 T < I  ( x ) 0 I  ( x ) < T - K 1 - ( T - I  ( x ) ) / K T - K ≦ I  ( x ) ≦ T where T is a threshold value to quantize the input data and K is a noise strength. ### Claim 24 (depends on 15) The image processing method according to claim 15, further comprising: an extraction step of extracting a singular portion based on the result of the stochastic resonance processing. ### Claim 25 (depends on 15) The image processing method according to claim 15, further comprising: a reading step of imaging the printed image. ### Claim 26 (depends on 25) The image processing method according to claim 25, further comprising: a printing step of printing the image based on the input image data. ### Claim 27 A non-transitory computer-readable storage medium which stores a program for allowing a computer to execute an image processing method, the image processing method comprising: a step of acquiring reading image data composed of a plurality of pixel signals by imaging an image printed based on input image data composed of a plurality of pixel signals; a stochastic resonance processing step of executing a stochastic resonance processing to obtain a result corresponding to a result that is calculated in a case where each of the plurality of pixel signals constituting the reading image data is added noise and subjected to a binary processing and a plurality of results obtained by parallelly performing above step are synthesized and the parallel number is infinite; and an output step of outputting the result of the stochastic resonance processing, wherein the stochastic resonance processing step sets, with regard to a pixel signal as a processing target among the plurality of pixel signals, at least one of a strength of the noise and a threshold value used for the binary processing based on a pixel signal of the input image data corresponding to the pixel signal.