# US 11,451,703 B2 · Method and system for customizing camera parameters > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,451,703 B2 - Document ID: US11451703B2 - Status: Granted - Kind: B2 - Application number: 17/094,213 - Filed: 2020-11-10 - Published: 2021-09-23 - Granted: 2022-09-20 - Earliest claimed: 2020-03-23 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Michael Scott Brown; Abhijith Punnappurath - Web page: https://patentgrep.com/patent/US11451703B2 ## CPC - H04N 23/62: Control of parameters via user interfaces - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - H04N 23/10: for generating image signals from different wavelengths - H04N 23/631: {Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters} - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract An apparatus for customizing camera parameters is provided. The apparatus includes: an image signal processor; and a processor configured to execute instructions to: generate a first edited image based on a first original image, the first original image including first original image data and first metadata indicating a first pattern of processed RGB colors; identify a first mapping function by analyzing the first pattern with respect to a fixed pattern of unprocessed-RGB color space samples; generate first unprocessed image data based on the first mapping function and the first original image; identify image signal processor adjustment parameters based on the first unprocessed image data and the first edited image; and image signal processor parameters of the image signal processor based on the image signal processor adjustment parameters. ## Claims ### Claim 1 An apparatus for customizing camera parameters, the apparatus comprising: an image sensor; an image signal processor; a touch display; a memory storing instructions; and a processor configured to execute the instructions to: provide, via the touch display, an image editing interface; generate, via the image editing interface, a first edited image based on a first original image, wherein the first original image comprises first original image data and first metadata indicating a first pattern of processed RGB colors; identify a first mapping function by analyzing the first pattern with respect to a fixed pattern of unprocessed-RGB color space samples; generate first unprocessed image data based on the first mapping function and the first original image; identify a first plurality of image signal processor adjustment parameters based on the first unprocessed image data and the first edited image; update a plurality of image signal processor parameters of the image signal processor based on the first plurality of image signal processor adjustment parameters; and control the image signal processor to generate, using the updated plurality of image signal processor parameters, a second original image comprising second original image data and second metadata indicating a second pattern of processed RGB colors based on second unprocessed image data received from the image sensor. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the processor is further configured to execute the instructions to generate the second pattern of processed RGB colors by processing the fixed pattern of the unprocessed-RGB color space samples using the updated plurality of image signal processor parameters together with the second unprocessed image data. ### Claim 3 (depends on 1) The apparatus of claim 1, wherein the processor is further configured to execute the instructions to: provide, via the touch display, an image gallery interface comprising a plurality of gallery images; receive, via the image gallery interface, an indication corresponding to a first gallery image from among the plurality of gallery images; generate first gallery unprocessed image data corresponding to the first gallery image by analyzing the first gallery image using a neural network; identify a second plurality of image signal processor adjustment parameters based on the first gallery unprocessed image data and the first gallery image indicated via the image gallery interface; and update the plurality of image signal processor parameters of the image signal processor based on the second plurality of image signal processor adjustment parameters. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein the processor is further configured to execute the instructions to: control the image signal processor to sample third unprocessed image data received from the image sensor; control the image signal processor to generate third original image data by processing the third unprocessed image data using the updated plurality of image signal processor parameters; and generate a third image by appending the samples of the third unprocessed image data to the third original image data. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein the unprocessed-RGB color space samples of the fixed pattern represent uniform samples of a full color space of the image sensor, wherein each processed RGB color of the first pattern respectively corresponds to one unprocessed-RGB color space sample of the fixed pattern, and wherein the processor is further configured to identify the first mapping function by comparing each processed RGB color of the first pattern with a corresponding unprocessed-RGB color space sample of the fixed pattern. ### Claim 6 (depends on 1) The apparatus according to claim 1, wherein the processor is further configured to execute the instructions to identify the first plurality of image signal processor adjustment parameters using a neural network, and wherein the neural network is trained based on a plurality of unprocessed images, each of which is processed using a plurality of image signal processor parameters. ### Claim 7 (depends on 1) The apparatus according to claim 1, wherein the plurality of image signal processor parameters comprise a first plurality of image signal processor parameters corresponding to a first image category and a second plurality of image signal processor parameters corresponding to a second image category, and wherein the processor is further configured to execute the instructions to: identify whether the first edited image corresponds to the first image category or the second image category; update the first plurality of image signal processor parameters according to the first plurality of image signal processor adjustment parameters based on the first edited image corresponding to the first image category; and update the second plurality of image signal processor parameters according to the first plurality of image signal processor adjustment parameters based on the first edited image corresponding to the second image category. ### Claim 8 (depends on 1) The apparatus according to claim 1, wherein the processor is further configured to execute the instructions to individually identify each of the first plurality of image signal processor adjustment parameters. ### Claim 9 (depends on 1) The apparatus according to claim 1, wherein a plurality of pre-defined sets of parameters are stored in the memory, wherein each of the plurality of pre-defined sets of parameters comprises a plurality of parameters respectively corresponding to the plurality of image signal processor parameters, and wherein the processor is further configured to execute the instructions to: identify one of the plurality of pre-defined sets of parameters based on the first unprocessed image data and the first edited image; and identify the first plurality of image signal processor adjustment parameters based on the plurality of parameters of the identified pre-defined set of parameters. ### Claim 10 A method of customizing parameters of an image signal processor of a mobile device, the method comprising: providing, via a touch display, an image editing interface; generating, via the image editing interface, a first edited image based on a first original image, wherein the first original image comprises first original image data and first metadata indicating a first pattern of processed RGB colors; identifying a first mapping function by analyzing the first pattern with respect to a fixed pattern of unprocessed-RGB color space samples; generating first unprocessed image data based on the first mapping function and the first original image; identifying a first plurality of image signal processor adjustment parameters based on the first unprocessed image data and the first edited image; updating a plurality of image signal processor parameters of the image signal processor based on the first plurality of image signal processor adjustment parameters; and generating, using the updated plurality of image signal processor parameters, a second original image comprising second original image data and second metadata indicating a second pattern of processed RGB colors based on second unprocessed image data received from an image sensor. ### Claim 11 (depends on 10) The method of claim 10, further comprising generating the second pattern of processed RGB colors by processing the fixed pattern of the unprocessed-RGB color space samples using the updated plurality of image signal processor parameters together with the second unprocessed image data. ### Claim 12 (depends on 10) The method of claim 10, further comprising: providing, via the touch display, an image gallery interface comprising a plurality of gallery images; receiving, via the image gallery interface, an indication corresponding to a first gallery image from among the plurality of gallery images; generating first gallery unprocessed image data corresponding to the first gallery image by analyzing the first gallery image using a neural network; identifying a second plurality of image signal processor adjustment parameters based on the first gallery unprocessed image data and the first gallery image indicated via the image gallery interface; and updating the plurality of image signal processor parameters of the image signal processor based on the second plurality of image signal processor adjustment parameters. ### Claim 13 (depends on 10) The method of claim 10, further comprising: sampling third unprocessed image data received from the image sensor; generating third original image data by processing the third unprocessed image data using the updated plurality of image signal processor parameters; and generating a third image by appending the samples of the third unprocessed image data to the third original image data. ### Claim 14 (depends on 10) The method of claim 10, wherein the unprocessed-RGB color space samples of the fixed pattern represent uniform samples of a full color space of the image sensor, wherein each processed RGB color of the first pattern respectively corresponds to one unprocessed-RGB color space sample of the fixed pattern, and wherein the identifying the first mapping function comprises comparing each processed RGB color of the first pattern with a corresponding unprocessed-RGB color space sample of the fixed pattern. ### Claim 15 (depends on 10) The method according to claim 10, further comprising identifying the first plurality of image signal processor adjustment parameters using a neural network, wherein the neural network is trained based on a plurality of unprocessed images, each of which is processed using a plurality of image signal processor parameters. ### Claim 16 (depends on 10) The method according to claim 10, wherein the plurality of image signal processor parameters comprise a first plurality of image signal processor parameters corresponding to a first image category and a second plurality of image signal processor parameters corresponding to a second image category, and wherein the method further comprises: identifying whether the first edited image corresponds to the first image category or the second image category; updating the first plurality of image signal processor parameters according to the first plurality of image signal processor adjustment parameters based on the first edited image corresponding to the first image category; and updating the second plurality of image signal processor parameters according to the first plurality of image signal processor adjustment parameters based on the first edited image corresponding to the second image category. ### Claim 17 (depends on 10) The method according to claim 10, wherein the identifying the first plurality of image signal processor adjustment parameters comprises individually identifying each of the first plurality of image signal processor adjustment parameters. ### Claim 18 (depends on 10) The method according to claim 10, wherein the identifying the first plurality of image signal processor adjustment parameters comprises: identifying one of a plurality of pre-defined sets of parameters based on the first unprocessed image data and the first edited image, wherein each of the plurality of pre-defined sets of parameters comprises a plurality of parameters respectively corresponding to the plurality of image signal processor parameters; and identifying the first plurality of image signal processor adjustment parameters based on the plurality of parameters of the identified pre-defined set of parameters. ### Claim 19 A non-transitory computer-readable storage medium storing instructions configured to cause a processor to: provide, via a touch display, an image editing interface; generate, via the image editing interface, a first edited image based on a first original image, wherein the first original image comprises first original image data and first metadata indicating a first pattern of processed RGB colors; identify a first mapping function by analyzing the first pattern with respect to a fixed pattern of unprocessed-RGB color space samples; generate first unprocessed image data based on the first mapping function and the first original image; identify a first plurality of image signal processor adjustment parameters based on the first unprocessed image data and the first edited image; update a plurality of image signal processor parameters of an image signal processor based on the first plurality of image signal processor adjustment parameters; and generate, using the updated plurality of image signal processor parameters, a second original image comprising second original image data and second metadata indicating a second pattern of processed RGB colors based on second unprocessed image data received from an image sensor. ### Claim 20 (depends on 19) The non-transitory computer-readable storage medium of claim 19, wherein the instructions are further configured to cause the processor to generate the second pattern of processed RGB colors by processing the fixed pattern of the unprocessed-RGB color space samples using the updated plurality of image signal processor parameters together with the second unprocessed image data. ### Claim 21 (depends on 19) The non-transitory computer-readable storage medium of claim 19, wherein the instructions are further configured to cause the processor to: provide, via the touch display, an image gallery interface comprising a plurality of gallery images; receive, via the image gallery interface, an indication corresponding to a first gallery image from among the plurality of gallery images; generate first gallery unprocessed image data corresponding to the first gallery image by analyzing the first gallery image using a neural network; identify a second plurality of image signal processor adjustment parameters based on the first gallery unprocessed image data and the first gallery image indicated via the image gallery interface; and update the plurality of image signal processor parameters of the image signal processor based on the second plurality of image signal processor adjustment parameters. ### Claim 22 (depends on 19) The non-transitory computer-readable storage medium of claim 19, wherein the instructions are further configured to cause the processor to: sample third unprocessed image data received from the image sensor; generate third original image data by processing the third unprocessed image data using the updated plurality of image signal processor parameters; and generate a third image by appending the samples of the third unprocessed image data to the third original image data. ### Claim 23 (depends on 19) The non-transitory computer-readable storage medium of claim 19, wherein the unprocessed-RGB color space samples of the fixed pattern represent uniform samples of a full color space of the image sensor, wherein each processed RGB color of the first pattern respectively corresponds to one unprocessed-RGB color space sample of the fixed pattern, and wherein the instructions are further configured to cause the processor to identify the first mapping function by comparing each processed RGB color of the first pattern with a corresponding unprocessed-RGB color space sample of the fixed pattern. ### Claim 24 (depends on 19) The non-transitory computer-readable storage medium of claim 19, wherein the instructions are further configured to cause the processor to identify the first plurality of image signal processor adjustment parameters using a neural network, and wherein the neural network is trained based on a plurality of unprocessed images, each of which is processed using a plurality of image signal processor parameters. ### Claim 25 (depends on 19) The non-transitory computer-readable storage medium of claim 19, wherein the instructions are further configured to cause the processor to identify the first plurality of image signal processor adjustment parameters by individually identifying each of the first plurality of image signal processor adjustment parameters. ### Claim 26 (depends on 19) The non-transitory computer-readable storage medium of claim 19, wherein the instructions are further configured to cause the processor to identify the first plurality of image signal processor adjustment parameters by: identifying one of a plurality of pre-defined sets of parameters based on the first unprocessed image data and the first edited image, wherein each of the plurality of pre-defined sets of parameters comprises a plurality of parameters respectively corresponding to the plurality of image signal processor parameters; and identifying the first plurality of image signal processor adjustment parameters based on the plurality of parameters of the identified pre-defined set of parameters.