# US 2020/0401889 A1 · Electronic device, image processing method of electronic device, and computer-readable medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401889 A1 - Document ID: US20200401889A1 - Status: Published application - Kind: A1 - Application number: 16/979,303 - Filed: 2019-03-06 - Published: 2020-12-24 - Earliest claimed: 2018-03-19 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Cheon LEE; Sungho KANG; Hyungdal KWON; Yunjae LIM - Web page: https://patentgrep.com/patent/US20200401889A1 ## CPC - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06F 9/5027: {the resource being a machine, e.g. CPUs, Servers, Terminals} - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06T 5/60: using machine learning, e.g. neural networks - G06T 5/70: Denoising; Smoothing - G06T 5/73: Deblurring; Sharpening - G06T 5/90: Dynamic range modification of images or parts thereof - G06N 3/063: using electronic means - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract The present disclosure relates to an artificial intelligence (AI) system that utilizes a machine learning algorithm, and applications therefore. Disclosed is an electronic device. The electronic device comprises: a storage unit which stores therein an artificial intelligence model trained to determine parameters for a plurality of filters used for image processing on the basis of a deep neural network (DNN); and a processor for determining, through the artificial intelligence mode, parameters for each of the plurality of filters used for image processing for an input image, and performing, through the plurality of filters, filtering of the input image on the basis of the determined parameters so as to perform image processing for the input image. ## Claims ### Claim 1 An electronic device, comprising: a storage storing an artificial intelligence model trained to, based on a deep neural network (DNN), identify a parameter on a plurality of filters used in an image processing; and a processor configured to, through the artificial intelligence model, identify a parameter on each of the plurality of filters used in an image processing of an input image, and perform filtering on the input image through the plurality of filters based on the identified parameter to perform image processing on the input image. ### Claim 2 (depends on 1) The electronic device of claim 1, wherein the plurality of filters include at least two of a filter for noise reduction, a filter for sharpness enhancement, a filter for contrast correction, a filter for color correction, a filter for brightness adjustment, and a filter for performing a mosaic processing on the input image. ### Claim 3 (depends on 1) The electronic device of claim 1, wherein the artificial intelligence model is trained based on an image and a parameter on each of the plurality of filters required when performing filtering on the image to convert the image to a target image. ### Claim 4 (depends on 3) The electronic device of claim 3, wherein the artificial intelligence model is trained on a feature of an image signal corresponding to the image and a correlation of a parameter on the required each of the plurality of filters. ### Claim 5 (depends on 4) The electronic device of claim 4, wherein the processor is configured to, based on a feature of an image signal corresponding to the input image and the correlation, identify a parameter on each of the plurality of filters used in the image processing of the input image through the artificial intelligence model. ### Claim 6 (depends on 3) The electronic device of claim 3, wherein the artificial intelligence model is additionally trained through the input image and the identified parameter after being trained based on the image and a parameter on each of the plurality of filters. ### Claim 7 (depends on 3) The electronic device of claim 3, wherein the artificial intelligence model is additionally trained on a content consumption environment of a user based on the image to be input after being trained based the image and the parameter on each of the plurality of filters. ### Claim 8 (depends on 1) The electronic device of claim 1, wherein the processor is configured to perform filtering on the input image sequentially through the plurality of filters based on the identified parameter. ### Claim 9 (depends on 1) The electronic device of claim 1, further comprising: a DNN accelerator, wherein the artificial intelligence model, using the DNN accelerator, is trained to identify a parameter on a plurality of filters used in image processing. ### Claim 10 (depends on 1) The electronic device of claim 1, wherein the each of the plurality of filters filtering the input image may be identified the parameter. ### Claim 11 An image processing method of an electronic device, the method comprising: based on a deep neural network (DNN), training an artificial intelligence model to identify a parameter on a plurality of filters used in image processing; through the artificial intelligence model, identifying a parameter on each of the plurality of filters used in an image processing of an input image; and performing filtering on the input image through the plurality of filters based on the identified parameter to perform image processing on the input image. ### Claim 12 (depends on 11) The image processing method of claim 11, wherein the plurality of filters include at least two of a filter for noise reduction, a filter for sharpness enhancement, a filter for contrast correction, a filter for color correction, a filter for brightness adjustment, and a filter for performing a mosaic processing on the input image. ### Claim 13 (depends on 11) The image processing method of claim 11, wherein the training the artificial intelligence model comprises training the artificial intelligence model based on an image and a parameter on each of the plurality of filters required when performing filtering on the image to convert the image into a target image. ### Claim 14 (depends on 13) The image processing method of claim 13, wherein the training the artificial intelligence model comprises training the artificial intelligence model to identify a feature of an image signal corresponding to the image and a correlation of a parameter on the each of the plurality of required filters. ### Claim 15 (depends on 14) The image processing method of claim 14, wherein the identifying the parameter comprises, through the artificial intelligence model, identifying a parameter on each of the plurality of filters used in the image processing of the input image based on a feature of an image signal corresponding to the input image and the correlation.