-
公开(公告)号:US20230069744A1
公开(公告)日:2023-03-02
申请号:US17891819
申请日:2022-08-19
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: JUNGMIN LEE , Seunghyeok JUNE , JIYUN BANG , SUNGSU KIM , JOON-SEO YIM
Abstract: Provided is a method of operating an assessment device which communicates with an image sensor and includes an input buffer and a processor, the method including receiving, by the input buffer, raw image data from the image sensor that is configured to capture a test chart, generating, by the processor, conversion image data based on color domain transformation of the raw image data, generating, by the processor, estimation image data by estimating a non-distorted image based on the conversion image data, and assessing, by the processor, color distortion of the image sensor based on the estimation image data and the conversion image data.
-
公开(公告)号:US20210266504A1
公开(公告)日:2021-08-26
申请号:US17078605
申请日:2020-10-23
Applicant: Samsung Electronics Co., Ltd.
Inventor: KUNDONG KIM , SUNGSU KIM , YOUNGHOON KIM , JUNGMIN LEE
Abstract: An electronic device includes a frequency analyzing circuit and a color difference calculating circuit. The frequency analyzing circuit receives an image signal including information about a subject, may convert the image signal into first color data which are based on a first color domain, converts the first color data into frequency data which are based on a frequency domain, and applies frequency weights corresponding to the frequency data to the first color data to generate processed color data. The color difference calculating circuit calculates color difference values for evaluating a color stain generated by the image signal, based on the processed color data. The frequency weights are selected based on sensitivity information of an observer according to a frequency change of the frequency data.
-
公开(公告)号:US20230117343A1
公开(公告)日:2023-04-20
申请号:US18067298
申请日:2022-12-16
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: YOUNGHOON KIM , SUNGSU KIM , JUNGMIN LEE
Abstract: A method of predicting optimal values for a plurality of parameters used in an operation of an image signal processor includes: inputting initial values for the plurality of parameters to a machine learning model having an input layer, corresponding to the plurality of parameters, and an output layer corresponding to a plurality of evaluation items extracted from a result image generated by the image signal processor; obtaining evaluation scores for the plurality of evaluation items using an output of the machine learning model; adjusting weights, applied to the plurality of parameters, based on the evaluation scores; and determining the optimal values using the adjusted weights.
-
-