Samsung Electronics Co., Ltd.

Sungsu Kim

Younghoon Kim

Sangwoo Lee

Jungmin Lee

Dongoh Kim

Kundong Kim

Young Heub Jang

Hyungwook Kim

Hankook Cho

Jaehyuk Hur

Eun-ji Yong

Jiyun Bang

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.

Predicting optimal values for parameters used in an operation of an image signal processor using machine learning

An image sensor includes a pixel unit including a plurality of pixels, and configured to generate an analog signal using the plurality of pixels, a data converter configured to receive the analog signal and convert the analog signal into a digital signal, and at least one processor configured to generate image data by performing crosstalk correction and remosaic on the digital signal, output the image data to an external device, receive image data information from the external device, determine a saturation ratio based on the image data information, and adjust settings of the remosaic based on the saturation ratio.

Image sensor correcting crosstalk, operating method of image sensor, and electronic device including image sensor

An image processing device includes an image sensor including a pixel array that includes a first pixel group, and a correlated double sampling circuit. The first pixel group includes a first plurality of normal pixels, a second plurality of normal pixels, and at least one first phase detection pixel. The correlated double sampling circuit is configured to generate first video data, based on charges of the first plurality of normal pixels, generate second video data, based on charges of the second plurality of normal pixels, and generate first phase detection data, based on an output of the at least one first phase detection pixel. The image processing device further includes an image signal processor configured to apply a first weight to the generated first video data, and apply a second weight to the generated second video data.

Image sensor configured to improve artifact in binning mode

Growing community of inventors

Suwon-si, South Korea

Sungsu Kim