Abstract: An image signal processor and an image sensor including the same are disclosed. An image sensor includes a pixel array configured to convert received optical signals into electrical signals, a readout circuit configured to convert the electrical signals into image data and output the image data, and an image signal processor configured to perform deep learning-based image processing on the image data based on training data selected from among first training data and second training data based on a noise level of the image data.

Abstract: An image sensor test device includes: an interface configured to transmit a control signal to an image sensor to be tested; and a host device configured to transmit, to the image sensor, a storage control signal instructing to store information about a bad pixel which is determined based on an output signal of the image sensor, wherein the output signal corresponds to the control signal, and wherein the storage control signal includes a signal of instructing to store the information about the bad pixel in a memory area of a plurality of memory areas.

Abstract: An electronic device may include a first defective pixel corrector configured to correct pixel values of defective pixels among the plurality of pixels by using pixel values of neighboring pixels of each of the defective pixels and generate first pixel data, the pixel values of the defective pixels being included in the image data, and a second defective pixel corrector configured to correct a pixel value of a cluster of defective pixels by using a neural network and generate second pixel data, the pixel value of the cluster of defective pixels being included in the image data, and the neural network being trained to correct the cluster of defective pixels.

Abstract: An image processing device, which includes processing circuitry configured to cause the image processing device to first detect a first bad pixel based on first image data, correct the first bad pixel based on first values of first peripheral pixels in response to the first detection to obtain a first correction result, the first peripheral pixels being peripheral to the first bad pixel, second detect the first bad pixel and a second bad pixel based on the first image data, the second bad pixel being adjacent to the first bad pixel, correct the second bad pixel based on second values of second peripheral pixels to obtain a second correction result, the second peripheral pixels being peripheral to the second bad pixel, and correct the first bad pixel by using the first correction result stored in a buffer in response to the second detection.

Abstract: Disclosed is an electronic device which includes a processing block, a crosstalk compensation block, and a dark level compensation block. The processing block receives image data from an active pixel region of an image sensor and performs pre-processing on the image data. The crosstalk compensation block performs crosstalk compensation on the pre-processed image data. The dark level compensation block performs the crosstalk compensation on dark level data received from an optical black region of the image sensor and performs a subtraction operation on the crosstalk-compensated image data and the crosstalk-compensated dark level data.

Abstract: An image signal processor and an image sensor including the same are disclosed. An image sensor includes a pixel array configured to convert received optical signals into electrical signals, a readout circuit configured to convert the electrical signals into image data and output the image data, and an image signal processor configured to perform deep learning-based image processing on the image data based on training data selected from among first training data and second training data based on a noise level of the image data.

Abstract: A method of calibrating an image sensor including a color filter array having a first-type array pattern, the method includes capturing a target using the image sensor to generate first image data, performing a white balance operation on the first image data to generate second image data, performing an inverse white balance operation on the second image data based on a second-type array pattern to generate third image data, the second-type array pattern being different from the first-type array pattern, and calibrating the image sensor based on the third image data.

Abstract: An image signal processor and an image sensor including the same are disclosed. An image sensor includes a pixel array configured to convert received optical signals into electrical signals, a readout circuit configured to convert the electrical signals into image data and output the image data, and an image signal processor configured to perform deep learning-based image processing on the image data based on training data selected from among first training data and second training data based on a noise level of the image data.

Abstract: An image processing device includes a memory and a color correction circuit. The memory stores first correction information that used for correcting first pixel values among a plurality of pixel values. The plurality of pixel values are received from an auto-focus image sensor including first pixels configured to detect a phase difference and second pixels configured to detect an image. The first pixel values are obtained from the first pixels and correspond to a first color. The first correction information is used for correcting the first pixel values to correspond to a second color different from the first color. The color correction circuit receives first image frame data including the plurality of pixel values from the auto-focus image sensor, loads the first correction information from the memory, and generates first corrected image frame data by correcting the first pixel values included in the first image frame data to correspond to the second color based on the first correction information.

Abstract: An image processing device, which includes processing circuitry configured to cause the image processing device to first detect a first bad pixel based on first image data, correct the first bad pixel based on first values of first peripheral pixels in response to the first detection to obtain a first correction result, the first peripheral pixels being peripheral to the first bad pixel, second detect the first bad pixel and a second bad pixel based on the first image data, the second bad pixel being adjacent to the first bad pixel, correct the second bad pixel based on second values of second peripheral pixels to obtain a second correction result, the second peripheral pixels being peripheral to the second bad pixel, and correct the first bad pixel by using the first correction result stored in a buffer in response to the second detection.

Abstract: An image processing device includes a memory and a color correction circuit. The memory stores first correction information that used for correcting first pixel values among a plurality of pixel values. The plurality of pixel values are received from an auto-focus image sensor including first pixels configured to detect a phase difference and second pixels configured to detect an image. The first pixel values are obtained from the first pixels and correspond to a first color. The first correction information is used for correcting the first pixel values to correspond to a second color different from the first color. The color correction circuit receives first image frame data including the plurality of pixel values from the auto-focus image sensor, loads the first correction information from the memory, and generates first corrected image frame data by correcting the first pixel values included in the first image frame data to correspond to the second color based on the first correction information.

Abstract: Disclosed is an electronic device which includes a processing block, a crosstalk compensation block, and a dark level compensation block. The processing block receives image data from an active pixel region of an image sensor and performs pre-processing on the image data. The crosstalk compensation block performs crosstalk compensation on the pre-processed image data. The dark level compensation block performs the crosstalk compensation on dark level data received from an optical black region of the image sensor and performs a subtraction operation on the crosstalk-compensated image data and the crosstalk-compensated dark level data.

Abstract: A method of calibrating an image sensor including a color filter array having a first-type array pattern, the method includes capturing a target using the image sensor to generate first image data, performing a white balance operation on the first image data to generate second image data, performing an inverse white balance operation on the second image data based on a second-type array pattern to generate third image data, the second-type array pattern being different from the first-type array pattern, and calibrating the image sensor based on the third image data.

Abstract: An image signal processor and an image sensor including the same are disclosed. An image sensor includes a pixel array configured to convert received optical signals into electrical signals, a readout circuit configured to convert the electrical signals into image data and output the image data, and an image signal processor configured to perform deep learning-based image processing on the image data based on training data selected from among first training data and second training data based on a noise level of the image data.

Abstract: Imaging systems, such as time-of-flight imaging systems, and methods with pixel sensitivity adjustments. An embodiment includes a method, comprising: for a plurality of pixels having a first output and a second output, measuring the first outputs and the second outputs in response to a demodulation signal; and adjusting the demodulation signal such that a combination of the first outputs is substantially similar to a combination of the second outputs.

Abstract: Imaging systems, such as time-of-flight imaging systems, and methods with pixel sensitivity adjustments. An embodiment includes a method, comprising: for a plurality of pixels having a first output and a second output, measuring the first outputs and the second outputs in response to a demodulation signal; and adjusting the demodulation signal such that a combination of the first outputs is substantially similar to a combination of the second outputs.