The disclosure herein relates to methods and systems for localized smoke removal and color restoration of a real-time video. Conventional techniques apply the de-smoking process only on a single image, by finding the regions having the smoke, based on manual air-light estimation. In addition, regaining original colors of de-smoked image is quite challenging. The present disclosure herein solves the technical problems. In the first stage, video frames having the smoky and smoke-free video frames are identified, from the video received in the real-time. In the second stage, an air-light is estimated automatically using a combined feature map. An intermediate de-smoked video frame for each smoky video frame is generated based on the air-light using a de-smoking algorithm. In the third and the last stage, a smoke-free video reference frame is used to compensate for color distortions introduced by the de-smoking algorithm in the second stage.

A method and apparatus of video coding incorporating Deep Neural Network are disclosed. A target signal is processed using DNN (Deep Neural Network), where the target signal provided to DNN input corresponds to the reconstructed residual, output from the prediction process, the reconstruction process, one or more filtering processes, or a combination of them. The output data from DNN output is provided for the encoding process or the decoding process. The DNN can be used to restore pixel values of the target signal or to predict a sign of one or more residual pixels between the target signal and an original signal. An absolute value of one or more residual pixels can be signalled in the video bitstream and used with the sign to reduce residual error of the target signal.

Disclosed in various embodiments of the present invention are a method and a device, the device comprising a camera, a display, and a processor, wherein the processor is configured to display, on the display in a preview state, a user's face acquired from the camera, correct the user's face on the basis of a configuration related to face correction, acquire an image including the corrected user's face when an avatar generation request is received, and generate an avatar by using the acquired image. Various embodiments are possible.

Aspects of the disclosed technology provide ways to detect the object of ultrasound scanning and to automatically, load system settings and image preferences necessary to generate high quality output images. In some aspects, an ultrasound system can be configured to perform steps including receiving a selection of a first transducer, identifying a body structure or organ based on a signal received in response to an activation of the first transducer, retrieving a first set of image parameters corresponding with the body structure, and configuring the first transducer based on the first set of image parameters. Methods and machine-readable media are also provided.

A processor-implemented imaging method includes: obtaining initial homography information between a plurality of tele images that covers a field of view (FOV) of a wide image; receiving a user input of zooming a partial region of the wide image from a screen on which the wide image is displayed; stitching tele images corresponding to the partial region using the initial homography information, based on whether a zoom level corresponding to the user input exceeds a maximum zoom level of the wide image; and rendering the stitched tele images and displaying an image obtained by the rendering on the screen.

Systems and methods involve detecting objects using a radar system of a vehicle. Tracks of the objects are initiated in a track database. The tracks store data, respectively, for the objects and are updated based on additional detections of the objects. The tracks of the objects are initially unclassified tracks. Two tracks corresponding to two of the objects are selected as a candidate pair. Criteria are applied to the candidate pair to determine whether one track is of a ghost object and another track is of a true object corresponding with the ghost object. The ghost object represents detection of the true object in an incorrect location. The candidate pair is classified as tracks of a true object and ghost object pair based on determining that the one track is of the ghost object and the other track is of the true object corresponding with the ghost object.

Embodiments relate to correcting pixels of images captured using a quadra image sensor. A defect detection circuit analyzes the pixels in the captured image and determines whether a pixel is defective. The defect detection circuit generates a first defect indication by determining whether pixel data of a pixel under test is brighter or darker by a first threshold value than pixel data of pixels in pixel tiles surrounding the pixel tile corresponding to the pixel under test. Moreover, the defect detection circuit generates a second defect indication by determining whether pixel data of the pixel under test is brighter or darker by a second threshold value than pixel data of other pixels in the pixel tile corresponding to the pixel under test. Using the first and second defect indications, the defect detection circuit identifies whether the pixel data of the pixel under test is defective.

An image processing apparatus, an imaging apparatus, an image processing method, and a non-transitory computer readable medium for storing an image processing program capable of controlling the brightness of a desired color in a captured image are provided. A brightness and color difference conversion processing unit generates a reference first brightness signal “Y1” and color difference signals “Cb and Cr” from color signals “R.sub.1, G.sub.1, and B.sub.1” of three primary colors after gamma conversion. A second brightness signal generation unit generates a second brightness signal “Y2” in which a value of a brightness signal corresponding to a target color is decreased with respect to the first brightness signal “Y1” from the color signals “R.sub.1, G.sub.1, and B.sub.1”. The brightness of the desired target color can be controlled according to the reference first brightness signal “Y1” and the second brightness signal “Y2”.

Techniques for generating an enhanced cone-beam computed tomography (CBCT) image using a trained model are provided. A CBCT image of a subject is received. a synthetic computed tomography (sCT) image corresponding to the CBCT image is generated, using a generative model. The generative model is trained in a generative adversarial network (GAN). The generative model is further trained to process the CBCT image as an input and provide the sCT image as an output. The sCT image is presented for medical analysis of the subject.

Automation of microscopic pathological diagnosis relies on digital image quality, which, in turn, affects the rates of false positive and negative cellular objects designated as abnormalities. Cytogenetic biodosimetry is a genotoxic assay that detects dicentric chromosomes (DCs) arising from exposure to ionizing radiation. The frequency of DCs is related to radiation dose received, so the inferred radiation dose depends on the accuracy of DC detection. To improve this accuracy, image segmentation methods are used to rank high quality cytogenetic images and eliminate suboptimal metaphase cell data in a sample based on novel quality measures. When sufficient numbers of high quality images are found, the microscope system is directed to terminate metaphase image collection for a sample. The International Atomic Energy Agency recommends at least 500 images be used to estimate radiation dose, however often many more images are collected in order to select the metaphase cells with good morphology for analysis. Improvements in DC recognition increase the accuracy of dose estimates, by reducing false positive (FP) DC detection. A set of chromosome morphology segmentation methods selectively filtered out false DCs, arising primarily from extended prometaphase chromosomes, sister chromatid separation and chromosome fragmentation. This reduced FPs by 55% and was highly specific to the abnormal structures (≥97.7%). Additional procedures were then developed to fully automate image review, resulting in 6 image-level filters that, when combined, selectively remove images with consistently unparsable or incorrectly segmented chromosome morphologies. Overall, these filters can eliminate half of the FPs detected by manual image review. Optimal image selection and FP DCs are minimized by combining multiple feature based segmentation filters and a novel image sorting procedure based on the known distribution of chromosome lengths. Consequently, the average dose estimation error was reduced from 0.4 Gy to <0.2 Gy with minimal manual review required. Automated image selection with these filters reduces the number of images that are required to capture metaphase cells, thus decreasing the number of images and time required for each sample. A microscope system integrates image selection procedures controls with an automated digitally controlled microscope then determines at what point a sufficient number of metaphase cell images have been acquired to accurately determine radiation dose, which then terminates data collection by the microscope. These image filtering approaches constitute a reliable and scalable solution that results in more accurate and rapid radiation dose es