Abstract: For registration of medical images with deep learning, a neural network is designed to include a diffeomorphic layer in the architecture. The network may be trained using supervised or unsupervised approaches. By enforcing the diffeomorphic characteristic in the architecture of the network, the training of the network and application of the learned network may provide for more regularized and realistic registration.

Abstract: A computer-implemented method for increasing the image resolution of a digital image is provided. The method includes performing bicubic upsampling of the digital image to generate a base high-resolution (HR) image. The digital image is converted from a red-green-blue (RGB) color space to a Luma (Y), Chroma Blue Difference (Cb), and Chroma Red Difference (Cr) (YCbCr) color space to generate a low-resolution (LR) residual image. A plurality of convolutional layers of a neural network model is applied to the LR residual image to convert it to a plurality of HR residual sub-images corresponding to the digital image. An HR image corresponding to the digital image is generated using the base HR image and the plurality of HR residual sub-images.

Abstract: A treatment efficacy of a treatment for treating a parkinsonian disease is determined. A first set of imaging information/data associated with a dMRI scan of an individual's brain captured at a first time and a second set of imaging information/data associated with a dMRI scan of the individual's brain captured at a second time are received. The individual underwent the treatment for a time period comprising at least part of the time between the first and second times. An expected change between the first and second times is determined based on a natural progression of the parkinsonian disease. The first and second sets of imaging information/data are analyzed to determine a first free-water pattern and a second free-water pattern. Based on the first and second free-water patterns, a disease progression score is determined. Based on the disease progression score and the expected change, a treatment efficacy for treating the individual with the treatment is determined.

Abstract: Provided is an image processing apparatus that includes an image processing section that executes filter processing using a filter coefficient. The filter coefficient is set at least on the basis of a detection result for details based on a first image and a detection result of detection of a disturbance performed on a second image.

Abstract: The present application provides a salt and pepper noise filtering method and device based on morphological component analysis. The method comprises: obtaining a to-be-filtered image containing salt and pepper noise; calculating the dimension of the to-be-filtered image, labeled as [n, m]; initializing an n*m-dimensional all-1 labeled matrix as a salt and pepper noise labeled map; obtaining a preset region centered on a pixel point with a pixel value of 0 or 255, and calculating a noise variance between the pixel points in the preset region; labeling the position of a salt and pepper noise point in the salt and pepper noise labeled map according to the noise variance between the pixel points in the preset region, and updating and determining the salt and pepper noise labeled map. The salt and pepper noise is filtered through the method based on morphological component analysis, which improves the quality of the image.

Abstract: A method of removing noise from a depth image includes presenting real-world depth images in real-time to a first generative adversarial neural network (GAN), the first GAN being trained by synthetic images generated from computer assisted design (CAD) information of at least one object to be recognized in the real-world depth image. The first GAN subtracts the background in the real-world depth image and segments the foreground in the real-world depth image to produce a cleaned real-world depth image. Using the cleaned image, an object of interest in the real-world depth image can be identified via the first GAN trained with synthetic images and the cleaned real-world depth image. In an embodiment the cleaned real-world depth image from the first GAN is provided to a second GAN that provides additional noise cancellation and recovery of features removed by the first GAN.

Abstract: The system and method are configured to identify cars and obtain information about the identified cars. The system and method involves a software application installed on a computing device that includes a camera configured to capture images. After the software application is installed, the user can activate the camera through the software application and point the camera at a vehicle. The software application includes an object recognition function that can recognize the vehicle in the view of the camera. After recognizing the vehicle, the software application displays information about vehicle on a screen of the computing device. The software application can be used with an event such as an auto show. In addition to identifying the cars, the identified information can be used for other purposes such as a part of a scavenger hunt or other contests. Awards can be given to participants who complete the contest.

Abstract: The inventive concepts herein relate to performing block retrieval on a block to be processed of a urine sediment image. The method comprises: using a plurality of decision trees to perform block retrieval on the block to be processed, wherein each of the plurality of decision trees comprises a judgment node and a leaf node, and the judgment node judges the block to be processed to make it reach the leaf node by using a block retrieval feature in a block retrieval feature set to form a block retrieval result at the leaf node, and at least two decision trees in the plurality of decision trees are different in structures thereof and/or judgments performed by the judgment nodes thereof by using the block retrieval feature; and integrating the block retrieval results of the plurality of decision trees so as to form a final block retrieval result.

Abstract: A system comprises an encoder configured to compress attribute information and/or spatial for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. The encoder is configured to convert a point cloud into an image based representation. The encoder packs patch images into an image frame and fills empty spaces in the image frame with a padding, wherein pixel values for the padding are determined based on neighboring pixels values such that the padding is smoothed in the image frame. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud.

Abstract: The present invention discloses an image processing circuit, wherein the image processing circuit comprises a receiving circuit, a sharpness processing circuit, a luminance variation processing circuit and an output circuit. In the operations of the image processing circuit, the receiving circuit is configured to receive image data; the sharpness processing circuit is configured to perform a high-pass filtering operation on the image data to generate processed image data; the luminance variation processing is configured to determine a high frequency component of each pixel within the image data, and for each pixel, the luminance variation processing circuit is configured to calculate a difference between high frequency components of the pixel and neighboring pixel(s) to generate auxiliary image data; and the output circuit is configured to generate output image according to the processed image data and the auxiliary image data.

Abstract: An image processing method and apparatus, an electronic device, and a storage medium are provided. The method includes: obtaining an infrared image and a color image for the same object in a predetermined scenario, and a first depth map corresponding to the color image; obtaining a first optical flow between the color image and the infrared image; and performing first optimization processing on the first depth map by using the first optical flow to obtain an optimized second depth map corresponding to the color image.

Abstract: Provided is an image processing apparatus including a memory storing at least one instruction, and a processor configured to execute the at least one instruction stored in the memory to obtain first feature information by performing a convolution operation on a first image and a first kernel included in a first convolution layer among a plurality of convolution layers, obtain at least one piece of characteristic information, based on the first feature information; obtain second feature information, based on the first feature information and the at least one piece of characteristic information, obtain third feature information by performing a convolution operation on the obtained second feature information and a second kernel included in a second convolution layer that is a layer next to the first convolution layer among the plurality of convolution layers, and obtain an output image, based on the third feature information.

Abstract: Artistic styles extracted from source images may be applied to target images to generate stylized images and/or video sequences. The extracted artistic styles may be stored as a plurality of layers in one or more neural networks, which neural networks may be further optimized, e.g., via the fusion of various elements of the networks' architectures. The artistic style may be applied to the target images and/or video sequences using various optimization methods, such as the use of a first version of the neural network by a first processing device at a first resolution to generate one or more sets of parameters (e.g., scaling and/or biasing parameters), which parameters may then be mapped for use by a second version of the neural network by a second processing device at a second resolution. Analogous multi-processing device and/or multi-network solutions may also be applied to other complex image processing tasks for increased efficiency.

Abstract: Systems and methods of enhanced display and viewing of three dimensional (3D) tomographic data acquired in tomosynthesis or tomography. A set of projection data is acquired with an image acquisition system and used to reconstruct enhanced 3D volume renderings that are viewed with motion, advanced image processing or stereotactically to assist in medical diagnosis. Various enhancements are provided for further processing the images, thereby providing additional features and benefits during image viewing.

Abstract: A method includes obtaining, using at least one processor, an image of a scene including image data in each of multiple channels of a color space. The method also includes decomposing a channel of the image into a first base layer and a first detail layer. The method further includes generating a first enhanced detail layer by manipulating a characteristic of the first detail layer. The method also includes decomposing the first base layer into a second base layer and a second detail layer. The method further includes generating a second enhanced detail layer by manipulating a characteristic of the second detail layer. In addition, the method includes combining the first enhanced detail layer, the second enhanced detail layer, and the second base layer to obtain an enhanced image of the scene.

Abstract: Techniques are disclosed for point cloud denoising systems and methods. In one example, a method includes determining a respective local coordinate system for each point of a point cloud. The method further includes determining a respective first adaptive-shape neighborhood for each point of the point cloud based on each respective local coordinate system. The method further includes performing filtering associated with each respective first adaptive-shape neighborhood to obtain a respective second adaptive-shape neighborhood for each point of the point cloud. The method further includes determining local estimates for points inside each of the second adaptive-shape neighborhoods. The method further includes aggregating the local estimates for each point of the point cloud to obtain a denoised point cloud. Related devices and systems are also provided.

Abstract: Apparatuses and methods for image processing are provided. The image processing apparatus performs area classification and object detection in an image, and includes a feature map generator configured to generate the feature map of the input image using the neural network, and an image processor configured to classify the areas and to detect the objects in the image using the generated feature map.

Abstract: One or more embodiments of an image enhancement system enable a computing device to generate an enhanced digital image. In particular, a computing device can enhance a digital image including, for example, a photograph of a whiteboard, document, chalkboard, or other object having a uniform background. The computing device can determine modifications to apply to the digital image by minimizing an energy heuristic that both causes pixels of the digital image to change to a uniform color (e.g., white) and preserves gradients from the digital image. The computing device can further generate an enhanced digital image by applying the determined modifications to the digital image.

Abstract: A method includes determining information indicative of at least one facial characteristic associated with at least one face in the source image, processing the source image using a filter based on the determined information, performing wavelet decomposition on each of the filtered image and the source image, determining weightage factors associated with the wavelet decomposition of each of the filtered image and the source image, based on the determined information, obtaining a wavelet image to generate a texture restored image from the wavelet decomposition of each of the filtered image and the source image based on the weightage factors.

Abstract: The present invention relates to an image processing device and method enabling noise removal to be performed according to images and bit rates. A low-pass filter setting unit 93 sets, from filter coefficients stored in a built-in filter coefficient memory 94, a filter coefficient corresponding to intra prediction mode information and a quantization parameter. A neighboring image setting unit 81 uses the filter coefficient set by the low-pass filter setting unit 93 to subject neighboring pixel values of a current block from frame memory 72 to filtering processing. A prediction image generating unit 82 performs intra prediction using the neighboring pixel values subjected to filtering processing, from the neighboring image setting unit 81, and generates a prediction image. The present invention can be applied to an image encoding device which encodes with the H.264/AVC format, for example.