A method for optimizing an image classification model can include determining a first image classification model based on initial training data; in response to model optimization, determining a second image classification model based on the first image classification model and a noise data set; and obtaining a third image classification model by optimizing the second image classification model based on the initial training data, the third image classification model being configured to update the noise data set based on noise data generated within a predetermined time period and the noise data set.

The present invention relates to a method for acquiring an object information, the method comprising: obtaining an input image acquired by capturing a sea; obtaining a noise level of the input image; when the noise level indicates a noise lower than a predetermined level, acquiring an object information related to an obstacle included in the input image from the input image by using a first artificial neural network, and when the noise level indicates a noise higher than the predetermined level, obtaining a noise-reduced image of which the environmental noise is reduced from the input image by using a second artificial neural network, and acquiring an object information related to an obstacle included in the sea from the noise-reduced image by using the first artificial neural network.

This disclosure relates to the use of “pseudo-images” to perform image recognition, e.g., to perform facial image recognition. In an embodiment, the pseudo-image is obtained by starting with a real world image and, after optional preprocessing, subjecting the image to a non-linear transformation that converts the image into a pseudo-image. While real world objects (or, more generally, real world patterns) may be perceivable in the starting image, they cannot be perceived in the pseudo-image. Image recognition takes place by comparing the pseudo-image with a library of known pseudo-images, i.e., image recognition takes place in pseudo-image space without a return to real world space. In this way, robust image recognition is achieved even for imperfect real world images, such as, real world images that have been degraded by noise, poor illumination, uneven lighting, and/or occlusion, e.g., the presence of glasses, scarves, or the like in the case of facial images.

A system including a processor, and memory having stored thereon instructions that, when executed by the processor, control the processor to receive image data of a sequence of images, and a current image of the sequence of images being after a previous image in the sequence of images, each of the current and previous images including a cell, filter the current image to remove noise, iteratively deconvolve the filtered current image to identify edges of the cell within the current image based on determined edges of the cell within the previous image, and segment the deconvolved current image to determine edges of the cell within the current image.

An image processing method includes a first step configured to obtain a first ground truth image and a first training image, a second step configured to generate a second around truth image and a second training image by applying mutually correlated noises to the first ground truth image and the first training image, and a third step configured to make a neural network learn based on the second ground truth image and the second training image.

A plurality of remote sensing images of a scene are received. A potential target object can be identified in one of the images, wherein the target object has a low signal-to-noise ratio (SNR). A candidate motion path of the target object can be generated based upon the images. A predicted position of the target object along the candidate motion path is determined for each of the remote sensing images. An image chip is extracted from each of the images, where each image chip is centered about the predicted position of the target object in its corresponding image. A sum image chip is generated based upon the image chips. An indication that the potential target object is an actual object in the images is output based upon a value of a center pixel of the sum image chip.

A method and apparatus is provided to reduce the noise in medical imaging by training a deep learning (DL) network to select the optimal parameters for a convolution kernel of an adaptive filter that is applied in the data domain. For example, in X-ray computed tomography (CT) the adaptive filter applies smoothing to a sinogram, and the optimal amount of the smoothing and orientation of the kernel (e.g., a bivariate Gaussian) can be determined on a pixel-by-pixel basis by applying a noisy sinogram to the DL network, which outputs the parameters of the filter (e.g., the orientation and variances of the Gaussian kernel). The DL network is trained using a training data set including target data (e.g., the gold standard) and input data. The input data can be sinograms generated by a low-dose CT scan, and the target data generated by a high-dose CT scan.

In one embodiment, a system identifies a road to be navigated by an ADV, the road being captured by one or more point clouds from one or more LIDAR sensors. The system extracts road marking information of the identified road from the point clouds, the road marking information describing one or more road markings of the identified road. The system partitions the road into one or more road partitions based on the road markings. The system generates a point cloud map based on the road partitions, where the point cloud map is utilized to perceive a driving environment surrounding the ADV.

The technology disclosed attenuates spatial crosstalk from sequencing images for base calling. In particular, the technology disclosed accesses an image whose pixels depict intensity emissions from a target cluster and intensity emissions from additional adjacent clusters. The pixels include a center pixel that contains a center of the target cluster. Each pixel in the pixels is divisible into a plurality of subpixels. Depending upon a particular subpixel, in a plurality of subpixels of the center pixel, which contains the center of the target cluster, the technology disclosed selects, from a bank of subpixel lookup tables, a subpixel lookup table that corresponds to the particular subpixel. The selected subpixel lookup table contains pixel coefficients that are configured to maximizes a signal-to-noise ratio. The technology disclosed element-wise multiplies the pixel coefficients with the pixels and determines a weighted sum.

The invention relates to a method of a fingerprint sensing system of extracting fingerprint feature data from an image captured by a fingerprint sensor of the fingerprint sensing system, and a fingerprint sensing system performing the method.