The present disclosure is directed to a method to generate a recovered image from a compressive measurement vector. The method uses a trained machine learning (ML) model, generated from a decomposed sensing matrix and a compressive measurement labeled pair, to generate a feature vector that has a dimensional value less than that for the recovered image. The feature vector can be linearly transformed into the recovered image. Also disclosed is a system operable to execute a process to train a ML model using a decomposed sensing matrix, a training image, and a compressive measurement vector representing the training image. A system is also disclosed that is operable to utilize a trained ML model and a decomposed sensing matrix to estimate a recovered image represented by a compressive measurement vector.

The disclosure relates to information processing apparatus and information processing method. The information processing apparatus according to an embodiment includes a processing circuitry configured to acquire a first depth image, a second depth image and an intensity image having a pixel correspondence with each other, wherein the second depth image being superior to the first depth image in terms of image quality. The processing circuitry is further configured to perform a training process based on the first depth image, the second depth image and the intensity image to derive parameters of an analysis sparse representation model modeling a relationship among the first depth image, the second depth image and the intensity image. The processing circuitry is configured to output the derived parameters.

Image data is run through a neural network, and the neural network produces a vector representation of the image data. Random sparse sampling masks are created. The vector representation of the image data is masked with each of the random sparse sampling masks, the masking generating corresponding sparsely sampled vectors. The sparsely sampled vectors are transmitted to nodes of a consensus network, wherein a sparsely sampled vector of the sparsely sampled vectors is transmitted to a node of the consensus network. Votes from the nodes of the consensus network are received. Whether a consensus is achieved in the votes is determined. Responsive to determining that the consensus is achieved, at least one of identification and verification of the image data may be provided.

A template creation device may include an acquisition unit configured to acquire a plurality of templates from a plurality of images of different poses of a single object, or a plurality of images for a plurality of objects. The template creation device may further include a clustering unit configured to divide the plurality of templates into a plurality of groups on the basis of a similarity score; and an integration unit configured to combine the templates in a group into an integrated template. A new template set may be created from the plurality of integrated templates corresponding to each group in the plurality of groups.

A method for generating a synthetic image of a region of an object, includes: generating, by a charged particle microscope, a charged particle microscope image of the region of the object; calculating a sparse representation of the charged particle microscope image; wherein the sparse representation of the charged particle microscope image comprises multiple first atoms; generating the synthetic image of the region, wherein the synthetic image of the region is formed from multiple second atoms; wherein the generating of the synthetic image of the region is based on a mapping between the multiple first atoms and the multiple second atoms; wherein the charged particle microscope image and the multiple first atoms are of a first resolution; and wherein the synthetic image of the region and the multiple second atoms are of a second resolution that is finer than the first resolution.

A method of comparing objects in images. A dictionary determined from a plurality of feature vectors formed from a test image and codes formed by applying the dictionary to the feature vectors is received, the dictionary being based on a difference in mean values between the codes. Comparison codes are determined for the objects in the images by applying the dictionary to feature vectors of the objects in the images. The objects in the images are compared based on the comparison codes of the objects.

One embodiment provides a method comprising identifying a salient part of an object in an input image based on processing of a region of interest (RoI) in the input image at an electronic device. The method further comprises determining an estimated full appearance of the object in the input image based on the salient part and a relationship between the salient part and the object. The electronic device is operated based on the estimated full appearance of the object.

A method of classifying signals using non-linear sparse representations includes learning a plurality of non-linear dictionaries based on a plurality of training signals, each respective nonlinear dictionary corresponding to one of a plurality of class labels. A non-linear sparse coding process is performed on a test signal for each of the plurality of non-linear dictionaries, thereby associating each of the plurality of non-linear dictionaries with a distinct sparse coding of the test signal. For each respective non-linear dictionary included in the plurality of non-linear dictionaries, a reconstruction error is measured using the test signal and the distinct sparse coding corresponding to the respective non-linear dictionary. A particular nonlinear dictionary corresponding to a smallest value for the reconstruction error among the plurality of non-linear dictionaries is identified and a class label corresponding to the particular non-linear dictionary is assigned to the test signal.

Technologies for classification using sparse coding are disclosed. A compute device may include a pattern-matching accelerator, which may be able to determine the distance between an input vector (such as an image) and several basis vectors of an overcomplete dictionary stored in the pattern-matching accelerator. The pattern matching accelerator may be able to determine each of the distances simultaneously and in a fixed amount of time (i.e., with no dependence on the number of basis vectors to which the input vector is being compared). The pattern-matching accelerator may be used to determine a set of sparse coding coefficients corresponding to a subset of the overcomplete basis vectors. The sparse coding coefficients can then be used to classify the input vector.

An optical system for capturing an image using compressive sensing includes: a digital micromirror device (DMD) array; an optical lens system; a first optical detector array; a first optical channel for projecting spatial information onto the first detector array; a second optical detector array; a second optical channel; a spectral filter and a polarization filter for projecting spectral and polarization information onto the second detector array; and an image processor to control the DMD array to generate a first and a second set of samples of the image using a sampling rate lower than required by the Shannon-Nyquist sampling theorem, and to reconstruct the image from the samples collected and digitized by the first and second optical detector arrays.