Pattern identification using convolution is described. In one or more implementations, a representation of a pattern is obtained that is described using data points that include frequency coordinates, time coordinates, and energy values. An identification is made as to whether sound data described using irregularly positioned data points includes the pattern, the identifying including use of a convolution of the frequency or time coordinates to determine correspondence with the representation of the pattern.

Methods, systems, and computer readable media for automated detection of abnormalities in medical images are disclosed. According to a method for automated abnormality detection, the method includes receiving a target image. The method also includes deformably registering to the target image or to a common template a subset of normative images from a plurality of normative images, wherein the subset of normative images is associated with a normal variation of an anatomical feature. The method further includes defining a dictionary using the subset of normative images. The method also includes decomposing, using sparse decomposition and the dictionary, the target image. The method further includes classifying one or more voxels of the target image as normal or abnormal based on results of the sparse decomposition.

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.

A method and apparatus for real-time target recognition within a multispectral image includes generating radiance signatures from reflectance signatures, sensor information and environment information and detecting targets in the multispectral image with a sparsity-driven target recognition algorithm utilizing set of parameters tuned with a deep neural network.

A computer-implemented method is provided for classifying an input signal against a set of pre-classified signals. A computer system may calculate, for each of one or more signals of the set of pre-classified signals, a parallelism value indicating a level of the parallelism between that signal and the input signal. The computer system may calculate, for a first subset of the set of pre-classified signals, a sparse vector, wherein each element of the sparse vector serves as a coefficient for a corresponding signal of the first subset. The computer system may determine, for each of the signals in the set of pre-classified signals, a similarity value indicating a level of similarity between that signal and the input signal.

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.

A template creation device includes 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; 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, and to create a new template set from the plurality of integrated templates corresponding to each group in the plurality of groups.

According to one technique, a modeling computer computes a Hessian matrix by determining whether an input matrix contains more than a threshold number of dense columns. If so, the modeling computer computes a sparsified version of the input matrix and uses the sparsified matrix to compute the Hessian. Otherwise, the modeling computer identifies which columns are dense and which columns are sparse. The modeling computer then partitions the input matrix by column density and uses sparse matrix format to store the sparse columns and dense matrix format to store the dense columns. The modeling computer then computes component parts which combine to form the Hessian, wherein component parts that rely on dense columns are computed using dense matrix multiplication and component parts that rely on sparse columns are computed using sparse matrix multiplication.

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.

Systems, methods, and other embodiments described herein relate to a deep learning approach for depth completion according to variable depth inputs. In one embodiment, a method includes acquiring sensor data including at least an image of a surrounding environment. The method includes encoding the sensor data into features using an encoder of a depth model. The method includes decoding the features into a depth map using a decoder of the depth model according to an affinity-based shift correction embedded with the decoder. The method includes providing the depth map that indicates depths within the surrounding environment.