A method includes acquiring, from a camera, an image data sequence of a real object in a real scene and performing a first template-matching on an image frame in the image data sequence using intensity-related data sets stored in one or more memories to generate response maps. The intensity-related data sets represent an intensity distribution of a reference object from respective viewpoints. The reference object corresponds to the real object. A candidate region of interest is determined for the real object in the image frame based on the response maps, and second template-matching is performed on the candidate region of interest using shape-related feature data sets stored in one or more memories to derive a pose of the real object. The shape-related feature data sets represent edge information of the reference object from the respective viewpoints.

A deep learning based compression (DLBC) system applies trained models to compress binary code of an input image to a target codelength. For a set of binary codes representing the quantized coefficents of an input image, the DLBC system applies a first model that is trained to predict feature probabilities based on the context of each bit of the binary codes. The DLBC system compresses the binary code via adaptive arithmetic coding based on the determined probability of each bit. The compressed binary code represents a balance between a reconstruction quality of a reconstruction of the input image and a target compression ratio of the compressed binary code.

The invention provides a method for recognition of information in digital image data, said method comprising a learning phase on a data set of example digital images having known information, and characteristics of categories are computed automatically from each example digital image and compared to its known category, said method comprises training a convolutional neural network comprising network parameters using said data set, in which via deep learning each layer of said convolutional neural network is represented by a linear decomposition of all filters as learned in each layer into basis functions.

A method is provided to perform local de-noising of an image. The method includes obtaining a region of interest and a region of noise within a scan. The method also includes determining, for a first image based on the region of interest and a second image based on the region of noise, sample blocks and atoms for each image, where each atom contributes to a weighted sum that approximates a sample block in the image. The method also includes determining a measure of similarity of each atom from the first image with atoms from the second image and removing an atom from the first image if the measure of similarity exceeds a predetermined threshold value. The method also includes reconstructing a de-noised image based on atoms remaining in the first image after removing the atom from the first image, and presenting the de-noised image on a display device.

A friction estimation system for estimating friction-related data associated with a surface on which a vehicle travels, may include a camera array including a plurality of imagers configured to capture image data associated with a surface on which a vehicle travels. The image data may include light data associated with the surface. The friction estimation system may also include an image interpreter in communication with the camera array and configured to receive the image data from the camera array and determine friction-related data associated with the surface based, at least in part, on the image data. The image interpreter may be configured to be in communication with a vehicle control system and provide the friction-related data to the vehicle control system.

A computerized method identifies an input and kernel similarity in binarized neural network (BNN) across different applications as they are being processed by processors such as a GPU. The input and kernel similarity in BNN across different applications are analyzed to reduce computation redundancy to accelerate BNN inference. A computer-executable instructions stored thereon an on-chip arrangement receives a first data value for a data source for processing by the BNN at an inference phase. The computer-executable instructions further receives a second data value for the data source for processing by the BNN at the inference phase. The first data value is processed bitwise operations. A difference between the first data value and the second data value is calculated. The difference is stored in the on-chip arrangement. The computer-executable instructions applies the bitwise operations to the stored difference.

A process for operating a machine guided photo and video composition system involves generating processed image data. The process operates an object detection engine to identify objects and object locations in the processed image data. The process operates a computer vision analysis engine to identify geometric attributes of objects. The process operates an image cropping engine to select potential cropped image locations within the processed image data. The image cropping engine generates crop location scores for each of the potential cropped image locations and determine highest scored cropped image location. The image cropping engine communicates a highest crop location score to a score evaluator gate. The process generates object classifications from the object locations and the geometric attributes. The process receives device instructions at a user interface controller by way of the score evaluator gate. The method displays device positioning instructions through a display device.

Systems, apparatuses, and methods for converting data to a tiling format when implementing convolutional neural networks are disclosed. A system includes at least a memory, a cache, a processor, and a plurality of compute units. The memory stores a first buffer and a second buffer in a linear format, where the first buffer stores convolutional filter data and the second buffer stores image data. The processor converts the first and second buffers from the linear format to third and fourth buffers, respectively, in a tiling format. The plurality of compute units load the tiling-formatted data from the third and fourth buffers in memory to the cache and then perform a convolutional filter operation on the tiling-formatted data. The system generates a classification of a first dataset based on a result of the convolutional filter operation.

Methods and apparatus associated with predicting colorectal cancer tumor invasiveness are described. One example apparatus includes a set of circuits, and a data store that stores radiological images of tissue demonstrating colorectal cancer. The set of circuits includes a circumferential resection margin (CRM) prediction circuit that generates a CRM probability score for a diagnostic radiological image, an image acquisition circuit that acquires a diagnostic radiological image of a region of tissue demonstrating colorectal cancer pathology and that provides the diagnostic radiological image to the CRM prediction circuit, and a training circuit that trains the CRM prediction circuit to quantify chemoradiation response in the region of tissue represented in the diagnostic radiological image. The training circuit trains the CRM prediction circuit using a set of composite images.

Techniques related to implementing convolutional neural networks for object recognition are discussed. Such techniques may include generating a set of binary neural features via convolutional neural network layers based on input image data and applying a strong classifier to the set of binary neural features to generate an object label for the input image data.