-
公开(公告)号：US20240211763A1
公开(公告)日：2024-06-27
申请号：US18241469
申请日：2023-09-01
Applicant: Smart Engines Service, LLC
Inventor： Anton Vsevolodovich TRUSOV , Elena Evgenyevna LIMONOVA , Dmitry Petrovich NIKOLAEV , Vladimir Viktorovich ARLAZAROV
IPC: G06N3/082 , G06N3/0495
CPC classification number: G06N3/082 , G06N3/0495
Abstract: Given their limited computational resources, mobile or embedded devices may not be capable of operating a full-precision convolutional neural network (CNN). Thus, quantized neural networks (QNNs) may be used in place of a full-precision CNN. For example, 8-bit QNNs have similar accuracy to full-precision CNNs. While lower-bit QNNs, such as 4-bit QNNs, are faster and more computationally efficient than 8-bit QNNs, they are also significantly less accurate. Accordingly, a 4.6-bit quantization scheme is disclosed that produces a 4.6-bit QNN with similar accuracy to an 8-bit QNN, but a speed and computational efficiency that is similar to 4-bit QNNs.
-
公开(公告)号：US12014449B2
公开(公告)日：2024-06-18
申请号：US17495617
申请日：2021-10-06
Applicant: Smart Engines Service, LLC
CPC classification number: G06T11/005 , G06T2210/41
Abstract: Computed tomography (CT) image reconstruction from polychromatic projection data. In an embodiment, polychromatic projection data is acquired using a CT system. An optimal correction value for linearization of the polychromatic projection data is determined, and the polychromatic projection data is linearized according to the determined optimal correction value. The image is then reconstructed from the linearized projection data.
-
3.发明公开
公开(公告)号：US20240193422A1
公开(公告)日：2024-06-13
申请号：US18104043
申请日：2023-01-31
Applicant: Smart Engines Service, LLC
Inventor： Artem Vladimirovich SHER , Anton Vsevolodovich TRUSOV , Elena Evgenyevna LIMONOVA , Dmitry Petrovich NIKOLAEV , Vladimir Viktorovich ARLAZAROV
IPC: G06N3/084 , G06N3/0495
CPC classification number: G06N3/084 , G06N3/0495
Abstract: Quantization of a convolutional neural network (CNN) into a quantized neural network (QNN) reduces the computational resources required to operate the neural network, which is especially advantageous for operation of a neural network on resource-constrained devices. However, QNNs with low bit-widths suffer from significant losses in accuracies. Accordingly, approaches for quantization-aware training are disclosed that utilize component-by-component quantization during training to improve the accuracy of the resulting QNN. Component-by-component quantization may include filter-by-filter quantization, or preferably neuron-by-neuron quantization with some form of gradient forwarding.
-
公开(公告)号：US20230252695A1
公开(公告)日：2023-08-10
申请号：US18135288
申请日：2023-04-17
Applicant: Smart Engines Service, LLC
Inventor： Konstantin Bulatovich BULATOV , Marina Valerievna CHUKALINA , Alexey Vladimirovich BUZMAKOV , Dmitry Petrovich NIKOLAEV , Vladimir Viktorovich ARLAZAROV
CPC classification number: G06T11/006 , G06T11/008 , A61B6/542 , A61B6/42 , G06T2211/424 , G06T2211/421
Abstract: A system for monitored tomographic reconstruction, comprising: an x-ray generator configure to generate x-ray beams for scanning an object; detectors configured to capture a plurality of projections for each scan; at least one hardware processor; and one or more software modules that, when executed by the at least one hardware processor, receive the plurality of projections from the detectors and as each of the plurality of projections is received, generate a partial reconstruction, and make a stopping decision with respect to whether or not another projection should be obtained based on a stopping problem and that defines when a reconstructed image quality is sufficient with respect to the expended cost as determined by a stopping rule.
-
公开(公告)号：US11663757B2
公开(公告)日：2023-05-30
申请号：US17180397
申请日：2021-02-19
Applicant: Smart Engines Service, LLC
Inventor： Konstantin Bulatovich Bulatov , Marina Valerievna Chukalina , Alexey Vladimirovich Buzmakov , Dmitry Petrovich Nikolaev , Vladimir Viktorovich Arlazarov
CPC classification number: G06T11/006 , A61B6/42 , A61B6/542 , G06T11/008 , G06T2211/421 , G06T2211/424
Abstract: A system for monitored tomographic reconstruction, comprising: an x-ray generator configure to generate x-ray beams for scanning an object; detectors configured to capture a plurality of projections for each scan; at least one hardware processor; and one or more software modules that, when executed by the at least one hardware processor, receive the plurality of projections from the detectors and as each of the plurality of projections is received, generate a partial reconstruction, and make a stopping decision with respect to whether or not another projection should be obtained based on a stopping problem and that defines when a reconstructed image quality is sufficient with respect to the expended cost as determined by a stopping rule.
-
6.发明公开
公开(公告)号：US20230162519A1
公开(公告)日：2023-05-25
申请号：US17985309
申请日：2022-11-11
Applicant: Smart Engines Service LLC
Inventor： Daniil Pavlovich MATALOV , Elena Evgenyevna LIMONOVA , Natalya Sergeevna SKORYUKINA , Vladimir Viktorovich ARLAZAROV
IPC: G06V30/413 , G06V30/418 , G06V10/70 , G06V30/414 , G06V10/32 , G06V10/774
CPC classification number: G06V30/413 , G06V30/418 , G06V10/87 , G06V30/414 , G06V10/32 , G06V10/774
Abstract: Memory-efficient feature descriptors for localization and classification of identity documents. In an embodiment, patches are extracted from an input image of a document. For each of the patches, a gradient map is constructed for a plurality of gradient orientations, a plurality of classifiers are applied to rectangles in the gradient map, and a feature descriptor is generated based on the values output by the plurality of classifiers. The feature descriptors are then compared to templates to match the document to one of the templates for document localization and classification.
-
公开(公告)号：US11640720B2
公开(公告)日：2023-05-02
申请号：US17180434
申请日：2021-02-19
Applicant: Smart Engines Service, LLC
IPC: G06V30/10 , G06V30/41 , G06V30/413
Abstract: Text recognition in a video stream using combined recognition results with per-character weighting. In an embodiment, for each frame in a video stream, a text-recognition result is obtained and a frame weight is calculated. The text-recognition results of the frames are combined by aligning character-recognition results and calculating a character weight for each character-recognition result. At each position in the alignment, the character-recognition results are accumulated based on the character weights and frame weights to produce an accumulated text-recognition result that represents a text field in the video stream.
-
公开(公告)号：US20230132261A1
公开(公告)日：2023-04-27
申请号：US17971190
申请日：2022-10-21
Applicant: Smart Engines Service, LLC
Inventor： Konstantin Bulatovich BULATOV , Pavel Vladimirovich BEZMATERNYKH , Dmitry Petrovich NIKOLAEV , Vladimir Viktorovich ARLAZAROV
IPC: G06V30/24 , G06V40/16 , G06V10/26 , G06V30/413 , G06V30/414
Abstract: Unified framework for analysis and recognition of identity documents. In an embodiment, an image is received. A document is located in the image and an attempt is made to identify one or more of a plurality of templates that match the document. When template(s) that match the document are identified, for each of the template(s) and for each of one or more zones in the template, a sub-image of the zone is extracted from the image. For each extracted sub-image, one or more objects are extracted from the sub-image. For each extracted object, object recognition is performed. This may be done over one iteration (e.g., for a scanned image or photograph) or a plurality of iterations (e.g., for a video). Document recognition is performed based on the one or more templates and the results of the object recognition, and a final document-recognition result is output.
-
公开(公告)号：US11636608B2
公开(公告)日：2023-04-25
申请号：US17237539
申请日：2021-04-22
Applicant: Smart Engines Service, LLC
Inventor： Alexander Vladimirovich Sheshkus , Dmitry Petrovich Nikolaev , Vladimir L'vovich Arlazarov , Vladimir Viktorovich Arlazarov
Abstract: Artificial intelligence using convolutional neural network with Hough Transform. In an embodiment, a convolutional neural network (CNN) comprises convolution layers, a Hough Transform (HT) layer, and a Transposed Hough Transform (THT) layer, arranged such that at least one convolution layer precedes the HT layer, at least one convolution layer is between the HT and THT layers, and at least one convolution layer follows the THT layer. The HT layer converts its input from a first space into a second space, and the THT layer converts its input from the second space into the first space. The CNN may be applied to an input image to perform semantic image segmentation, so as to produce an output image representing a result of the semantic image segmentation.
-
公开(公告)号：US20220122267A1
公开(公告)日：2022-04-21
申请号：US17237539
申请日：2021-04-22
Applicant: Smart Engines Service, LLC
Inventor： Alexander Vladimirovich SHESHKUS , Dmitry Petrovich NIKOLAEV , Vladimir L`vovich ARLAZAROV , Vladimir Viktorovich ARLAZAROV
IPC: G06T7/168
Abstract: Artificial intelligence using convolutional neural network with Hough Transform. In an embodiment, a convolutional neural network (CNN) comprises convolution layers, a Hough Transform (HT) layer, and a Transposed Hough Transform (THT) layer, arranged such that at least one convolution layer precedes the HT layer, at least one convolution layer is between the HT and THT layers, and at least one convolution layer follows the THT layer. The HT layer converts its input from a first space into a second space, and the THT layer converts its input from the second space into the first space. The CNN may be applied to an input image to perform semantic image segmentation, so as to produce an output image representing a result of the semantic image segmentation.
