13379 results about "Convolutional neural network" patented technology

The present invention is directed to a computer automated method of selectively identifying a user specified behavior of a crowd. The method comprises receiving video data but can also include audio data and sensor data. The video data contains images a crowd. The video data is processed to extract hierarchical human and crowd features. The detected crowd features are processed to detect a selectable crowd behavior. The selected crowd behavior detected is specified by a configurable behavior rule. Human detection is provided by a hybrid human detector algorithm which can include Adaboost or convolutional neural network. Crowd features are detected using textual analysis techniques. The configurable crowd behavior for detection can be defined by crowd behavioral language.

The invention discloses a vehicle type recognition method based on a rapid R-CNN deep neural network, which mainly comprises unsupervised deep learning, a multilayer CNN (Convolutional Neural Network), a regional advice network, network sharing and a softmax classifier. The vehicle type recognition method realizes a framework for implementing end-to-end vehicle detection and recognition by using one rapid R-CNN network in a real sense, and is capable of carrying out quick vehicle sub-category recognition with high accuracy and robustness under the environment of being applicable to the shape diversity, the illumination variation diversity, the background diversity and the like of vehicle targets.

A coprocessor and method for processing convolutional neural networks includes a configurable input switch coupled to an input. A plurality of convolver elements are enabled in accordance with the input switch. An output switch is configured to receive outputs from the set of convolver elements to provide data to output branches. A controller is configured to provide control signals to the input switch and the output switch such that the set of convolver elements are rendered active and a number of output branches are selected for a given cycle in accordance with the control signals.

The invention discloses a fundus image retinal vessel segmentation method and a fundus image retinal vessel segmentation system based on deep learning. The fundus image retinal vessel segmentation method comprises the steps of performing data amplification on a training set, enhancing an image, training a convolutional neural network by using the training set, segmenting the image by using a convolutional neural network segmentation model to obtain a segmentation result, training a random forest classifier by using features of the convolutional neural network, extracting a last layer of convolutional layer output from the convolutional neural network, using the convolutional layer output as input of the random forest classifier for pixel classification to obtain another segmentation result, and fusing the two segmentation results to obtain a final segmentation image. Compared with the traditional vessel segmentation method, the fundus image retinal vessel segmentation method uses the deep convolutional neural network for feature extraction, the extracted features are more sufficient, and the segmentation precision and efficiency are higher.

The invention relates to a visual recognition and positioning method for robot intelligent capture application. According to the method, an RGB-D scene image is collected, a supervised and trained deep convolutional neural network is utilized to recognize the category of a target contained in a color image and a corresponding position region, the pose state of the target is analyzed in combinationwith a deep image, pose information needed by a controller is obtained through coordinate transformation, and visual recognition and positioning are completed. Through the method, the double functions of recognition and positioning can be achieved just through a single visual sensor, the existing target detection process is simplified, and application cost is saved. Meanwhile, a deep convolutional neural network is adopted to obtain image features through learning, the method has high robustness on multiple kinds of environment interference such as target random placement, image viewing anglechanging and illumination background interference, and recognition and positioning accuracy under complicated working conditions is improved. Besides, through the positioning method, exact pose information can be further obtained on the basis of determining object spatial position distribution, and strategy planning of intelligent capture is promoted.

The invention discloses an attention CNNs and CCR-based text sentiment analysis method and belongs to the field of natural language processing. The method comprises the following steps of 1, training a semantic word vector and a sentiment word vector by utilizing original text data and performing dictionary word vector establishment by utilizing a collected sentiment dictionary; 2, capturing context semantics of words by utilizing a long-short-term memory (LSTM) network to eliminate ambiguity; 3, extracting local features of a text in combination with convolution kernels with different filtering lengths by utilizing a convolutional neural network; 4, extracting global features by utilizing three different attention mechanisms; 5, performing artificial feature extraction on the original text data; 6, training a multimodal uniform regression target function by utilizing the local features, the global features and artificial features; and 7, performing sentiment polarity prediction by utilizing a multimodal uniform regression prediction method. Compared with a method adopting a single word vector, a method only extracting the local features of the text, or the like, the text sentiment analysis method can further improve the sentiment classification precision.

A computer-implemented method executed by at least one processor for training fast models for real-time object detection with knowledge transfer is presented. The method includes employing a Faster Region-based Convolutional Neural Network (R-CNN) as an objection detection framework for performing the real-time object detection, inputting a plurality of images into the Faster R-CNN, and training the Faster R-CNN by learning a student model from a teacher model by employing a weighted cross-entropy loss layer for classification accounting for an imbalance between background classes and object classes, employing a boundary loss layer to enable transfer of knowledge of bounding box regression from the teacher model to the student model, and employing a confidence-weighted binary activation loss layer to train intermediate layers of the student model to achieve similar distribution of neurons as achieved by the teacher model.

The invention belongs to the technical field of digital image processing and mode identification, and specifically relates to an FPGA-based deep convolution neural network realizing method. The hardware platform for realizing the method is XilinxZYNQ-7030 programmable sheet SoC, and an FPGA and an ARM Cortex A9 processor are built in the hardware platform. Trained network model parameters are loaded to an FPGA end, pretreatment for input data is conducted at an ARM end, and the result is transmitted to the FPGA end. Convolution calculation and down-sampling of a deep convolution neural network are realized at the FPGA end to form data characteristic vectors and transmit the data characteristic vectors to the ARM end, thus completing characteristic classification calculation. Rapid parallel processing and extremely low-power high-performance calculation characteristics of FPGA are utilized to realize convolution calculation which has the highest complexity in a deep convolution neural network model. The algorithm efficiency is greatly improved, and the power consumption is reduced while ensuring algorithm correct rate.

The invention discloses a convolution neural network parallel processing method based on a large-scale high-performance cluster. The method comprises the steps that (1) a plurality of copies are constructed for a network model to be trained, model parameters of all the copies are identical, the number of the copies is identical with the number of nodes of the high-performance cluster, each node is provided with one model copy, one node is selected to serve as a main node, and the main node is responsible for broadcasting and collecting the model parameters; (2) a training set is divided into a plurality of subsets, the training subsets are issued to the rest of sub nodes except the main mode each time to conduct parameter gradient calculation together, gradient values are accumulated, the accumulated value is used for updating the model parameters of the main node, and the updated model parameters are broadcast to all the sub nodes until model training is ended. The convolution neural network parallel processing method has the advantages of being capable of achieving parallelization, improving the efficiency of model training, shortening the training time and the like.

The present invention relates to artificial neural network, for example, convolutional neural network. In particular, the present invention relates to how to implement and optimize a convolutional neural network based on an embedded FPGA. Specifically, it proposes an overall design process of compressing, fix-point quantization and compiling the neural network model.

The invention discloses a deep convolutional neural network-based lung cancer preventing self-service health cloud service system. The system comprises a convolutional neural network used for deep learning and training identification, a segmentation module which segments out a lung region from a CT image based on a full convolutional neural network, a deep convolutional neural network used for lung cancer diagnosis classification, and a self-service health cloud service platform used for performing early prevention and treatment according to an identified suspected lung cancer type. According to the system, the automation and intelligentization level of mobile internet-based lung cancer screening can be effectively improved, more citizens can know and participate in self-service health detection, assessment and guidance, the sensitivity, specificity and accuracy of early lung cancer screening and clinical diagnosis are improved, the lung cancer can be early discovered, early diagnosed and early treated, and the self-health management capability is enhanced.

The invention discloses a depth image human body joint positioning method based on a convolution nerve network. The method is characterized by comprising a training process and an identification process. The training process comprises the following steps: 1, inputting a training sample; 2, initializing a deep convolution nerve network and its parameters, wherein the parameters comprise a weight and a bias of each layer edge; and 3, by use of a forward algorithm and a backward algorithm, learning the parameters of the constructed convolution nerve network. The identification process comprises the following steps: 4, inputting a test sample; and 5, performing regression on the input test sample by use of the trained convolution nerve network to find positions of human body joints. According to the invention, by use of the deep convolution nerve network and large data, multiple challenges such as shielding, noise and the like can be resisted, and the accuracy is quite high; and at the same time, by means of parallel calculation, the effect of accurately positioning the human body joints in real time can be realized.

The present invention discloses a multi-task learning convolutional neural network (CNN)-based face attribute analysis method. According to the method, based on a convolutional neural network, a multi-task learning method is adopted to carry out age estimation, gender identification and race classification on a face image simultaneously. In a traditional processing method, when face multi-attribute analysis is carried out, a plurality of times of calculation are required, and as a result, time can be wasted, and the generalization ability of a model is decreased. According to the method of the invention, three single-task networks are trained separately; the weight of a network with the lowest convergence speed is adopted to initialize the shared part of a multi-task network, and the independent parts of the multi-task network are initialized randomly; and the multi-task network is trained, so that a multi-task convolutional neural network (CNN) model can be obtained; and the trained multi-task convolutional neural network (CNN) model is adopted to carry out age, gender and race analysis on an inputted face image simultaneously, and therefore, time can be saved, and accuracy is high.

A 1D-CNN-based ((one-dimensional convolutional neural network)-based) distributed optical fiber sensing signal feature learning and classification method is provided, which solves a problem that an existing distributed optical fiber sensing system has poor adaptive ability to a complex and changing environment and consumes time and effort due to adoption of manually extracted distinguishable event features, The method includes steps of: segmenting time sequences of distributed optical fiber sensing acoustic and vibration signals acquired at all spatial points, and building a typical event signal dataset; constructing a 1D-CNN model, conducting iterative update training of the network through typical event signals in a training dataset to obtain optimal network parameters, and learning and extracting 1D-CNN distinguishable features of different types of events through an optimal network to obtain typical event signal feature sets; and after training different types of classifiers through the typical event signal feature sets, screening out an optimal classifier.

Methods of detecting an object in an image using a convolutional neural-network-based architecture that processes multiple feature maps of differing scales from differing convolution layers within a convolutional network to create a regional-proposal bounding box. The bounding box is projected back to the feature maps of the individual convolution layers to obtain a set of regions of interest (ROIs) and a corresponding set of context regions that provide additional context for the ROIs. These ROIs and context regions are processed to create a confidence score representing a confidence that the object detected in the bounding box is the desired object. These processes allow the method to utilize deep features encoded in both the global and the local representation for object regions, allowing the method to robustly deal with challenges in the problem of object detection. Software for executing the disclosed methods within an object-detection system is also disclosed.

The invention discloses a face recognition method, device, system and apparatus based on a convolutional neural network (CNN). The method comprises the following steps: S1, face detection: using a multilayer CNN feature architecture; S2, key point positioning: obtaining the key point positions of the face by using connecting reference frame regression networks in a cascaded way in deep learning; S3, preprocessing: obtaining a face image with a fixed size; S4, feature extraction: obtaining a feature representative vector by means of a feature extraction model; and S5: feature comparison: determining the similarity according to a threshold or giving a face recognition result according to distance sorting. The method adds a multilayer CNN feature combination to a traditional CNN single-layer feature architecture to treat different imaging conditions, trains a face detection network with good robustness in the monitoring environment from massive image data sets based on a deep convolution neural network algorithm, reduces a false detection rate, and improves detection response speed.

A method for sentiment classification of a text document using high-order n-grams utilizes a multilevel embedding strategy to project n-grams into a low-dimensional latent semantic space where the projection parameters are trained in a supervised fashion together with the sentiment classification task. Using, for example, a deep convolutional neural network, the semantic embedding of n-grams, the bag-of-occurrence representation of text from n-grams, and the classification function from each review to the sentiment class are learned jointly in one unified discriminative framework.

Systems and methods for defection classification in a semiconductor process are provided. The system includes a communication line configured to receive a defect image of a wafer from the semiconductor process and a deep-architecture neural network in electronic communication with the communication line. The neural network has a first convolution layer of neurons configured to convolve pixels from the defect image with a filter to generate a first feature map. The neural network also includes a first subsampling layer configured to reduce the size and variation of the first feature map. A classifier is provided for determining a defect classification based on the feature map. The system may include more than one convolution layers and/or subsampling layers. A method includes extracting one or more features from a defect image using a deep-architecture neural network, for example a convolutional neural network.

Described are systems, media, and methods for applying deep convolutional neural networks to medical images to generate a real-time or near real-time diagnosis.

Embodiments of a multimodal question answering (mQA) system are presented to answer a question about the content of an image. In embodiments, the model comprises four components: a Long Short-Term Memory (LSTM) component to extract the question representation; a Convolutional Neural Network (CNN) component to extract the visual representation; an LSTM component for storing the linguistic context in an answer, and a fusing component to combine the information from the first three components and generate the answer. A Freestyle Multilingual Image Question Answering (FM-IQA) dataset was constructed to train and evaluate embodiments of the mQA model. The quality of the generated answers of the mQA model on this dataset is evaluated by human judges through a Turing Test.

Methods of detecting an object in an image using a convolutional neural network based architecture that processes multiple feature maps of differing scales from differing convolution layers within a convolutional network to create a regional-proposal bounding box. The bounding box is projected back to the feature maps of the individual convolution layers to obtain a set of regions of interest. These regions of interest are then processed to ultimately create a confidence score representing the confidence that the object detected in the bounding box is the desired object. These processes allow the method to utilize deep features encoded in both the global and the local representation for object regions, allowing the method to robustly deal with challenges in the problem of robust object detection. Software for executing the disclosed methods within an object-detection system is also disclosed.

An image processing system and/or method obtains source images in which a damaged vehicle is represented, and performs image processing techniques to determine, predict, estimate, and/or detect damage that has occurred at various locations on the vehicle. The image processing techniques may include generating a composite image of the damaged vehicle, aligning and/or isolating the image, applying convolutional neural network techniques to the image to generate damage parameter values, where each value corresponds to damage in a particular location of vehicle, and/or other techniques. Based on the damage values, the image processing system/method generates and displays a heat map for the vehicle, where each color and/or color gradation corresponds to respective damage at a respective location on the vehicle. The heat map may be manipulatable by the user, and may include user controls for displaying additional information corresponding to the damage at a particular location on the vehicle.

The invention discloses an image classification method based on a convolution neural network. The method comprises the following steps: constructing a deep convolution neural network; improving the deep convolution neural network; training and testing the deep convolution neural network; and optimizing the network parameter. By using the image classification method disclosed by the invention, the improvement and the optimization are respectively performed on the network structure and multiple parameters of the convolution neural network, the recognition rate of the deep convolution neural network can be effectively improved, and the accuracy of the image classification is improved.

Systems and methods for providing convolutional neural network based image synthesis using localized loss functions is disclosed. A first image including desired content and a second image including a desired style are received. The images are analyzed to determine a local loss function. The first and second images are merged using the local loss function to generate an image that includes the desired content presented in the desired style. Similar processes can also be utilized to generate image hybrids and to perform on-model texture synthesis. In a number of embodiments, Condensed Feature Extraction Networks are also generated using a convolutional neural network previously trained to perform image classification, where the Condensed Feature Extraction Networks approximates intermediate neural activations of the convolutional neural network utilized during training.

The subject disclosure presents systems and computer-implemented methods for automatic immune cell detection that is of assistance in clinical immune profile studies. The automatic immune cell detection method involves retrieving a plurality of image channels from a multi-channel image such as an RGB image or biologically meaningful unmixed image. A cell detector is trained to identify the immune cells by a convolutional neural network in one or multiple image channels. Further, the automatic immune cell detection algorithm involves utilizing a non-maximum suppression algorithm to obtain the immune cell coordinates from a probability map of immune cell presence possibility generated from the convolutional neural network classifier.

The invention discloses a face identification method and apparatus. The method includes the steps of extracting face characteristic vectors of a face image to be identified by using a convolution neural network model. The face characteristic vectors comprise image characteristics and facial attribute characteristics. Matching degree between the face image to be identified and face images in a face template database is calculated according to the face characteristic vectors, and the identification result of the face image to be identified is determined according to the matching degree. During a face identification process, the face identification accuracy is effectively improved based on comprehensive comparison of the face image characteristics and facial attribute characteristics.

The invention discloses a human face detection method and a detection device based on multi-task cascade-connection convolution neural network, wherein the method comprises: establishing a cascade-connection multi-level convolution neural network; using the human face front samples, the human face back samples, some parts of the human face and the human face's key point samples as the training samples to train the multi-level convolution neural network to learn the tasks of human face categorizing, human face area position regression and human face's key point positioning; and utilizing the well trained multi-level convolution neural network to make human face detection from the to-be-detected image wherein in the training stage, both the online manner and the offline manner are combined to extract the human face back samples as the training samples. According to the invention, based on the cascade-connection multi-level convolution neural network, it is possible to learn the characteristics with stronger robustness, and at the same time, through the combination of the online manner and the offline manner to extract the back samples, the categorizing capability of the network is enhanced, so that the detection capability and the accuracy of the network are increased, and that the running speed of the method in an actual product is ensured.

The invention discloses a ship object recognition method based on a multilayer convolution neural network, and the method comprises the steps: S1, employing the existing images, parameters and model data for the building of a ship sample library, and continuously increasing the data in a use process through target detection; S2, carrying out the ship target feature training under the frame of a convolution neural network, and forming visible light/infrared and two-dimensional/three-dimensional fusion ship feature knowledge library through the recognition training of the ship sample library, wherein the ship feature knowledge library is used for the classification and recognition of ships; S3, carrying out the data collection of a ship target: carrying out the real-time high-resolution collection of the visible light or infrared video data of the ship target on the sea; S4, carrying out the detection of the ship target on the sea; S5, carrying out the coarse classification of the imagesof the ship target; S6, carrying out the fine classification and recognition of the ship target based on a depth neural network completed through the ship target feature training, and accurately recognizing the type of the recognized ship. The method overcomes a difficulty in recognition of the ship target.

The present invention relates to the field of deep learning techniques, in particular to a deep convolution neural network training method and a device. The deep convolution neural network training method and the device comprise the steps of a, pretraining the DCNN on a large scale data set, and pruning the DCNN; b, performing the migration learning on the pruned DCNN; c, performing the model compression and the pruning on the migrated DCNN with the small-scale target data set, In the process of migrating learning of large-scale source data set to small-scale target data set, the model compression and the pruning are performed on the DCNN by the migration learning method and the advantages of model compression technology, so as to improve the migration learning ability to reduce the risk of overfitting and the deployment difficulty on the small-scale target data set and improve the prediction ability of the model on the target data set.

The invention relates to an image retrieval method based on deep learning and Hash. According to the image retrieval method, on the basis of powerful learning capacity of a deep convolutional neural network, deep features of images are extracted, and the problems of weak feature expression capacity and low retrieval precision caused by use of lower features of the images in the prior art are solved; a Hash layer is introduced for construction of a Hash function, learning of the deep features of the images and the construction of the Hash function are completed in the same process, an internal relation of the image features and the Hash function is explored, and the accuracy rate of the image retrieval is greatly increased; quantization error loss is added to a loss layer of the deep convolutional neural network, the expression capacity of Hash codes is enhanced, by means of a Softmax classifier loss module and a quantization error loss module, quantization errors caused by binaryzation in the Hash function are effectively reduced, and the accuracy rate of the image retrieval is further increased.