110 results about "Automatic image annotation" patented technology

The invention provides a semi-supervised X-ray automatic labeling method based on a generative adversarial network. A traditional training method is improved on the basis of an existing generative adversarial network method, and a semi-supervised training method combining supervised loss and unsupervised loss is used for carrying out image classification recognition based on a small number of labeled samples. The problem of data scarcity annotation of the X-ray image is studied. The method comprises: firstly, on the basis of a traditional unsupervised generative adversarial network, using a softmax for replacing a final output layer; expanding the X-ray image into a semi-supervised generative adversarial network, defining additional category label guide training for the generated sample, optimizing network parameters by adopting the semi-supervised training, and finally, automatically labeling the X-ray image by adopting a trained discriminant network. Compared with traditional supervised learning and other semi-supervised learning algorithms, the method has the advantage that in the aspect of medical X-ray image automatic labeling, the performance is improved.

An automatic image annotation method for weakly supervised semantic segmentation. The object border is located by an image object detection method, and the semantic label is given. The object border and the semantic label are regarded as a kind of weak supervised semantic label of image level. By using traditional image segmentation method, the whole object region is segmented out, and the segmentation template for training classification network is generated. Then, the segmentation template is used as a supervisory signal to train the classification network. Finally, the trained classification network is used to segment the test image semantically. The technical proposal of the invention utilizes an object detection method to obtain a border and a semantic tag of an object in an image, utilizes a traditional image segmentation method to segment an object region, and combines the semantic tag to serve as a training sample for weak supervision semantic segmentation. The method to automatically generate training samples for weak supervised semantic segmentation, solves the problem of time-consuming and laborious manual labeling of a large number of images.

In a method, device and storage medium encoded with programming instructions for automatic image registration of image data of a current medical image MR study and at least one reference study, corresponding image pairs of the current study and the reference study are formed automatically with an association machine without needing the analyze the respective image data or pixel data. The pair determination takes place exclusively on the basis of the DICOM header data. A synchronized image processing and / or presentation of the generated image pairs takes place at a monitor.

Systems and Methods for multi-modal or multimedia image retrieval are provided. Automatic image annotation is achieved based on a probabilistic semantic model in which visual features and textual words are connected via a hidden layer comprising the semantic concepts to be discovered, to explicitly exploit the synergy between the two modalities. The association of visual features and textual words is determined in a Bayesian framework to provide confidence of the association. A hidden concept layer which connects the visual feature(s) and the words is discovered by fitting a generative model to the training image and annotation words. An Expectation-Maximization (EM) based iterative learning procedure determines the conditional probabilities of the visual features and the textual words given a hidden concept class. Based on the discovered hidden concept layer and the corresponding conditional probabilities, the image annotation and the text-to-image retrieval are performed using the Bayesian framework.

The invention discloses an automatic image annotation method based on semi-supervised learning. The method comprises the steps that a data set is divided into a training data set, an unlabeled data set and a test set; the SIFT feature and the HOG feature of a training sample are extracted to train an LDA_SVM classifier; color and texture features are extracted to train a neural network; unlabeleddata are used to enable two classifiers to label and predict the same unlabeled sample simultaneously; according to the contribution of the classifiers to the unlabeled sample classification accuracy,the classification results of two classifiers are weighted and fused by an adaptive weighted fusion policy, so as to acquire the final prediction label probability vector of the sample; and finally two classifiers are updated by the sample with high confidence and the predictive label thereof until the preset maximum number of iterations is reached. According to the invention, the method can makefull use of the unlabeled sample to excavate the inherent law of the image feature; the number of annotation samples required for the classifier training is effectively reduced; the annotation effectis great.

The invention relates to an image mantic automatic mark method based on mark importance sequence, wherein it comprises: (1) classifying the training images, to form a serial of same image groups; (2) building mantic skeleton for each image, to express its image with mantic skeleton, at the same time, calculating the keyword importance sequence of image and the importance sequence of image sub block; (3) using static method to automatic mark the image. The invention considers the importance of sub block of image area and the importance sequence of training text, to support the image search based on mantic, without word frequency distortion distribution.

The invention relates to an interactive method of image semi-automatic annotation, comprising S1 dividing an initial sample into three different types of annotation samples according to different category attributes; labeling the three types of labeling samples manually to get different kinds of labeling results, and then using three models of Mask-RCNN, Fast-RCNN and FCN to train separately; S2 processing the data set of the picture to be annotated in an offline manner, wherein the annotating process is that the data set of the picture to be annotated passes through the three depth learning models in turn to output the json format files of all types and coordinate points of the data samples; S3 calling the relevant attribute tag value and coordinate point value of the json format file according to the name of the annotated image; S4 displaying the corresponding automatic marking result in the marking software, and judging whether the category and area marking of the target object arestandardized and reasonable by manpower; S5 carrying out data augmentation on the correctly labeled labeling samples and feeding back the augmented data to the model for retraining.

An apparatus and a method for automated semantic annotation of a process model having model elements named by natural language expressions, wherein said apparatus comprises at least one semantic pattern analyser which analyses the textual structure of each natural language expression on the basis of predefined semantic pattern descriptions to establish a semantic linkage between each model element to classes and instances of a reference process ontology for generating a semantically annotated process model.

The invention provides an image segmentation method based on an annotated image learn. The method comprises two processes of: 1, learning an annotated training sample, namely segmenting the training image, performing scene classification on the training image, and establishing connection between the annotated words and the segmentation region on a special scene; and 2, determining the annotated words of the region to be segmented according to a model parameter acquired by learning in the process 1, performing information fusion according to the annotated information of the region and finishing segmentation. According to the method, the image segmentation and the identification process are fused by learning the annotated image; the annotated words serve as connecting link of the image segmentation and object identification; connection is established between low-grade visual stimulation and the annotated words representing high-grade semantic information to guide the image segmentation process, so that the cognitive ability of the image segmentation result is improved. The method can be directly applied to the actual application fields such as automatic image annotation, computer-aided diagnosis of a medical image, segmentation and classification of remote sensing images, multimedia information retrieval and the like.

The invention relates to the image processing technology field and provides an image annotation method and a terminal device. The method comprises the following steps of acquiring an image to be annotated, and inputting the image to be annotated into a target detection model so as to obtain the first annotation set of the image to be annotated; displaying the image to be annotated containing the first annotation set; acquiring adjusting information input by a user, and according to the adjusting information, adjusting the first annotation set; and according to the adjusted first annotation set, determining the final annotation set of the image to be annotated. In the invention, the automatic annotation and the manual annotation of the image can be combined, image annotation efficiency is greatly increased, and annotation accuracy can be ensured.

Systems and Methods for multi-modal or multimedia image retrieval are provided. Automatic image annotation is achieved based on a probabilistic semantic model in which visual features and textual words are connected via a hidden layer comprising the semantic concepts to be discovered, to explicitly exploit the synergy between the two modalities. The association of visual features and textual words is determined in a Bayesian framework to provide confidence of the association. A hidden concept layer which connects the visual feature(s) and the words is discovered by fitting a generative model to the training image and annotation words. An Expectation-Maximization (EM) based iterative learning procedure determines the conditional probabilities of the visual features and the textual words given a hidden concept class. Based on the discovered hidden concept layer and the corresponding conditional probabilities, the image annotation and the text-to-image retrieval are performed using the Bayesian framework.

The invention aims at providing a method, apparatus and device for controlling automatic image shooting. The method comprises the steps of acquiring position information of one or more view finding regions in a view finding frame, controlling a corresponding shooting device to perform shooting so as to obtain an initial image, and acquiring images respectively corresponding to one or more view finding regions from the initial image according to the position information of one or more view finding regions. The method, apparatus and device for controlling the automatic image shooting has the advantages that the shooting is performed according to the regions selected by a user in the view finding frame so as to directly show the images corresponding to the selected regions to the user, the user does not need to cut pictures and perform other operations at a later stage, and the using process of the user is simplified. In addition, shooting parameters can be adjusted according to the regions selected by the user, accordingly an aperture, a shutter, a focal distance part and other related devices can be adjusted based on the characteristics of the regions selected by the user, the regions selected by the user have high imaging quality, and the user experience is improved.

The invention discloses an automatic image annotation method based on deep learning and canonical correlation analysis. The method includes: using a depth Boltzmann machine to extract the high-level feature vectors of images and annotation words, selecting multiple Bernoulli distribution to fit annotation word samples, and selecting Gaussian distribution to fit image features; performing canonical correlation analysis on the high-level features of the images and the annotation words; calculating the Mahalanobis distance between to-be-annotated images and training set images in canonical variable space, and performing weighted calculation according to the distance to obtain high-level annotation word features; generating image annotation words through mean field estimation. The depth Boltzmann machine comprises I-DBM and T-DBM which are respectively used for extracting the high-level feature vectors of the images and the annotation words. Each of the I-DBM and the T-DBM sequentially comprises a visible layer, a first hidden unit layer and a second hidden unit layer from bottom to top. By the method, the problem of 'semantic gap' during image semantic annotation can be solved effectively, and annotation accuracy is increased.

The embodiment of the invention discloses a method, device and system for automatically labeling a target object in an image, and the method comprises the steps: obtaining an image training sample which comprises a plurality of images, each image is obtained through the shooting of the same target object, and the adjacent images have the same environmental feature points; Taking one image as a reference image, determining a reference coordinate system, and creating a three-dimensional space model based on the reference three-dimensional coordinate system; When the three-dimensional space modelis moved to the position where a target object is located in the reference image, determining position information of the target object in the reference three-dimensional coordinate system; And respectively mapping the three-dimensional space model to the image plane of each image according to the respective corresponding camera attitude information determined by the environmental feature pointsin each image. According to the embodiment of the invention, automatic image labeling can be carried out more accurately and effectively, and the universality of the method is improved.

The present invention relates to an image automatic marking method based on Monte Carlo data balance. The method comprises the steps of carrying out the region segmentation on the training sample images in a public image library, enabling the segmented regions possessing different characteristic description to correspond to one marking word, then carrying out the Monte Carlo data balance on the different types of image sets, extracting the multiscale characteristics of the balanced images, and finally inputting the extracted characteristic vectors in a robustness least squares increment limit learning machine to carry out the classification training to obtain a classification model in the image automatic marking; for the to-be-marked images, carrying out the region segmentation on the to-be-marked images, adopting the same multiscale characteristic fusion extraction method and inputting the extracted characteristic vectors in the least squares increment limit learning machine to obtain a final image marking result. Compared with a conventional image automatic marking method, the method of the present invention enables the images to be marked more effectively, is strong in timeliness, can be used for the automatic marking of the large-scale images, and possesses the actual application meaning.

The invention relates to an automatic image annotation method integrating depth features and semantic neighborhood. In view of the problem that manual selection of features takes time and energy in the traditional image annotation method, the problem that the traditional label propagation algorithm ignores semantic neighborhood, which results in visual similarity and semantic dissimilarity and affects the annotation result, and the like, the invention puts forward an automatic image annotation method integrating depth features and semantic neighbors. First, a unified and adaptive depth feature extraction framework based on a depth convolutional neural network (CNN) is built; then, a training set is grouped semantically, and a neighborhood image set of an image to be annotated is built; and finally, the contribution value of each label of the neighborhood images is calculated according to the visual distance, and the contribution values are sorted to get annotation keywords. The method is simple and flexible, and is of strong practicability.

The invention discloses an automatic image annotation algorithm which includes the steps: (1) extracting features of images in a data set to acquire bottom information of the images; (2) selecting an image training set: training the automatic image annotation algorithm by selecting the most authoritative and the most standard data set with various features and the most abundant image resources, and selecting n data from the data set as training samples; (3) training the image annotation algorithm: selecting features of the obtained samples and optimizing annotation results by bound terms; (4) automatically annotating the images: processing forecast tags by selecting threshold values. Parts of the samples are annotated, and the rest samples are not annotated. The image annotation algorithm based on sparse structure feature selection can be used for automatically annotating the images and is innovative.

A digital camera that automatically corrects dust artifact regions within acquired images by compiling a statistical dust map from multiple images acquired under different image acquisition conditions includes an optical system for acquiring an image including a lens assembly and an aperture stop. An electronic sensor array is disposed approximately at an image focal plane of the optical system for collecting image data according to spectral information associated with multiple pixels that collectively correspond to the image. Digital processing electronics include a processor for converting the image data to digital data and processing the digital data according to programming instructions. A memory has programming instructions stored therein for performing a method of automatic image correction of dust defect regions.

The invention discloses a network news acquisition and text sentiment prediction system. A news text crawled by a network is taken as a training set, a text classification algorithm is used for establishing a training model, a news text to be predicted is classified according to the training model, automatic sentiment annotation is carried out, an influence, which may be caused for public emotions, of a network news text to be published is predicted, the text sentiment prediction system capable of predicting the influence of social news on public sentiment is constructed, a public opinion which may be caused by news is predicted, and convenience is provided for network security.

The present invention provides a power fault diagnosis and early warning system based on the infrared spectrum technology. The system comprises an identification module, an analysis module and a diagnosis display module that are sequentially connected. The identification module comprises an image collection client and a processing circuit connected with the image collection client; the analysis module comprises an image intelligent analysis unit and a communication unit connected with the image intelligent analysis unit; and the diagnostic display module comprises an early warning unit and a display unit. The processing circuit is connected with the image intelligent analysis unit; the communication unit is connected with the diagnostic display module; and the image collection client collects infrared data, the infrared data is combined with equipment information collected in a visible light manner, and after being subjected to processing, the combined infrared data and equipment information is transmitted to the analysis module to form an equipment image automatic annotation model. According to the system provided by the present invention, by identifying the infrared spectrum of the power equipment, identification and annotation are carried out on the equipment, a bidirectional equipment type annotation model is established, and fault diagnosis of the power equipment is implemented.

The embodiment of the invention provides a method for training an image semantic annotation device, and the method comprises the steps: a, providing a plurality of training images, wherein the semantic and visual attribute description of each training image is known; b, enabling at least a part of the training images to be inputted to a positioner of the image semantic annotation device; c, enabling the positioner to determine at least one local area of each inputted training image, and inputting the determined local regions into an attribute predictor of the image semantic annotation device; d, obtaining the visual attribute prediction result of each inputted local region through the attribute predictor; e, training the positioner and the attribute predictor according to an obtained visual attribute prediction result of each local region and the known visual attribute description of the corresponding training images.

The invention discloses an automatic image annotation and translation method based on decision tree learning. A new image is automatically annotated, and a text word list with a visualized content is translated by a machine so as to realize the machine retrieval of image data, comprising a training annotation image set and image automatic annotations, wherein the training annotation image set utilizes an image segmentation algorithm to segment a training image set into sub areas and extract low-level visual features of each sub area; the feature data is discretized, and then the training annotation image set is classified by a clustering algorithm based on a low-level feature discrete value to construct a semantic dictionary; the low-level feature discrete value is used as an input attribute of the decision tree learning; and self training learning is carried out on the constructed dictionary by a decision tree machine learning corresponding to preset semantic concepts so as to generate a decision tree and obtain a corresponding decision rule. The training annotation image set has expandability and robustness and can improve the recall ratio and the precision ratio of the retrieval when the training annotation image set is applied to semantic image retrievals.

The invention provides a random walking image automatic annotation method and device based on a label graph model. The method comprises the following steps: providing an annotated image set and an image to be annotated; acquiring an adjacent image set related to the image to be annotated; acquiring a candidate label set; constructing a co-occurrence matrix; acquiring a typical vector; constructing a tendency matrix for the candidate label set according to the typical vector; fusing the co-occurrence matrix and the tendency matrix, so as to obtain a relation matrix; constructing a label graph model; and carrying out random walking on the label graph model, so as to obtain a weight vector of a node; and determining the label of the image to be annotated according to the corresponding weightvalue of each node in the weight vector. The method can be used for effectively annotating the images according to the co-occurrence relation and tendency relation between the labels; and the method has the advantage of accuracy in annotation; the image automatic annotation device has the advantages of being simple in structure and being easy to realize.

A first image having annotations is segmented into one or more image regions. Image feature vectors and text feature vectors are extracted from all the image regions to obtain an image feature matrix and a text feature matrix. The image feature matrix and the text feature matrix are projected into a sub-space to obtain the projected image feature matrix and the text feature matrix. The projected image feature matrix and the text feature matrix are stored. First links between the image regions, second links between the first image and the image regions, third links between the first image and the annotations, and fourth links between the annotations are established. Weights of all the links are calculated. A graph showing a triangular relationship between the first image, image regions, and annotations is obtained based on all the links and the weights of the links.

The invention discloses an image automatic annotation method based on digraph unequal probability random search, which comprises the following steps: inputting an image to be annotated and an annotated image set; extracting a plurality of feature vectors of the image to be annotated; selecting an adjacent image set; constructing a digraph model of the image to be annotated; calculating a word similarity matrix Se between tags and a symbiotic relationship matrix Co between tags; fusing the word similarity matrix Se between tags and the symbiotic relationship matrix Co between tags, so as to obtain a tag similarity matrix TT; and carrying out unequal probability random search on each candidate tag in a candidate tag set in the digraph model, so as to calculate the score, and obtaining a plurality of high-score candidate tags to be used as the label results. The invention also discloses an image automatic annotation device based on digraph unequal probability random search. In the invention, the dependency relation between images and similarity relation between tags are utilized fully and reasonably, thus the image automatic annotation can be effectively carried out, and the annotation effect is better.

A method and system for automatically generating names for files uploaded from a computer to a server is disclosed. Aspects of the present invention include allowing a user to define a file-naming template using information available from a variety of sources including, the uploaded files, an application environment of the server, and an operating environment of the computer. Names are then automatically generated for each file when files are uploaded based on the template pattern.

A method of automatically categorizing an input image comprises extracting texture features of the input image and generating a signature vector based on extracted texture features. The generated signature vector is processed using at least one classifier to classify the input image.

The invention belongs to the sub-field of the learning theory and application in the technical field of computer application, and relates to a CCA and 2PKNN based automatic image annotation method, in order to solve problems of a semantic gap, a weak annotation, and category imbalance that exist in an automatic image annotation task. The method comprises: firstly, for a semantic gap problem, mapping two features to a CCA sub-space, and solving a distance between the two features in the sub-space; for a weak annotation problem, establishing a semantic space for each annotation; for a category imbalance problem, by combining a KNN algorithm, finding out k nearest neighbors of a test image in the semantic space of each annotation, constituting the k nearest neighbors to an image sub-set, and by using a visual distance between the sub-set and the test image, and by combining a Bayesian formula, assigning a few annotations with the highest score to the test image; and finally, optimizing an image annotation result by using correlation between annotations. The method disclosed by the present invention has a greater degree of improvement for image annotation performance.

The invention discloses an image automatic marking method and a device based on depth learning, the method comprises the following steps: extracting visual features of an image to be marked by using depth learning technology; constructing the candidate tag set of the image to be annotated by using the image library, and extracting the semantic features of the image to be annotated from the candidate tag set of the image to be annotated by using the depth learning technology, fusing visual features and semantic features of the image to be annotated to obtain high-level features of the image tobe annotated; according to the high-level features of the images to be annotated, calculating the probabilities of each label in the image library by depth learning technique, according to the high-level features of the image to be annotated, predicting the number of tags needed for the image to be annotated by using depth learning technology. According to the calculated label probability and thepredicted label number, the first N labels with the highest probability are used to label the label image to be labeled. The invention can establish the relationship between the low-level feature andthe high-level semantic tag, thereby improving the accuracy of the image labeling.