Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

524 results about "Image description" patented technology

An image description is a textual, audio or graphical content portraying the image in a representation intelligible by the addressees. The description should be comprehensive as well as perceptible by the target audience.

System and method for efficiently building virtual appliances in a hosted environment

A system and method for efficiently building virtual appliances in a hosted environment is provided. In particular, a plurality of image archives may be stored in a build database, with each image archive including a file system having a directory structure and a plurality of files installed within the directory structure. In response to a build request containing an image description, a build engine may create a file system layout defining a directory structure for an image. The build engine may then copy the file system for one of the image archives to the file system layout for the image, wherein the copied file system may provide a subset of the file system for the image. The build engine may then build the image, which may include a file system having various files installed within various directories in accordance with the directory structure defined for the image.
Owner:SUSE LLC

Image intelligent mode recognition and searching method

The invention puts forward an image intelligent mode identification search method. The method can establish an image sample training set database and combine with basic text search engine technology and basic image content inquiry technology, so that a network creeper can perform Internet image search and URL information resolution, so as to catch the image URL and relevant information into a local primary database; perform such pre-processes as preliminary filtration, decompression and image pre-classification and etc for the images; then, calculate color characteristics, grain characteristics and shape characteristics of the extraction images, so as to gain corresponding characteristic vector sets; combine with the image URL information before saving the images into the image basic database and establishing an index for the images; perform characteristic vector similarity calculation for images in the image basic databases and sample training sets, and then, save the classified images into an image classification database; accept key words or image description that are input by the user, create the index vector, perform similarity calculation with the image characteristic vectors in the image classification database, and then, return the index results to the user.
Owner:SHANGHAI XINSHENG ELECTRONICS TECH

Digital composition of a mosaic image

A mosaic image resembling a target image is composed of images from a data base. The target image is divided into regions of a specified size and shape, and the individual images from the data base are compared to each region to find the best matching tile. The comparison is performed by calculating a figure of visual difference between each tile and each region. The data base of tile images is created from raw source images using digital image processing, whereby multiple instances of each individual raw source image are produced. The tile images are organized by subject matter, and tile matching is performed such that all required subject matters are represented in the final mosaic. The digital image processing involves the adjustment of colour, brightness and contrast of tile images, as well as cropping. An image description index locates each image in the final mosaic.
Owner:TAMIRAS PER PTE LTD LLC

System and method for efficiently building virtual appliances in a hosted environment

A system and method for efficiently building virtual appliances in a hosted environment is provided. In particular, a plurality of image archives may be stored in a build database, with each image archive including a file system having a directory structure and a plurality of files installed within the directory structure. In response to a build request containing an image description, a build engine may create a file system layout defining a directory structure for an image. The build engine may then copy the file system from one of the image archives to the file system layout of the image, wherein the copied file system may provide a subset of the file system for the image. The build engine may then build the image, which may include a file system having various files installed within various directories in accordance with the directory structure defined for the image.
Owner:SUSE LLC

Image description generation method based on depth LSTM network

The invention relates to an image description generation method based on a depth LSTM network, comprising the following steps: (1) extracting the CNN characteristics of an image in an image description dataset, and acquiring an embedded vector corresponding to the image and describing the words in a reference sentence; (2) building a double-layer LSTM network, and carrying out series modeling based on the double-layer LSTM network and a CNN network to generate a multimodal LSTM model; (3) training the multimodal LSTM model by means of joint training; (4) gradually increasing the number of layers of the LSTM network in the multimodal LSTM model, carrying out training each time one layer is added to the LSTM network, and finally, getting a gradual multi-objective optimization and multilayer probability fused image description model; and (5) fusing the probability scores output by the branches of the multilayer LSTM network in the gradual multi-objective optimization and multilayer probability fused image description model, and outputting the word corresponding to the maximum probability through common decision. Compared with the prior art, the method has such advantages as multiple layers, improved expression ability, effective updating, and high accuracy.
Owner:TONGJI UNIV

Gesture tracking method and gesture tracking system

ActiveCN102831439AGuaranteed uptimeReduce the amount of image processingInput/output for user-computer interactionCharacter and pattern recognitionVisibilityForecast verification
The invention provides a gesture tracking method. The gesture tracking method includes steps of designing gesture appearance models including image description modes for tracking prediction and prediction verification; acquiring initial states, positions and size information of targets by gesture detection; initializing a tracker for the targets according to the initial states by details of initializing the appearance models, namely initializing image description templates for tracking prediction and prediction verification, and initializing types, states and visibility of gestures; tracking; processing the states and the visibility of the targets according to information of the tracker so as to make a final estimate; and judging the visibility of the targets, starting the process of gesture detection again to acquire a tracking target if information is lost permanently, otherwise, continuing tracking the targets. The invention further provides a gesture tracking system. The gesture tracking method and the gesture tracking system have the advantages of simplicity, rapidness and stability.
Owner:SHENZHEN INST OF ADVANCED TECH

Generation method of image description from structured text

The invention discloses a generation method of an image description from a structured text. The generation method comprises the steps of downloading pictures from the internet to form a picture training set; conducting morphological analysis on descriptions which correspond to the pictures in the picture training set to form the structured text; using an existing neural network model to extract convolution neural network characteristics of the pictures in the training set, and using <, picture characteristics and structured text < as inputs to form a multitasking recognition model; using the structured text extracted from the training set and a description which corresponds to the structured text as inputs of a recurrent neural network, and conducting training to obtain a parameter of a recurrent neural network model; inputting the convolution neural network characteristics of an image ready to be described, and obtaining a predicted structured text through the multitasking recognition model; inputting the predicted structured text, and obtaining the image description through the recurrent neural network model. Compared with the prior art, a better image description effect, accuracy and sentence variety can be generated through the method, and the generation method of the image description from the structured text can be effectively popularized in an application of image retrieval.
Owner:哈尔滨米兜科技有限公司

Synthetic image and video generation from ground truth data

A system and a method are disclosed for generating video. Object information is received. A path of motion of the object relative to a reference point is generated. A series of images and ground for a reference frame are generated from the ground truth and the generated path. A system and a method are disclosed for generating an image. Object information is received. Image data and ground truth may be generated using position, the image description, the camera characteristics, and image distortion parameters. A positional relationship between the document and a reference point is determined. An image of the document and ground truth are generated from the object information and the positional relationship and in response to user specified environment of the document.
Owner:RICOH KK

Visual salience and semantic attribute based cross-modal image natural language description method

The invention belongs to the technical field of computer vision and natural language processing, and discloses a visual salience and semantic attribute based cross-modal image natural language description method. The method comprises the steps that multiscale deep visual features of all regions are extracted by adopting a convolutional neural network; by means of a pre-trained significance model,an image significance graph is returned, and an original image is weighted; a predefined dictionary is built to serve as a semantic attribute category, and semantic attribute detection is conducted ona visual significance image; semantic attributes are calculated through multi-instance learning; image features are weighted through the semantic attributes; visual-salience-based semantic attributefeatures are decoded through a long short-term memory network, and image description is generated. The method has the advantage of being high in accuracy and can be used for image retrieval under complex scenes, multi-objective image semantic understanding and the like.
Owner:XIDIAN UNIV

Multiple attention and multiple scale-based image describing method

The invention discloses a multiple attention and multiple scale-based image describing method. The method comprises the steps of selecting an image detecting model for extracting image features, dividing into a network training set, a verification set and a test set, extracting the image features, constructing an attention recurrent neural network model, training the attention recurrent neural network model and carrying out image description. According to the method disclosed by the invention, an image description generating network model formed by original image feature extracting, multi-attention multi-scale feature mapping, recurrent neural network residual connecting and recurrent neural network language decoding is constructed, so that the quality of the image description is improvedand the detail of the image description is enriched. By means of the method disclosed by the invention, a high quality image can be generated by adopting the neural network model to carry out description under the circumstance of only having an image.
Owner:SHAANXI NORMAL UNIV

Image description method and system based on vision and semantic attention combined strategy

The invention discloses an image description method and system based on a vision and semantic attention combined strategy. The steps include utilizing a convolutional neural network (CNN) to extract image features from an image whose image description is to be generated; utilizing a visual attention model of the image to process the image features, feeding the image features processed by the visual attention model to a first LSTM network to generate words, then utilizing a semantic attention model to process the generated words and predefined labels to obtain semantic information, then utilizing a second LSTM network to process semantics to obtain words generated by the semantic attention model, repeating the abovementioned steps, and finally performing series combination on all the obtained words to generate image description. The method provided by the invention not only utilizes a summary of the input image, but also enriches information in the aspects of vision and semantics, and enables a generated sentence to reflect content of the image more truly.
Owner:CHINA UNIV OF PETROLEUM (EAST CHINA)

Image description method based on convolution cyclic hybrid model

The present invention discloses an image description method based on a convolution cyclic hybrid model, and belongs to the deep learning field of machine learning. For text description, due to the fact that words in sentences have strong context relationships, text data can be encoded by using a language model. The image description method specifically comprises the steps of (1) extracting image characteristics; (2) encoding the image characteristics; (3) encoding image description texts; (4) training the model; and (5) generating image text description by utilization of the trained model. The image description method is widely used in machine vision and natural language processing, and new thought and solutions are provided in an image description method aspect. At present, in image description, text encoding is randomly generated, which has a certain blindness, and the effect is not good. The texts are encoded by utilization of word2Vec, the encoding problem of the description texts in image description is solved, and the defects of randomness, blindness and instability are remedied. Application ability of the image description is largely increased, and foundation is established for development of machine vision.
Owner:BEIJING UNIV OF TECH

Deep learning model-based image Chinese description method

The invention discloses a deep learning model-based image Chinese description method and belongs to the field of computer vision and natural language processing. The method comprises the steps of preparing an ImageNet image data set and an AI Challenger image Chinese description data set; pre-training the ImageNet image data set by utilizing a DCNN to obtain a pre-trained DCNN model; performing image feature extraction and image feature mapping on the AI Challenger image Chinese description data set, and transmitting image features to a GRU threshold recursive network recurrent neural network;performing word coding matrix construction on an AI Challenger image mark set in the AI Challenger image Chinese description data set; extracting word embedding features by utilizing an NNLM, and finishing text feature mapping; taking the GRU threshold recursive network recurrent neural network as a language generation model, and finishing image description model building; and generating a Chinese description statement. According to the method, the blank of image Chinese description is filled up; a function of automatically generating the image Chinese description is realized; the accuracy ofdescription contents is well improved; and a foundation is laid for development of Chinese NLP and computer vision.
Owner:HARBIN UNIV OF SCI & TECH

Image description generation method and device, model training method and device and storage media

The invention discloses an image description generation method and device, a model training method and device and storage media, and belongs to the technical field of machine learning. The image description generation method comprises that a target image is obtained; a first global characteristic vector and a first mark vector set of the target image are generated; the target image is input to a matching model, a first multi-mode characteristic vector of the target image is generated by the matching model; the matching model is obtained by training a training image and reference image description information of the training image; and description information of the target image is generated according to the first multi-mode characteristic vector, the first global characteristic vector andthe first mark vector set. The multi-mode characteristic vector of the target image is generated via the matching model which is obtained by training, and the multi-mode characteristic vector is theninput to a calculation model to obtain the description information of the target image, and thus, the generated image description information is more accurate.
Owner:SHENZHEN TENCENT COMP SYST CO LTD

An image description information generation method and device and an electronic device

The invention discloses an image description information generation method and device and an electronic device. The method comprises the steps of obtaining a to-be-processed target image; Inputting the target image into a target image description information generation network, wherein the target image description information generation network is a generation network which is obtained by performing adversarial training by utilizing a plurality of sample images and is used for generating image description information; wherein the adversarial training is alternating training based on an initialized image description information generation network matched with the target image description information generation network and an initialized judgment network, and the judgment network is used forjudging an output result of the image description information generation network; And generating an output result of the network according to the target image description information, and generatingtarget image description information for describing the target image. The image description information generation method and device solve the technical problem that an image description information generation method provided by related technologies is poor in generation quality.
Owner:TENCENT TECH (SHENZHEN) CO LTD

Image description generating method based on neural network and image attention focuses

The invention provides an image description generating method based on a neural network and image focuses. The method is characterized in that an original one-layer word embedding structure is replaced by a two-layer word embedding structure, and accordingly word expression can be learned effectively; image feature expression is directly used as the input of an m-RNN model, and accordingly the capacity of a circulating layer can be fully utilized, and the small-dimension circulating layer can be used; by a decision soft attention mechanism, the attention of an image salient region is reflected and used as one input of a multi-modal layer. By the method, the focus relation between targets or scenes is utilized effectively, and the semantic features of the image is described in a targeted manner.
Owner:SYSU CMU SHUNDE INT JOINT RES INST +1

Multi-angle and multi-mode fused image description generation method and system

The invention discloses a multi-angle and multi-mode fused image description generation method and system, and the method comprises the following steps: receiving a to-be-described image, extracting the global visual features and local visual features of the image, and carrying out the fusion of the global visual features and local visual features, and obtaining fused visual features; using a single-layer long-short-term memory network, the fused visual features serving as input, and obtaining a first sentence of image description; generating a first sentence semantic vector according to the first sentence image description; and generating a next image description sentence by adopting an attention-based long-term and short-term memory network language generation model and taking the localvisual features and the first sentence semantic vector as input, thereby obtaining complete image description. According to the method, two modes of visual features and text semantic features are fused, and an attention mechanism is combined, so that multi-angle comprehensive description of the image is realized.
Owner:QILU UNIV OF TECH

Image description method of bidirectional multi-mode recursive network

The invention provides an image description method of a bidirectional multi-mode recursive network. The image description method comprises the steps that downward images serve as a training set, and images in the training set and description sentences corresponding to the images are obtained; words emerging in the sentences in the training set are extracted, and a vocabulary is established; a pre-trained convolutional neural network is utilized to extract characteristics in the images in the data set; a bidirectional multi-mode recursive model is established, and the extracted image characteristics are fused with corresponding text characteristics; the bidirectional multi-mode recursive model is trained; a picture is input into the pre-trained model to obtain a corresponding description sentence.
Owner:南通斑马智能科技有限公司

Method and system for strengthening navigation performance based on image capture and recognition technology

The invention discloses a method and a system for strengthening navigation performance based on an image capture and recognition technology. The method comprises following steps: A. inputting destination information, and obtaining user location information and route information; B. realtime capturing images in real scenes through image capture equipment and displaying the images; C. identifying the characteristics of the obtained images, obtaining parameters of image description, and checking and matching in a preset database by utilizing the parameters; D. after successful matching, obtaining the coordinate information of the captured images in the virtual map stored in the database, obtaining the specific route between the user and the capture images according to the coordinate information of the capture images and the user location information, converting the specific route into guiding information and displaying in the real scene image; E. repeating B. C. D. steps in circulation, until the navigation is finished. The invention changes conventional navigation mode of traditional navigation systems and users can precisely choose the direction and route according to the navigation guiding identification.
Owner:佛山电视台南海分台

An image description generation system and method based on a weighing attention mechanism

The invention relates to the field of image understanding, discloses an image description generation system and method based on a weighing attention mechanism, and solves the problems that an existingimage description scheme lacks a polishing process, the training process and the testing process are inconsistent, and the generation description recognition degree is not high. The method comprisesthe following steps: a, processing a data set: extracting global features and local features of an image, constructing the data set, marking words in the data set, and generating corresponding word embedding vectors; B, training an image description generation model: generating rough image description by adopting a first layer of decoder based on a residual attention mechanism, and carrying out polishing on the generated image description by adopting a second layer of decoder based on the residual attention mechanism; And c, further training the model in combination with reinforcement learning: simulating a test process of the model in the training process, guiding the training of the model by generating a described CIDEr score, and adjusting the model in combination with reinforcement learning.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Retrieval system based on multi-lesion region characteristic and oriented to medical image database

The invention discloses a retrieval system based on a multi-lesion region characteristic and oriented to a medical image database. In the invention, the image is omni-directionally described by advanced image description symbols, including image region contents, pathological representation and anatomical position information, thus realizing the quick positioning and matching method on a plurality of lesion regions; by adopting the method of combining the semantic navigation and high-dimension data index, the quick retrieval of large-scale image characteristic value can be realized, the retrieval efficiency is improved, and the 'semantic gap' phenomenon existing in the traditional image retrieval technology is relieved to certain degree. The retrieval system sufficiently utilizes the historical image and diagnosis data in a PACS (picture archiving and communication system) database, can be used as an effective measure for computer aided diagnosis, and can be widely applied to the fields such as medical clinics, researches and teaching.
Owner:SHANGHAI INST OF TECHNICAL PHYSICS - CHINESE ACAD OF SCI

Method for encoding depth image of three-dimensional television system

The invention discloses a method for encoding a range image in a stereo-television system. The method comprises the following steps: 1) the edge strength value of each pixel in the range image is calculated, and then the edge strength value of each macroblock is calculated based on the edge strength value of the pixel point; 2) all the macroblocks in the range image are divided into three types, i.e., strong edge macroblocks, medium edge macroblocks and weak edge macroblocks; 3) the lower quantification parameter is configured for the strong edge macroblocks, the medium quantification parameter is configured for the middling edge macroblocks and the higher quantification parameter is configured for the weak edge macroblocks; and 4) the range image is encoded by utilizing the video coding technique based on the quantification parameter configured for all the macroblocks in the range image. The lower quantification parameter is configured for the strong edge macroblocks, so that the edge information of the range image is effectively protected and the quality of the free viewport image description of the client is improved.
Owner:ZHEJIANG UNIV

RNN-based automatic picture description generation method

The invention discloses an RNN-based automatic picture description generation method. A deep web which is well trained in advance is firstly used for image feature extraction; non-noun and non-verb components are removed for words in the sentence; an LSTM network is finally used for joint training on the image features and lexical features; during the sentence generation process, a sentence formed by nouns and verbs is generated through the inputted image and the well-trained LSTM network; and then, through large corpus on the network, the final outputted sentence is generated. Automatic recognition can be realized, a digital image uploaded by the user is understood, and a natural sentence understood by a human being is generated.
Owner:SOUTH CHINA UNIV OF TECH

Personal navigation device and related method of adding tags to photos according to content of the photos and geographical information of where photos were taken

A method of automatically adding tags to photos based on content of the photos and geographical information about where the photo was taken includes taking a photo with a camera of a personal navigation device, generating a geographical tag for the photo with the personal navigation device and attaching the geographical tag to the photo to generate a geotagged photo, transferring the geotagged photo to an optical character recognition (OCR) server, performing OCR on the geotagged photo with the OCR server and generating image description tags from text recognized in the geotagged photo, attaching selected tags to the geotagged photo, the selected tags being selected from the generated image description tags, and uploading the geotagged photo along with the attached selected tags to a photo sharing server, photos on the server being searchable by geographical tags or selected tags associated with the photos.
Owner:MITAC INT CORP

Picture description generation method and system based on Actor-Critic generative adversarial network

The invention discloses a picture description generation method and system based on an Actor-Critic generative adversarial network, and the method comprises the following steps: (1) obtaining a picture described by a known text, carrying out the preprocessing, and constructing a training set, (2) establishing a target network based on a generative adversarial network and an Actor-Critic algorithm,wherein the target network comprises a generator network, a discriminator network and a Critic network, (3) inputting the pictures in the training set and the text description of the pictures into the target network, performing pre-training and adversarial training on the generator and the discriminator, and performing single-step updating on the parameters of the generator by adopting an Actor-Critic algorithm, and (4) inputting the target picture needing to generate the text description into the trained generator to obtain the text description of the target picture. According to the method,based on the Actor-Critic algorithm, an adversarial network technology is adopted, and diversified text description can be generated on a given image.
Owner:ZHEJIANG UNIV

Personnel behavior identification implementation system and method based on image segmentation and semantic extraction

The invention relates to a personnel behavior identification and detection implementation system and method based on image segmentation and semantic characteristic extraction. The system comprises an image acquisition unit, a personnel behavior detection host computer, a user inquiry unit and an output interface unit. The method comprises the following steps: the personnel behavior detection host computer identifies personnel behaviors in the image data acquired by the image acquisition unit through image segmentation and image semantic characteristic extraction so as to generate personnel behavior presentation information. In the method, the personnel behavior detection host computer maps low-level features of an image into high-level semantics through a support vector machine so as to establish a mapping relation between the image and the image description, so that the content in the picture can be comprehended through digital image processing and analysis, the behaviors of personnel in the scene can be intelligently detected, and the identification accuracy of personnel behaviors in the image can be greatly improved. The system provided by the invention has a simple structure, and the method provided by the invention is simple and convenient to implement, low in application cost and wider in application range.
Owner:THE THIRD RES INST OF MIN OF PUBLIC SECURITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products