151 results about "Web image" patented technology

A system and method for creating and serving image-based contextual advertising through programmatically composed image collages, including the procurement, indexing and matching of query images, the procurement, indexing and matching of web images and the transferring of indexed and matched data from those web images to the query images, the procurement, indexing and matching of product images to be used as collage ad components, the matching and selection of one or more decorative template elements and one or more structural templates, the programmatic combining of the product images and the templates and template elements into a collage and the distribution of this collage for display to a user as a collage ad, based at least in part on the visual data extracted and indexed from the query image.

Systems and methods to present web image search results for effective image browsing are described. In one aspect, task-based attention objects for each of multiple images associated with image search results are generated. Thumbnail images from respective ones of the images are created as a function of at least the task-based attention objects. The thumbnail images emphasize image region(s) of greater priority to a user in view of a keyword or expanded keyword associated with the search results.

Disclosed is a method for displaying sections of large images such as maps. A grid is placed over an image database that references the various files contained in the database. When an area is identified for a query, the cells of the grid refer only to those files to be searched that pertain directly to the query. Further, the grid reference system also allows panning and zooming of the image to be dynamic and virtually instantaneous without limitation to the bandwidth of an Internet connection.

A pure web browser based medical imaging system that requires no installation of application software or any browser plug-in and functions in the same way as traditional full blown medical imaging PACS (Picture Archiving and Communication Systems) viewer fat clients. In addition, the system intelligently distributes the computing tasks of image rendering between browser and servers from complete server-side rendering to complete client-side rendering and anything between. It comprises a JavaScript medical image rendering library that can process original DICOM (Digital Imaging and Communications in Medicine) data sets and all standard web images at pixel level, a medical imaging server and a rendering load balancing component that can dynamically split the rendering computing from server to client according to their capabilities.

A methodology for displaying a website on a hand held display device (HHDD) is disclosed. The present invention comprises an Image Modification Program (IMP) and a Navigation Program (NP). The IMP analyzes the webpage HTML to determine if an image is present and if the image exceeds the allotted image display space on the HHDD display screen. The IMP calculates the required number of x-axis and y-axis divisions and fragments the image accordingly. The IMP displays the reduced web page on the HHDD, but replaces the reduced image with a fragment from the fragmented image. The fragment is displayed at the intended resolution allowing the user to view a portion of the image at full size, as opposed to the whole image at a reduced size. The NP of the present invention allows the user to move from one fragment to another. An alternative embodiment utilizing a proxy is also disclosed.

The invention provides a method for finding a landing page from a phishing web page. The method comprises the followings: firstly, keywords are extracted from web page text and web graphics, so as to form the lexical signature of the phishing web page, then searching for the lexical signature is performed on a plurality of search engines, the front K most relevant web pages are found out by synthesizing the results of those search engines, the K web pages and the phishing web pages are kept in a picture form, an image perception hash sequence is extracted, finally, the Hamming distances between the K web graphics and the phishing web graphics can be respectively calculated, and one or more lawful web pages simulated by the phishing web page can be selected according to the sizes of the distances.

An image segmentation system selects candidate images from an image collection. Image analysis on individual images proceeds by first detecting salient features on each image. Patches are centered on points of interest located on the salient features of the image. Each patch is gridded into blocks. The block feature vectors are merged to generate a patch feature vector. A fingerprint for each image is obtained by merging patch feature vectors across the image. Images with similar fingerprints are identified and geometric matching is performed to further select images with similar objects. Common regions are tabulated and merged into single regions to segment out coherent objects.

The invention discloses a latent semantic image retrieval method of region-oriented multi-feature integration and multi-level feedback. It uses result list returned by the initial keyword search, extracting a variety of region-oriented images characteristics, constructing attribute-image matrix, using latent semantic indexing algorithm to get the semantic space of image sets and semantic features of each image, and then using similar images by users feedback to construct or update image query vector, searching again the semantic space, calculating image semantics features and images inquiries vector similarity, getting outcome sets by descending order, and repeatable retrieval. The invention takes full advantage of image content information, making up for the deficiencies of the keyword search, and through the region-oriented multi-feature integration, enhances image content information from the bottom physical layer to the object layer, then further enhances to the semantic layer by HCI feedback, thereby reducing the gap between the image bottom features and high-level semantic, and allowing Web image retrieval to get higher retrieval accuracy.

The invention belongs to the technical field of image processing and particularly provides a semantic propagation and mixed multi-instance learning-based Web image retrieval method. Web image retrieval is performed by combining visual characteristics of images with text information. The method comprises the steps of representing the images as BoW models first, then clustering the images according to visual similarity and text similarity, and propagating semantic characteristics of the images into visual eigenvectors of the images through universal visual vocabularies in a text class; and in a related feedback stage, introducing a mixed multi-instance learning algorithm, thereby solving the small sample problem in an actual retrieval process. Compared with a conventional CBIR (Content Based Image Retrieval) frame, the retrieval method has the advantages that the semantic characteristics of the images are propagated to the visual characteristics by utilizing the text information of the internet images in a cross-modal mode, and semi-supervised learning is introduced in related feedback based on multi-instance learning to cope with the small sample problem, so that a semantic gap can be effectively reduced and the Web image retrieval performance can be improved.

The invention discloses a picture display method and device based on a website, wherein the method and device are used for solving the problem that because website focus pictures are all in the fixed state in the prior art, the presentation effect of the focus pictures is affected. The method includes the steps that a service request of a client is received; according to the resolution ratio used by the client currently, the current display width of a browsing window of the client is obtained; a corresponding webpage is acquired according to identification of the webpage, the width of the webpage is determined, and the sizes of the focus pictures in the webpage are determined; the ratio of the current display width of the browsing window to the width of the webpage is calculated; the sizes of the focus pictures are adjusted according to the ratio, and the webpage containing the adjusted focus pictures is sent to the client to be presented. According to the method, the sizes of the pictures of the webpage are adjusted according to the browsing window of the client and the resolution ratio used by the client currently, and thus the presentation effect of the focus pictures is guaranteed.

A webpage image loading method includes: acquiring the size of a to-be-loaded image file from a server; judging whether the size of the to-be-loaded image file is smaller than a preset threshold or not; if yes, through the server, loading the to-be-loaded image file, loading the to-be-loaded image file which is loaded and displaying the same in a webpage; if not, through the server, reading a local image file, loading the preset local image file and displaying the same in the webpage. In addition, the invention further provides a webpage image loading device. With the webpage image loading method and the webpage image loading device, loading speed of webpage images can be effectively increased, and network flow can be saved.

A webpage picture filter method includes the following steps of extracting corresponding picture characteristics from pictures on a webpage; judging whether the pictures are trash or not according to the characteristics of the pictures, and if so, deleting the trash pictures; and downloading the pictures which are not deleted from the webpage. In the webpage picture filter method and the system utilizing the same, whether the pictures are trash pictures is judged according to the characteristics of the pictures, if so, the trash pictures cannot be downloaded, and accordingly network bandwidth consumption is reduced effectively, no trash pictures appear in the wap page converted from the webpage, and noise in the webpage is effectively reduced.

The invention relates to a website picture tampering detection method based on deep learning. The method comprises the steps of collecting a sample picture with a text, establishing a training set after preprocessing, training a corresponding network model, further training a semantic similarity detection model and constructing a sensitive word bank, crawling and preprocessing a website picture tobe detected, obtaining a text content result in the website picture through the network model, calculating the semantic similarity between the text content result and the sensitive word bank throughthe semantic similarity detection model after word segmentation, and judging whether the sensitive content and the website picture are tampered based on the similarity. The text block recognition precision is improved; the method is accurate in text extraction, small in model, high in convergence speed and good in performance, semantic recognition is carried out on texts in pictures, sensitive speech in webpage pictures can be accurately detected, whether a website is invaded by hackers or not can be quickly and efficiently recognized, an alarm is given in time, the method plays an important role in maintaining website safety, and spreading of bad illegal information can be blocked in time.

The invention discloses a web image display method and device. The method comprises the steps that web image data in a current mobile terminal browser page are obtained, wherein the web image data comprise at least one web image sub file and web image associated information; when an image display touch command is received, a browser full screen display window is set up in a mobile terminal browser, wherein the browser full screen display window comprises an image display area and an associated information display area; at least one web image sub file is displayed in the image display area, and the web image associated information is displayed in the associated information display area. The browser full screen display window can be set up in the mobile terminal browser, display and editing of the web image data can be achieved on the application program side of a mobile terminal browser client side, a user can look up and edit web images in the browser full screen display window, and the intelligence of the mobile terminal browser for the user to look up and edit the web images is improved.

The present invention discloses a local web image updating method, device and system. The method comprises acquiring regional position data of a selected to-be-updated local image in a currently-displayed image on a screen of an equipment terminal; sending local image data acquisition request and the regional position data to a server, so as to allow the server to respond to the local image data acquisition request and acquire corresponding original local image data from original image data based on the regional position data; and updating the to-be-updated local image by using the received original local image data after the original local image data returned by the server is received. High-definition display can be carried out according to local regions selected by a user, thereby realizing local high-definition display of the image, avoiding wastes on data transmission quantity in an image display requesting process, reducing waiting time for image loading, and raising user experience.

The invention aims to provide a method and equipment for operating a webpage picture. Compared with the prior art, the invention has the advantages that: according to the scaling operation of a specific picture in a webpage, corresponding pictures with different sizes are acquired as required; by inserting the pictures in the webpage, the aims of separately scaling the pictures and clearly showing the locals of the pictures are fulfilled; and a user can perform the associated operation of scaling on the pictures to which the user pays attention while opening speed of the webpage is guaranteed, so that the using experience of the user is improved.

The invention discloses a kind of image processing method and device. The described method includes: web image editor based on the user's choice, to obtain the image selected by the user from the local computer, and present the selected image in the web image editor; process the selected image according to the user's operations; and upload the processed image to the server. The described device includes: access module, display module, processing module and uploading module. The invention directly reads the local image through the network image editor and edits the image and then uploads the confirmed image to the server which does not need to upload files to the server and download and may save network resources and server storage resources. At the same time, it can also ensure that the local computer will not be under virus attack during the process of reading the local image.

The present invention relates to a method for directly making web page picture be applied in instantaneous communication tool. The described instantaneous communication tool includes a picture application scenario program, and the described method includes the following steps: creating an option for making web page picture be used in the instantaneous communication tool; calling picture application scenario program, obtaining URL address information of picture in the web page and creating an OLE object; transfer-interpreting URL address information and obtaining a path for storing the web page picture into on-line computer Cache and file name and creating a main operation object, said main operation object can utilize interface, path and file name as parameters and can make the web page picture be directly used in instantaneous communication tool.

The invention discloses a horrible image identification method and system based on visual significance analyses. The method comprises the steps that a training set containing horrible image samples and non-horrible image samples is built; visual significance analyses are conducted on each training sample image through an image significance analysis algorithm to acquire a visual significance image of each training sample image; each training sample image is divided into small W*W image blocks, virtual and affective characteristics are conducted on each image block, and virtual word histogram representation of each training sample image is acquired through a packet representation model based on visual significance; a classification model of horrible images is acquired through an acquired virtual word histogram of each training sample image and a label training support vector machine corresponding to the acquired virtual word histogram, and new testing image is identified through the classification model to judge whether the new testing image is a horrible image or not. The horrible image identification method and system based on visual significance analyses can be applied to the fields like horrible web image filtration and affective and semantic image recognition, and has wide application prospects.

The invention relates to a distributed information hiding detection method facing mass web images, which comprises the following steps of: a, setting up a Hadoop operation environment on a cloud computing platform; b, generating a Nutch crawling queue; c, according to a MapReduce architecture of the Hadoop, carrying out distributed webpage crawling; d, analyzing a webpage and extracting images in the webpage; 3, storing the extracted web images by adopting Hbase; f, carrying out universal blind detection of the images; g, screening out images with a BMP (Bitmap) format and a JPEG (Joint Photographic Experts Group) format; h, detecting the images with the BMP format; and i, detecting the image with the JPEG format. The image hiding detection method disclosed by the invention adopts open source technologies such as Hadoop, Nutch and the like, is easy to design, develop and implement, has a good detection effect, is suitable for extraction of mass images and detection of hidden information in the current network environment and has important practical significance for finding out and tracking lawless people who utilize public channels to carry out covert communication and maintaining national information security.