41 results about "Visual modality" patented technology

The invention discloses an image annotation method and system based on a weak matching probability canonical correlation model, relating to the technical field of processing of network cross-media information. The image annotation method comprises the following steps: obtaining an annotated image and a non-annotated image in an image database, respectively extracting image features and textual features of the annotated image and the non-annotated image, and generating a matched sample set and an unmatched sample set, wherein the matched sample set contains an annotated image feature set and an annotated textual feature set; and the unmatched sample set contains a non-annotated image feature set and a non-annotated textual feature set; training the weak matching probability canonical correlation model according to the matched sample set and the unmatched sample set; and annotating an image to be annotated through the weak matching probability canonical correlation model. According to the invention, correlation between a visual modality and a textual modality is learned by using the annotated image, keywords of the annotated image and the non-annotated image simultaneously; and an unknown image can be accurately annotated.

Systems and methods enforce an expiration date for an electronic document and represent the expiration visually. In various exemplary embodiments, the author specifies an expiration date for an electronic document. The expiration date is either a date stamp or is an integer representing a period of time from the creation date. In one embodiment, the access to the document is unavailable to a user after the expiration date. In various exemplary documents, the visual representation of the document ages after a milestone date is reached. In one embodiment, random pixels are added to the visual representation until the document expires. In another embodiment, an algorithm applies visual metaphor bitmaps to the document's visual representation. In one embodiment, the bitmaps are templates. In one embodiment, the document is mapped to the applied bitmaps. The document may be rendered illegible after the expiration date is reached.

The invention provides a multi-modality vocabulary representing method. The multi-modality vocabulary representing method comprises the steps of calculating a text representing vector of a vocabulary to be represented in text modality and a picture representing vector of the vocabulary to be represented in visual modality; inputting the text representing vector into a pre-established text modality weight model to obtain the weight of the text representing vector in the text modality; inputting the picture representing vector into a pre-established visual modality weight model to obtain the weight of the picture representing vector in picture modality; conducting calculation to obtain a multi-modality vocabulary representing vector according to the text representing vector, the picture representing vector and weights corresponding to the text representing vector and the picture representing vector respectively. The text modality weight model is a neural network model of which input is the text representing vector and output is the weight of the text representing vector in the corresponding text modality; the visual modality weight model is a neural network model of which input is the picture representing vector and output is the weight of the picture representing vector in the corresponding visual modality.

A system, method and computer program produce for handling and minimizing miscommunication and transformation of tokens that are processed by humans, either verbally or in writing, during some part of a usage scenario. This is accomplished by filtering out confusing tokens, as determined by calculating a distance metric for each token. A distance metric may be calculated along a print modality, a visual modality or a verbal modality.

The invention discloses a personalized auricle data model building method based on normal auricle morphological classification. Classification indexes for describing a precise auricle structure and building indexes of the personalized data model for describing a basic auricle shape are included. On one hand, data measuring is carried out on auricle indexes, the position of a crus of helix serves as a boundary for partitioned clustering analysis to obtain the auricle data model; on the other hand, according to personalized index data, the personalized auricle data model is further obtained on the basis of the data model obtained through normal auricle classification. Compared with traditional auricle visual modality description and classification, the data model in the method is obtained after clustering analysis of quantitative auricle morphological indexes, so that classification is more accurate, standard and objective, and real auricle information can be reflected better. The personalized auricle data model built due to the fact that personalized index values are introduced into the auricle data model has significant meaning in manufacturing personalized ear cartilage supports and further reconstructing personalized auricles.

The method comprises storing a set of images captured of the anterior chamber of various eyes, and using a processor for: a) processing some of said stored images by implementing an homogenization process that adjusts an horizontal and a vertical spatial resolution of each image of the set to be the same, and a centering and aligning process that computes statistical properties of the images, and uses said computed statistical properties to compute a centroid and a covariance matrix of each image; b) performing pair-wise distance measures between images of said processed images providing a pair-wise distance matrix; c) analyzing said pair-wise distance matrix by executing a nonlinear dimensionality reduction algorithm that assigns a point in an n-dimensional space associated to each analyzed image; and d) outputting the results of said analysis in a visual way enabling being usable to detect if said eyes suffer from glaucoma.

The invention discloses a projection interaction method based on pure machine vision positioning, and the method comprises the following steps: S1, carrying out the graying of a source image collectedby a vision sensor, and positioning the boundary and four vertexes of a projection region in the image; S2, establishing a coordinate mapping relationship from a source image coordinate system to a projection scene coordinate system, and solving a coordinate transformation matrix H; S3, detecting a contact position of an interactive carrier in the source image on a projection plane based on a target detection algorithm in deep learning; S4, mapping the contact to a projection scene coordinate system through the coordinate transformation relationship established in the step S2 to complete human-computer interaction. Aiming at the defect that a current projection interaction scheme based on infrared positioning depends on infrared equipment, a projection plane is positioned by adopting a method based on straight line detection, contact detection is realized by adopting a pure vision mode for positioning, interaction carrier coordinates are mapped into a projection scene coordinate system through a coordinate mapping relationship, and accurate interaction is realized.

A dispensing and storage vessel for use in housing a gas such as toxic and hazardous gas in combination with a temperature sensitive label is described. Example dispensing and storage vessels includean adsorbent and a reagent gas within an internal volume of the vessel. A thermochromic label is adhered to the vessel and communicates temperature-sensitive information in a visual fashion to a user.

The method for creating or using or re-using one or more visual communication unit(s) to visually portray and convey information to be communicated, visually. This visual communication can be in lieu of or in conjunction with other written, and/or spoken, and/or machine language, voice/audible media, and/or any other communication methods. This is done by creating or using one or more visual element(s), picture(s), geometric object(s), painting(s), drawing(s), video(s), movie(s), clip(s), art(s), animation(s), (please note, these are not an exhaustive list of elements), or re-using already made or existing visual communication unit(s), or a combination of, for visually portraying and conveying the information to be communicated, visually. Then communicating the visual communication unit(s) conveying the information visually, through the communication channel(s), tool(s), format(s), and medium(s) of choice.

Visually registering a camera using an optical code and a picture file, including: receiving the picture file and the optical code from the camera, where the optical code includes a public key of the camera; generating a visual challenge using the random number created by the random number generator; transmitting the visual challenge to a user of the camera to capture the visual challenge; receiving the captured visual challenge from the camera; extracting a response from the captured visual challenge; comparing the response to a random number to verify a signature of the captured visual challenge using a public key of the camera and convert an optical code received from the camera into a valid certificate; and registering the camera and adding the valid certificate to the key store.