Peking University

Founder Apabi Technology Limited

Nuctech Company Limited

Beijing Founder Apabi Technology Limited

Tsinghua University

Founder Information Industry Holdings Co., Ltd.

Zhi Tang

Jianbo Xu

Li Ni Zhang

Qingping Huang

Yunda Sun

Zhiqiang Chen

Yang Wang

Xiaoqing Lv

Shuo Wang

Xin Tao

Canhui Xu

Lei Lei

Yi Wang

Xin Jin

Li Zhang

Jing Zhou

Mao Ye

Lifeng Jin

Wei Wan

Cao Shi

Hu Tang

Le Shen

Qianlu Ren

Xuefeng Yang

Yuanlong Wang

Cheng Qu

Yinyan Yu

Xiaoyu Cui

Dengsha Yuan

Qin Qiu

Changqiao Wang

Aixia Jia

Disclosed is a method for positioning a target in a three-dimensional CT image and a CT system for security inspection. The method includes: displaying a three-dimensional CT image; receiving a selection by a user of at least one area of the three-dimensional CT image at a viewing angle; generating at least one set of three-dimensional objects in a depth direction based on the selection; and determining a target object from the set. With the above technical solutions, the user may be facilitated in marking a suspected object in a CT image in a quick manner.

Methods for positioning a target in a three-dimensional CT image and CT systems for security inspection

A method and system for key knowledge point recommendation are provided, the method comprising calculating knowledge point relationship strengths of knowledge points in a set of knowledge points; calculating weights for knowledge points according to the knowledge point relationship strengths of knowledge points in the set of knowledge points, and storing the knowledge points and weights correspondingly; determining key knowledge points according to the weights of the knowledge points and recommending the key knowledge points to a user. With this solution, knowledge point relationship strengths are obtained through calculating knowledge point relationship strengths of knowledge points in a set of knowledge points; and recommendation is given to the user for learning knowledge according to knowledge point relationship strengths, so as to help the user to learn key knowledge points selectively in a more objective and effective manner, and avoid problems of information recommendation based on fuzzy logical information recommendation technology.

Method and system for key knowledge point recommendation

The present invention provides a semantic information acquisition method and system, and corresponding keyword expansion and search methods and systems, comprising: searching for, then classifying an article; then, performing word segmentation according to the classified article to obtain the words in said category, and setting said category and words to serve as the semantic information of the keyword; also, a method and system using the semantic information acquisition method to expand a keyword, and a method and system using keyword expansion to perform a search. The described semantic information acquisition method effectively avoids the technical problems in the prior art of only being able to obtain semantic information of English vocabulary; and it also being impossible to classify semantic information based on category information. The invention is particularly suitable for searching using a keyword, searching a large number of texts, and organizing large amounts of related data and information.

Method and system of acquiring semantic information, keyword expansion and keyword search thereof

A method and system for obtaining a knowledge point implicit relationship are provided; first, establishing a knowledge point explicit relationship map according to knowledge point explicit relationship strengths; second, computing according to said knowledge point explicit relationship map a simple path set of two knowledge points; then, computing the implicit relationship strength values corresponding to each simple path in said simple path set; further, comparing the relationship strength values of the simple paths and setting as the significant implicit relationship strength value the simple path relationship strength having the largest value also greater than a preset threshold value. The described solution effectively avoids the problems of only using the relationship strengths between knowledge points and the ratio of relationship strengths to obtain the implicit relationship of knowledge points, the manner of searching for an implicit relationship being insufficiently accurate, and not performing normalization processing on the relationship strengths.

Method and system for obtaining knowledge point implicit relationship

A method for positioning a target in a three-dimensional CT image and a security check system. The method includes: displaying a three-dimensional CT image; receiving a selection by a user of at least one area of the three-dimensional CT image at a first viewing angle to generate a first three-dimensional description; receiving a selection by the user of at least one area of the three-dimensional CT image at a second viewing angle to generate a second three-dimensional description, wherein an angle between the first viewing angle and the second viewing angle is within a predetermined range and the first three-dimensional description and the second three-dimensional description are related to a size, a location, and/or a physical property of a target at corresponding viewing angles; and determining the target in the three-dimensional CT image based on the first three-dimensional description and the second three-dimensional description.

Method for positioning target in three-dimensional CT image and security check system

The present disclosure discloses an image display method in a CT system. The method comprises: implementing CT scanning on an inspected object, to obtain CT projection data; organizing the CT projection data according to a predetermined interval; extracting basic data from the organized CT projection data by using a fixed angle as a start angle and using 360 degrees as an interval; forming a DR image based on the extracted basic data; reconstructing a three-dimensional image of the inspected object from the CT projection data; and displaying the DR image and the reconstructed three-dimensional image on a screen at the same time. In the solution, the CT data is processed to obtain DR data. After the DR data is obtained, a DR image is obtained directly using a DR data processing algorithm. This enables an image recognizer to more accurately and more rapidly inspect goods carried by a passenger using the existing experience in image recognition of the DR image.

Image display methods

A CT system for security check and a method thereof are provided. The method includes: reading inspection data of an inspected object; inserting at least one three-dimensional (3D) Fictional Threat Image (FTI) into a 3D inspection image of the inspected object, which is obtained from the inspection data; receiving a selection of at least one region in the 3D inspection image including the 3D FTI or at least one region in a two-dimensional (2D) inspection image including a 2D FTI corresponding to the 3D FTI, wherein the 2D inspection image is obtained from the 3D inspection image or is obtained from the inspection data; and providing a feedback of the 3D inspection image including at least one 3D FTI in response to the selection. With the above solution, it is convenient for a user to rapidly mark a suspected object in the CT image, and provides a feedback of whether a FTI is included.

CT system for security check and method thereof

A logic process apparatus for composite graphs in a fixed layout document is provided in this invention. The apparatus includes a composite graph block extraction unit, for extracting composite graph blocks from the fixed layout document, a document parsing unit, for parsing the fixed layout document to obtain text primitives contained therein, a legend primitive extraction unit, for extracting legend primitives from the text primitives, a correlation detection unit, for detecting correlations between the composite graph blocks and the legend primitives, and a correlation storage unit, for storing the detected correlations. A logic process method for composite graphs in a fixed layout document is also provided.

Logic processing apparatus and logic processing method for composite graphs in fixed layout document

The present invention provides an apparatus for logically processing a composite graph in a formatted document, the apparatus comprising: a composite graph block extraction unit, used to extract a composite graph block in the formatted document; a document parsing unit, used to parse the formatted document to obtain a text element contained therein; a cutline element extraction unit, used to extract a cutline element from the text element; a correlativity detection unit, used to detect correlativity between the composite graph block and the cutline element; a correlativity storage unit, used to store the detected correlativity. The present invention also provides a method for logically processing a composite graph in a formatted document. According to the technical scheme disclosed in the present invention, it is easily achieve layout understanding of the composite graph in a graph-text mixed layout of the formatted document, so as to avoid a logical error.

Apparatus and a method for logically processing a composite graph in a formatted document

The present invention discloses recognizing methods of flaky or blocky prohibited articles, explosives or drugs. Specifically, the method for recognizing flaky prohibited articles, explosives or drugs comprises steps of: (1) reading in tomogram data of an object to be inspected for one tomogram; (2) pre-processing the tomogram data; (3) splitting the pre-processed tomogram data into a plurality of regions that have similar physical properties; (4) analyzing whether each of the split regions is a flaky region; (5) determining whether the flaky region recognized in the current tomogram can be merged with the flaky region detected from the previous tomogram, so as to form a flaky target; (6) determining whether each detected flaky target is complete or finished; (7) repeating steps (1)-(6) and processing each tomogram data layer by layer, until all of the tomogram data have been processed.

Recognizing method of flaky or blocky prohibited articles, explosives or drugs

An apparatus for preventing replay attacks and a method for preventing replay attacks are provided in this invention, wherein the apparatus for preventing replay attacks comprises: an acquisition unit for, when a request for operating a digital content is received, acquiring current location information of a set of placeholder files; a determination unit for determining whether the current location information is consistent with recorded location information of the placeholder file; a protection unit for, when inconsistent as determined by the determination unit, wherein there is a correspondence between the digital content and the set of placeholder files.

Apparatus for preventing replay attack and method for preventing replay attack

The present invention provides a method and an apparatus for detecting a traffic monitoring video. The method comprises: determining a background reference model; determining a target area image in the traffic monitoring video according to the background reference model; updating the background reference model by using the target area image; summating all target points in detection area of each frame of image in the traffic monitoring video according to the updated background reference model to obtain a total area of all the target points; segmenting the frame with the biggest total area to obtain a target area at the best position; and extracting vehicle information from the target area at the best position. By using the present invention, the accuracy of a detection result in a complex environment may be improved.

Method and apparatus for detecting traffic monitoring video

Provided is a table recognizing method, comprising: parsing and analyzing metadata information in an original fixed-layout document, and extracting basic elements on a page of the document; segmenting the basic elements, extracting segmented text lines on the page, and acquiring fragments; constructing an undirected graph with respect to each of the fragments; extracting an image on the page, detecting intersection points of horizontal lines and vertical lines, detecting an external bounding box of the intersection points, and taking whether the segmented text lines fall within the external bounding box as local relationship features; training a learning model according to the local relationship features, local features of the fragments, and neighborhood relationship features among the fragments, acquiring model parameters, and establishing a table recognizing model; and invoking the table recognizing model to perform table recognizing for the document, and acquiring a recognizing result.

Table recognizing method and table recognizing system

The present invention provides a method and an apparatus for detecting traffic video information. The method includes: acquiring a traffic video stream; determining color features of each frame of image in the traffic video stream; calculating the inter-frame distance between adjacent frames according to the color features; calculating the boundary of an image clustered frames' group according to the inter-frame distance by adopting an image clustering evaluation standard in RGB space and an image clustering evaluation standard in YUV space respectively; and determining a final boundary of the image clustered frames' group according to the boundaries of the image clustered frames' group in RGB space and YUV space. By using the present invention, the stability of detection results in different environments may be improved.

Growing community of inventors

Beijing, China

Zhi Tang