50 results about "Stick figure" patented technology

A walk-through screening station scans individuals to detect contraband such as a concealed weapon or improvised explosive device (IED) using ultra wideband (UWB) radar sensing and imaging systems employing wafer scale active array antennas. UWB radar and advanced imaging technology enable automated threat recognition and display for monitoring personnel. The station may scan subjects passing close to or within an aperture width of an array of radar transceivers. Direct calibration by use of reflectors positioned at known locations in the image may be used to implement scanning and imaging so close to the array. The scanning station may employ an easy-to-set-up pair of panels that may be readily deployed by security providers wherever access control—such as to a meeting place or transportation boarding—is needed. Imaging and display processing may provide an abstract display—such as a stick figure representation of anatomy—to address privacy issues and concerns.

The invention relates to a data object logic control system and method based on real-time stroke input. The data object logic control system comprises a computer input device, a preprocessing module, a stick figure identification module, a computer data base, a control module and a computer display output device, and the data object logic control method comprises obtaining real-time stroke input through the computer input device, conducting noise removal identification and adjusting corresponding graphic data objects from the computer data base; and timely generating dynamic demonstration data according to respective interaction logic between dynamic properties and graphic data of called graphic data objects and displaying through the display output device. The control method is based on strokes to identify stick figures, generates different animation effects according to change logic and interaction logic according to identification results of the stick figures and finally achieves stick figure animation story description. Compared with traditional child cultivation software, the system increases participation property and interestingness of man-machine interaction and is prone to receive by children.

The invention relates to a stick figure generation method based on a face photo, belonging to the field of image processing. The method comprises steps of collecting a face database, and using an on-line open source database as a training object; training a face recognition and key point detection model by using the collected database; extracting feature points from a real face picture; sketchingthe input picture; positioning and segmenting the face, five sense organs, hair, clothing and the like based on the extracted feature points; smoothing, enhancing, graying and binarizing the segmentedimage; and recombining the processed components to form a final result. Compared with the prior art, the method has the advantages that the five sense organs are positioned more accurately; a large number of samples are not needed for training, and less picture data is needed; the training time is shorter, the requirement for hardware is low, no cost increases; the training model is very sufficient, and error-prone details are avoided; and the method can be provided to chocolate 3D printers for printing and can be widely used.

A stick figure structure for conveying information to observer of the structure. The stick figure structure may have a torso member, left and right leg members, left and right arm members, and a head member configured to resemble a stick figure. The stick figure structure's members may be further configured to convey information to observers. The stick figure structure may support a sign or a banner. One or more stick figure structures may be located along a route to convey direction information to observers of the structures. Two or more stick figure structures may be arranged to jointly support a sign or a banner or to form a barricade.

The invention provides a stick figure computer scoring and auxiliary coloring method. The method comprises the steps that step 1 a hand drawing and a template map are loaded, and normalization adjustment of size and sliding window weighted smoothing are carried out; 2 the image edge and the contour are extracted to acquire the optimal threshold and the optimal contour; 3 the optimal contour is used to replace the original contour in an image, and a clear image contour is acquired through expansion and corrosion; 4 the contour is extracted again and saved as a second-layer contour; 5 the extracted contour is decomposed into sub-contours, the center position of the sub-contours is calculated to form a deformation model for the relative distance between the centers; 6 contour matching is carried out, and the area and the deformation position the sub-contours are constrained to acquire a comprehensive score; and 7 pseudo-color coloring is carried out on the contour of the original painting. The method can promote intelligent man-machine interaction, stimulates children to learn a painting interest, and has an important application value in the field of children's education.

The embodiment of the invention provides a portrait stick figure generation method and system and a drawing robot. According to the portrait stick figure generation method provided by the embodiment of the invention, image preprocessing is carried out according to the portrait photo to obtain the preprocessed portrait image; and then according to the preprocessed portrait image and the stick figure style photo, a stick figure image is obtained through a convolutional neural network model, so that high-quality stick figures can be quickly generated from the portrait photo, the method is suitable for a drawing robot, and the portrait stick figures can be drawn in a short time. The problem that a stick figure generation method in the prior art cannot be well applied to a drawing robot to drawvivid portrait stick figures is solved.

The invention is suitable for the technical field of computers, and provides a method and system for inputting expression pictures. The method includes the steps that handwritten stick figures input by a user are received and identified to find the expression pictures related to the stick figures, and the found expression pictures are output; the input expression pictures are determined according to selection of the user. In this way, the user only needs to input the stick figures through handwriting, and input of the expression pictures can be achieved; the input mode of the expression pictures is simplified, the input efficiency of the expression pictures is improved, and the interactivity of an applicative wearable device is further improved.

The invention provides a visual data processing method facing an intelligent robot. The method comprises the following steps of acquiring an original picture to be learnt of a current child user; through deep learning, carrying out contour detection and extraction on the original picture so as to acquire a stick figure picture; outputting the stick figure picture to a display screen; and receiving a stick figure picture color filling instruction input by the child user, according to the instruction, carrying out color filling on the stick figure picture and outputting the color-filled picture to the display screen. By using the visual data processing method provided in the invention, children of each age can use the intelligent robot to carry out painting; and during an auxiliary science and education painting process, artistic appreciation and creation capabilities can be imperceptibly increased. The picture whose contour can be extracted can be acquired from a current scene in an on-site mode so that interests for the children to learn painting graffiti can be greatly increased. In addition, because cloud processing is used, picture contour detection and extraction speeds and accuracy are greatly increased.

The embodiment of the invention provides a portrait photo-based stick figure generation method and system, and a storage medium. The portrait photo-based stick figure generation method comprises the steps of performing image preprocessing according to a portrait photo to obtain a preprocessed portrait image; performing illumination attribute detection and processing according to the preprocessed portrait image to obtain an illumination processing image; and finally, performing stick figure fusion according to the illumination processing image and the stick figure style photo to obtain a stickfigure image. The problem that different illumination and postures in one photo are difficult to consider due to the fact that an existing stick figure generation method adopts a global synthesis strategy is solved.

The invention discloses a human face stick figure generation method and device. The method comprises the following steps of: identifying each part area of a human face in a human face image; cutting out an image block corresponding to each part area from the face image; inputting the face image into a trained global portrait generation model to enable the global portrait generation model to generate a global face stick figure of the face image; for the image block of each part region, inputting the image block into a local portrait generation model corresponding to the part region, so that thelocal portrait generation model generates a local human face stick figure of the part region; and fusing the global face stick figure and each local face stick figure to obtain a final face stick figure. The invention aims to consider the difference between different parts of a human face so as to overcome the influence of image domain representation of different parts of the human face on the synthesis quality of the stick figure, and synthesize the high-quality human face stick figure with clearness, attractiveness and vivid texture in combination with the representation mode of different part regions in the stick figure.

The invention discloses a stick figure generation method and device, electronic equipment and a storage medium, and belongs to the technical field of image processing. The method comprises: analyzing line pixel points on all lines in a to-be-split line image, and obtaining split points on all the lines, wherein the split points are determined based on pixel coordinates of the line pixel points on all the lines; according to the splitting points and each line, generating an adjacent edge set corresponding to the line image to be split, wherein the adjacent edge set is determined based on line pixel points between adjacent splitting points on each line; based on a first line splitting strategy, splitting the adjacent edge set in sequence, and storing the adjacent edge set after each time of splitting to obtain a split line image set corresponding to the to-be-split line image, wherein the first line splitting strategy is determined based on the splitting point of each line; and generating a stick figure drawing step based on the split line image set.

The present invention provides a learning method based on a handwriting terminal and a handwriting terminal. The method comprises the steps that: the handwriting terminal regulates a learning mode ofthe handwriting terminal to a target learning mode according to a learning type selected by a user, wherein the learning type comprises pinyin, Chinese characters or stick figures; and in the target learning mode, description steps of the learning content are searched in a learning database in the handwriting terminal for the learning content input by the user, and speech output is performed to allow the user to complete learning of the learning content according to the description steps through speech output by employing the handwriting terminal. According to the embodiment of the invention,the learning method based on the handwriting terminal and the handwriting terminal can rapidly search the content to be learned by the user and give learning guidance for the learning content so as toimprove user learning efficiency and a user learning effect.

The invention provides a method and device for searching objects based on stick figures. The method includes the steps of receiving the stick figures input by a user, searching the target objects matched with the stick figures in a social network, and providing the target objects for the user. By means of the method and device for searching the objects based on the stick figures, the objects can be searched quickly and efficiently in the social network.

The invention discloses a stick figure recognition and generation method based on Raspberry Pi and a recurrent neural network. The method comprises the following steps: (1) collecting a vector stick figure data set; (2) establishing a mathematical model of vector stick figure data; (3) preprocessing vector stick figure data; (4) constructing a recurrent neural network vector stick figure generation model based on a sequence-to-sequence model and a long-term and short-term memory network; (5) training the recurrent neural network vector stick figure generation model; (6) deploying the trained model on the Raspberry Pi; (7) collecting user voice by using a microphone, understanding user semantics by using a Google voice-to-text module and a natural language processing module, mapping the user semantics into a stick figure generation model as input, and controlling a printer to output a generated stick figure picture through Raspberry Pi. According to the method, the problem that vector data are difficult to process in an existing image generation method is solved, and the limitation of an end-to-end system for realizing language-to-image is solved.

Silicon processing technology is used to generate an array of micro messages. These micro messages can contain at least one stick figure, or at least one word, or at least one stick figure and at least one word, or at least one stick figure and a grid mark, or at least one word and a grid mark, or at least one stick figure and at least one word and a grid mark. Grid marks are associated with the micro message and used to identify the X and Y Cartesian coordinates of the message. A plurality of conductive traces is used to form the micro messages. Each micro message can be completely encapsulated in silicon dioxide or at least one conductive trace can be connected to one of the tubs.

The invention discloses a small data set sketch generation method based on BPL. The method comprises the steps: learning strokes, stroke positions and stroke position association, generating probability models of various types, and carrying out the implementation of sketches according to different probability models; wherein the probability model of the category T meets the following conditions: eis one example of the category T, I is a specific image of the example e, M is the number of examples corresponding to the category T, P is the probability, and m is the cycle number. According to the small data set stick figure generation method based on the BPL, the image with the good effect can be generated based on the small data set, the current situation that AI drawing can be conducted only through a large amount of original data is changed, efficiency is improved, and cost is reduced; on the basis of realizing the simulation of the original painting style, the template can be recreated according to the original painting style.

The invention belongs to the technical field of cluster unmanned aerial vehicle performance formation manufacturing, and discloses a performance character picture generation method and system, a cluster unmanned aerial vehicle, a medium and a terminal, and the method comprises the steps: inputting a to-be-presented character content, and selecting a proper font to obtain a character picture; determining the number of unmanned aerial vehicles for cluster performance, the minimum safety distance between the unmanned aerial vehicles and position parameters presented by pictures during hovering performance; obtaining all contour coordinates and sequences of the pattern shown in the stick figure by using an image processing related algorithm; and calculating three-dimensional world coordinatesof hovering points of all the unmanned aerial vehicles during performance according to the determined position parameters and all obtained contour coordinates and sequences of the patterns. Accordingto the method, the character performance picture required by the cluster unmanned aerial vehicle performance can be quickly manufactured, the method is convenient and simple to use, and the efficiencyof manufacturing the cluster unmanned aerial vehicle performance formation is greatly improved.

The invention provides an interesting enlightenment system which can be installed on a smart phone or on a tablet computer. Animation can be played on the system through the multimedia function. Learners can learn stick figures, Chinese characters, letters and the like, and practice through the touch operation function. The hands-on ability and learning ability of children can be improved, and aneffect of 'teaching going together with pleasure' is achieved.

The invention discloses a template subgraph acquisition method and device, a processor and an electronic device. The method comprises the following steps: respectively extracting a plurality of key sub-graphs from each sample of a stick figure data set without a label to obtain a key sub-graph set; performing feature extraction processing on each sample in the key sub-graph set to obtain a key sub-graph feature data set; and performing clustering processing on the key sub-graph feature data set to obtain a plurality of template sub-graphs, wherein the key sub-graph feature data set comprises aplurality of sub-graph feature clusters, and the gravity center of each sub-graph feature cluster in the plurality of sub-graph feature clusters corresponds to one template sub-graph. According to the method and the device, the technical problem that a stick figure recognition mode provided in the related technology is completely characterized by manually designing and extracting rules and does not have a function of characterizing stick figure characteristics is solved.

The invention discloses an indoor safety door with a door lock on an upper side and belongs to the technical field of the office supplies. The indoor safety door comprises a main body, wherein the main body is mounted on a door frame through a folder, a door lock is mounted on the main body, and specifically, the door lock is mounted on the upper part of the main body so that children cannot reach the door lock easily, and a sticking region is arranged on the main body. The indoor safety door is rational in design and simple in structure; the door lock is arranged on the upper part of the main body within a range that children cannot reach, and as a result, various serious consequences caused by children going out by opening the door while staying in an office alone are avoided; in the meantime, the sticking region is arranged on the lower part of the main body, and thus is convenient for a user to paste some important information and also convenient for children to paste stick figures or pasters.

The invention provides a method and a device for automatically generating stick figures of objects. Stick figure materials corresponding to an object are quickly selected through object detection, object feature extraction and matching of an image, thereby solving the problem of high requirements on image size, image annotation and system resources when the object stick figures are generated from a shot image in the prior art. The influence of the image size on the algorithm is avoided, the consumption of complex image annotation is reduced, and the processing efficiency of the system is effectively improved.

The invention discloses an image processing method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of determining attribute information of an object; determining a corresponding region map of the attribute information in the picture of the object by using a deep learning model; inputting the picture of the object and the corresponding region map of the attribute information in the picture of the object into an image conversion network for image conversion to obtain a stick figure image of the object. According to the embodiment, important details of an object in the image can be fully reflected after the image is converted into the stick figure, edge noise is reduced, and the conversion effect of generating the stick figure by the image is improved.