36 results about "Sketch recognition" patented technology

The invention discloses a method for identifying a freehand sketch. The method comprises the steps of acquiring a current processing track inputted by a user, and carrying out preprocessing on the current processing track; detecting valid angular points according to a preprocessing result; segmenting the preprocessing result by utilizing the valid angular points, carrying out curve fitting on each section of track, and identifying a geometric shape of the current track according to all fitting results; storing the processing result of the current processing track as at least one geometry. The invention also discloses a method for editing the freehand sketch as well as a device for identifying and editing the freehand sketch.

The invention discloses a method for creating a three-dimensional surface model by using a perspective sketch. The method comprises the following steps of: identifying and processing a hand-drawn sketch into a vertex-edge graph consisting of contour sides and articulation points, and identifying closed areas; identifying the symmetric relation of the three-dimensional surface model, and completing hidden contours for the contours according to symmetry and visibility; establishing an object coordinate system of the surface model according to a symmetrical relation, calculating three-dimensional coordinates of the contour sides and the articulation points of the surface model, and recovering the coordinates of three-dimensional space curves among the articulation points according to curve projection between the three-dimensional coordinates of the articulation points and the articulation points; categorizing the three-dimensional closed areas of the model into different closed area pieces according to the characteristics of a level modeling method and a B-spline surface fitting method; and modeling the closed area pieces into sub-surfaces according to the characteristics of the closed area pieces by the level modeling method or the B-spline surface fitting method and jointing the sub-surfaces into a three-dimensional model through dispersing, blending and splicing.

A method of generating synthetic data from time series data, such as from handwritten characters, words, sentences, mathematics, and sketches that are drawn with a stylus on an interactive display or with a finger on a touch device. This computationally efficient method is able to generate realistic variations of a given sample. In a handwriting or sketch recognition context, synthetic data is generated from real data in order to train recognizers and thus improve recognition accuracy when only a limited number of samples are available. Similarly, synthetic data can also be used to test and validate such recognizers. Also discussed is a dynamic time warping based approach for both segmented and continuous data that is designed to be a robust, go-to method for gesture recognition across a variety of modalities using only limited training samples.

The invention discloses a support-vector-machine-based kernel matrix approximating method. The method comprises the following steps of: firstly, mapping a hand-drawn sketch into a feature string on the basis of a region-filling concept; secondly, training a training sample by using a support vector machine (SVM) on the basis of a string kernel to obtain a classifier; and finally, classifying and recognizing the sketch to be recognized by using the classifier obtained through training, and mapping the blurred and irregular hand-drawn sketch into a precise geometrical shape. Compared with the prior art, the method has the advantages that: the method is unrelated to the position, the size and the drawing way of the sketch and a user is allowed to draw the sketch in an individual habitual way; and by the string-kernel-based hand-drawn sketch recognition method, the recognition accuracy is relatively high and the method is easy to implement.

The invention discloses a sketch completion and recognition method and device based on a generative adversarial network. The sketch completion and recognition method comprises the following steps: (1)based on a conditional generative adversarial neural network, improving the generative adversarial neural network by utilizing a cascading strategy according to the characteristic that a sketch is sparse relative to semantic information of a color picture; (2) expanding the category universality of the sketch completion network, setting a sketch recognition task as an auxiliary task, and adding asketch recognition auxiliary network in the network structure; (3) applying the sketch completion method to the recognition task of the incomplete sketch, the image retrieval task based on the incomplete sketch and the sketch scene editing task; and (6) integrating the sketch completion method to form a sketch completion application platform, supporting application functions of interactive sketchcompletion, sketch completion and identification, sketch scene segmentation and completion, interactive sketch completion assistance and the like, and being capable of being applied to various devices and terminals such as a PC, a mobile phone, a tablet personal computer and an electronic whiteboard.

The present invention discloses a system and method to recognize the geometric primitives and estimate the intended geometric relationship between the primitives. The system also provides its user an interactive feedback mechanism to better provide the graphic results intended by the user. The areas enclosed by the lines drew by the user is also considered by the system in the graphic result calculation process to improve the graphic results. One main feature of the present system is to provide geometric constraints estimations based on calculation of the constraints' effect on all related primitives and previously existing geometric constraints.

The invention provides a machine room sketch identification method and device based on a legend library, and the method is characterized in that the method comprises the following steps: formulating asketch drawing standard, building a standard legend library, and carrying out the regularization constraint of the drawing of a machine room sketch; obtaining sketch data; performing hierarchical segmentation on the whole image in the machine room sketch to obtain a component diagram of the machine room sketch; performing matching identification by utilizing a standard legend library so as to realize detection and identification of the machine room sketch components; carrying out reasonable position constraint on the machine room sketch component; and performing parameterized output of results. The machine room sketch recognition method and device based on the legend library have the advantages that the standard graph recognition result matched with the input sketch can be output quicklyand accurately in real time, therefore a more visual reference basis is provided for designers to conduct quick design after the designers combine a sketch exploration report.

The invention provides a graphical interface test case generation method based on hand drawing recognition. According to the method, for the problems that in existing graphical interface test case generation, the manual test cost and the script test difficulty are too high, the test case generation process is assisted through a hand-drawn sketch recognition technique, and therefore graphical interface interaction tests of mobile equipment software and personal computer software are easier, more convenient and more efficient to operate.

The invention belongs to the technical field of road traffic accident handling, and particularly relates to a road traffic accident field sketch recognizing and drawing method. The method includes the following steps of A, drawing a field record sketch based on the road surface form and related accident elements of an accident field by bare hand through an electronic sketch obtaining device; B, recognizing a track input by a user each time through a track recognizing module, and completing the recognition of the road contour and the road elements; C, completing the recognition of the traffic accident field record sketch through a road overall form recognizing module and a road recognizing preview module; D, completing the drawing of a road traffic accident field scale drawing according to a recognition result through the combination of a legend system and an auxiliary system. The bottleneck problems that an existing conventional traffic accident field handling method is low in efficiency and precision and poor in standardability can be solved.

The invention proposes a sketch semantic recognition method and a sketch semantic recognition system for on-line capture of design intent. The method comprises the following steps of: building a relation model between sketch drawing rule and the design intent; drawing a sketch; and performing sketch semantic recognition on the sketch according to the relation model between the sketch drawing rule and the design intent to acquire a design chart matched with the sketch. According to the method, better recognition results can be obtained from the sketches drawn by users of different design thinking and drawing habits, and the method has the advantages of low computation complexity and high recognition rate.

The invention discloses a freehand sketch recognition method based on an attention mechanism, and the method comprises the steps: inputting an original freehand sketch into a deep convolution neural network, and obtaining a feature map outputted by a last convolution layer; inputting the feature map into a channel attention module to obtain a feature map based on channel attention optimization; training a classification network used for predicting the vertical overturn of the freehand sketch, and inputting the original freehand sketch into the trained classification network to obtain a vertical overturn space attention graph; combining the feature map based on the channel attention optimization and the vertical overturning space attention map, and calculating to obtain a feature map basedon the vertical overturning space attention optimization; and finally, outputting an identification result through the full connection layer. The method has the advantages that channel attention and vertical overturn space attention are adopted to optimize the characteristics of the convolutional neural network, so that the network can pay attention to learning of a part with higher discrimination, and therefore, the recognition precision of the freehand sketch can be effectively improved.

The embodiment of the invention provides a sketch-based webpage generation method, which comprises the steps of identifying a sketch to obtain element information of a plurality of elements, each element corresponding to a sketch pattern in the sketch; generating a syntax tree according to the element information of the plurality of elements; generating a webpage code according to the syntax tree;and generating a target webpage corresponding to the sketch according to the webpage code. According to the sketch-based webpage generation method provided by the embodiment of the invention, the webpage layout for webpage generation and the element information of the plurality of elements can be obtained through sketch identification, and the syntax tree is generated based on the information andthen the webpage code is generated, so that the page code and the corresponding target page are automatically generated by a machine, the sketch does not need to be manually converted into a webpagecode, and the webpage development efficiency is improved.

The invention discloses an online handwritten formula recognition method and device based on user feedback information. User participation such as deletion operation, pen refilling operation and/or structural movement operation is introduced into an existing recognition method. By means of the idea of man-machine mixed intelligence, user feedback information is fused in different stages of a character segmentation-character recognition-structure analysis recognition method, and an interaction technology suitable for user writing and error correction is designed. According to the method, an interaction means suitable for sketch recognition is designed, various problems encountered by a formula recognition method mainly based on image processing are avoided, basic guarantee is provided for a user to modify strokes with stroke errors or ambiguity, structural errors of formulas and the like, the effect of the formula recognition rate is improved, and the requirements of the user are met.

The invention provides a small sample character and freehand sketch recognition method and device, and the method is characterized in that the method comprises the following steps: erasing unlabeled source data in a point sequence format according to a fixed erasing proportion, and obtaining augmented network pre-training data; building a BERT augmented network based on a Gaussian mixture model, and training based on augmented network pre-training data and unlabeled source data in a point sequence format to obtain an augmented device; erasing the labeled small sample data in the point sequence format according to each random erasing ratio to obtain erased small sample data; respectively predicting states and coordinates of the erased small sample data by using an augmenter to obtain prediction points, integrating the prediction points with the erased small sample data, and converting by using a neural renderer to obtain bitmap format augmented data; and training a convolutional neural network classifier based on the augmented data in the bitmap format and the labeled small sample data in the bitmap format to obtain a small sample character and freehand sketch recognition model, thereby recognizing the to-be-recognized image to obtain a classification result.

The invention belongs to the field of computer vision and discloses a sequential sketch identification method fusing texture features and shape features. The method comprises the steps of firstly, according to a stroke sequence of a sketch, obtaining an image sequence; secondly, extracting the texture features and the shape features of images to form a feature sequence corresponding to the image sequence; and thirdly, inputting the features to a network containing two stages for performing learning, wherein in the first stage, two recurrent neural networks receive the texture features and theshape features of the images; and in the second stage, outputs in the previous stage are fused firstly, then a fused output is input to a third recurrent neural network, and finally a result is obtained through a classifier, so that iterative learning is performed according to the sequence in the sequences. The method has the advantages that a geometric descriptor is used for sketch identification, and the recurrent neural networks are adopted for performing effective learning on sequential features, so that the defect that an original identification model ignores the shape features and the sequential features of the sketch is remarkably improved and the sketch identification efficiency is better improved.