8 results about "Sketch recognition" patented technology

A method, system, device and medium for simultaneous recognition and segmentation of hand-drawn sketches, the method comprising: obtaining a hand-drawn sketch in a scalable vector graphics format from hand-drawn sketch acquisition software, and converting the result into an RGB format image and graph format data; constructing a dual-stream network for simultaneous recognition and segmentation based on a convolutional neural network and a graph convolutional network; inputting the RGB format hand-drawn sketch image into the convolutional neural network stream to obtain global features and category recognition results that characterize the hand-drawn sketch category; inputting the graph format hand-drawn sketch data into the graph convolutional network stream to obtain stroke-level features and point-level features, and splicing the global features, stroke-level features and point-level features to achieve point-level segmentation; utilizing the KL divergence method to achieve supervision of the segmentation results; the system, device and medium are used for simultaneous recognition and segmentation of hand-drawn sketches; the present invention can simultaneously perform hand-drawn sketch recognition and segmentation tasks, is more efficient than performing only segmentation or only recognition tasks, and improves the accuracy of hand-drawn sketch recognition and segmentation.

Provided are a device and method for recognizing a sketch. The device includes a memory configured to store at least one instruction and a processor configured to execute the at least one instruction stored in the memory. The processor generates a plurality of frames from sketch data about a sketch image created by a user, extracts features from each of the plurality of frames, trains a deep learning model configured to classify a sketch image into a class, on the basis of the extracted features, and performs sketch recognition using the trained deep learning model.

The utility model belongs to the technical field of high-precision sketch recognition, analysis and reconstruction devices, and particularly relates to a real-face-based high-precision sketch recognition, analysis and reconstruction device which comprises a box body, protection boxes are arranged on the two sides of the top of the box body, and clamping mechanisms are arranged in the protection boxes; by adopting the adjustable clamping mechanism which specifically comprises the threaded shaft, the threaded block, the connecting frame and the like which are arranged in the protection box, the position of the fixing plate can be flexibly adjusted, so that the sketch plate clamping device adapts to sketch plates of various sizes, and the connecting shaft is driven by the driving motor to rotate through the driving mechanism; and the power is transmitted to the driven roller through the transmission toothed belt, so that automatic and accurate movement control is realized, the operation convenience and the working efficiency of the equipment in the use process are further enhanced, and the problem that a high-precision sketch recognition, analysis and reconstruction device in the prior art cannot be effectively compatible with sketch plates with different sizes is solved.

The invention relates to the technical field of image processing, and discloses a sketch and data driving-based knitted pattern retrieval method and system, a computer readable storage medium and a computer program product. The method comprises the following steps: taking a knitted pattern sample set and a sketch sample set as training sets, and inputting the training sets into a predetermined generative adversarial network for training; generating a corresponding sketch for each knitted pattern in the knitted pattern database by using the trained generator to obtain a sketch data set; inputting the sketch data set into a predetermined sketch recognition network for training, and constructing an index database for retrieval; and retrieving the sketch to be queried by utilizing the index database, and outputting the most matched retrieval result and the corresponding knitted pattern. According to the method, robust and efficient retrieval of the sketch is realized, the characteristics of high repeatability and no specific object of the knitted pattern can be well processed, and compared with a traditional algorithm, the retrieval speed and accuracy are improved.

The invention discloses a sketch recognition method. The method comprises the following steps: acquiring sketch original data, converting the sketch original data into sketch sequence data, removing repeated points and isolated nodes in the sketch sequence data, and acquiring sketch sequence optimization data; sampling the sketch sequence optimization data by adopting a vertex distance maximization sampling method, and normalizing the sampled sketch sequence optimization data to obtain sketch sequence standard data; according to the sketch sequence standard data, constructing sketch data with a time sequence structure; and constructing a sketch recognition model, and obtaining a sketch recognition result according to the sketch data with the time sequence structure and the sketch recognition model. According to the method, when the graph structure of the sketch is constructed, the time sequence information is introduced and is directly processed by GNNs, so that participation of a traditional neural network model is not needed, the scale and calculation overhead of the model are reduced, and the accuracy of subsequent sketch recognition is improved.

The invention discloses a freehand sketch recognition method based on multi-level stroke sequence feature extraction, and the method comprises the steps: obtaining a handwritten formula image sample through a tablet device, and recording stroke track data; secondly, preprocessing the data by utilizing a spatial variant character data enhancement (SCDE) method to improve the retrieval capability of the model; then, a CPCA method is adopted to carry out channel and spatial dimension attention correction on the feature map of the convolutional neural network so as to enhance the feature extraction effect; and finally, decoding the image features into character vectors by using a GRU-based character decoder, and generating a final recognition result by calculating a multi-character loss function. According to the method, the recognition precision of handwritten mathematical formulas is improved, and particularly, the method has excellent performance when coping with handwritten formulas with sparse and complex structures. In addition, space channel attention perceived by characters is further utilized, and the generalization ability and the real-time performance of the model are effectively improved.

The application discloses a sketch recognition method and device based on three-dimensional sparse convolution and two-dimensional convolution fusion, obtains a sketch image, extracts features of the sketch image to obtain sketch image features, simultaneously extracts sketch point features and voxelizes, extracts geometric information of each point on a stroke of the sketch, voxelizes the sketch points based on the geometric information to obtain point voxels, then extracts features of voxels of each point of the sketch to obtain sketch voxel features, finally, fuses the sketch image features and the sketch voxel features, and classifies and recognizes the sketch through a classifier. The application fully utilizes features of the sketch and all sparse points of the sketch, removes large blank areas of the sketch through Sketch-SparseVoxelNet, directly extracts spatial relationships of all points of the sketch, and fuses texture and color features extracted by a convolutional neural network, so that high-precision intelligent recognition of hand-drawn sketches is realized, and designers are better assisted.

The application relates to a sketch-recognition-based fast generation method and system of a garment three-dimensional model, and relates to the technical field of three-dimensional model generation, which comprises the following steps: collecting a garment sketch uploaded by a user and demand input information; generating a garment image according to the garment sketch; generating a garment initial three-dimensional model according to the garment features extracted from the garment image; calling input types and demand contents based on the demand input information; extracting the demand contents based on the input types to obtain input fabrics and input colors; combining the input fabrics and the input colors, optimizing the garment initial three-dimensional model to generate a garment final three-dimensional model, and outputting the garment final three-dimensional model. The application has the effect of improving the generation efficiency of the garment three-dimensional model.