31 results about "Scribble" patented technology

The invention discloses a low-power-consumption Beidou high-precision positioning receiving device and system, and belongs to the technical field of slope safety monitoring and early warning. The method comprises the following steps: S1, marking a tampered picture by using graffiti marking, and constructing an image tampering positioning data set; s2, inputting the image in the data set into a tampering discriminator, and generating real area priori and tampered area priori related to the image; s3, performing data enhancement processing on the images in the data set, inputting the enhanced images into an image encoder, and extracting tampering features of the images; s4, inputting the prior features obtained in the S2 and the tampering features obtained in the S3 into a feature modulation module, and dynamically modulating the tampering features by using the prior features; s5, inputting the modulated features into a gating adaptive module to enrich context information, and generating an accurate mask; and S6, comparing the generated mask with the graffiti label, calculating a loss function, and training the model according to the loss function.

The present application relates to the technical field of face image editing, in particular to a kind of face image editing method based on multi-modal interactive module of scribble. Through two-way multi-modal interactive module, cross attention graph is calculated from position dimension and channel dimension respectively, the cross attention graph obtained and scribble vector are used to carry out latent space latent reflection on face image latent vector iterative modification, complete scribble and image target editing position semantic content alignment, and scribble is embedded into corresponding latent space;Through single-path multi-modal interactive module, save the original face identity feature after editing, the texture supplement vector obtained carries out latent space latent reflection on face image latent vector iterative modification, and finally generates face image editing result.The present application can more intuitively and fully express the editing intention of user, realize the real feeling editing effect that meets user's expectation, and the present application has superiority in editing effect, editing real feeling and face identity information saving of face image editing.

Compared with the prior art, the double-sided multifunctional drawing board for children has the advantages that children can graffiti and learn drawing, numbers and Chinese characters through the electronic drawing boards and the white boards on the two sides, and sliding columns at the upper end and the lower end are clamped in corresponding strip-shaped overturning grooves in the using process of the electronic drawing boards; when the electronic drawing board needs to be overturned, the two sliding columns at one end are driven by the control mechanism to extend out of the strip-shaped overturning groove, after the electronic drawing board is driven by 180 degrees, the two sliding columns are clamped into the strip-shaped overturning groove, and at the moment, the back face of the electronic drawing board faces outwards; and the screen of the electronic drawing board is effectively prevented from being collided and damaged.

The application discloses a medical image segmentation model training method and device based on scribble annotation and a terminal, and uses two weight-shared medical image segmentation models to construct a double-network structure. A standard enhanced view and a composite enhanced view are obtained through processing of an input medical image via an enhancement operation, and the standard enhanced view and the composite enhanced view are respectively taken as inputs of the double-network structure to obtain pseudo labels and prediction labels. A consistency regularization loss that measures the similarity between the pseudo labels and the prediction labels is calculated. In the model training process, a loss function including the consistency regularization is minimized to optimize model parameters. Compared with the prior art, the application uses the weight-shared double-network structure to perform consistency regularization training, maximizes the similarity of predictions of different enhanced views of the same image, has good optimization effect, and can complete network parameter optimization in one training, without the need to perform multiple iterative training, and has high training efficiency.

Systems and methods for image processing are described. Embodiments of the present disclosure identify an original image depicting a face, identify a scribble image including a mask that indicates a portion of the original image for adding makeup to the face, and generate a target image depicting the face using a machine learning model based on the original image and the scribble image, where the target image includes the makeup in the portion indicated by the scribble image.

The utility model relates to the technical field of model production, in particular to DIY doll model production equipment which comprises a supporting frame, a first motor, a rotating shaft, a second motor, a rotating disc, a connecting frame, a fixing frame and a first elastic piece. And a second motor is installed on the rotating shaft, a rotating disc is installed on an output shaft of the second motor, two connecting frames are fixedly connected to the rotating disc, fixing frames are arranged on the connecting frames in a sliding mode, and the fixing frames are sleeved with first elastic pieces. The telescopic hose is pulled downwards, so that the end of the telescopic hose is located in the mold, then the electromagnetic valve is started, gypsum liquid in the storage frame enters the discharging pipe and is discharged out of the positioning cylinder through the telescopic hose, and therefore the mold can be automatically charged, it is guaranteed that the gypsum liquid is directly injected into the bottom of the mold, impact force is reduced, and the gypsum liquid is prevented from splashing all around.

The application discloses an information pushing method and device, terminal equipment and a storage medium, and belongs to the technical field of picture processing. The method is applied to terminal equipment, and the method comprises the following steps: obtaining a scribble picture; obtaining a material picture set corresponding to the scribble picture according to the scribble picture; in response to a selection operation on a first picture, obtaining category information of the first picture, the first picture being any one in the material picture set, and the category information being used for indicating the category of a target object in the first picture; and pushing target content of the first picture according to the category information, the target content being used for describing the target object of the first picture. The scribble picture drawn by a user can be more conveniently understood, and the diversity and accuracy of the recognition result are improved.

1. The name of the design product: color filling scribble toy (inflatable ball). 2. The use of the design product: for playing. 3. The design points of the design product: in the pattern. 4. The picture or photo that best indicates the design points: perspective view.

The application discloses a coloring body, a mosaic scribbling toy and a use method of the coloring body. The coloring body has a coloring surface, and the coloring surface comprises a plurality of coloring areas which are separated by a separation gap, and each of the coloring areas is provided with fluff. The mosaic scribbling toy comprises the coloring body, and further comprises a template body. The template body has a printing surface, and the printing surface comprises a plurality of color distinguishing areas which are separated by a separation line, and each of the color distinguishing areas is provided with a coating hole. The printing surface is used for printing a pattern. The use method of the coloring body comprises the following steps: coloring in part or all of each coloring area; and attaching a diffusion liquid in each coloring area. The application solves the problem that the color of a detail part is easy to exceed the contour boundary of a pattern, and the area with a large area cannot be completely coated, thereby leading to a messy pattern when a current drawing toy is colored, so that the whole pattern presents a more beautiful effect, and the drawing interest of children is improved.

The application relates to the technical field of paper-cut design, and discloses a paper-cut design pattern line reconstruction generation method and system based on deep learning, which comprises the following steps: scribble preprocessing is performed on an original paper-cut design drawing to draw a scribble picture, paper-cut patterns, geometric features and texture features are collected to construct a prior knowledge base; preprocessing features, prior knowledge and latent feature representation are input into a ControlNet-GAN model; a generator of a GAN network analyzes a conditional tensor through a Transformer layer, a Control-UNet layer is integrated into a convolution module and an attention module of the generator, and a reconstructed paper-cut pattern design drawing is generated; a discriminator extracts pattern features in the reconstructed paper-cut pattern design drawing, compares the pattern features with the prior knowledge base, and punishes a generated result that does not conform to paper-cut rules; the application optimizes a ControlNet algorithm, integrates prior knowledge of paper-cut patterns, makes the generated image conform to paper-cut pattern rules, improves the generation efficiency and quality of a paper-cut design drawing, and meets the digital creation needs of a traditional paper-cut process.

The invention belongs to the technical field of intelligent luggage cases, and particularly relates to a multifunctional luggage case with a voice assistant. The luggage case comprises a main case body and an auxiliary case body, the main case body and the auxiliary case body are jointly provided with a flexible connecting part, the main case body and the auxiliary case body are jointly provided with a zipper, and by arranging a voice assistant module, a sensor module and a network module, the luggage case has the capabilities of voice control, real-time reminding, path navigation, online interaction and the like; the intelligent level of travel and the user experience are obviously improved; a drawing board capable of being erased by one key and a matched drawing pen are arranged in the writing board, so that a user, particularly a child, can do graffiti creation conveniently, interactivity and interestingness are enhanced, meanwhile, quick cleaning is achieved through a clearing button, and repeated use is facilitated; the detachable longitudinal partition plates and the transverse partition plates are arranged in the main storage cavity, flexible partition is achieved through cooperation of the clamping blocks and the clamping grooves, the storage requirements of objects of different sizes are met, and the space utilization rate is increased.

1. The name of the design product: heat-sensitive color-changing drawing healing drawing board. 2. The use of the design product: for drawing, doodling, heat-sensitive color-changing creation and emotional healing. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective drawing.

Disclosed in the present application are a page display method and an electronic device, which are used for fixing the layout positions of texts and doodles in display interfaces, such that the layout positions of the texts and the doodles do not change along with the rotation of electronic devices or along with changes of display windows. The method comprises: when a display interface of an application comprises both text and doodles, an electronic device may display the text and doodles on a layer where the text is located. Specifically, the electronic device displays the display interface of the application, the display interface comprising a first layer and a brush tool, the first layer comprising a first text; then, in response to a first operation on the brush tool, the electronic device creates a second layer, and displays a drawn first doodle on the second layer; and finally, in response to a drawing completion operation, the electronic device hides the second layer, and displays on the first layer the first doodle drawn on the second layer, the first doodle being located below the first text.

1. Name of the product in this design: Handwriting tablet. 2. Intended use of this design: This design is intended for writing, drawing, or graffiti. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

1. Name of the designed product: whiteboard (cheese). 2. Use of the designed product: for drawing, scribbling, writing. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view.

1. The name of the design product: graffiti drawing graphical user interface for electronic equipment. 2. The use of the design product: for an electronic device. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best indicates the design points: front view. 5. The electronic device is a conventional design, and other views are omitted. 6. The use of the graphical user interface: for AI magic graffiti drawing; select the "start graffiti" display interface change state diagram 1 on the left side of the main view interface, select the circular icon at the bottom right of the interface change state diagram 1 to select the color, after the color selection is completed, display the interface change state diagram 2 for drawing, select the "clear" button in the upper left corner of the interface change state diagram 2 to display the interface change state diagram 3, the button is highlighted, select the "clear" display interface change state diagram 4 to confirm whether to clear the graffiti. 7. Other circumstances that need to be explained: the single gray filled area in the interface is the content picture.

1. The name of the design product: multi-faceted color geometry teaching model. 2. The use of the design product: a magnetic and splicable teaching cube, each face can be combined or unfolded by magnetic adsorption, and the surface has bright color graffiti design, which is used for classroom teaching, children's spatial cognition training and creative splicing. 3. The design points of the design product: the combination of shape, pattern and color. 4. The picture or photo that best shows the design points: perspective view. 5. The design to be protected contains color.

Embodiments of the present application provide a scribbling processing method and related device. The method comprises: a terminal device displays a first picture; the terminal device receives a first operation; in response to the first operation, the terminal device displays a first layer of scribbling on an upper layer of the first picture; the terminal device receives a second operation; in response to the second operation, the terminal device adds a first type of element to the first picture, wherein the first type of element does not belong to scribbling; the terminal device receives a third operation; in response to the third operation, the terminal device displays a second layer of scribbling on an upper layer of the first picture; the terminal device receives an erasing operation, and a region affected by the erasing operation comprises the first layer of scribbling and the second layer of scribbling; in response to the erasing operation, the terminal device erases the region affected by the erasing operation in the first layer of scribbling, and erases the region affected by the erasing operation in the second layer of scribbling, to obtain a second picture. In this way, the flexibility and convenience of scribbling processing can be improved, and the user experience can be improved.

1. The name of the design product: the operation area of the work management graphical user interface of electronic equipment. 2. The use of the design product: an electronic device. 3. The design points of the design product: the partial graphical user interface in the electronic equipment. 4. The picture or photo that best indicates the design points: design 1 front view. 5. Design 2 is designated as the basic design. 6. The use of the graphical user interface: the graphical user interface is used to manage works. The partial graphical user interface claimed in the design is used for work management operation. In design 1, the user can upload a graffiti work by touching or clicking the "go to contest" button in the graphical user interface. In design 2, the user can share a graffiti work by touching or clicking the share button in the graphical user interface. In response to the user touching or clicking the "go to contest" button in the design 3 front view and uploading a graffiti work, the graphical user interface changes from the design 3 front view to the design 3 change state view to display the graffiti work for the contest. 7. Other circumstances that need to be explained: the part of the graphical user interface shown by the dashed line in each view of designs 1 to 3 does not constitute the part claimed in the design.

1. Name of this design product: Light and Shadow Graffiti Board. 2. Purpose of this design: This design is intended for use as a light and shadow graffiti board for writing, drawing, and doodling. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

The present invention relates to a compound suitable for providing an anti-graffiti effect on a surface of a substrate, a composition for providing an anti-graffiti effect on a surface of a substrate, a process for preparing said compound, a process for providing an anti-graffiti effect on a surface of a substrate, the use of said compound for providing an anti-graffiti effect on a surface of a substrate, and the use of said compound for providing an anti-graffiti effect on a surface of a substrate. And a substrate including a layer formed with or from the compound. The invention relates in particular to the field of surface treatment of the construction industry and glass refining.

1. Name of the designed product: cup (scribble). 2. Use of the designed product: for cup. 3. Design points of the designed product: combination of shape and pattern. 4. Picture or photo best indicating the design points: perspective view.

1. Name of the product in this design: Graffiti Building Blocks (EVA). 2. Intended use of this design: for toys. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model. 5. The bottom view is the side that is not easily seen during use, so the bottom view is omitted.

1. Name of the product in this design: Graphical User Interface for Generating Doodle Drawings for Electronic Devices. 2. Intended use of this design: for use in an electronic device. 3. The key design feature of this product is its graphical user interface. 4. The image or photograph that best illustrates the design's key features: the front view. 5. Electronic devices are designed in a conventional way, so other views are omitted. 6. Purpose of the graphical user interface: Used for generating AI magic doodle paintings; In the main view interface, selecting the menu button on the remote control displays interface change state diagram 1. Selecting "Cancel" in interface change state diagram 1 displays interface change state diagram 2. Selecting "Generate AI Doodle" in the upper right corner of interface change state diagram 2 displays interface change state diagram 3. During the generation process, selecting the menu on the remote control displays interface change state diagram 4. When prompted whether to cancel the generation, selecting "Cancel" in interface change state diagram 4 displays interface change state diagram 5. Selecting "Regenerate" in the lower left corner of interface change state diagram 5 displays interface change state diagram 6. Selecting "Cancel" in interface change state diagram 6 displays interface change state diagram 7. When prompted whether to return to the canvas, selecting "Cancel" in interface change state diagram 7 displays interface change state diagram 8. Selecting "Share to Mobile Phone" in the upper right corner of interface change state diagram 8 displays interface change state diagram 9. If scanning the code fails, interface change state diagram 10 is displayed. 7. Other situations requiring explanation: Other explanation: The single gray filled area in the interface is the content screen.

The application discloses a camouflage target detection method based on scribble annotation and structural integrity enhancement, comprising the following steps: collecting images and preprocessing; adopting a pyramid vision Transformer as an encoder to extract multi-level original feature maps; constructing a direction context attention module to optimize the original feature maps, aggregating the predicted features of different layers after optimization to generate segmentation prediction results of the camouflage target; constructing an asymmetric local structure consistency loss function, using high-confidence pixels of scribble annotation to asymmetrically propagate supervision signals to neighboring pixels to enhance boundary consistency and suppress noise; combining partial binary cross-entropy loss, structure consistency loss and contrast loss to perform end-to-end optimization training on the camouflage target detection model; and the application realizes accurate segmentation of the camouflage target under weak supervision, significantly improves boundary definition and structural integrity, and has strong robustness and wide application value.

The invention discloses a weak supervision camouflage target detection method and a weak supervision camouflage target detection system based on graffiti labeling and depth information assistance, and designs a cooperative training and feature fusion mechanism through graffiti labeling with extremely low cost in combination with complementary information of RGB and depth images. Through multi-modal information fusion and a pseudo label optimization mechanism, on the premise of only needing sparse graffiti labeling, high-precision camouflage target detection is realized while the data labeling burden is remarkably reduced, scene understanding and detail retention capability which are not inferior to that of a fully supervised model are realized, and the detection accuracy is improved. And a practical solution is provided for low-cost and high-precision camouflage target detection.

The utility model discloses a toy for guiding a pen-holding hand shape in the technical field of pen-holding training, which comprises a holding ball, a limit post and a positioning ring, the lower end of the holding ball inclines towards one side, the limit post is vertically arranged at the top of the holding ball, the inclination direction of the lower end of the holding ball is opposite to the direction of the limit post, and the limit post is vertically arranged on the top of the holding ball. The positioning ring is fixedly arranged on the side wall of the holding ball, the holding ball, the limiting column and the positioning ring form an integral structure to be held and played by an infant, the infant who cannot hold a pen in the infant can be trained through a toy type device, the infant can form a correct pen holding gesture habit in long-term holding learning, and the interestingness of the infant is improved. When the child begins to hold the pen to scrawl, the pen holding posture in a hollow hand shape can be naturally formed, the correct pen holding posture of the child can be corrected and guided in the initial period, and the guiding and assisting effects on learning of the correct pen holding posture are achieved.