21 results about "Brush stroke" patented technology

The invention discloses a universal style migration method based on a diffusion model and stroke enhancement, which relates to the technical field of multimedia, and comprises the following steps: firstly, carrying out noise addition processing on an input content image and an input style image in a potential space of the diffusion model to obtain content noise features and style noise features; performing feature extraction on the content image by utilizing flow field graph generation, channel fusion, edge enhancement and channel exchange operation to obtain stroke texture features; and finally, under the guidance of the stroke texture features, fusing the content features and the style features through an inverse process of a diffusion model so that the stylized noise features are gradually denoised, and generating a stylized image with complete content and enhanced style stroke under the decoding of an image decoder. According to the method, the diffusion model and the stroke enhancement are simultaneously applied to the general style migration, so that the problems of low content generation quality and weak style stroke in the general style migration are solved, and the training cost of the style migration network is reduced.

The application discloses an artistic image generation method based on semantic graph guidance and style prior constraint. The method is characterized by different features of content attributes and style attributes. The target content is represented by a semantic graph to accurately specify the required generation scene in a more controllable manner. Meanwhile, the target style is represented by painting to utilize the style prior information such as color matching, brush stroke, texture, light and shadow, etc. Through the above manner, the effect of artistic image generation can be significantly improved, and the generated image has higher quality and is closer to the artistic works of human experts. The artistic image generation method provided by the application can effectively promote the technical development of the generation model in the aspects of high quality, high controllability and artistry.

The application provides a hand-drawn material parameter generation method and device, electronic equipment and a storage medium, and the method comprises the following steps: acquiring a basic material rendering parameter for a target three-dimensional model, acquiring a color block material rendering parameter for the target three-dimensional model, acquiring a brush stroke material rendering parameter for the target three-dimensional model, generating a hand-drawn material parameter of the target three-dimensional model according to the basic material rendering parameter, the color block material rendering parameter and the brush stroke material rendering parameter, and the hand-drawn material parameter is used for material rendering of the target three-dimensional model, so that the rendered model has a hand-drawn effect. Therefore, the rendered model has a three-dimensional rendering two-dimensional material with color block and brush stroke effects, and the rendering efficiency is improved.

A processor-implemented method for image generation using an artificial neural network (ANN) includes receiving an input including one or more of an image or a text prompt. The ANN processes the input to determine one or more virtual brush strokes to generate an output image or one or more commands for controlling an image drawing application to generate the output image. A list of the one or more virtual brush strokes to generate the output image or the one or more commands for controlling the image drawing application to generate the output image. The one or more virtual brush strokes or commands may be executed to generate a sketch based on the input.

The embodiment of the invention provides a writing track display method, device and equipment and a readable storage medium, electronic equipment obtains track points generated when writing operation acts on a screen of the electronic equipment, interpolation is carried out between every two adjacent track points to obtain a plurality of interpolation points, and the interpolation points are used for displaying the writing track. And determining the brush of each of the two adjacent track points and the brush of each interpolation point between the two adjacent track points so as to obtain a plurality of brushes. And then, the electronic equipment determines a stroke segment contour between two adjacent track points according to the plurality of brushes and displays a writing track. By adopting the scheme, the electronic equipment performs interpolation on any two adjacent track points to obtain a plurality of interpolation points and generates the brush for each track point and the interpolation point, and the brush of each track point and the interpolation point is different, so that the writing track has the effects of thinning and thickening, the brush tip effect is highlighted to a certain extent, and the writing quality is improved. The purpose of improving the display effect is achieved.

Predefined mark making tools within graphics applications address initial or final stages of a stroke whilst jitter addresses the intervening section of the stroke. Whilst this allows a brush stroke to be simulated as having increasing pressure initially, pressure variability during the stroke, and ending with decreasing pressure this approach does not reflect or mimic the artist's reality. This reality is that an artist applying multiple strokes of a medium, e.g. watercolour, pastels, oils, etc., with an applicator, e.g. a brush, pen, airbrush, marker, sponge or a knife, to a canvas where brush marks may accumulate. Prior art mark making tools and software do not account for aspects of opacity, grain (of the underlying canvas), and blending (of the multiple strokes). Accordingly, there are provided controls with respect mark making tools that address these aspects providing the digital artist with increased control, increased reproducibility, and incorporation of real world effects.

The invention relates to the field of image processing and artificial intelligence, discloses a Chinese landscape painting style migration method considering structure retention and stroke details, and aims to solve the problem that content structure retention and fine artistic style migration are difficult to consider in an existing method. The method comprises the following steps: respectively capturing global long-distance structural dependence and local detail features of an input image in a parallel mode by adopting a double-branch encoder consisting of a bidirectional state space modeling branch and a self-attention branch; self-adaptive information compensation and enhancement are performed on a feature missing region caused by sparse strokes or large-area blank leaving through a multi-scale context sensing module; a dual-path decoder formed by a spatial hierarchical state space modeling branch and a trans-attention branch is utilized, the spatial hierarchical state space modeling branch is responsible for faithful reconstruction of a content structure under the guidance of style features, and the trans-attention branch is responsible for accurate injection of style strokes and textures; and finally, fusing the output of the dual-path decoder, and generating a stylized image through a convolution decoder.

This invention discloses a deep learning evaluation system and method for ink painting brushwork techniques. The system includes: a multimodal data acquisition module, a data fusion and preprocessing module, a brushwork deep feature extraction module based on a temporal convolutional network, a brushwork technique recognition and quantitative evaluation module, and a real-time feedback and correction guidance generation module. The multimodal data acquisition module synchronously collects brushwork process data; performs temporal synchronization and feature extraction on the data to generate a multimodal feature matrix; extracts deep temporal feature vectors through a dilated causal temporal convolutional network; outputs technique classification probabilities and quantitative scores in parallel; and generates real-time visual correction guidance. Through the above technical solutions, this invention can significantly improve the recognition accuracy of complex brushwork techniques and provide scientific quantitative evaluation and personalized teaching feedback.

A method for implementing a brush stroke of an electronic whiteboard marker, a storage medium, and an electronic whiteboard are disclosed. The method includes: obtaining touchpoint coordinates in a writing process, and constructing a Bézier curve equation based on the touchpoint coordinates; dividing a handwriting curve into continuous handwriting units equidistantly based on the Bézier curve equation; connecting adjacent ones of the handwriting units to form a closed compensation zone; and filling the compensation zone with a handwriting-related color. In this way, different brush strokes such as horizontal, vertical line, left-falling, and right-falling strokes can be formed, and a toothed border formed by superposition of the handwriting units can be effectively covered, making a boundary contour smoother.

The application provides a robot painting skill learning method, system, electronic equipment and storage medium, and belongs to the technical field of artificial intelligence, and comprises the following steps: searching in a painting primitive library based on a target painting requirement to obtain a plurality of target painting primitives; the painting primitive library comprises a plurality of painting primitives, and the painting primitive comprises a brush stroke sequence; combination transformation parameters of the target painting primitives are determined, all the target painting primitives are combined according to the combination transformation parameters to obtain a target painting scheme; and painting control instructions corresponding to the generated target painting scheme are sent to a target robot. The application comprehensively learns painting skills by constructing a painting primitive library, searches for target painting primitives comprising brush stroke sequences, and combines the target painting primitives based on combination transformation parameters to generate a target painting scheme, so that new painting works can be created by using the mastered painting skills.

The application discloses an art work analysis method and a terminal. Art work data input by a user is received and preprocessed, and a convolutional neural network is used to extract multi-level art features from the preprocessed art work data, so that multiple art key features of the art work, such as composition features, color features and brush stroke features, can be effectively extracted. Furthermore, multi-dimensional analysis results are generated according to the art key features, the analysis of the art work can be performed according to user requirements, and intelligent and interactive analysis of the art work is realized.

The application discloses an infrared motion capture-based large painting interaction method and device, and relates to the technical field of human-computer interaction.The method comprises the following steps: based on an ultrahigh-definition large display terminal and an infrared motion capture system, collecting user skeletal joint data, and generating a screen interaction cursor coordinate sequence; recognizing the motion characteristics of a gesture action, determining an interaction intention, and generating an operation instruction; when a focusing instruction is recognized, intercepting image data to be segmented; calling an improved cuckoo catfish optimization algorithm to optimize the optimal threshold parameter set of image segmentation; using an image segmentation model to disassemble the image data to be segmented into brush stroke layer data, ink color layer data, and seal layer data; and fusing and rendering the brush stroke layer data, the ink color layer data, and the seal layer data with preset painting analysis information, and performing layered and superimposed display.The application solves the problems of low interaction precision, single intention recognition, and poor local detail layering and analysis capability of large paintings in the prior art.

The invention discloses a rapid manufacturing method of a medium-sized figure sculpture pattern, and relates to the technical field of sculpture manufacturing. According to the method, a three-dimensional initial model is generated by adopting multi-modal input, parameterization constraint and AI self-iteration, and the problem of proportion imbalance of AI modeling is solved; a three-dimensional standard model is optimized through layering carving, traditional stroke mapping and physical simulation, digital carving and handwork art texture are achieved, a partitioning scheme is designed in a unified mode, and through matching of mechanical positioning, elastic buffering and data association interfaces, the partitioning machining and splicing precision is ensured; and the overall manufacturing is completed through CNC carving, composite gypsum rollover, 3D printing and AR splicing subsequently. According to the method, the problems of low manufacturing efficiency, detail loss, insufficient artistic texture and poor assembly precision in the prior art are solved, the manufacturing period is shortened by 60% or above, the detail reduction degree is larger than or equal to 98%, the model compressive strength is improved by 87%, the assembly error is smaller than or equal to 0.08 mm, and the method is suitable for manufacturing various figure sculptures with the requirements for the artistic effect and the production efficiency.

According to the drawing assisting system and method based on intelligent composition, personalized and dynamic drawing assisting is achieved through cooperation of multiple modules, the stroke position, pressure and speed are monitored in real time, composition complexity and a pressure thermodynamic diagram are calculated, a user concerned area is marked, the user stroke is compared with an art rule base, a three-dimensional lookup table is established, and the drawing assisting effect is achieved. The method comprises the following steps: storing user preferences, historical analysis and general rule coefficients, dynamically switching a local lightweight AI and a cloud deep optimization model, identifying a creation environment through multi-sensor fusion, calculating a fatigue index in combination with stroke pressure, speed and path curvature, providing strength adjustment suggestions, and storing user data by adopting a time sequence database. Through K-means clustering and LSTM behavior prediction, a model is updated in a weekly incremental manner, preference changes are captured, suggestions are optimized through testing, and through multi-dimensional data fusion, dynamic model adaptation and user behavior learning, creation efficiency and an artistic effect are remarkably improved.

The application discloses a digital painting therapy generation system based on dynamic difficulty adjustment and reinforcement learning, and particularly relates to the field of psychological disorder auxiliary treatment, and comprises the following steps: an initialization module establishes a painting task area and configures a task target and difficulty, a closed composition recognition module detects brush stroke stacking and jump retention behavior in the painting process, identifies a closed composition area, and excludes a task point; a task guide module generates an executable task path in a remaining area according to semantic coherence and difficulty order, a cognitive load evaluation module collects emotional response data, identifies a first composition transfer event, and marks a cognitive load upper limit; a strategy network construction module constructs a reinforcement learning strategy model by taking the cognitive load upper limit as input, and a dynamic adjustment module adjusts the path and difficulty in combination with real-time drawing and emotional data, so that a painting task guide mechanism that can be adaptively updated is formed.

The invention relates to the technical field of artificial intelligence, in particular to a painting scoring method and system based on intelligent recognition, and the method comprises the steps: S1, obtaining a to-be-scored painting image, and obtaining the creation description of a painting; s2, extracting multi-dimensional correlation features to obtain multi-dimensional basic features of the painting works and inter-dimensional correlation features among the multi-dimensional basic features; and S3, dynamic attention fusion is carried out, and the dynamic attention fusion is realized based on the quality of the inter-dimension correlation features, so that a fused single-dimension total score can be obtained. According to the method, multi-dimensional basic features of composition, color, stroke and theme of the painting work are extracted through the multi-branch convolutional network, cross-dimensional associated features are obtained in combination with creation description and a feature association mapping mechanism, and the problem of existing intelligent scoring dimension splitting is solved.

The invention is applicable to the technical field of intelligent equipment, and provides a paintbrush drawing method and device, terminal equipment and a storage medium, the method comprises the following steps: when a drawing instruction is generated according to a touch point, marking a color layer and a result layer in an off-screen rendering buffer area as a writable state; reading a historical region texture corresponding to a historical touch point and a current region texture corresponding to a current touch point in the color layer; performing color mixing calculation on the texture of the historical region and the texture of the current region to obtain a mixing result, and writing the mixing result into the color layer; carrying out mixing processing on the mixing result and a predefined paintbrush stroke texture to generate a stroke effect, and writing the stroke effect into the result layer; and outputting the texture content of the result layer to a screen. According to the method, efficient paintbrush drawing can be realized on low-performance hardware equipment, and meanwhile, the paintbrush drawing quality is guaranteed.

This invention relates to a text-driven progressive neural painting method, comprising: performing semantic parsing, spatial guidance, and semantic alignment processing on the acquired text information to obtain multi-level text guidance conditions; employing a three-stage progressive optimization strategy of drafting-coloring-refinement, combined with the multi-level text guidance conditions, sequentially optimizing the brush stroke parameters through structural determination, color application, and detail enhancement to obtain optimized foreground brush stroke parameters; and rendering the optimized background brush stroke parameters and the optimized foreground brush stroke parameters sequentially onto the same canvas using a renderer, outputting a final image that is semantically consistent with the text information and has enhanced details. This method can significantly improve the semantic consistency and visual quality of scalar brush stroke neural painting, filling the technological gap in text-driven scalar brush stroke generation.

Oral hygiene monitoring system is disclosed to track motion and orientation of an oral hygiene device. The control system may process data output from a motion sensor to determine position and orientation of an oral hygiene device with respect to a user's mouth. In some examples, the system may use machine learning techniques to identify position and orientation, brush stroke type, and other specific actions.

The invention belongs to the technical field of image emotion analysis, and particularly discloses a hand-drawn emotion recognition method based on multi-feature fusion and ensemble learning, and the method comprises the steps: carrying out the image preprocessing based on a hand-drawn image, and obtaining a preprocessed hand-drawn image, the image preprocessing being used for removing the noise in the image and enhancing the image; based on the preprocessed hand-drawn image, performing multi-dimensional feature extraction to obtain a color temperature feature, a stroke dynamic feature and a composition space distribution feature; performing cross attention fusion coding based on the color temperature feature, the stroke dynamic feature and the composition space distribution feature to obtain an emotional feature vector; the cross attention fusion coding is used for extracting attention vectors through a plurality of attention paths and carrying out fusion coding on the extracted attention vectors; and based on the emotion feature vector, predicting emotion classification of the hand-drawn image through ensemble learning. According to the invention, the emotion classification of the hand-painted works can be efficiently and accurately identified.

The invention discloses a VR real-time simulation and rendering method for chapping strokes of clear court landscape paintings, and relates to the technical field of digital image processing, and the method comprises the steps: selecting the authentic traces of painters such as Keemun, scanning to obtain an image, extracting the line, ink color and wielding stroke characteristics of chapping methods such as axe chapping, and building a quantitative feature library; constructing a parameterized model based on the feature library, and defining stylus wielding and stylus touch form parameters and a mapping relation; calibrating a VR handle and a virtual canvas coordinate system, capturing a pen wielding track and smoothing the pen wielding track; inputting parameters to generate strokes, and simulating ink color diffusion, white flying and ink accumulation effects of the Chinese art paper; the stroke and the background are fused, and GPU parallel rendering is used to guarantee smoothness; comparing and generating stroke and a feature library, feeding back deviation through vision and tactile sense, and optimizing parameter mapping. Immersive pen wielding simulation is achieved through VR, the Clear chapping technique and ink color levels are precisely restored, real-time feedback and learning planning are provided, rendering is smooth, multiple scenes are adapted, and traditional drawing technique inheritance and efficient teaching are assisted.