38 results about "Scribble" patented technology

A computer-implemented method for assigning attributes to an image. The method comprises allowing a user to mark a plurality of pixels of an image as a single marked area by a single scribble, the single marked area defines, for a current iteration, a target attribute, determining according to the target attribute an optimal function that defines at least one respective attribute of pixels in the image, assigning the at least one respective attribute to pixels in the image according to the optimal function, and displaying the at least one attribute of the pixels.

An interactive segmentation framework for 3-D teeth CT volumetric data enables a user to segment an entire dental region or individual teeth depending upon the types of user input. Graph cuts-based interactive segmentation utilizes a user's scribbles which are collected on several 2-D representative CT slices and are expanded on those slices. Then, a 3-D distance transform is applied to the entire CT volume based on the expanded scribbles. Bony tissue enhancement is added before feeding 3-D CT raw image data into the graph cuts pipeline. The segmented teeth area is able to be directly utilized to reconstruct a 3-D virtual teeth model.

This invention is about drawing cafe that separate indoor playgrounds and dining room spaces in the cafes, but allows visitors to see indoor playgrounds in the restaurants. The interior wall of the indoor playground is equipped with a drawing wall that can wipe the paint off with water and a blackboard for drawing or scribbling with chalk and parents in the restaurant can observe or monitor their own children playing in the indoor playground. It is the drawing cafe that allows children to move from a static environment of sitting back and painting to a dynamic play where they can mingle independently without parental interference and run around and paint as much as they want. And the composition is composed of indoor playgrounds and restaurants separated by compartment walls, and the above indoor playgrounds are constructed with drawing wall that allows children to draw or play with paint on one inner wall. The compartment wall is constructed for viewing indoor playgrounds from the restaurant by glass windows at the top, the lower side of the compartment wall has other inner walls of the indoor playground (112), and the other inner walls of the indoor playground have blackboards (114) along the length direction, allowing children to paint or scribble with chalk.

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 invention discloses a multimedia interactive system and method based on preschool education. The method comprises the steps that the content of an image is recognized, wherein the image is from static images drawn through a magic whiteboard in a touch control handheld device or a touch control desktop device; a portion material is manufactured according to the recognized content; prefabricated animations are extracted from an animation library according to the recognized content; corresponding portions of the prefabricated animations are endowed with the manufactured material to guarantee that the obtained is the drawn; finally formed intelligent animations are displayed through a screen; Kinect computer external equipment is connected, and voice interaction with the intelligent animations is performed through the Kinect; gesture interaction with the intelligent animations is performed through the Kinect; and a touch control screen is connected, and interaction with the intelligent animations can be performed through the touch control screen. By adoption of the multimedia interactive system and method based on preschool education, kids can let imagination run wild fully and draw what the kids want; and meanwhile, seeing that the drawn static images are changed into the voice or gesture interactive animations, the kids can learn associated knowledge through interaction with the animations.

The invention discloses a dual-position multipurpose smart pen and a method of using the same, belonging to the field of smart pens. A dual-position multi-purpose smart pen and a method of using the same include a pen shell, which includes a rear half shell and a front half that are mutually adsorbed The main control board is embedded in the end of the rear half shell, and the main control switch matched with the main control board is installed on the outside of the rear half shell. The main control board includes a wireless transmission module, a wireless receiving module and a processing module. This scheme An erasable water-soluble pen and a pressure-sensitive pen are installed inside the smart pen for writing on smart paper notebooks and electronic boards, which realizes paperless writing and saves environmental protection. Correct typos and bad habits of writing scribbles in real time. Voice prompts can be provided when encountering words that you cannot remember, which improves the learning efficiency of multilingual words such as Chinese and English. In addition, when children use smart pens, the sensor can retract the refill at any time. , protect the refill and also protect children.

The present invention relates to scribble matching methods. The invention entails the identification and encoding of velocity minima in the input scribble. Three scribble matching algorithms are described: a syntactic matcher, a word matcher and an elastic matcher. The syntactic matcher encodes the input scribble according to the shape of the scribble in the region of the velocity minima. The word matcher encodes the input scribble according to the heights of the velocity minima from a reference line, using a continuous height encoding scheme. The elastic matcher encodes the input scribble according to a classification of the velocity minima and intermediate points.

The invention discloses a method for automatically processing test paper answer sheets based on machine learning. The method is: first train the graffiti target detector; then determine the format of the test paper, generate the test paper and print it; the examiner and the reviewer fill in the corresponding area, the tester scribbles the answer area of ​​the objective question and the answer area of ​​the subjective question, and the reviewer reviews the subjective question and writes the corresponding area Then scan the completed test paper as an image, perform image processing and sub-area cutting; use the trained graffiti target detector to judge the target, and then calculate the score combined with the correct answer; finally, make statistics and analysis on the test paper: including Calculate the average score of the whole batch of test papers and the average score of each topic; calculate the distribution of the whole batch of test papers and each topic; conduct trend analysis, and retrieve the answer part from the database for teachers or individuals to check. The invention has the advantages of low cost, high precision and good flexibility, and can efficiently count and analyze the answers to the test papers.

The invention provides a color painting creation method based on image semantic extraction and doodles; the method can immigrate semantic styles into a doodle image, thus further converting into an exquisite color painting; the method collects existing color painting materials, tags semantics in the material images, uses the semantics to form a doodle image, and uses a style immigration technology combining a Markov Random field with a convolution neural network to obtain an exquisite color painting with fused material image style and doodle semantics. The method can reduce the drafting time of a painter repeatedly drafting a same topic, can fast change the composition while keeping the original style, and can provide color painting inspirations, thus solving the color painting supply and demand imbalance pain spot in certain level.