309 results about "Stroke order" patented technology

A method for incremental recognition of ideographic handwriting comprises in order the steps of: (1) entering in a natural stroke order at least one stroke of an ideographic character from a computer entry tablet; (2) providing the at least one stroke to an incremental character recognizer, which produces a hypothesis list of at least one candidate character; (3) displaying a hypothesis list of candidate characters containing the at least one stroke; (4) selecting a correct character from among the candidate characters on the hypothesis list if it a correct character appears thereon; (5) entering in natural stroke order at least one additional stroke of the ideographic character from the computer entry tablet if no candidate character is a correct character; (6) providing the additional stroke(s) to the incremental character recognizer, which produces an updated hypothesis list; (7) displaying the updated hypothesis list of candidate characters containing every stroke; (8) selecting a correct character from among the candidate characters on the updated hypothesis list if it a correct character appears thereon; and (9) repeating steps (5) through (8) until a correct character is selected from the updated hypothesis list.

A technique for continuously recognizing a character entry into a computer. In one example embodiment, this is achieved by drawing a character in a continuous stroke order using a stylus [210] on touch screen [220]. As associated data of the drawn continuous stroke order is then inputted into a continuous character recognizer [930] via the touch screen [220]. One or more hypothesis candidate characters including the continuous stroke order are then produced by the continuous character recognizer [930] upon a partial recognition. The produced one or more hypothesis candidate characters are then displayed substantially over the drawn continuous stroke order on a display device [230].

Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed.

The invention discloses a method and a device for performing standardability judgment of character writing operation of an electronic device. The method includes: S1, obtaining stroke information of standard characters, wherein the stroke information comprises number of strokes contained in the characters, inter-frame structure information and stroke tracks, stroke types, stroke sequences and stroke directions of the strokes, and the stroke tracks are composed of dot matrixes contained by the current strokes and represented in a coordinate sequence mode; S2, obtaining stroke information of handwriting characters, wherein the stroke information of the handwriting strokes are the same as that of the standard characters in formation; S3, judging whether stroke orders, strokes, inter-frame structures and stroke numbers of the handwriting characters are in accordance with the standard according to the stroke information of the standard characters; S4, comprehensively judging whether writing of the handwriting characters are in accordance with the standard according to the judgment results. By means of the method and the device for performing standardability judgment of character writing operation of the electronic device, whether character writing is in accordance with the standard can be automatically judged, and the problem of character standard judgment of randomly writing can be effectively solved.

The present invention provides processing approach of dynamic Chinese character font library containing write order information. The processing approach includes processing static Chinese character image to extract the strokes and extract the contour and skeleton of each stroke in the write order; tracing the time sequence information of stroke skeleton and time sequence information of the stroke contour in preset policy; and performing sectional curve fitting and time sequence information fitting to convert the input static Chinese character information into dynamic Chinese character data. The present invention may be applied for dynamic display of Chinese characters in various styles and simulating dynamic Chinese character writing process. The present invention has also static zooming and dynamic restoring function of Chinese characters, and is suitable for various fields where dynamic Chinese character display is needed.

A mechanism for allowing a user to prove their identity on touch-based devices employing the use of a touch surface in firmware-controlled environments is discussed. The user may prove his or her identity by entering a series of strokes on the touch-based device to form a word or image. Characteristics of the entered strokes such as stroke order and stroke direction are compared to stored stroke characteristics that were gathered from a drawing of the same word or image during a user enrollment process. If the stroke characteristics comparison is acceptable, the user identity is verified.

System and method for performing Unicode matching for comparing and merging similar data objects having Unicode strings that are equivalent yet not exact matches. Unicode characters are characterized by number of strokes, stroke order, radicals, geometry, phonemes in association with input method editor and keyboard characteristics such as location of a character on an IME or keyboard (or number of GUI interface interactions used in entering the character, e.g., via tapping where “a” on a mobile device keyboard takes 1 tap of a key, “b” takes 2 taps). These characteristics associated with code points and IME's/keyboards are utilized to create subdomains for matching and determining “distance” to other Unicode code points (e.g., number of keyboard keys away). Allows for determining whether close, yet incorrect data entry may have taken place. Enables merging of duplicate data objects into master data object where minor differences or spelling errors introduce actually represent duplicate data.

A method, computer program product, and a data processing system for performing handwriting recognition of a language having character stroke order rules. A stroke parameter set describing attributes of a handwritten stroke is calculated, and a user input indicates a stroke order knowledge. A reference character dictionary includes a record having a plurality of reference parameter sets each defining attributes of reference character strokes. A stroke sequence number of the stroke parameter set is identified and at least one of the reference parameter sets are excluded from a comparison with the stroke parameter set based on the stroke sequence number.

The invention relates to a portable language learning system and provides a Chinese learning system, aiming at the defects that the existing portable Chinese learning system can not meet a Chinese learner to learn the Chinese systematically and completely by self under the condition without the base of Chinese completely. The system comprises a hand-held computer system and a Chinese learning software package; wherein, the hand-held computer system comprises a central control unit, a touch screen and a loudspeaker and also comprises a character font module used for storing Chinese characters and attribute information of each Chinese character, a character-inquiring module used for receiving character-inquiring instructions sent by the central control unit and inquiring and displaying the character, and an explaining module which is connected with the central control unit and is used for receiving explaining instructions sent by the central control unit and inquiring and playing or displaying the attribute of the character. An animation mode is used for displaying the stroke order of the character vividly so as to help a user to master the correct method for writing the character; and a pronouncing schematic diagram mode is used for showing how to pronounce so as to help the user to spell and read the character correctly.

The embodiment of the invention provides a text information identification method and identification device. The method comprises the steps of obtaining a to-be-processed UGC text; preprocessing the UGC text to obtain a stroke order feature vector and a pinyin feature vector of the UGC text; and inputting the stroke order feature vector and the pinyin feature vector into a pre-trained text recognition model to obtain a target type recognition result of the UGC text. According to the embodiment of the invention, the target type of the UGC text can be accurately identified, so that the bad UGC text can be identified more accurately.

The invention relates to a painting and writing method with a self-learning function, which comprises the following steps of: dividing a painting and writing object into a stroke set with a stroke order and storing the stroke set into a computer database; reading current stroke data in the stroke set for outputting a voice prompt; inducting the position coordinate change during writing and painting by a writing and painting pen and recognizing a generated stroke according to the position coordinate change; then comparing the generated stroke with the current stroke data; if the generated stroke is not consistent with the current stroke data, outputting an error voice prompt and repeating the step; otherwise, outputting a correct voice prompt, turning to the next stroke and repeating the step till the next stroke is null; writing and painting on a medium by the writing and painting pen during writing and painting and retaining chirography. The method can be used for automatically prompting users to paint and write on the basis of the traditional painting and writing and inspecting the practical painting and writing result, thereby greatly meeting the child character/painting self-learning requirement.

The invention discloses a Chinese character writing exercising method, which is characterized in that the writing exercising method comprises the splitting of Chinese characters according to writing stroke orders and the marking of strokes in different writing order with different colors. The strokes of a Chinese character are split according to the writing order, different strokes are marked with different colors, and the Chinese character writing exercise can be realized by portraying along the stroke order that is marked with colors. The Chinese character writing exercising method combines novel, interest and scientific Chinese character writing exercise into one, and not only can lead Chinese character writing exercisers to definitely understand and learn correct Chinese character strokes, but also can increase the interest of the exercising and studying process; copybooks of the Chinese character writing exercising method have concise structure and simple production, and are convenient for Chinese character writing exercisers to portray or write with reference.

The invention relates to a technology for judging the normalization of handwritten Chinese character stroke position, in particular to a method and a device for judging the normalization of the handwritten Chinese character stroke position. The method for judging the normalization of the handwritten Chinese character stroke position comprises the steps of obtaining the strokes of handwritten Chinese characters, obtaining a vector that the starting point of the No. k stroke according to the direction of the stroke order of a handwritten Chinese character points to the starting point of the No. (k-1) stroke according to the direction of the stroke order; obtaining the vector that the starting point of the No. k stroke according to the direction of the stroke order of a Chinese character of a standard-word-base corresponding to the handwritten Chinese character points to the starting point of the No. (k-1) stroke according to the direction of the stroke order, calculating an included angle theta between the vector of the handwritten Chinese character stroke and the vector of the Chinese character stroke of the standard-word-base, and judging whether the included angle theta is within a preset error range delta theta, if so, the stroke position of the handwritten Chinese character is standard, otherwise, the stroke position of the handwritten Chinese character is non-standard. The technical proposal of the invention can identify the situation of incorrect writing stroke order of the handwritten Chinese characters with the same strokes and stroke features.

The invention provides a character similarity judgment method and device and belongs to the Internet technical field. The method includes the following steps that: a first character sequence to be detected and a second character sequence to be detected are acquired; a first stroke order sequence and a second stroke order sequence are obtained, wherein the first stroke order sequence is strokes in the first character sequence arranged according to a writing order, and the second stroke order sequence is strokes in the second character sequence arranged according to a writing order; a minimum edit distance between the first stroke order sequence and the second stroke order sequence is obtained, wherein the edit distance is the number of the times of transformation operation required by the transformation of the first stroke order sequence to the second stroke order sequence; and the similarity of the first character sequence and the second character sequence is obtained. According to the method and device of the invention, based on the similarity of stroke order sequences, the similarity of corresponding character sequences can be obtained, and therefore, the similarity of characters can be automatically judged, human resources can be saved, and the objectiveness of the judgment of character similarity can be enhanced.

The invention discloses a Chinese counterfeit domain name detection method and a Chinese counterfeit domain name detection system, which are suitable for detecting Chinese counterfeit domain names formed by using similar Chinese characters. The Chinese counterfeit domain name detection system comprises a domain name preprocessing module, which is used for counting length and a total stroke number of every input domain name; a target domain name filtering module, which is used to compare the lengths and the total stroke numbers of the to-be-detected domain names and that of the target domain names, and is used to filter target domain names of a possibly-imitated target domain name set; a domain name disassembling module, which is used to disassemble the to-be-detected domain names and the filtered target domain names correspondingly into single Chinese characters; a single character similarity calculation module, which is used to convert the Chinese characters into character strings of stroke orders, and is used to calculate single character similarity based on character string editing distance; a domain name similarity calculation module, which is used to calculate the similarity of the integral domain name based on the single character similarity; and a counterfeit domain name decision module, which is used to determine and output the most possibly-imitated target domain name based on the domain name similarity. By adopting the above mentioned method and the above mentioned system, the Chinese counterfeit domain names formed by using the similar Chinese characters are effectively identified, and a wide application prospect is provided in a network safety field.

The present invention relates to a set of multi-media Chinese character educational software system utilizing handwriting input recognition technique, speech synthesis technique and Chinese character dynamic stroke order display technology and a new type Chinese dictionary indexing system. The system can be used handwriting recognition technique and speech synthesis technique to implement self-helping evaluation test, intelligent speech tutor and handwriting emulation, and the user can freely select the required learning contnets according to the prompting of system or can utilize handwriting input equipment to input learning contents. The system also can display the normalized Chinese character writing stroke order, and can make speech output, at the same time can utilize input modes of handwriting input and keyboard input to index the dictionary contents according to the user-selected contents.

A multiple dimensional Chinese studying system of the invention belongs to a language studying method, the system comprises a computer host, a data storage device mounted in the computer host, and an input device, the data storage device includes: a pinyin module, a character learning module, a dictionary word looking up module; the studying method is firstly studying initial consonant, final consonant, total reading, spelling of syllables and four tones of Chinese pinyin, then studying five basic strokes composing Chinese characters, stroke order, and structure, studying parts composing Chinese characters and single-part, composite-part characters composed by the parts, further performing part coding exercise. The invention has advatages of simple, easy to study, easy to memorize, easy to use, and accorded with a studying rule of the Chinese characters. The new Chinese studying system realizes characteristics of man-machine integration, accepting interaction, having meaning and interest, etc.

The invention relates to a handwritten Chinese character input method and an electronic device with the same. The handwritten Chinese character input method comprises the steps of obtaining handwritten input operation strokes; recognizing stroke types, positions and stroke orders formed by handwritten input operation tracks; encoding the recognized stroke types, positions and stroke orders; and performing corresponding Chinese character screening and Chinese character display arrangement according to encoding information of the strokes. According to the method, the Chinese character strokes can be sequentially input in a handwritten mode, corresponding candidate characters are displayed by fully utilizing every stroke input by users, complete Chinese characters do not need writing, input operation by the users can be saved, and the handwritten input speed is improved.

The invention relates to a multiple building block type interactive Chinese character input method, which comprises the steps of: taking first strokes of radicals as a basis, classifying the radicals of Chinese characters into five classes, namely, the horizontal character stroke, the straight down character stroke, the slanting stroke towards the left, the spot and the stroke with a bend or twist; and retrieving the radical of each group according to the order of strokes or retrieving related words according to preset radicals in a preset interface. In the input method, an encoding frame, a Chinese character pre-selection area, a radical display area, a radical index area and a stroke index area are set, wherein the encoding frame displays input codes which are the radicals and the strokes; the Chinese character pre-selection area dynamically displays candidate Chinese characters or word groups related to the input Chinese characters; and the radical display area dynamically displays the Chinese characters, and radicals and strokes of the Chinese characters which are all predefined and correspond to basic strokes. The Chinese character input method does not need to remember a great number of Chinese character input rules, and can adopt multiple input modes flexibly to input the Chinese characters, so the Chinese character input method is intuitive, simple, quick, convenient and easy to learn.

The invention relates to a method to build up random stoke order database and a evaluate system of online hand writing character recognition technology. The invention comprises the collection of standard sample database and the creation of random stoke order database. The evaluating system comprises: storage device used to store standard sample database and random order stoke database; collection module used to collect standard sample database; conversion module used to converse the online character stoke data into a two-value image; separating module used to separate at least one section form the two-value image according to the connection of the stoke; a creation module that includes a unit to disturb the stokes of every section and a unit to disturb the order of the sections.

Disclosed are a device and method for editing ink text data. More specifically, a device for editing digital ink data displayed on a display includes a stroke order rearrangement processing unit configured to rearrange an input order of two or more strokes on the basis of a predefined criterion to generate a rearranged input order when receiving a user input including the two or more strokes, a data generation unit configured to generate digital ink data corresponding to a rearrangement stroke reflecting the rearranged input order, and an editing unit configured to change the digital ink data displayed on the display when an editing signal is generated. Thus, a user can intuitively and easily perform the editing operation, such as update, deletion, and insertion, on digital ink data displayed on a screen, and thus feel satisfaction.

Disclosed is a kanji stroke order learning device including a kanji part stroke order storage unit which stores a plurality of stroke order data of kanji parts, a kanji part combination storage unit which stores kanji and kanji parts included in the kanji in association to each other, a kanji specifying unit which specifies any kanji as a specified kanji, a stroke order input unit which inputs stroke order of the specified kanji, a kanji part stroke order determination unit which determines whether the stroke order of the specified kanji input by the stroke order input unit is correct or incorrect for each kanji part included in the specified kanji, and a kanji part stroke order correct/incorrect display control unit which displays a determination result obtained by the kanji part stroke order determination unit for each kanji part included in the specified kanji.

The invention discloses a teaching tool for writing characters and a use method thereof. The teaching tool is provided with a plurality of writing points on general grid line paper, wherein the writing points are arranged according to strokes and stroke orders of the characters and comprise stroke starting points and pen putting points of strokes, turned strokes, turning points and writing points of different strokes; and the writing points are distinguished by adopting different symbols. According to the use method, the sequential writing is carried out according to the stroke orders of the characters; and each stroke is started to write from the stroke starting point, passes through the turning point and is ended by a stroke ending point. Learners can learn to write standard characters through a mode of connecting the writing points, and repeatedly practice until the learners learns to grasp standard writing modes of various characters by using a method for judging positions by using points, so as to write standard characters under the conditions of separating from the grid lines.