8338 results about "Chinese characters" patented technology

The invention discloses a locomotive license automatic identifying method and a realizing device thereof for shooting video in real time under a complex background; wherein, the identifying steps include: (1) locating a movement multi-target locomotive body area; (2) capturing a candidate license area image; (3) capturing a real license edge point; (4) capturing the smallest license area; (5) dividing characters and removing non-character images;(6) normalizing the character images and extracting the original coarse gridding characteristics of the character images; (7) using a trained BP neutral network for realizing the accurate identification of the license characters. The device for realizing the locomotive license automatic method includes a pick-up device and a computer; the pick-up device is connected with the computer by an IEEE1394 cable. The invention is suitable for the automatic identifying method and the realizing device thereof for dividing and identifying the locomotive licenses which are not interfered by the shoot traffic video image quality under a complex background with good identifying effects to the characters.

A method and apparatus for inputting Chinese character text into a machine such as a word processor or personal computer. The system consists of an apparatus which forms a closed feedback loop with the operator. The operator supplies stroke selections and other data to the apparatus which presents character selection information in response to the user's input. As a consequence of the feedback provided to the operator and subsequent actions by the operator, the desired Chinese text is produced with significant improvements in speed and ease.

The invention discloses a license plate detection method based on a convolutional neural network. The method specifically includes the steps that an Adaboost license plate detector based on Haar characteristics detects license plate images to be detected, license plate roughing regions are acquired, a convolutional neural network complete license plate recognition model recognizes the license plate roughing regions, a final license plate candidate region is acquired, the final license plate candidate region is segmented through a multi-threshold segmentation algorithm, license plate Chinese characters, letters and numbers are acquired, a Chinese character, letter and number convolutional neural network recognition model recognizes the license plate Chinese characters, letters and numbers, and then a license plate recognition result is acquired. License plate images under different conditions can be accurately recognized through the Adaboost license plate detector based on the Haar characteristics and the convolutional neural network complete license plate recognition model, meanwhile, characters are segmented through the multi-threshold segmentation algorithm, character images can be more easily and conveniently segmented, and the good effect is achieved in engineering application.

Calculates a word n-gram probability with high accuracy in a situation where a first corpus), which is a relatively small corpus containing manually segmented word information, and a second corpus, which is a relatively large corpus, are given as a training corpus that is storage containing vast quantities of sample sentences. Vocabulary including contextual information is expanded from words occurring in first corpus of relatively small size to words occurring in second corpus of relatively large size by using a word n-gram probability estimated from an unknown word model and the raw corpus. The first corpus (word-segmented) is used for calculating n-grams and the probability that the word boundary between two adjacent characters will be the boundary of two words (segmentation probability). The second corpus (word-unsegmented), in which probabilistic word boundaries are assigned based on information in the first corpus (word-segmented), is used for calculating a word n-grams.

The invention discloses a vehicle license plate character recognition method based on rough grid feature extraction and a BP neural network. The method comprises the following steps: (1). preprocessing a vehicle license plate image to eliminate various interferences and obtain a minimum vehicle license plate region; (2). segmenting the vehicle license plate characters by combining vertical projection and a drop-fall algorithm; (3). screening the segmentation results to eliminate interferences of vertical frames, separators, rivets and the like; (4). normalizing the characters according to the position of a centre of mass; (5). taking each pixel of a normalized characters dot-matrix as a grid to extract the original features of the characters; (6). designing the BP neural network with a secondary classifier according to the situation of the vehicle license plate; and (7). reasonably constructing a training sample database to train the neural network, and adjusting the training samples by the recognition effect to realize accurate recognition of the network. The method effectively eliminates the noise interference, quickly and accurately segments the characters, steadily and effectively recognizes Chinese characters, and realizes the balance between real-time property and accuracy in the whole recognition course.

An operation interface for instant messages (IM) on a portable communication device is provided. In method of implementing such interfaces, the contacts or IM systems are organized and sorted. In addition, a counter can be set to record of the number of times an incoming message is received or an outgoing message is sent for each contact and / or to record the number of messages that are read or unread for each contact. The sequence order of contacts can be rearranged according to a predefined sort preference for display on the screen of the device. The user may specify the sort preference to be by display name, date last contacted, most frequent contacts, relationship, company, etc. The user may also specify the sort preference to display names in order alphabetically, by stroke number or when expressed in Chinese characters, or in Pinyin order when expressed in Pinyin.

A method and apparatus for character entry and more particularly Chinese character entry. The method improves the ease of entry for Chinese characters on a device that has a keypad arrangement of at least a 3×3 matrix (106). For example wireless communication devices such as radiotelephones have a keypad (108) for dialing phone numbers. Arranging the Chinese characters on the device display in a 3×3 matrix to match the at least 3×3 matrix of the keypad allows the user to quickly select from the pin yin list (104) the key on the keypad that corresponds to the desired character in the matching matrix.

A convenient form of text editing in a camera device utilizing complex character sets is disclosed. The device includes a digital camera device able to sense an image; a manipulation data entry card adapted to be inserted into the digital camera device and to provide manipulation instructions for manipulating the image, including the addition of text to the image; a text entry device for the entry of the text which includes a series of non-roman font characters utilised by the digital camera device in conjunction with the manipulation instructions so as to create new text characters for addition to the image. The font characters are transmitted to the digital camera device when required and rendered by the camera in accordance with the manipulation instructions. The non-roman characters can include at least one of Hebrew, Cyrillic, Arabic, Kanji or Chinese characters.

A system and method for inputting Chinese characters using Pinyin without requiring the entry of a delimiter key between Pinyin entries in a reduced keyboard is disclosed. The system searches for all possible single or multiple Pinyin spellings based on the entered Latin alphabets. Once the user has completed the inputting of the Pinyin spellings for desired Chinese phrase or characters, all possible matching phrases or characters are displayed on screen and off-screen due to screen size. The user then scrolls through a list of matching phrases or characters and selects the desired one by clicking.

The invention discloses a microblog user interest recognizing method based on text mining, and belongs to the field of text mining and natural language processing. The method includes the steps of collecting the newest topical microblog text data of a microblog text set and microblog text data of a designated user, standardizing the collected microblog text data, recognizing the newest microblog words and renewing a new word dictionary for the standardized topical microblog text data through the microblog new word recognition method, conducting Chinese character word separation on the standardized microblog text data of the designated user through the new word dictionary word separation method to achieve text vector expression, clustering the microblog text data, expressed through text vectors, of the designated user, recombining original microblog text data, extracting new text set features through a topic model, presetting topic dictionaries, calculating the weight of each topic dictionary based on the new text set features to obtain the final topic, and enabling the final topic to serve as the microblog user interest recognition, thereby improving accuracy of feature extraction.

The invention discloses a character segmentation method and a character segmentation device, which can recognize character unit image blocks containing touching characters and character unit image blocks containing components and radicals, and assure the correctness of the character segmentation result. In the technical proposal of the invention, a plurality of character unit image blocks are obtained by making line segmentation and column segmentation to a text image, character unit image blocks containing touching characters are recognized and continue to be segmented, Chinese character unit image block areas and English character unit image block areas are recognized, character unit image blocks occupied by components and radicals of Chinese characters are recognized in the Chinese character unit image block areas, and character unit image blocks occupied by components and radicals of adjacent Chinese characters are merged into a character unit image block. The invention ensures that the character segmentation result does not depend too much on a character recognition feedback mechanism and further improves the recognition rate of the characters.

The invention discloses an automatic generation method for a handwritten Chinese font library based on a deep neutral network. The method is characterized in that font characteristics are reconstructed through a small number of handwritten Chinese characters; a font style migration network is established; and font style characteristics of font forms not handwritten by a user are estimated throughthe font style migration network, font form contents of a reference font are combined with a handwriting style of the user to achieve migration to a target handwriting style, and target font form pictures are generated, so that the complete handwritten Chinese font library is obtained. The method provided by the invention has the advantages that the method is an end-to-end generation method, and high-quality Chinese font forms are generated without extraction of strokes or components of Chinese characters or manual intervention, so that the handwritten font library creation efficiency is greatly improved, the generation of a personalized font library becomes simple and convenient, the requirement of ordinary people for the personalized handwritten font library can be met, and the development progress of the personalized font library can be accelerated.

The invention relates to a realization method and system for electronic medical record post-structuring and auxiliary diagnosis. A combination mode of multiple types of distance measurement is used: a character string editing distance refers to a minimum number of replacement, insertion and deletion operations required for converting a character into another character string; a Jaro-Winkler distance measures similarity between two character strings and is used for repeated recording detection; a geometric mean value of a Chinese character distance and a Chinese character input method is adopted as comprehensive similarity measurement for measuring similarity between characteristic texts; characteristic ranking is realized by using a TF-IDF method and is used for assessing the importance of characteristic terms relative to documents in a file set or a corpus library, and the importance of the characteristic terms is in direct proportion to an occurrence frequency in the documents and is in inverse proportion to an occurrence document in the corpus library; and files are converted to be in a file format of PU learning of a positive example data set and an unlabelled data set according to the generated characteristic terms, and through the PU learning, the system automatically recommends related diagnoses for clinical medical personnel to refer.

A system and method for inputting Chinese characters using phonetic-based or stroke-based input method in a reduced keyboard is disclosed. By introducing common indices to ideographic characters, the system allows the ideographic characters to be shared among different type of input methods such as phonetic-based input method and stroke-based input method. The system matches input sequences to input method specific indices such as phonetic or stroke indices. These input method specific indices are then converted into indices to ideographic characters, which is then used to retrieve ideographic characters.

A handwritten Chinese character input method and system is provided to allow users to enter Chinese characters to a data processor by adding less than three strokes and one selection movement such as mouse clicking or stylus or finger tapping. The system is interactive, predictive, and intuitive to use. By adding one or two strokes which are used to start writing a Chinese character, or in some case even no strokes are needed, users can find a desired character from a list of characters. The list is context sensitive. It varies depending on the prior character entered. Compared to other existing systems, this system can save users considerable time and efforts to entering handwritten characters.

The invention discloses a fingerprint identification device and a fingerprint identification method with prompt information. The method comprises the steps of sampling a fingerprint grayscale image in a dot interlace mode, and representing a local texture direction of the dot interlace at each pixel point in the original fingerprint grayscale image by using a point direction map; dividing the point direction map into blocks, and dividing each block into a foreground block or a background block; calculating a ratio of the active area of the foreground map to the area of the whole image, performing image quality analysis if the active area meets the requirements, calculating a ratio of the advantage direction area to the fingerprint foreground area if each point in the foreground image block has direction advantages; performing finger arrangement position analysis if the image is preliminarily determined to be qualified; and if the finger arrangement position is inaccurate, performing finger position deviation analysis, and if the image is unqualified, performing fingerprint dryness / humidity analysis. When the fingerprint is not clear or the operation is improper, the Chinese character prompt information is adopted, the finger arrangement position deviation and finger dryness / humidity conditions can be accurately judged, and the success rate of fingerprint identification is improved.

The invention discloses a character detection method and a device. The character detection method comprises steps of receiving image to be detected, generating a character area probability graph of the whole text of the image to be detected which is generated by a semantic prediction model, wherein the character area probability graph uses different the pixel value area to distinguish the Chinese character area of the image to be detected and the non-Chinese character area of the image to be detected and performing segmentation operation on the probability graph of the Chinese character area in order to determine the Chinese character area. The Character detection method disclosed by the invention can detect the characters of various languages, directions, colors, fonts and sizes while effectively inhibiting the interference of the complex background. Besides, the Chinese character detection method and the device have characteristics of strong robustness and effectively resisting the interferences of the image noise, image fuzziness, the complex image background and the non-uniform light irradiation.

The invention relates to a polyester flax-like type different shrinkage composite yarn and a preparation method thereof. Firstly, a modified polyester yarn POY and a modified polyester yarn FDY are prepared respectively, then the modified polyester yarn POY and the modified polyester yarn FDY are compounded to prepare the polyester flax-like type different shrinkage composite yarn; the chromatic aberration [delta]E of the prepared polyester flax-like type different shrinkage composite yarn is less than 0.200; a bundle of the yarn POY or FDY extruded by a same spinneret plate contains a singleyarn shaped in a Chinese character 'wang' manner and a five-leaf single yarn; a molecular chain of modified polyester consists of a diol chain segment with a branched chain, and diol with the branchedchain has the structural formula defined in the specification, wherein R1 and R2 are straight-chain alkylene with the carbon atom number of 1-3 , R3 is alkyl with the carbon atom number of 1-5, and R4 is alkyl with the carbon atom number of 2-5. The method is simple and reasonable, and the prepared composite yarn has good fluffy property and moisture absorption and perspiration elimination properties.

Disclosed is manufacturing equipment for a round-head T-shaped pile. The lower end of a drill rod is fixed to the upper end of a motor. A speed changing box is arranged at the lower end of the motor. A first rotating shaft, a second rotating shaft, a third rotating shaft and a fourth rotating shaft are arranged at the lower end of the speed changing box. The lower end of each rotating shaft is provided with a drill bit. A first arm shaped like a Chinese character 'gan' and a second arm shaped like the Chinese character 'gan' are symmetric. A plurality of second stirring cutters are arranged on the left and right sides of the first arm shaped like the Chinese character 'gan'. A plurality of first stirring cutters are arranged at the lower end of the first arm shaped like the Chinese character 'gan'. A plurality of second stirring cutters are arranged on the left and right sides of the second arm shaped like the Chinese character 'gan'. A plurality of first stirring cutters are arranged at the lower end of the second arm shaped like the Chinese character 'gan'.

The invention relates to a method, which comprises: performing class encapsulation on each display unit of a display wall, and performing class encapsulation on lines drawn by a light pen each time; using data members to record general attributes such as stroke color, stroke thickness and the like of a certain display unit object in a display unit class, and arranging a line container inside the display unit to store the drawn lines; and judging the position of a coordinate point of a first stroke of a Chinese character first and then processing the stroke attribute according to the position of the coordinate point of the first stroke of the Chinese character under the condition of drawing a line from the first stroke of the Chinese character. The invention provides the method capable of supporting the arbitrary alteration of the attributes such as label and written stroke in a large-screen display wall system by people simultaneously. The invention not only can realize the maintenance and alteration of the attributes such as the stroke color and the stroke thickness of lines on the current screen but also can realize the maintenance of the stroke attributes of the lines in the whole display wall positioning system under the condition of cross-screen writing and labeling.

The invention provides an identification method to identify Chinese printed formula, including analysis of typeface, character recognition and mathematical formula recognition three modules; typeface analysis module two-value pretreats BMP images, split out literal block, image block and list block using projection method combined with bottom-up typeface analysis algorithm, preserve image block and list block; Chinese character recognition module false merge rows against literal block, select segmentation parameters, extract characteristics and recognize Chinese characters, record the rejected results, combine adjacent rejected results in the same row in order to locate formula region; mathematical formula recognition is to extract,divide formula characters in the rejected character region, merger some characters and recognize; finally obtain the relationship between characters through structure analysis of formula characters, and output the final one-dimensional character strings. the identification effect of this invention is famous after test.

Provided is a Chinese character handwriting verification system and a method, applied in an electronic information process device, wherein a character database for storing a plurality of Chinese characters and standard stroke sequences corresponding to each Chinese character and handwriting tracks corresponding to each standard stroke. In a handwriting process of a Chinese character, the stroke sequence of the Chinese character and the handwriting tracks of each stroke are detected, and the stroke sequence of the detected Chinese character and the standard stroke sequence corresponding to the Chinese character in the character database are compared, therefore a handwriting error prompt is generated when out of accord, thereby prompting the stroke sequence error of the Chinese character, increasing learning effect of the Chinese character.

The invention belongs to the technical field of vehicle identification and particularly discloses a number plate identification method and an identification system of the number plate identification method. The method comprises the steps of number plate image positioning, character separation and character identification, wherein the character identification step comprises pre-treatment, coarse classification, Chinese character identification and number and letter identification. Through the improvement on a Chinese character identification method (through a Gabor filter and a minimum distance classifier) and a number and letter identification method (based on correlation feature selection (CFS) and a Bayes classifier), the number plate Chinese character identification rate and the number plate number and letter identification rate are greatly improved.

The invention discloses a method for detecting ferrous magnetic material thickness by utilizing electromagnetic ultrasound, and is characterized in that a magnet inside an electromagnetic ultrasound transducer takes a U-shaped permanent magnet, a coil takes a PCB double-layer coil that takes the shape of a Chinese character, 'Hui' and is positioned at an opening of the permanent magnet, and an effective lead part of the coil is parallel to the direction of a bias magnetic field. In thickness measurement, the electromagnetic ultrasound transducer is positioned on a detected object, high-frequency electric sinusoidal pulse current passes through the coil, according to the magnetostrictive effect, the detected object generates partial stretching deformation and oscillation, and consequently excites ultrasonic transverse wave and leads the ultrasonic transverse wave to spread downwards in a direction vertical to surfaces of the detected object. The ultrasonic wave is reflected by a lower surface of the detected object, and then the reflected wave is received by the coil. A received ultrasonic signal is collected and input into a computer after being amplified. If the ultrasonic wave spreading velocity in the detected object is v, and the spreading time is t, then the thickness of the detected object d is equal to a half of v multiplied by t. The method for detecting ferrous magnetic material thickness by realizing the thickness detection of ferrous magnetic materials, has the non-contact and couplant-free advantages, and can be used in high-temperature environment and for detecting materials with rough surfaces.

Text input is corrected on a touch-sensitive display by presenting a list of candidate words in the interface which can be selected by touch input. The candidate list can include candidate words having two or more character types (e.g., Roman, kana, kanji). In one aspect, the candidate list can be scrolled using a finger gesture. When a user's finger traverses a candidate word and the touch is released, the candidate word is inserted into a document being edited. In another aspect, characters can be erased by touching a key (e.g., a backspace or delete key) and making a sliding, swiping, or other finger gesture. A number of characters proportional to a distance (e.g., a linear distance) of the finger gesture across the display are erased. If there are characters in a text input area, those characters are erased first, followed by characters in the document being edited.

The present invention discloses a portable digital mobile communication apparatus with voice operation system and controlling method of voice operation. The feature vector sequences of speech are quantify encoded when the speech is recognized, and in decoding operation, each code in efficiency speech character codes are directly looked up observation probability of on search path from the probability schedule in the decode operation. In association with the present invention, full syllabic speech recognition can be achieved in mobile telephone without the need of training, and input Chinese characters by speech and speech prompting with full syllable. This system comprises semantic analysis, dialogue management and language generation module, and it can also process complicated dialog procedure and feed flexible prompting message back to the user. The present invention can also customize speech command and prompting content by user.

The invention discloses a Chinese domain term recognition method based on mutual information and a conditional random field model. The Chinese domain term recognition method includes the following steps: (1) gathering domain text corpus and marking all the punctuations, spaces, numbers, ASSCII (American Standard Code for Information Interchange) characters and characters except Chinese characters in the corpus; (2) setting character strings and computing the mutual information values of the character strings, (3) computing the left comentropy and the right comentropy of every character string, (4) defining character string evaluation function, setting evaluation function threshold, computing the evaluation function values of every character string, determining that every character string is a word, comparing in sequence the evaluation function value of the former character with the evaluation function value of the latter character in the character string and segmenting character meaning character strings one by one, (5) utilizing conditional random fields to train a conditional random field model and recognizing domain terms with the conditional random field model. When the Chinese domain term recognition method is used to recognize terms, the data sparsity of legitimate terms is overcome, the amount of calculation of conditional random fields is reduced, and the accuracy of the Chinese domain term recognition is improved.

The invention discloses a text classification method based on feature information of characters and terms. The method comprises the steps that a neural network model is utilized to perform character and term vector joint pre-training, and initial term vector expression of the terms and initial character vector expression of Chinese characters are obtained; a short text is expressed to be a matrixcomposed of term vectors of all terms in the short text, a convolutional neural network is utilized to perform feature extraction, and term layer features are obtained; the short text is expressed tobe a matrix composed of character vectors of all Chinese characters in the short text, the convolutional neural network is utilized to perform feature extraction, and Chinese character layer featuresare obtained; the term layer features and the Chinese character layer features are connected, and feature vector expression of the short text is obtained; and a full-connection layer is utilized to classify the short text, a stochastic gradient descent method is adopted to perform model training, and a classification model is obtained. Through the method, character expression features and term expression features can be extracted, the problem that the short text has insufficient semantic information is relieved, the semantic information of the short text is fully mined, and classification of the short text is more accurate.

The invention provides a hand-written Chinese character beautification method, which is a handwriting processing method for hand-written Chinese characters on the basis of retaining the writing style of the writer. The invention aims at the input trail captured by general input devices (such as mouse, and touch-screens without pressure-level induction) and carries out speed-based calligraphy stroke simulation, stroke matching and template matching to the input trail so as to achieve the purpose of beautifying the writing trail. The invention also provides a personalized hand-written trail processing way which enables people who lack of specialized calligraphy practice to create beautiful handwritten calligraphic Chinese characters with personal style.

The invention relates to a moving voice synthetic method in the field of information changing and processing technology between Chinese character and voice. It is characterized in that it relates to a moving end device especially to an intelligent handset to do words changing. It comprises a voice base structure of the voice synthetic system, a rhythm module practice and a synthetic method and so on. It comprises a CART-Classification and Regression Trees method to choose the base unit sample from the large scale voice data base and to quickly establish the voice base unit database which is suit for the moving end; the rhythm module practice method based on the large scale voice database can extract the base audio curve from nature voice to generate the rhythm platen. So that it can achieve the changing method and system from text to voice on the moving end.