50 results about "Character interval" patented technology

The invention relates to a character extracting method in a digital video based on character segmentation and color cluster, which comprises the following steps: (1) character segmentation: utilizing the characteristic differences of a character area and a character interval area to carry out vertical projection to segment images in the character area, namely, segmenting each row of area image containing a plurality of characters into a plurality of subarea images only containing a single character so as to reduce the post operating and treating difficulties and improve the identifying accuracy rate of OCR; and (2) character extraction: firstly, using the character color characteristic in the image to cluster colors, finding out an image layer containing maximum character information as a target image layer, and deleting the background area; and then, using the communicating characteristics of the characters to analyze a communicating area of the target image layer, and removing non-character areas to obtain such three results as single character images, an integral image of the character area and an integral image spliced by the single character images respectively, wherein all the three results are input to an OCR system to be identified, and the latter two results use the semantic processing function of the OCR and can accurately determine the characters with similar forms according to the context to improve the identifying effect.

The invention discloses a license plate character segmentation method based on parts. The method includes extracting seven characters in a license plate area as the parts, dividing the characters into two categories of Chinese characters and letter/number characters according to the appearance characteristics of the parts for assembly of a license plate part model, utilizing a vertical edge detection and morphological processing method to determine a target candidate area, respectively detecting the Chinese characters and the letter/number characters in a license plate, filling the characters according to the character interval, analyzing the space position relation between the characters, verifying the license plate type, utilizing the detected character position and size to modify the target candidate area to acquire the license plate modified area, utilizing the license plate position and the license plate type to modify the character position in the reverse direction to accurately segment the license plate characters. The method has the advantages of being easy to achieve, good in robustness, capable of adapting to different illumination conditions, capable of segmenting the license plate under good illumination condition, capable of processing the noisy license plate and capable of being applied to license plate character segmentation under poor illumination condition or under the noisy condition.

The invention provides a self-adaptive license plate character segmentation method in a complex scene. The method comprises the steps of 1, obliquely correcting a license plate, 2, prelocating the interval position between the second character and the third character, and using the projection texture characteristics and combining the aspect ratio of the license plate to set multi-criteria judgment to simply and quickly search the interval position between the second character and the third character to provide stable and reliable initial position judgment information of the next step of character segmentation, and segmenting the license plate characters. Furthermore, in order to enable character segmentation to be more accurate, 0 element sections meeting the criterions are searched to update the segmentation character width and the interval width between the characters, and the character width parameters are updated again according to the searched position of the middle character. Thus, the defect that the single character is instable to segment is effectively overcome. The method can adjust segmentation parameters adaptively by quickly and accurately searching the interval position between the second character and the third character, so that the license plate characters can be segmented stably and reliably. In addition, the roughness in the complex environment is strong.

A method for detecting possible fraud in a document includes receiving an electronic image of the document and extracting data from the image that includes a plurality of printed characters. Next, one or more properties of the characters are measured, the properties are compared to at least one corresponding normative property to determine whether anomalies are present, and a determination is made as to whether to provide a fraud alert based on the anomalies, if any. Preferably, the method includes reporting the one or more anomalies, if any, to a classifier engine, wherein the classifier engine determines whether to provide the alert. Also, methods for determining character spacing ands/or acuity are provided.

The invention discloses a webpage content extraction method and device based on a Markov random field. The method comprises the following steps: sequentially parsing HTML (hypertext markup language) texts and preprocessing the HTML texts; extracting label text windows from the preprocessed HTML texts to obtain a label text window set, wherein each label text window comprises a content text surrounded by a label and the related attributes of the content text; creating a Markov random field model by the label text windows according to an adjacent relation; taking text length and label type as basic characteristics, and initializing the Markov random field model by a minimum deviation threshold value method; optimizing the Markov random field model by using an ICM method according to the line numbers of the label text windows and the character intervals between each adjacent label text windows and reconstructing the content according to the optimized Markov random field model to obtain extracted content. The method can be applied to automatic abstracting and classifying systems in the field of information retrieval, and has the advantages of high extraction precision, high extraction speed, low maintenance cost, good adaptability, high flexibility and the like.

The invention is used for solving the issue that is the currently-used technology can't set, detect and display the intra-frame and inter-frame character interval time of Modbus RTU. The Modbus bus interface of first communication unit on master node and the Modbus of second communication unit on slave node are respectively connected on Modbus bus; setting up 3 character interval times in the master node and inputs two frames of transmission message; dividing the types of transmission messages into two types, namely error type 1 and error type 2, and transmitting them; according to the detected time interval, the slave node divides and displays the received messages.

The invention relates to the technical field of image processing in machine vision. A method for segmenting a traffic guide sign image comprises the following steps of 1 extracting features;2 extracting that geometrical features and the character interval of the guide mark image from the MSER region, extracting the geometrical features on the basis of the MSER eigenvalue, and deleting the non-conforming features; 3 extracting blob features of the guide mark image, scanning the image line by line from the first line of the binary image, and counting non-zero clusters in the guide mark binary image. The method of the invention divides the guiding signs in the road, especially in the urban road, and lays a foundation for detecting and recognizing the traffic signs for the development of the intelligent traffic, especially for the auxiliary driving and even the unmanned driving.

Character spacing values in a document image are extracted and a variance is calculated for fluctuations in the character spacing values. When the calculated variance is lower than a preset threshold value, the document image is determined as having watermark information embedded therein. Such use of the variance in the character spacing values enables high-speed determination of the presence or absence of character-spacing watermark information. At this time, it is possible to speed up the determination by using only some character spacing values in the document, instead of using all character spacing values.

The invention discloses a portable character recognition device and method. The device comprises a CMOS (Complementary Metal Oxide Semiconductor) black and white camera, an LCD display screen, a character recognition IP core, a microprocessor, a BRAM (Broadcast Recognition Access Method) memory and a voice speaker. The recognition method is as follows: acquiring a to-be-recognized character data area, enabling the top left corner of the to-be-recognized area to coincide with the top left corner of the display screen; dividing a to-be-recognized character area image into a plurality of blocks,calculating the grey level histogram of each block of the image, determining the threshold value, finishing binarization processing of the image; filtering a median value of a possible character interval area according to the height of the to-be-recognized character area image, the common character edge distance and the aspect ratio to obtain the number of single characters; extracting the characteristic of the single character, finishing recognizing the character by classifying and matching the character; and transmitting a recognized character string to a user side through Bluetooth. The character is recognized by designing the IP core of hardware, the recognition efficiency and accuracy is improved, and the device and the method are convenient and efficient.

Based on text coding, the method for detecting message of ultra long signaling includes steps: (1) based on signaling protocol of text coding to construct function for identifying ultra long message; (2) using the identifying function to identify whether the received signaling message is a ultra long message or not; (3) if yes, filtering it out; otherwise, continuing other processes. The identifying function includes character interval table, which denotes allowed maximal interval between two character separators, and constraint relation table for character separators, which denotes whether two character separators are allowed to appear continuously and repeatedly. Being implemented by software or hardware, the method is in use for detecting ultra long message at network entry. Replacing or adjusting corresponding parameters in the said two tables, the method is suitable to all text typed signaling message. The method prevents attack and destruction from hijacker.

The invention relates to the technical field of radio, and provides a Morse code radio frequency signal receiving and identifying method and device and an analog radio station host, which are used forimproving the decoding accuracy. The method comprises the following steps: carrying out edge capture on a received 48KHz bit stream to find a rising edge and a falling edge of a corresponding Morse code message; timing each rising edge and each falling edge according to a preset 64S timer; caching the time of each rising edge and each falling edge; further establishing a cached high-low level duration time table; and calculating a dot code time length, a code division time length, a code interval, a character interval and a word interval time length according to the high-low level duration time table so as to determine a decoding time window, so that an ASCII code of a character corresponding to the 48KHz bit stream is inquired according to a preset Morse code ASCII code lookup table. According to the invention, the problem of low Morse code identification and decoding accuracy of the Morse code radio frequency signals received by the analog radio station host and sent manually is solved.

The present invention discloses an authentication method. The method comprises: receiving an input operation used for inputting a password, wherein the input operation comprises a first operation carrying first information and/or a second operation carrying second information, and a third operation; identifying a Morse code corresponding to the input operation, wherein the first information and the second information correspond to a dot and a dash in the Morse code respectively, and the third operation is used for representing a character spacing in the Morse code; according to the third operation and the Morse code, determining a character corresponding to the input operation; and determining whether the character matches a preset password, wherein if yes, authentication succeeds. Implementing the foregoing scheme can enhance authentication security.

The invention aims to provide an input method and an input system for generating a character interval, which belongs to the technical filed of computers and software. The method comprises the following steps of: step 1, collecting character string information input in an input method interface by a user; steps 2, collecting interval input information, generating the interval between the character strings of the input method interface, and obtaining two or more character string sub sets; and step 3, outputting the character string information with intervals, and a candidate phrase list corresponding to character string information with the intervals. Through the method and the system, more effective character input modes or more effective character alter modes can be obtained through the intervals between the characters.

The invention relates to the technical field of radio, and discloses a Morse code recognition method, device and equipment based on a newspaper machine and a storage medium, which are used for improving the Morse code recognition efficiency. The method comprises the following steps: receiving a Morse code message, and judging according to a preset judgment threshold; wherein the level is a high level when greater than or equal to the judgment threshold and is a low level when less than the judgment threshold; carrying out edge capture to obtain duration time of a high level and duration time of a low level; calculating and adjusting a reference interval according to a preset rule, and determining a point code, a scratching code, a character interval and a word interval of the Morse code message in a current period of time according to the reference interval; separating character boundaries according to the dot codes, the scribing codes, the character intervals and the word intervals; and querying and obtaining corresponding characters in a preset Morse code comparison table according to the dot-row combination of the Morse message, and determining an identification result of the Morse message according to the characters and character boundaries.

The invention provides a Serdes interface circuit, and the circuit comprises a plurality of receiving network bridge units; each receiving network bridge unit comprises an alignment adjustment moduleused for receiving decoded data decoded in each channel of a Serdes interface, adjusting the decoded data to an alignment state and outputting alignment state data; a compensation frequency differencedeleting module which is used for deleting the special character skip pattern in the alignment state data and writing the compensation frequency difference deleting data into the FIFO cache; a data adjustment module which is used for performing data adjustment on the read-out data of the FIFO and outputting adjustment data; a frequency difference compensation module which is used for performing insertion operation on the adjustment data and outputting alignment adjustment data; and a state generation module which is used for controlling multi-channel alignment and judging whether alignment iscompleted or not. According to the interface circuit disclosed by the invention, the influence of the change of special character Apattern intervals in each channel caused by error codes is eliminated, the smooth completion of data alignment is ensured, and the transmission performance of serdes and the stability of system work are improved.

The invention discloses a Tibetan language encoding and decoding method and device, and belongs to the field of communication. The encoding method includes the steps that a Tibetan language syllable is obtained; characters at all the positions are sequentially judged from left to right; if the current position includes one character, a preset code table is searched to obtain a code corresponding to the character; if the current position includes multiple characters arrayed vertically, the code table is searched for all the characters arrayed vertically sequentially in the first consonant and later vowel sequence and the top-to-bottom consonant sequence; in the encoding process, a character space mark is added between every two adjacent codes, and the Tibetan language syllable codes are obtained after compiling of the characters at all the positions in the Tibetan language syllable is completed. The scheme of achieving code encoding and decoding based on the minority language is given, which greatly facilitates Tibetan language communication, and the Tibetan language encoding and decoding method plays a great role in emergency communication and security and secrecy communication.

A tape printing apparatus includes: a paragraph creating unit which creates a paragraph including plural lines of character strings; a justification setting unit which sets justification to evenly allocate other lines to the same length as a longest line, of the plural lines in the paragraph; a character mode setting unit which sets a non-target range to be a non-target of the justification, on a character basis within the paragraph, and sets a length of character spacing within the non-target range; a character arrangement deciding unit which carries out justification based on the justification setting unit in a target range excluding the non-target range set by the character mode setting unit, and thus decides an arrangement of characters in each line included in the paragraph; and a printing unit which prints the paragraph on a tape with the character arrangement decided by the character arrangement deciding unit.

The invention discloses a voice recording method and device, equipment and a medium, which are used for solving the problems of inflexible storage and query operation and poor user experience of the existing voice recording. When the intention template matching the text information of to-be-recognized voice information is determined to exist and the matched intention template is the target operation for recording the event by using the voice, according to the character interval in which each keyword in the matched intention template is located, each keyword contained in the text information of the to-be-recognized voice information can be determined, and the target operation is executed on each keyword, so that the target operation is more flexible and convenient when voice recording is used, the process for determining each keyword contained in the text information of the to-be-recognized voice information is simplified. And the efficiency of the voice recording process is improved.

The invention discloses a MODBUS message frame receiving method for a DSP/BIOS. The method is realized based on DSP/BIOS software. The method comprises a message frame receiving process and a message frame processing process. The message frame receiving process is realized through an SCI hardware interrupt thread. The message frame processing process is realized through a period software interrupt thread. A timing clock of the message frame processing period software interrupt thread is driven by a system clock; a clock period value is enabled to be equal to interval time of MODBUS message frames; and when the timing value of the timing clock is accumulated to be equal to the clock period, the message frame processing software interrupt thread is entered. According to the method, the interval time between characters is determined by the system clock instead of a timer, two message frames are distinguished accurately, hardware resources of a microprocessor can be effectively saved, and the demand of an automatic control system for peripheral resources of the microprocessor is reduced.

The invention discloses an e-book typesetting processing method, electronic equipment and a storage medium, and the method comprises the steps: carrying out analysis of an original text line contained in an original document of an e-book, and generating a conversion text line corresponding to the original text line in a conversion document; obtaining the position offset of each character contained in the converted character line of the converted document in the original document, and calculating the interval between two adjacent characters in the converted character line of the converted document in the original document; obtaining a style space threshold corresponding to the style information of the original text line; and determining whether to add a space between two adjacent characters in the converted character line or not according to a comparison result of the interval of the two adjacent characters in the converted character line in the original document and the style space threshold. The style space threshold corresponding to the style information can be determined according to the statistical distribution data of the character intervals in the plurality of original character lines with the same style, and whether the space needs to be added or not is judged.