JPS6325387B2 - - Google Patents

Description

[Detailed description of the invention]

The present invention relates to a character transcription device, and more particularly to a character transcription device that converts character information written on an input form into visually superior information and outputs the converted information. Conventionally, there are the following devices for processing character information. The first is a typewriter device,
This is a method in which a person visually checks character information written in a manuscript and presses a key with his/her hand, thereby printing a font in a certain shape using corresponding typefaces.
The second is an optical character reader (OCR), which mechanically recognizes characters written in predetermined positions on a document and inputs the results into, for example, a computer. The third type is facsimile, which separates the input document into pixels, converts them into electrical signals, and transmits them to a remote location.At the receiving location, the electrical signals are reversely converted into visible information to obtain a faithful copy. The above devices are auxiliary devices used in offices and other places where a large amount of documents are handled, and they have the characteristics shown in the table below.

[Table] As is clear from the table above, typewriters print beautiful characters, but they have the drawback of always requiring human operation. Although OCR is originally intended as a recognition device, it is relatively easy to convert recognition results into visible information using an additional device. However, current recognition technology has the disadvantage that it is difficult to completely recognize handwritten characters including Chinese characters, and it is expensive. Also,
Although facsimile is superior in terms of faithful copying, it has the disadvantage that it does not include cleanliness at all. Therefore, the main object of the present invention is to develop a new type of character that has a character information input/output mechanism like a facsimile, but can automatically convert input character information into visually superior output character information. The purpose is to provide a fair copying device. To summarize, this invention reads character information written in an input manuscript, extracts skeleton lines of the read character information, corrects the extracted skeleton lines, and further adds predetermined flesh to the corrected skeleton lines. This is how it is output. The above objects and other objects and features of the present invention will become more apparent from the following detailed description with reference to the drawings. Note that character information used in this specification means not only kanji, alphanumeric characters, and numbers, but also simple symbols. FIG. 1 is a schematic block diagram showing one embodiment of the present invention. In terms of structure, the photoelectric converter 1 is similar to a photoelectric converter in a so-called facsimile machine, and decomposes an input document (not shown) into pixels and converts them into electrical signals. The output of this photoelectric converter 1 is given to a memory 2 and stored therein. This memory 2
has a capacity that can store the entire screen of the input document. Although not shown, the skeleton line extractor 3 includes, for example, a microcomputer, a RAM, and the like. This skeleton line extractor 3 reads character information stored in the memory 2 character by character and extracts its skeleton lines.
The skeleton line information extracted by the skeleton line extractor 3 is given to the skeleton line feature extractor 4. Although not shown, this skeleton line feature extractor 4 includes, for example, a microcomputer, and extracts the geometric features of the given skeleton line information. Skeletal line shaper 5
Although not shown, includes, for example, a microcomputer, RAM, etc. This skeletal line shaper 5 shapes the position, orientation, size, symmetry, linearity, etc. of the corresponding skeletal line provided from the skeletal line extractor 3 based on the feature information provided from the skeletal line feature extractor 4. do. The output of this skeleton line shaper 5 is given to a filler 6. Although not shown, the filler 6 may be used, for example, with a microcomputer or ROM.
etc., it adds a certain amount of flesh to the given skeleton line information, converts it into a font similar to printed characters, and outputs it. The output of the filler 6 is given to the memory 7 and stored therein. The recorder 8 reads out one screen worth of character information stored in the memory 7 and converts it into visible information. In operation, information inscribed on an input document (not shown) by the photoelectric converter 1 is resolved into pixels;
It is converted into an electrical signal and written into the memory 2. Next, the microcomputer (not shown) of the skeleton line extractor 3 reads out character information for each character from the memory 2, extracts the skeleton lines, and stores them in its RAM (not shown). FIG. 2 is a diagram showing the relationship between the characters written on the input form and the skeleton lines extracted by the skeleton line extractor 3. In this FIG. 2, dotted lines indicate skeleton lines. By the way, a skeleton line refers to the number of connected figures (here, a line is expressed as a chain of points with an area of at least one pixel, and the chain is called a connection), the order (the number of connected white areas, or the degree of connection). ) is a figure in which as many black pixels as possible are changed to white pixels without changing them. The skeletal line feature extractor 4 is similar to the skeletal line extractor 3 described above.
The skeleton lines stored in RAM (not shown) are read out and their geometric features are extracted. The geometrical features mentioned here include the center of the figure, the length of the maximum side, the slope of the straight line with respect to the square, the symmetry, the unevenness of the line, etc. FIG. 3 is a diagram showing the relationship between the skeleton lines in FIG. 2 and shaped skeleton lines, which will be explained later. The operation of the skeleton line feature extractor 4 will be explained in more detail using FIG. This third
In the figure, the skeleton line corresponding to Figure 2 is shown as a dotted line,
The geometrical reference line is indicated by a dash-dot line. The skeletal line feature extractor 4 detects that the horizontal lines of the skeletal lines indicated by dotted lines are not horizontal but tilted and are not symmetrical, the vertical lines also have poor symmetrical symmetry, and the position of the center of gravity and the vertical direction. Extract features such as symmetry being a good thing. The extracted features are given to the skeleton line shaper 5 as parameters for shaping. A microcomputer (not shown) of the skeleton line shaper 6 geometrically simplifies the skeleton lines read from the RAM (not shown) of the skeleton line extractor 3 based on parameters given from the skeleton line feature extractor 4. The skeletal line is shaped into a stable and aesthetically pleasing skeletal line.
Store it in RAM (not shown). The solid lines in FIG. 3 indicate the shaped skeleton lines. As is clear from FIG. 3, the shaped skeleton line shown by the solid line has better linearity and symmetry than the original skeleton line shown by the dotted line. The microcomputer (not shown) of the filler 6 stores the shaped skeleton lines in the RAM of the skeleton line shaper 5.
(not shown) and fleshes out the font. This is done, for example, so that the font resembles a printed font. Data for this fleshing is stored in advance in a ROM (not shown) included in the fleshing device 6. FIG. 4 is a diagram showing an example in which the shaped skeleton lines shown in FIG. 3 are fleshed out. The character information fleshed out by the fleshing device 6 is stored in a memory 7, read out by a recorder 8, and printed by, for example, a printer. In the above-described embodiment, an example of fleshing-out is shown in FIG. 4, but the target font can be easily changed to various types, such as printed font or Gothic font. For example, in this case, this can be realized by changing the fleshing data in a ROM (not shown) included in the fleshing device 6. Furthermore, by storing a plurality of types of fleshing data in this ROM and fleshing out using any of the data, a desired font can be obtained. Further, although the above-mentioned embodiment shows a case in which the transmission function is not included, it is also possible to transmit the output of the filler 6 by a method similar to a so-called facsimile, and various usage methods can be considered. FIG. 5 is a schematic block diagram showing another embodiment of the invention. The feature of this circuit in FIG. 5 is that, unlike the circuit in FIG. 1, it has a transmission function. That is, the output of the photoelectric converter 1 is modulated by a modulator 9, transmitted to a remote location via a communication path 11, demodulated by a demodulator 10, and stored in the memory 2. For example, this modulation/demodulation may be performed in a manner similar to so-called facsimile as described above. Note that the modulator 9 and demodulator 10 may be inserted between the memory 7 and the recorder 8 as shown in FIG. Note that in FIGS. 5 and 6, parts that can be constructed in the same way as in FIG. 1 are given the same reference numerals. As described above, according to the present invention, it is possible to obtain a character transcription device that is much cheaper than conventional optical character reading devices. Further, according to the present invention, the skeleton lines of characters handwritten in an input manuscript are extracted, and the geometric features (at least the inclination, position, symmetry, and linearity) of the extracted skeleton lines are extracted. Then, the skeleton lines are shaped based on the extracted geometric features and then fleshed out, so the inclination, position, symmetry, etc. of the characters written on the input form are automatically and without misrecognition. sex,
It is possible to correct linearity, etc., thereby providing a character inscription device that can convert characters to look very clean. Furthermore, according to the present invention, when fleshing out the shaped skeleton lines, the fleshing is performed based on any one of the fleshing data related to the plurality of types of fonts stored in advance. It also has the effect of allowing you to cleanse the characters using the font.

[Brief explanation of the drawing]

FIG. 1 is a schematic block diagram showing one embodiment of the present invention. FIG. 2 is a diagram showing the relationship between the characters written on the input manuscript paper and the skeleton lines extracted by the skeleton line extractor 3. FIG. 3 is a diagram showing the relationship between the skeleton lines in FIG. 2 and the skeleton lines shaped by the skeleton line shaper 5. FIG. 4 is a diagram showing an example of adding flesh to the skeleton line shaped by the skeleton line shaper 5. FIG. 5 is a schematic block diagram showing another embodiment of the invention. FIG. 6 is a schematic block diagram showing still another embodiment of the present invention. In the figure, 1 is a photoelectric converter, 2 is a memory, and 3 is a photoelectric converter.
4 is a skeleton line extractor, 4 is a skeleton line feature extractor, 5 is a skeleton line shaper, 6 is a filler, 7 is a memory, and 8 is a recorder.

Claims (1)

[Scope of Claims] 1. Character information reading means for reading character information written on an input manuscript and deriving it as an electrical signal; and skeletal line information based on the character information read by the character information reading means. skeletal line information extraction means for extracting the skeletal line information extraction means; a feature extraction means; a skeleton line shaping means for shaping the corresponding skeleton line information based on the geometric features extracted by the geometric feature extraction means; and fleshing data regarding a plurality of types of fonts in advance. a fleshing data storage means that stores the fleshing data; What is claimed is: 1. A character transcription device, comprising: a skeleton line fleshing means for fleshing out the skeleton line; and an output means for converting the output of the skeleton line fleshing means into visual information and outputting it. 2. The character transcription device according to claim 1, which is configured to be incorporated into a facsimile machine.