Abstract: A character recognition system is disclosed in which an input character is compared to a plurality of standard characters. Each standard character is stored with respect to its black meshes in a first character memory area, and with respect to its white meshes in a second character memory area. The characters are stored in parallel such that one "row" of the memory corresponds to the same mesh area of each character. The input character is stored in a third memory area in terms of either its white or its black meshes. Means are provided which produce the address of the character memory area row which corresponds to an address of a mesh bit within the input character memory. The row is sequentially read out, and a counter is provided for each character. These counters are initiated when logical 1's are present in both the particular input character memory mesh bit and the corresponding character memory area bit. The outputs of the counters are cumulatively stored and compared.

Abstract: In a pattern matching method, the input pattern of a character is compared with each of a plurality of standard patterns to detect similarities and differences by counting the number of pattern elements which are or are not matched with each other. To do this, a high-speed comparator stores a plurality of comparing data in a memory, which is driven by a clock pulse train. The memory produces a plurality of sequence signals during each time interval when the clock pulses of a number responding to a plurality of comparing data are applied thereto. The first or last produced sequence signal is detected from among the plurality of sequence signals and is used to extract the maximum or minimum data.

Abstract: Responsive to each character field, a word recognition apparatus separates a first train of characters .alpha..sub.1, .alpha..sub.2, . . . .alpha..sub.n, which are regarded as characters of a first kind, and a second train of characters .beta..sub.1, .beta..sub.2, . . . .beta..sub.n, which are regarded as characters of second kind. First and second registers store the first and second train of characters, respectively. A first storage device stores a first kind of intercharacter distance of the first kind of characters and a second storage device stores a second kind of intercharacter distance of the second kind of characters. A third storage device stores a dictionary of words, which is compared with the output character train of the character reader. The first and second kinds of intercharacter distances in the dictionary words are compared with items in the contents of the first and second registers.