Abstract: An interval ?0, 1! of the output of neural network is equally divided into M (M being an integer of two or more), and the numbers or frequencies of data for the correct/incorrect patterns contained in the i-th interval ?(i-1)/M, i/M! are .mu.1i and .mu.0i, respectively (where, i=1 . . . M). In this case, if this network provides an output contained in the i-th interval to unknown pattern data, this pattern is stored as a likelihood conversion table so that the pattern outputs likelihood P1i, which is a category, in an equation P1i=(.mu.1i+1)/(.mu.1i+.mu.0i+2). Then, when a value contained in the i-th interval ?(i-1)/M, i/M! is output from a neural network, the likelihood convertor receives it as an input and outputs P1i which is so to speak normalized likelihood.

Abstract: The present invention provide a method for extracting a tree structure by using image analysis results of an actual document and generating a flexible layout model. A tree structure and layout model are newly generated by automatically extracting the tree structure in accordance with document image analysis before a user executes graphical correction. That is, an inputted document image is physically analyzed to extract a separator with a high possibility to separate the objects of the document and segment the above document image into a plurality of areas in accordance with the information for the separator. Then, the area segmentation is displayed on a display unit together with a document image and interactively corrected by the user to define a desired tree structure and complete a flexible layout model by setting a parameter to each node of the tree structure.

Abstract: Character recognition apparatus capable of automatically modifying its recognition tree is disclosed. When a character is erroneously recognized, its image is used to select a leaf node of the character recognition tree which has a high probability of recognizing the character correctly. The tree is split at that node, creating one new leaf node which is assigned to the character formerly assigned to the split node, and a second new leaf node assigned to the erroneously recognized character. The split node is then assigned to test a pel address in a character image which has a high probability of discriminating between the two characters of its new leaf nodes.

Abstract: A system for processing image data of a text document in compressed form wherein pel signals of the original image are stored in pel positions in an input image buffer and the pel signals stored in every other pel (EOP) positions in the input buffer are sequentially fetched, along with respective pluralities of neighboring pel signals stored in EOP positions and compressed by adaptive arithmetic compression to generate a first set of compressed data which is stored in a memory. The pel signals stored in remaining pel (RP) positions in the input image buffer are also sequentially fetched, along with respective pluralities of neighboring pel signals, including at least one signal stored in an RP position and a plurality of signals stored in EOP positions, and compressed by adaptive arithmetic compression to generate a second set of compressed data which is stored in a memory.

Abstract: A system is disclosed for arithmetically compressing bi-level data of an image by sampling history pels, which are adjacent pels to a current pel to be processed, and pels so separated from the adjacent pels as to adapt to a period of a dither matrix for a dither image. From the sampled pels it is determined whether the sampled image has a dither dominant image pattern or a text-graphic dominant image pattern and an appropriate signal is generated, a first signal representing that the image has the dither dominant image pattern, a second signal representing that the image has the text-graphic dominant image pattern, and a third signal representing that the image is not classified as either of these image patterns.

Abstract: In a red-emitting phosphor which includes ZnSe as a host material, copper (Cu) as an activator and aluminum (Al) as a coactivator, the improvement comprising the inclusion of a small amount of cobalt (Co) to provide superlinear characteristics to said phosphor in combination with said Cu and Al. A preferred range of concentration of said Co is 10.sup.-6 -2.times.10.sup.-5 g atom/mol. A specific application of said red-emitting superlinear phosphor is as a phosphor screen for a current density sensitive, single gun color CRT, when mixed with a green-emitting sublinear phosphor.