Fuji Xerox Co., Ltd.

Shozo Yokota

Hiroyuki Kataoka

Yoshio Arai

Isao Suzuki

Matsumi Suzuki

Tetsuro Morino

The image converting system including an image input step or apparatus for converting an original document information into electric image signals an inputting them, an image processing step or apparatus for processing the original document information supplied by the image input step in a predetermined process or order to provide converted image signals different from the original image, and a recording step or apparatus for recording the image on a recording medium in accordance with the image signals derived from the image processing step thereby recording a pattern materially different from the original image on the recording medium or displaying same on an indicator. The converted image signals may be obtained by the use of a coding or scrambling signal and an Exclusive OR operation. Line shifting may be employed. The original image may also be divided into a number of grid components and mixed in accordance with the coding rule.

Image conversion system

An image transcribing system for transferring an image from an original document to a recording sheet in which the original image is scanned, converted to binary signals and stored in a first page memory. An image processing section transfers the image data from the first page memory to a second page memory while it is simultaneously enlarged by a predetermined factor. In the enlargement process, the image data is first enlarged by an integer factor then reduced by a fractional factor in accordance with stored bit patterns corresponding to the required fractional factor.

Image transcribing system

Method and apparatus for eliminating noise in a digitally recorded visual image wherein the proportion of picture elements in an area surrounding an objective area having a first visual level or component is determined and the objective area concluded as having the same visual level or component when the proportion is above a predetermined value. In one embodiment, both picture elements in the surrounding and objective areas are counted to determine the proportion while in another only those picture elements in the surrounding area are counted.

Visual image noise eliminating system

Speech recognition in prior art uses one extracted characteristic component (x.sub.i) to represent one phoneme (X.sub.i) as spoken by one speaker. This invention provides for recognizing the same phoneme as spoken by different speakers, by deriving a group of such components (x.sub.ik), each a slight variant of the others, to allow finding one component most similar to both the specific phoneme and specific speaker, the method comprising the steps of: normalizing the sound pressure level of an input speech from an unknown speaker; analyzing the normalized voice in a plurality of channels having different frequencies; setting, with respect to the output F.sub.j of each frequency band thus analyzed, a weight .alpha..sub.j of the output F.sub.j so that weight .alpha..sub.j corresponds to a characteristic of a predetermined phoneme X.sub.i ; extracting the characteristic component x.sub.i of the phoneme X.sub.i, setting a weight .beta..sub.j of output F.sub.j so that, when the extracted characteristic component x.sub.i causes a malfunction or error due to another phoneme X.sub.e, a characteristic of phoneme X.sub.e is corresponded to; simultaneously extracting the characteristic component x.sub.e of phoneme X.sub.e and, when the difference between the characteristic components thus extracted is greater than a predetermined threshold value .gamma..sub.i, applying the difference as a characteristic parameter for the phoneme x.sub.i ; expanding the characteristic parameter to obtain a characteristic parameter group based on the characteristic parameter, each being slightly different from each other so as to be adapted for individual characteristics of different speakers; subsequently extracting from the characteristic parameter group a characteristic parameter, having maximum similarity to a reference parameter previously memorized, as an adaptive parameter adaptive to the unknown speaker; and, matching a standard pattern derived from the extracted adaptive parameters with an unknown pattern corresponding to the unknown speakers, thereby effecting recognition or analysis of the voice.

Growing community of inventors

Ebina, Japan

Shozo Yokota