Character recognition employing compressed image data

Claim 3

The method of claim 1, wherein the creation of said first table comprises the establishment of a frame of constant width through storage of a frame marker therein, which marker defines the vertical position of the frame; further comprising the step of stores displacement value defining the lower limit of the frame, and selecting portions of said compressed video date by reference to said frame marker and to said displacement value.

Claim 4

Method according to claim 1, wherein the creation of said first table comprises scanning the data in the compressed memory area, storing in said table those position addresses that indicate a start of scan and storing flag bits in association with those addresses when all white scans are followed by scans of black and white information and vice versa.

Claim 5

Method according to claim 2, including the step of shifted said frame marker and/or said displacement value after an unsuccessful character recognition operation, whereafter another expansion operation and character recognition operation is performed by means of the new corrected frame.

Claim 6

Method according to claim 4, wherein said correction of the frame is based on statistical experience information and/or upon calculating the amount of black information.

Claim 7

Method according to claim 5, wherein the calculation of the amount of black information is performed by subtracting successive entries of said compressed video data and successively adding the results of the subtraction.

Claim 8

Character recognition apparatus comprising an optical document reader, a video detector for digital detection of video data, a memory for storing video data, a control unit for recognition of characters from stored video data and an output channel for transferring recognized characters from the memory to a user unit wherein the improvement comprises an encoder for coding detected video data into a compressed code, means for transferring compressed video data from the encoder into a first memory area for storing the video data in compressed form, a second memory area for storing table data defining a frame around a character sub-area in said first memory area, a third memory area for storing video data in expanded form, whereby the control unit controls setting up table data in the second memory area, expanding compressed video data from the first memory area and recognition of a character from expanded video data in the third memory area.

Claim 9

Character recognition apparatus comprising an optical document reader, a video detector for digital detection of video data, a memory for storing video data, a control unit for recognition of characters from stored video data and an output channel for transferring recognized characters from the memory to a user unit wherein the improvement comprises an encoder for coding detected video data into a compressed code, means for transferring compressed video data from the encoder into a first memory area for storing the video data in compressed form, a second memory area for storing table data defining a frame around a character sub-area in said first memory area, a third memory area for storing video data in expanded form, whereby the control unit controls setting up table data in the second memory area, expanding compressed video data from the first memory area and recognition of a character from expanded video data in the third memory area.

Claim 10

Character recognition apparatus according to claim 7, wherein the encoder includes a one-bit delay circuit, the input of which is connected to the output of the video detector, an EXCLUSIVE OR circuit, one input of which is connected to the output of the delay circuit, the second input of which is connected to the output of the video detector and the output of which is connected to the data transferring means, and a counter that is connected to a clock circuit and that is stepped upwards synchronously with the detection by the video detector of the digital data bits and the output of which is connected to the memory.

Claim 11

Character recognition apparatus according to claim 7, wherein said means for transferring compressed video data to said memory comprises a direct memory access unit that operates asynchronously with said control unit.