System for analysis and reproduction of text data

Patent metadata

Field	Value
Publication number	US-10467330-B2
Application number	US-201816160450-A
Country	US
Kind code	B2
Filing date	Oct 15, 2018
Priority date	May 4, 2015
Publication date	Nov 5, 2019
Grant date	Nov 5, 2019

Abstract

Systems and associated methodology are presented for Arabic handwriting synthesis including partitioning a dataset of sentences associated with the alphabet into a legative partition including isolated bigram representation and classified words that contain ligature representations of the collected dataset, an unlegative partition including single character shape representation of the collected data set, an isolated characters partition, and a passages and repeated phrases partition, generating a pangram, the pangram including the occurrence of every character shape in the collected dataset and further including a special lipogram condition set based on a desired digital output of the collected dataset, and outputting a digital representation of the pangram including synthesized text.

First claim

The invention claimed is:

1. A system for analysis and reproduction of text data comprising:
circuitry configured to
synthesize a text sample and form a collected dataset,
partition, according to a 4-shapes model, the collected dataset of an Arabic alphabet including sentences associated with the Arabic alphabet and Arabic typography, the 4-shapes model including
a legative partition including isolated bigram representation and classified words that contain ligature representations of the collected dataset,
an unlegative partition including single character shape representation of the collected data set,
an isolated characters partition, and
a passages and repeated phrases partition;

identify legative bigrams of character shapes within the collected dataset;
generate a pangram based on the partitions of the 4-shapes model, the pangram including an occurrence of every character shape in the collected dataset and further including a lipogram condition set based on a desired digital output of the collected dataset, the lipogram condition omitting legative bigrams of predetermined Arabic character shapes; and
output a digital representation of the pangram as synthesized text.

2. The system of claim 1 , wherein, based on the lipogram condition, the circuitry is further configured to identify legative bigrams of character shapes that are not omni-ligatives, omni-ligatives being character shapes that are ligatable with every previous character.

3. The system of claim 1 , wherein the pangram includes every instance of the 4-shapes model.

4. The system of claim 1 , wherein the circuitry is further configured to:
(1) identify Arabic sentences within the collected dataset;
(2) initiate a dataset to include all elements in the collected dataset;
(3) derive a histogram of character shapes from the dataset based on probabilities computed from the identified Arabic sentences; and
repeat (1)-(3) until all elements in the dataset are derived into the histogram.

5. The system of claim 1 , wherein the circuitry is further configured to:
identify Arabic sentences within the collected dataset;
compute a cost function for each identified Arabic sentence based on an occurrence of a least frequent character shape detected;
identify an Arabic sentence with a lowest cost function; and
add the identified Arabic sentence to the pangram.

6. The system of claim 1 , wherein the circuitry is further configured to:
identify a ligature shape with a corresponding location of a letter within a bigram into four categories: isolated ligature shape, beginning ligature shape, middle ligature shape and end ligature shape; and
display a four quadrant plot of the ligature shape based on the four shapes, such that the plot comprises a first beginning-middle quadrant, a second beginning-ending quadrant, a third middle-middle quadrant, and a fourth middle-ending quadrant.

Assignees

• Univ King Fahd Pet & Minerals

Inventors

• Elarian Yousef S I

Classifications

• G06F40/109 Primary

  Font handling; Temporal or kinetic typography · CPC title

• G06F40/129 Primary

  Handling non-Latin characters, e.g. kana-to-kanji conversion · CPC title

• G06F17/214 Primary

  Physics · mapped topic

• G06K9/00859

  Physics · mapped topic

• G06F17/2223

  Physics · mapped topic