FIELD: printing industry.
SUBSTANCE: method for correct alignment of images containing texts in Roman or Slavic languages, in case of automatic printing includes highlighting of text blocks; checking whether the number of text blocks N is less than the specified threshold T; if the number of text blocks N is less than the specified threshold T, detection of document alignment is not carried out; if the number of text blocks N is higher than the specified threshold T, non-text areas are filled with white; an RGB image is converted into a binary one; parameters of text asymmetry asym0, asym90 are calculated; as well as horizontal - ah, and vertical - av coefficients; depending on the calculated values, it is decided that a document has proper alignment for a text in Roman languages, for a text in Slavic languages the image is turned by 180 degrees; that a document has proper alignment for a text in Slavic languages, for a text in Roman languages the image is turned by 180 degrees; the image is turned by 90 or 270 degrees.
EFFECT: higher correctness of alignment of a page containing text in Roman or Slavic languages, also if colour images are available, provision of the possibility to correct possible errors of alignment.
9 dwg
Title | Year | Author | Number |
---|---|---|---|
CONTENT-BASED DOCUMENT IMAGE CLASSIFICATION | 2014 |
|
RU2571545C1 |
METHOD FOR TEXTUAL INFORMATION RECOGNITION AND ITS INTEGRITY EVALUATION IN INTERNET ELECTRONIC DOCUMENTS | 2013 |
|
RU2550543C1 |
METHOD AND SYSTEM OF PREPARING TEXT-CONTAINING IMAGES TO OPTICAL RECOGNITION OF SYMBOLS | 2016 |
|
RU2636097C1 |
METHOD AND SYSTEM OF PREPARING TEXT-CONTAINING IMAGES TO OPTICAL RECOGNITION OF SYMBOLS | 2016 |
|
RU2628266C1 |
DETERMINATION OF TEXT LINE ORIENTATION | 2016 |
|
RU2633182C1 |
METHODS AND SYSTEMS FOR EFFECTIVE AUTOMATIC RECOGNITION OF SYMBOLS USING FOREST SOLUTIONS | 2014 |
|
RU2582064C1 |
METHOD FOR SEPARATING TEXTS AND ILLUSTRATIONS IN IMAGES OF DOCUMENTS USING A DESCRIPTOR OF DOCUMENT SPECTRUM AND TWO-LEVEL CLUSTERING | 2017 |
|
RU2656708C1 |
IDENTIFICATION OF CHINESE, JAPANESE AND KOREAN SCRIPT | 2013 |
|
RU2613847C2 |
DEVICES AND METHODS, WHICH PREPARE PARAMETERED SYMBOLS FOR TRANSFORMING IMAGES OF DOCUMENTS INTO ELECTRONIC DOCUMENTS | 2013 |
|
RU2625020C1 |
METHODS AND SYSTEMS FOR PROCESSING IMAGES OF MATHEMATICAL EXPRESSIONS | 2014 |
|
RU2596600C2 |
Authors
Dates
2012-12-10—Published
2011-10-07—Filed