Method and apparatus employing font size determination for resolution-independent rendered text for electronic documents
AssigneeKonica Minolta Business Solutions U.S.A., Inc.
InventorJason Grams
Life of this patent
Estimating the term…
Loading patent…
AssigneeKonica Minolta Business Solutions U.S.A., Inc.
InventorJason Grams
Estimating the term…
Method and apparatus for determining font point size in bitmapped text does not rely on accuracy of an optical character recognition (OCR) engine, or on generation of heuristics (e.g. assumption of certain amounts of different types of text, such as capital, lowercase, ascending, descending) to determine a likely font size. A deep learning model for determining text size is based on extraction of features from existing text to obtain a more general solution.
A method comprising:
An apparatus comprising at least one processor and at least one non-transitory memory storing instructions which, when executed by the at least one processor, perform a method comprising:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
From the US filing history. Foreign family members aren’t listed.
No references of this kind are recorded.
Extraction of features or characteristics of the image: by performing operations within image blocks or by using histograms
Using pattern recognition or machine learning: using neural networks
Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields: based on…
Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation:…
About 18 years 1 month of term left · ends 5 Dec 2044 (estimated)
Aspects of the present invention relate to image processing, and more specifically text processing in electronic document generation. Yet more specifically, aspects of the invention relate to font point size determination for rendered lines of text in electronic document generation.
In electronic documents, it is desirable to have text paragraphs with the same text font size. One issue in providing uniform text font size in electronic document paragraphs is uniform font point size determination, because font point size affects font size. Placing a bounding box around rendered text has been one approach to font point size determination. However, there are numerous aspects of fonts, from upper case versus lower case, to ascenders or descenders, to various kinds of accents, diacritical marks, and the like, all of which can have an effect on character appearance, and hence on font point size determination. Simply placing a bounding box around the text does not enable inference of font point size, because point size does not necessarily match directly to text height.
FIGS. 1A-1E show examples of different heights of characters and words in different cases and with different marks, to illustrate how point size does not necessarily imply font size or word height. In FIG. 1A, the lower case word “ace” is next to the upper case word “ACE”. These are the same letters, but not in the same case, and so the resulting text heights, even for the same font size, potentially can yield different font sizes. FIG. 1B presents a different type of problem, with all lower case letters, but with a word, “age,” with a descender which likewise can affect determination of font point size. FIG. 1C is like FIG. 1B, but with a word, “ade,” with an ascender. FIG. 1D shows an upper case word next to a lower case word with a descender. The conditions in FIGS. 1C and 1D also can affect font point size determination.
Aspects of the present invention now will be described in detail with reference to embodiments, as depicted in the accompanying drawings, in which:
FIGS. 1A-1E show examples of letters, words, and diacritical marks to exemplify issues in point size determination;
FIG. 2 is a high level diagram of process flow according to an embodiment;
In aspects of the present invention, efficiency and/or performance is not affected by the need to decipher different type of lines of text of different characters, e.g. all upper case letters versus all lower case letters versus all letters with descenders or all letters with ascenders, combinations of any or all of the foregoing, etc.
Embodiments of the invention employ machine learning (ML) systems which are trained on large sets of bitmapped text, all or substantially all of this bitmapped text being of known point size. The training data may be rendered at a specific resolution RG (ground truth), with text scaled to a target scale height HN. In one aspect, known point size for each training input may be scaled based on a ratio of a rendered text bounding box height H0 to the target scale height HN. With this approach, model outputs may be scaled to this target scale height, and thus can be used independently from a target resolution. In embodiments, automatically-generated data with the indicated specific resolution and scaled text height may be used to train the system and thus promote identification of font size in processed bitmapped text. Such identification facilitates generation of electronic documents in word processing software such as Microsoft's Office 365™, Google's G Suite™, Apache OpenOffice, LibreOffice, and the like.
One desired effect of aspects of the invention is to provide consistent font size in electronic documents. For example, font size may be tailored for an electronic document on standard letter sized paper (8.5″×11″), with standard margins (1″ all around). 12 point fonts may be considered to be most common. Accordingly, a desired target point size to achieve the desired font size may be desirable.