US5253307A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image analysis to obtain typeface information
Assignee: Xerox Corp
•
Filing: 1991-07-30
•
Granted: 1993-10-12
•
Expires: 2011-07-30
Abstract
Abstract Dominant typeface, including point size, of text in an image is identified by measuring distances across connected components in each of plural directions to obtain distribution data. The distribution data indicate a distribution of distances across connected components in each direction for the image. The distribution data are then used to obtain typeface data indicating the dominant typeface of characters in the text. Distance can be measured from each of a set of pixels that are inside or on edges of connected components to an edge of a connected component. The distances for each direction can be combined, such as by obtaining an average or other measure of central value, so that the combined distances indicate the distribution of distances in the direction. The distribution data can be used to form a profile that can be compared or clustered with other profiles to identify similar profiles or to find a matching profile. Skew can be obtained and used in forming profiles that are independent of skew. The comparisons can be independent of differences in character scale. A machine can store a set of model profiles of known typeface and point size in memory and can compare a profile for an image with each model profile to find the closest match, providing an identifier of its dominant typeface and point size. A machine could also store an input image in memory, obtain data indicating its dominant typeface, modify the stored data according to the dominant typeface, and provide an output image based on the modification. Profiles can be stored or transmitted, and a product can include a model profile together with code for operating a processor to obtain a profile for an image and code for operating the processor to compare the profile for the image with the model profile.
Inventors
- 👤 Peter C. Wayner
- 👤 Daniel P. Huttenlocher
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-28 22:34
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/18; G06V30/184
Claims Analysis
Total Claims: 37
Claim 1
Independent Claim
127 words
A method of performing image processing on an image that includes text with characters having a dominant typeface, the image including connected components that form the text; the method comprising steps of: measuring distances across connected components in each of a plurality of directions and using the measured distances to obtain, for each direction, distribution data indicating a distribution of distances across connected components in the direction for the image; the step of measuring distances comprising measuring distances across a plurality of connected components, each distance being measured across one of the connected components; the plurality of connected components being in a plurality of the characters in the text; and using the distribution data for the plurality of directions to obtain typeface data indicating the dominant typeface.
Claim 2
Independent Claim
127 words
A method of performing image processing on an image that includes text with characters having a dominant typeface, the image including connected components that form the text; the method comprising steps of: measuring distances across connected components in each of a plurality of directions and using the measured distances to obtain, for each direction, distribution data indicating a distribution of distances across connected components in the direction for the image; the step of measuring distances comprising measuring distances across a plurality of connected components, each distance being measured across one of the connected components; the plurality of connected components being in a plurality of the characters in the text; and using the distribution data for the plurality of directions to obtain typeface data indicating the dominant typeface.
Claim 3
Dependent Claim
34 words
The method of claim 1 in which the plurality of directions covers a range, each direction being separated from adjacent directions by approximately the same angle so that the directions cover the range evenly.
Claim 4
Dependent Claim
11 words
The method of claim 2 in which the range is 360°.
Claim 5
Dependent Claim
87 words
The method of claim 1 in which the step of measuring distances comprises: for each of the plurality of directions, a respective plurality of distance obtaining substeps, each of a direction's distance obtaining substeps obtaining distance data indicating distance from a respective starting location to an edge of a connected component in the direction; and for each of the plurality of directions, a respective distribution obtaining substep; each direction's distribution obtaining substep using distance data from the direction's distance obtaining substeps to obtain the direction's distribution data.
Claim 6
Dependent Claim
31 words
The method of claim 4 in which each direction's distribution obtaining step comprises a substep of combining distance data from the direction's distance obtaining substeps to obtain the direction's distribution data.
Claim 7
Dependent Claim
28 words
The method of claim 5 in which each direction's distribution data indicates a central value of the distances indicated by distance data from the direction's distance obtaining substeps.
Claim 8
Dependent Claim
36 words
The method of claim 4 in which each connected component includes locations at which the image has a first color, each of the starting locations being a location at which the image has the first color.
Claim 9
Dependent Claim
40 words
The method of claim 7 in which each connected component is surrounded by locations at which the image has a second color, each of the starting locations being adjacent to an edge between the first color and the second color.
Claim 10
Dependent Claim
15 words
The method of claim 4 in which each of the starting locations is a pixel.
Claim 11
Dependent Claim
44 words
The method of claim 1 in which the step of using the distribution data to obtain typeface data comprises a substep of operating on the distribution data of the directions together to form a profile for the image, the profile being the typeface data.
Claim 12
Dependent Claim
22 words
The method of claim 10, further comprising a step of comparing the profile for the image with a profile for another image.
Claim 13
Dependent Claim
18 words
The method of claim 11 in which the other image includes text with characters having a known typeface.
Claim 14
Dependent Claim
18 words
The method of claim 11 in which the other image includes text with characters having an unknown typeface.
Claim 15
Dependent Claim
48 words
The method of claim 11 in which the text in the image includes characters having a first size and the other image includes text with characters having a second size; the step of comparing the profile being independent of differences between the first size and the second size.
Claim 16
Dependent Claim
35 words
The method of claim 10, further comprising a step of comparing the profile for the image with each of a set of model profiles, each of the model profiles being for a respective known typeface.
Claim 17
Dependent Claim
52 words
The method of claim 15 in which the step of comparing comprises substeps of: determining which of the model profiles is most similar to the profile for the image; and providing an identifier indicating the respective known typeface of the model profile that is most similar to the profile for the image.
Claim 18
Dependent Claim
46 words
The method of claim 16 in which each of the model profiles is for a known point size of the model profile's known typeface; the identifier further indicating the known point size of the model profile that is most similar to the profile for the image.
Claim 19
Dependent Claim
21 words
The method of claim 10, further comprising a step of clustering the profile for the image with profiles for other images.
Claim 20
Dependent Claim
20 words
The method of claim 10, further comprising a step of providing the profile for the image to a storage medium.
Claim 21
Dependent Claim
20 words
The method of claim 10, further comprising a step of providing the profile for the image to a transmission medium.
Claim 22
Dependent Claim
61 words
The method of claim 10 in which the text includes lines of characters at a skew; the method further comprising a step of obtaining skew data indicating the skew; the substep of operating on the distribution data comprising a substep of using the skew data in forming the profile for the image so that the profile is independent of the skew.
Claim 23
Dependent Claim
44 words
The method of claim 1 in which the text includes lines of characters at a skew; the method further comprising a step of obtaining skew data indicating the skew; the plurality of directions being directions relative to the skew indicated by the skew data.
Claim 24
Dependent Claim
138 words
An image processing machine comprising: memory for storing image data defining an image that includes text with characters having a dominant typeface, the image including connected components that form the text; and a processor connected for accessing the memory, the processor comprising: distribution obtaining means for using the image data to obtain, for each of a plurality of directions, respective distribution data indicating a distribution of distances across connected components in the direction, the distribution obtaining means obtaining each direction's distribution data by measuring distances across a plurality of connected components, each distance being measured across one of the connected components; the plurality of connected components being in a plurality of the characters in the text; and typeface obtaining means for using the distribution data for the plurality of directions to obtain typeface data indicating the dominant typeface.
Claim 25
Dependent Claim
138 words
An image processing machine comprising: memory for storing image data defining an image that includes text with characters having a dominant typeface, the image including connected components that form the text; and a processor connected for accessing the memory, the processor comprising: distribution obtaining means for using the image data to obtain, for each of a plurality of directions, respective distribution data indicating a distribution of distances across connected components in the direction, the distribution obtaining means obtaining each direction's distribution data by measuring distances across a plurality of connected components, each distance being measured across one of the connected components; the plurality of connected components being in a plurality of the characters in the text; and typeface obtaining means for using the distribution data for the plurality of directions to obtain typeface data indicating the dominant typeface.
Claim 26
Dependent Claim
28 words
The machine of claim 23 in which the typeface obtaining means operates on the respective distribution data of the directions together to form a profile for the image.
Claim 27
Dependent Claim
27 words
The machine of claim 24 in which the processor further comprises profile comparing means for comparing the profile for the image with a profile for another image.
Claim 28
Dependent Claim
48 words
The machine of claim 24 in which the memory comprises profile storing means for storing a set of model profiles; the processor further comprising profile comparing means for accessing the stored set of model profiles to compare the profile for the image with each of the model profiles.
Claim 29
Dependent Claim
25 words
The machine of claim 24 in which the processor further comprises clustering means for clustering the profile for the image with profiles for other images.
Claim 30
Dependent Claim
28 words
The machine of claim 24, further comprising a storage medium; the processor further comprising profile storing means for providing the profile for the image to the storage medium.
Claim 31
Dependent Claim
34 words
The machine of claim 24, further comprising a connection between the processor and a transmission medium; the processor further comprising profile transmitting means for providing the profile for the image to the transmission medium.
Claim 32
Dependent Claim
57 words
The machine of claim 24 in which the text includes lines of characters at a skew; the processor further comprising skew obtaining means for obtaining skew data indicating the skew; the profile forming means comprising means for using the skew data in forming the profile for the image so that the profile is independent of the skew.
Claim 33
Dependent Claim
120 words
The machine of claim 23 in which the machine further comprises: an image input device for receiving an input image and for providing input image data defining the input image; and an image output device for receiving output image data defining an output image and for providing the output image; the processor further comprising: image data storing means for storing the input image data from the image input device in the memory; image data modifying means for modifying the image data stored in memory in accordance with the typeface indicated by the typeface data to obtain modified image data; and image data output means for providing output image data to the image output device based on the modified image data.
Claim 34
Independent Claim
155 words
A method of performing image processing on an image that includes text with characters having a dominant typeface, the image including connected components that form the characters in the text; the method comprising steps of: measuring distances across connected components in each of a plurality of directions and using the measured distances to obtain, for each direction, distribution data indicating a distribution of distances across connected components in the direction for the image; the step of measuring distances comprising measuring distances across a plurality of connected components, each distance being measured across one of the connected components; the plurality of connected components being in a plurality of the characters in the text; each distribution including distances across connected components from a sufficient number of the characters in the text that the distribution data indicate the dominant typeface; and using the distribution data for the plurality of directions to obtain typeface data indicating the dominant typeface.
Claim 35
Independent Claim
155 words
A method of performing image processing on an image that includes text with characters having a dominant typeface, the image including connected components that form the characters in the text; the method comprising steps of: measuring distances across connected components in each of a plurality of directions and using the measured distances to obtain, for each direction, distribution data indicating a distribution of distances across connected components in the direction for the image; the step of measuring distances comprising measuring distances across a plurality of connected components, each distance being measured across one of the connected components; the plurality of connected components being in a plurality of the characters in the text; each distribution including distances across connected components from a sufficient number of the characters in the text that the distribution data indicate the dominant typeface; and using the distribution data for the plurality of directions to obtain typeface data indicating the dominant typeface.
Claim 36
Dependent Claim
163 words
An image processing machine comprising: memory for storing image data defining an image that includes text with characters having a dominant typeface, the image including connected components that form the text; and a processor connected for accessing the memory, the processor comprising: distribution obtaining means for using the image data to obtain, for each of a plurality of directions, respective distribution data indicating a distribution of distances across connected components in the direction, the distribution obtaining means obtaining each direction's distribution data by measuring distances across a plurality of connected components, each distance being measured across one of the connected components; the plurality of connected components being in a plurality of the characters in the text; each distribution including distances across connected components from a sufficient number of the characters in the text that the distribution data indicate the dominant typeface; and typeface obtaining means for using the distribution data for the plurality of directions to obtain typeface data indicating the dominant typeface.
Claim 37
Dependent Claim
163 words
An image processing machine comprising: memory for storing image data defining an image that includes text with characters having a dominant typeface, the image including connected components that form the text; and a processor connected for accessing the memory, the processor comprising: distribution obtaining means for using the image data to obtain, for each of a plurality of directions, respective distribution data indicating a distribution of distances across connected components in the direction, the distribution obtaining means obtaining each direction's distribution data by measuring distances across a plurality of connected components, each distance being measured across one of the connected components; the plurality of connected components being in a plurality of the characters in the text; each distribution including distances across connected components from a sufficient number of the characters in the text that the distribution data indicate the dominant typeface; and typeface obtaining means for using the distribution data for the plurality of directions to obtain typeface data indicating the dominant typeface.
References Cited (Backward Citations)
US2838602A
Cited
US2983822A
Cited
US3297989A
Cited
US3634822A
Cited
US4379283A
Cited
US4468809A
Cited
US4499499A
Cited
US5113453A
Cited
US4933979A
Cited
US4802230A
Cited
US4850026A
Cited
US5058182A
Cited
US4831657A
Cited
US5111516A
Cited
US5054094A
Cited
US5181255A
Cited
US5185818A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1996-10-11 | 1997-04-12 | 1997-10-12 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2000-10-11 | 2001-04-12 | 2001-10-12 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2004-10-11 | 2005-04-12 | 2005-10-12 | $7700.00 | Window Closed / Lapsed |