IRIS

Bergen, Norway
Bergen, Norway
SEARCH FILTERS
Time filter
Source Type

A method for correcting an image acquired by a hand-held scanning device. A binarized image of an acquired image is cropped by removing columns on the left end and on the right end of only first components. A work image is created from the cropped image by replacing in each row of components series of first components smaller than a predetermined distance with series of second components. In the work image, a central line is identified. The identified central line in the work image is used to identify the corresponding central line in the cropped image forming a central line image, and in the central line image, the central text line is straightened.


A method implemented on a mobile device for selecting information on a paper document using a hand-held scanning device. The method provides an interface to the user, receives information from the hand-held pen scanning device connected to the mobile device and determines if the received information is valid information for the type of information to be selected. The invention further relates to using a remote computer for performing image processing and data extraction when more powerful resources are needed.


Patent
I.R.I.S. | Date: 2015-10-15

The invention relates to a method for combining a first Optical Character Recognition (OCR) and a second OCR. The first OCR is run first on an image of string of characters. Its output (first identified characters, positions of the characters and likelihood parameters of the characters) is used to generate a first graph. Segmentation points related to the positions of the first identified characters are used as input by the second OCR performing a combined segmentation and classification on the image of string of characters. The output (second identified characters, positions of the characters and likelihood parameters of the characters) of the second OCR is used to update the first graph to generate a second graph that combines the output of the first OCR with the output of the second OCR. Decision models are then used to modify the weights of paths in the second graph to generate a third graph. A best path is determined on the third graph to obtain the identification of the characters present in the image of string of characters.


Patent
I.R.I.S. | Date: 2014-11-05

The invention is directed to a method for comparing in a binary image a first pixel blob with a second pixel blob to determine whether they represent matching symbols. The method comprises the steps of dilating the first blob and checking if the second blob fits inside the dilated first blob, and dilating the second blob and checking if the first blob fits inside the dilated second blob. If the dilating steps result in a match, the method checks whether the match is erroneous or not by checking if the non-dilated first pixel blob contains a line not present in the non-dilated second pixel blob and vice versa. This latter step further comprises directly comparing corresponding sets of NxN crosses of two crossing lines in the non-dilated first and second pixel blobs, wherein each corresponding set of NxN crosses comprises a first NxN cross considered on the non-dilated first pixel blob and a second NxN cross considered on the non-dilated second pixel blob in the same position, and declaring an erroneous match if for at least one of the sets one of the two crossing lines of the first NxN cross has a different color from the other line of the two crossing lines of the second NxN cross, wherein N is a number of bits.


A system for tracking and processing handwritten pen strokes, including: a digital pen to allow a user to write pen strokes on a substrate; a receiver station for use in combination with said digital pen and adapted for tracking said pen strokes and storing digital pen strokes which include electronic data representing said tracked pen strokes, said receiver station including a wireless transceiver adapted for communicating with a mobile terminal over a wireless connection to transfer said digital pen strokes to said mobile terminal; and a software application executable on said mobile terminal and including software code fragments for receiving and processing said transferred digital pen strokes.


Pattern recognition process that includes, starting from an input pattern: normalization of the input pattern into a normalized pattern of predetermined size; generation of a reliable pattern from the normalized pattern by using at least one morphological operator; calculation of a distance between the reliable pattern and selected templates which are selected from a template library; classification of the reliable patterns into at least one of the classes of the selected templates by means of at least one non-parametric classification method, which uses the classes of the selected templates and the calculated distances as inputs and outputs identified classes along with confidence levels.


Patent
I.R.I.S. | Date: 2014-06-09

The optical character recognition method applies a first OCR engine to provide an identification of characters of at least a first type of characters and zones of at least a second type of characters in the character string image. A second OCR engine is applied on the zones of the at least second type of characters to provide an identification of characters of a second type of characters. The characters identified by the first OCR engine and by the second OCR engine are in a further step combined to obtain the identification of the characters of the character string image.


Patent
I.R.I.S. | Date: 2014-04-16

A method for identifying a pattern in an image. In a first step the image is normalized to a binary matrix. A binary vector is subsequently generated from the binary matrix. The binary vector is filtered with a sparse matrix to a feature vector using a matrix vector multiplication wherein the matrix vector multiplication determines the values of the feature vector by applying program steps which are the result of transforming the sparse matrix in program steps including conditions on the values of the binary vector. Lastly, from the feature vector, a density of probability for a predetermined list of models is generated to identify the pattern in the image,


Patent
I.R.I.S. | Date: 2014-04-16

A line segmentation method which starts with determining a first starting point coordinate and generating a list of potential character widths dependent on a maximum character width stored in a database and on characteristics of the portion of the line of text corresponding to the maximum character width. The method determines a second portion of the line of text corresponding to the first starting point coordinate and the first width on the list of potential character widths. On the second portion, a classification method is applied providing a likelihood of error for the first width and a candidate character. The likelihood of error is compared with a first threshold determined by a trade-off between speed and accuracy, and if the likelihood of error corresponding to the first width is lower than the threshold value, the candidate character is selected as the character meaning that a segment is known.


Patent
I.R.I.S. | Date: 2013-12-23

A method for creating a binary mask image from an inputted digital image of a scanned document, including the steps of creating a binarized image by binarizing the inputted digital image, detecting first text regions representing light text on a dark background, and inverting the first text regions, such that the inverted first text regions are interpretable in the same way as dark text on a light background. A method for comparing in a binary image a first pixel blob with a second pixel blob to determine whether they represent matching symbols, including the steps of detecting a line in one blob not present in the other and/or determining if one of the blobs represents an italicized symbol where the other does not.

Loading IRIS collaborators
Loading IRIS collaborators