A method of generating and optimizing a codebooks for document analysis comprises: receiving a first set of document images; extracting a plurality of keypoint regions from each document image of the first set of document images; calculating local descriptors for each keypoint region of the extracted keypoint regions; clustering the local descriptors such that each center of a cluster of local descriptors corresponds to a respective visual word; generating a codebook containing a set of visual words; and optimizing the codebook by maximizing mutual information (MI) between a target field of a second set of document images and at least one visual word of the set of visual words.

Systems can be configured for detecting license plates and recognizing characters in license plates. In an example, a system can receive an image and identify one or more regions in the image that include a license plate. Character recognition can be performed in the one or more regions to determine contents of a candidate license plate. Location-specific information about a license plate format can be used together with the determined contents of the candidate license plate to determine if the recognized characters are valid.

The invention concerns a method implemented by a device for displaying strokes of digital ink in a display area and for performing text line extraction to extract text lines from the strokes. In particular, the text line extraction may involve slicing the display area into strips, ordering for each strip the strokes into ordered lists which form collectively a first set of ordered lists, forming for each strip a second set of ordered lists by filtering out from the ordered lists of the first set strokes which are below a given size threshold, and performing a neural net analysis based on said first and second sets to determine for each stroke a respective text line to which it belongs.

A method of price text detection by an imaging controller comprises obtaining, by the imaging controller, an image of a shelf supporting labels bearing price text, generating, by the imaging controller, a plurality of text regions containing candidate text elements from the image, assigning, by the imaging controller, a classification to each of the text regions, selected from a price text classification and a non-price text classification. The imaging controller, within each of a subset of the text regions having the price text classification: detects a price text sub-region and generates a price text string by applying character recognition to the price text sub-region. The method further includes presenting, by the imaging controller, the locations of the subset of text regions, in association with the corresponding price text strings.

Audio distortion compensation methods to improve accuracy and efficiency of audio content identification are described. The method is also applicable to speech recognition. Methods to detect the interference from speakers and sources, and distortion to audio from environment and devices, are discussed. Additional methods to detect distortion to the content after performing search and correlation are illustrated. The causes of actual distortion at each client are measured and registered and learnt to generate rules for determining likely distortion and interference sources. The learnt rules are applied at the client, and likely distortions that are detected are compensated or heavily distorted sections are ignored at audio level or signature and feature level based on compute resources available. Further methods to subtract the likely distortions in the query at both audio level and after processing at signature and feature level are described.

Audio distortion compensation methods to improve accuracy and efficiency of audio content identification are described. The method is also applicable to speech recognition. Methods to detect the interference from speakers and sources, and distortion to audio from environment and devices, are discussed. Additional methods to detect distortion to the content after performing search and correlation are illustrated. The causes of actual distortion at each client are measured and registered and learnt to generate rules for determining likely distortion and interference sources. The learnt rules are applied at the client, and likely distortions that are detected are compensated or heavily distorted sections are ignored at audio level or signature and feature level based on compute resources available. Further methods to subtract the likely distortions in the query at both audio level and after processing at signature and feature level are described.

A document forgery detection method comprising using at least one processor for providing at least one histogram of gray level values occurring in at least a portion of at least one channel of an image assumed to represent a document including text, the histogram having been generated by image processing at least a portion of at least one channel of an image assumed to represent a document including text, the image having been sent by a remote end user to an online service over a computer network, evaluating monotony of at least a portion of the at least one histogram; and determining whether the image is authentic or forged based on at least one output of the evaluating.

An image processing apparatus has a color image, the image data being constituted by multiple pixels, each of the multiple pixels having a gradation value, and a controller, which is configured to generate a histogram of index values corresponding to brightness values of the multiple pixels constituting the image data, set an original threshold value based on the histogram which is referred to for binarization, detect a mound-shaped part, in the histogram, satisfying a particular condition, set an adjusting direction in which the original threshold value is to be adjusted, set the index value at a base on a particular direction side of a particular mound-shaped part which is one of mound-shaped parts existing on the adjusting direction side with respect to the original threshold value in the histogram as an adjusted threshold value, and apply a binarizing process to the image data using the adjusted threshold value.

In the case where a user extracts a desired character string by specifying a range by using a finger or the like of him/herself on an image including a character, a specific character (space or the like) located at a position adjacent to the desired character string is prevented from being included unintendedly in the selected range. The character area corresponding to each character included in the image is identified and character recognition processing is performed for each of the identified character areas. Then, from results of the character recognition processing, a specific character is determined and the character area corresponding to the determined specific character is extended. Then, the range selected by the user in the displayed image is acquired and character recognition results corresponding to a plurality of character areas included in the selected range are output.

An image processing apparatus counts at least one of the number of pixels having an identical color to a target pixel, the number of pixels having a similar color to the target pixel, and the number of pixels having a different color from the target pixel in a target window, and determines an attribute of the target pixel based on a result of the counting.