Abstract: A method that includes receiving an image, automatically determining at least one region of interest in the image based on at least one color deficiency type from a plurality of color deficiency types, modifying the image by correcting the at least one region of interest and producing an output of the modified image.

Abstract: An image processing system is described which is arranged to highlight information in image displays by selectively blurring less important areas of an image. By generating such displays comprising areas which are in focus and areas which are out of focus, a viewer's attention is preferentially drawn towards those areas of an image which appear sharp. By having a display system which is arranged to generate such images a means is provided to direct a viewer's attention towards considering the sharp areas of the image display first. Further the selective blurring portions of an image reduces rather than increases the amount of information presented to a viewer and hence reduces the likelihood that a viewer will become overloaded with information. Display systems of this type are therefore especially applicable to complex control environments as means of directing viewer's attention.

Abstract: Navigation techniques including map based and object recognition based and especially adapted for use in a portable reading machine are described.

Abstract: A monitoring system for use with a sewing machine. The monitoring system includes a camera assembly mounted to a base of the sewing machine with a camera that collects images from a bottom side of the fabric. The camera assembly delivers images of the back side of the fabric to a monitor assembly that includes a display device. The display device displays the images collected by the camera. The monitor can be mounted to an upper or arm portion of the sewing machine for convenient viewing by the operator during use of the sewing machine.

Abstract: There is presented a system and method for providing real-time object recognition to a remote user. The system comprises a portable communication device including a camera, at least one client-server host device remote from and accessible by the portable communication device over a network, and a recognition database accessible by the client-server host device or devices. A recognition application residing on the client-server host device or devices is capable of utilizing the recognition database to provide real-time object recognition of visual imagery captured using the portable communication device to the remote user of the portable communication device. In one embodiment, a sighted assistant shares an augmented reality panorama with a visually impaired user of the portable communication device where the panorama is constructed from sensor data from the device.

Abstract: Embodiments of the invention provide devices and methods for capturing text found in a variety of sources and transforming it into a different user-accessible formats or medium. For example, the device can capture text from a magazine and provide it to the user as spoken words through headphones or speakers. Such devices are useful for individuals such as those having reading difficulties (such as dyslexia), blindness, and other visual impairments arising from diabetic retinopathy, cataracts, age-related macular degeneration (AMD), and glaucoma.

Abstract: The invention deals with an aid device for reading a printed text, comprising a data acquisition peripheral with a camera and a communication interface, said peripheral being movable by a user on a printed text to frame a portion of text, a processing unit, communication means between the peripheral and the processing unit, and a vocal reproduction device. The processing unit is programmed to acquire a sequence of images framed by the camera, to detect when the user has stopped on the text, to recognize at least one word which the user intends reading, and to reproduce the sound of said at least one word by means of vocal synthesis by means of the vocal reproduction device.

Abstract: A microform imaging apparatus comprising a chassis including a microform media support structure configured to support a microform media within a plane substantially orthogonal to a first optical axis, a fold mirror supported along the first optical axis to reflect light along a second optical axis that is angled with respect to the first optical axis, a lens supported along one of the first and second optical axis, an area sensor supported along the second optical axis, a first adjuster for moving the area sensor along at least a portion of the second optical axis and a second adjuster for moving the lens along at least a portion of the one of the first and second optical axis.

Abstract: An image processing apparatus includes a color converting unit that converts input image data into image forming data used for image formation; and a control unit that controls the image formation by the image forming data, wherein the color converting unit converts each of a plurality of predetermined colors that are difficult for colorblind people to mutually distinguish among colors included in a color space of the input image data, as difficult colors for colorblind people, into a same color in a color space of the image forming data.

Abstract: Disclosed is a system and method for converting a digital number to text and for pronouncing the digital number. The system includes a filtration system for determining whether the digital number has nonnumeric symbols and for generating a filtrated number, an analyzing system for analyzing the filtrated number, a composition system configured to collect words associated with ternary units of the filtrated number, a linking system configured to link the words, and a pronouncing system for pronouncing the linked words.

Abstract: A method controls a projection of a projector. The method predetermines hand gestures, and assigns an operation function of an input device to each of the predetermined hand gestures. When an electronic file is projected onto a screen, the projector receives an image of a speaker captured by an image-capturing device connected to the projector. The projector identifies whether a hand gesture of the speaker matches one of the predetermined hand gestures. If the hand gesture matches one of the hand gestures, the projector may execute a corresponding assigned operation function.

Abstract: The present invention provides a user interface for providing press-to-talk-interaction via utilization of a touch-anywhere-to-speak module on a mobile computing device. Upon receiving an indication of a touch anywhere on the screen of a touch screen interface, the touch-anywhere-to-speak module activates the listening mechanism of a speech recognition module to accept audible user input and displays dynamic visual feedback of a measured sound level of the received audible input. The touch-anywhere-to-speak module may also provide a user a convenient and more accurate speech recognition experience by utilizing and applying the data relative to a context of the touch (e.g., relative location on the visual interface) in correlation with the spoken audible input.

Abstract: Briefly, in accordance with one or more embodiments, an image-processing system is capable of receiving an image containing text, applying optical character recognition to the image, and then audibly reproducing the text via text-to-speech synthesis. Prior to optical character recognition, an orientation corrector is capable of detecting an amount of angular rotation of the text in the image with respect to horizontal, and then rotating the image by an appropriate amount to sufficiently align the text with respect to horizontal for optimal optical character recognition. The detection may be performed using steerable filters to provide an energy versus orientation curve of the image data. A maximum of the energy curve may indicate the amount of angular rotation that may be corrected by the orientation corrector.

Abstract: A method of identifying a person by his iris through determining an interior limit and using a predefined exterior limit to form an analysis zone. A code associated with the analysis zone is generated and compared with a previously generated reference code. If there is no match another predefined exterior limit is used. The process repeats as long as predefined exterior limits exist or until a positive match is made.

Abstract: Methods and apparatus for facilitating detection of a presence or an absence of at least one underground facility within a dig area. A digital image that does not include an aerial image of a geographic area including the dig area is displayed on a display device. Via a user input device associated with the display device, at least one indicator is added to the displayed digital image to provide at least one indication of the dig area and thereby generate a marked-up digital image. Information relating to the marked up digital image is electronically transmitted and/or electronically stored so as to facilitate the detection of the presence or the absence of the at least one underground facility within the dig area.

Abstract: Methods and system for providing vision assistance using a portable telephone with a built-in camera. In some embodiments, the system identifies the value of a bank note by determining the average number of transitions between black and white in each vertical line of pixels corresponding to a numeric digit. In other embodiments, the system captures an image and identifies an object in the image by comparing the value of each pixel in the image to a threshold intensity and marking the pixels that exceed the threshold. The system then generates a plurality of candidate groups by grouping marked pixels that are within a predetermined distance from other marked pixels. The object is identified based on the relative position of each candidate group to other candidate groups.

Abstract: A reading machine has processing for detecting common text between a pair of individual images. The reading machine combines the text from the pair of images into a file or data structure if common text is detected, and determines if incomplete text phrases are present in the common text. If incomplete text phrases are present, the machine signals a user to move an image input device in a direction to capture more of the text.

Abstract: A digital microform imaging apparatus which includes an approximately monochromatic illumination source transmitting an incident light through a diffuse window along a first optical axis of the apparatus. A microform media support is configured to support a microform media after the diffuse window and along the first optical axis. An approximately 45 degree fold mirror reflects the incident light transmitted through the microform media approximately 90 degrees along a second optical axis. An imaging subsystem includes a lens connected to a first carriage which is linearly adjustable approximately parallel with the second optical axis, and an area sensor connected to a second carriage which is linearly adjustable approximately parallel with the second optical axis.

Abstract: Methods and apparatus for generating a searchable electronic record of a locate operation performed by a locate technician, in which a presence or an absence of at least one underground facility within a dig area is identified. An image of a geographic area comprising the dig area is electronically received, and combined with image-related information so as to generate the searchable electronic record. The image-related information comprises at least a geographic location associated with the dig area, and a timestamp indicative of when the locate operation occurred. The searchable electronic record of the locate operation is electronically transmitted and/or electronically stored so that performance of the location operation is verifiable.

Abstract: A method for ringtone, voice, and sound notification of printer status, comprising obtaining status information of a printer, converting it into an audible report, and delivering the audible report. The method is especially useful for visually-impaired users and for shared printers in crowded situations where it is difficult for each user to see the panel or monitor display. The methods also include detection by the events controller, UI manager instructing an audio manager, codec decoding an audio file in firmware and hardware organization; job owner identification information embedded into a print job with a unique tag; user identification sound data embedded in a print job; audible report for multiple jobs in a job queue, with positional information; text-to-speech conversion; unique ringtone melody for each user, comprising department prefix, higher pitch modulation for higher priority, and automatically converting an alphanumeric character into the corresponding note.

Abstract: The present invention discloses an on-line identifying method of hand-written Arabic letter. The advantage of the present invention is that the multilayer coarse classification algorithm based on the local characteristic of Arabic letter fully utilize the various local characteristics of Arabic letter, obtain the first candidate letter aggregation matching with the inputted hand-written Arabic letter according to the first level coarse classification formed by the stroke number of letter, and then obtain the second candidate letter aggregation matching with inputted hand-written Arabic letter according to the other local characteristics and the first candidate letter aggregation. The application of the algorithm enables that the inputted hand-written Arabic letter only need to match with the standard letter stored in the predetermined letter library and the corresponding standard letters of the second candidate letter aggregation.

Abstract: A portable reading machine detects poor image conditions for performing optical character recognition processing. The portable reading machine receives an image of sufficient resolution to distinguish lines of text but not necessarily of sufficient resolution to distinguish individual characters and processes the image to determine imaging conditions from the image. The reading machine reports imaging conditions to the user.

Abstract: One embodiment a vision substitution system for communicating audio and tactile representations of features within visual representations includes selecting (1) activity-related parameters; obtaining (2) images or other visual representations according to the activity-related parameters; acquiring (3) features including shapes and corners related to the visual representations according to the activity-related parameters; and outputting (4) effects related to the features on audio and/or tactile displays according to the activity-related parameters. The corners of shapes and other lineal features are emphasized via special audio and tactile effects while apparently-moving effects trace out perimeters and/or shapes. Coded impulse effects communicate categorical visual information. Special speech and braille codes can communicate encoded categorical properties and the arrangements of properties.

Abstract: In some embodiments, disclosed is reading device that comprises a camera, at least one processor, and a user interface. The camera scans at least a portion of a document having text to generate a raster file. The processor processes the raster file to identify text blocks. The user interface allows a user to hierarchically navigate the text blocks when they are read to the user.

Abstract: Methods and apparatus for facilitating detection of a presence or an absence of at least one underground facility within a dig area. A digital image of a geographic area including the dig area is electronically received, and at least a portion of the received digital image is displayed on a display device. The dig area is delimited on the displayed digital image, via a user input device associated with the display device, so as to generate a marked-up digital image including a delimited dig area, without acquiring geographic coordinates to delimit the dig area. Information relating to the dig area is electronically transmitted and/or electronically stored so as to facilitate the detection of the presence or the absence of the at least one underground facility within the dig area.

Abstract: In some embodiments, a reading device is provided with a shortcut read mode in which a user can instruct the reading device of the type of document (e.g., invoice, package label, newspaper, etc.) that is to be read so that the device can more efficiently find and read back to the user desired (target) information from the document.

Abstract: One embodiment of the invention includes a gesture recognition interface system. The system may comprise a substantially vertical surface configured to define a gesture recognition environment based on physical space in a foreground of the substantially vertical surface. The system may also comprise at least one light source positioned to provide illumination of the gesture recognition environment. The system also comprises at least two cameras configured to generate a plurality of image sets based on the illumination being reflected from an input object in the gesture recognition environment. The system further comprises a controller configured to determine a given input gesture based on changes in relative locations of the input object in each of the plurality of image sets. The controller may further be configured to initiate a device input associated with the given input gesture.

Abstract: A portable reading machine that operates in several modes and performs image preprocessing to prior to optical character recognition. The portable reading machine receives a low resolution image and a high resolution image of a scene and processing the low resolution image to recognize a user-initiated gesture using a gesturing item that indicates a command from the user to the reading machine and the high resolution image to recognize text in the image of the scene, according to the command from the user to the machine.

Abstract: Briefly, in accordance with one or more embodiments, an image processing system is capable of receiving an image containing text, applying optical character recognition to the image, and then audibly reproducing the text via text-to-speech synthesis. Prior to optical character recognition, an orientation corrector is capable of detecting an amount of angular rotation of the text in the image with respect to horizontal, and then rotating the image by an appropriate amount to sufficiently align the text with respect to horizontal for optimal optical character recognition. The detection may be performed using steerable filters to provide an energy versus orientation curve of the image data. A maximum of the energy curve may indicate the amount of angular rotation that may be corrected by the orientation corrector.

Abstract: Methods and apparatuses to provide improved Braille support are described herein. A connection to a Braille device is received, and a Braille caption panel that includes a Braille code is displayed to simulate an output to the Braille device. The Braille caption panel can include a text translated to the Braille code. The Braille caption panel can include a control element. An accessibility service can be automatically launched to provide the output to the Braille device.

Abstract: A reading device for blind or visually impaired persons for recognizing and reading text passages comprises an image capturing unit being configured to capture an image of an environment of a blind or visually impaired person and to output image data corresponding thereto, an image processing unit being configured to process the image data such that text is recognized and extracted from the image data and to output text data corresponding thereto, a text outputting unit being configured to output data corresponding to the text data in a form noticeable or convertable to be noticeable by the blind or visually impaired person, and a housing comprising a first part and a second part, the first part having the image capturing unit attached thereto and the second part accommodating the image processing unit and the text outputting unit.

Abstract: The invention is a system whereby a video image can be converted into an audio signal. A portable apparatus is described which allows a visually blind person to hear the images and thus ‘see’. This does not require expensive equipment nor does it require surgery. It has applications for non-blind people such as with a pilot seeing radar information. It can be performed with an inexpensive video camera, a portable computer, and earphones. It is also readily adapted to a customized and compact system involving a micro camera, specialized computer, and ear buds.

Abstract: A method and device for entering data is provided wherein the pressing of up to two combinations of proximate keys on a keypad concurrently sends a signal or signals from the keypad to a processor. The processor receives the signal or signals and identifies a character, symbol, or function associated with the signal or signals and reports the same. In one embodiment, the keypad used for entering the data has a configuration of three columns and four rows. A method of identifying a character, symbol, or function comprises comparing the signal or signals to a data set of associated characters, symbols, or functions wherein the data set is mapped to said signal or signals with a modified Braille cell.

Abstract: An information presenting apparatus, based on display status on a screen, estimates text blocks that a user is likely to classify as poor-legibility blocks and is likely to wish to be read aloud. A simple device that allows selecting from the text blocks is provided. A poor-legibility-block extractor divides text to be displayed on the screen into blocks corresponding to individual text blocks, classifies blocks including characters of sizes less than or equal to a predetermined size as poor-legibility blocks, and assigns block numbers to the poor-legibility blocks. A document display unit displays areas of the respective poor-legibility blocks as distinguished from other areas, with block numbers assigned to the respective poor-legibility blocks. When the user presses a numeric key corresponding to a block number, text in the corresponding block is read aloud.

Abstract: A reading machine has processing for detecting common text between a pair of individual images. The reading machine combines the text from the pair of images into a file or data structure if common text is detected, and determines if incomplete text phrases are present in the common text. If incomplete text phrases are present, the machine signals a user to move an image input device in a direction to capture more of the text.

Abstract: A method and system for supporting and augmenting a non-reading sighted person's capabilities to interact with her environment using visual language hieroglyphics and computer sensory perception. This invention provides navigational support by displaying orientation hieroglyphics in a dialog with the user similar to that of a “seeing-eye” dog and visually-disabled owner. The present invention supports and augments a person's capability to plan, problem solve, and learn. This is accomplished through interactive dialogue executed in real time between the non-reading sighted person and the system, by utilizing an artificially intelligent method for providing visual communication and cognitive reasoning support for non-reading sighted persons.

Abstract: A system for the automated conversion to audio of text displayed on a surface.

Abstract: Disclosed are a method and a system that adaptively transform visual contents inputted from a network, in accordance with the visual characteristics of a terminal user. A visual characteristics descriptor that describes the information of the user visual characteristics in a predetermined format is proposed. The descriptor includes the information of the color vision deficiency type and the color vision deficiency degree. The color vision deficiency may be described in numerical degree or textual degree. The invention adaptively transforms visual contents differently in accordance with the color vision deficiency type.

Abstract: A portable reading machine that operates in several modes and performs image preprocessing to prior to optical character recognition. The portable reading machine receives a low resolution image and a high resolution image of a scene and processing the low resolution image to recognize a user-initiated gesture using a gesturing item that indicates a command from the user to the reading machine and the high resolution image to recognize text in the image of the scene, according to the command from the user to the machine.

Abstract: In some embodiments, disclosed is reading device that comprises a camera, at least one processor, and a user interface. The camera scans at least a portion of a document having text to generate a raster file. The processor processes the raster file to identify text blocks. The user interface allows a user to hierarchically navigate the text blocks when they are read to the user.

Abstract: A user selects one or more check boxes on a collection coversheet to identify, by location on the coversheet, target documents within a previously stored collection of documents. The check boxes also specify actions to be performed on the target documents. The coversheet is scanned and the check boxes are located and read to determine which have been marked. The specified actions are then performed on the target documents. If the specified actions change the organization or architecture of the document collection, an updated version of the collection may be generated and stored, and a new coversheet may be printed.

Abstract: A method for tracking paper currency in a holder, includes: scanning paper currency deposited or removed from a holder; determining the total number of each individual denomination of paper currency contained within the holder based on the scanned paper currency deposited and removed from the holder; recording the total number of each individual denomination of paper currency; determining the total value of the paper currency within the holder; outputting the denomination of paper currency when the paper currency is scanned during depositing or removal from the holder; outputting the recorded number of each individual denomination of paper currency and the total value of the currency within the holder; and wherein the recorded number of each individual denomination of paper currency and the total value of the currency within the holder is dynamically tabulated based on the scanning of paper currency deposited or removed from the holder.

Abstract: Embodiments of the invention provide devices and methods for capturing text found in a variety of sources and transforming it into a different user-accessible formats or medium. For example, the device can capture text from a magazine and provide it to the user as spoken words through headphones or speakers. Such devices are useful for individuals such as those having reading difficulties (such as dyslexia), blindness, and other visual impairments arising from diabetic retinopathy, cataracts, age-related macular degeneration (AMD), and glaucoma.

Abstract: A method and system for enabling user interaction with computer software running in a computer system. The user is provided with an interface surface containing information relating to the computer software and including coded data indicative of at least one interactive element relating to the computer software. A sensing device in the form of an optically sensing stylus contains identifying data indicative of an identity of the user. When the user writes with the stylus, or uses it as a pointer, an operative end of the stylus is brought into contact with the interface surface. The sensing device senses indicating data indicative of the at least one interactive element using at least some of the coded data. The computer system receives the identifying data and the indicating data from the sensing device. The interactive element is identified in the computer system using the indicating data, and user data is identified using the identifying data.

Abstract: Systems, methods and devices for capturing environmental image data and providing tactile feedback about the visual environment to a user. One or more image sensing devices are mounted on various appendages of a user and are used to sense the environment. The image data is sent to a computer vision system where it is processed in order to identify specific objects within the environment. When the computer vision system makes such an identification it may send a signal to a haptic stimulator mounted on a user's appendage or may be used to control an object in the environment.

Abstract: A method and system for enabling user interaction with computer software running in a computer system. A user is provided with an interface surface containing information relating to the computer software and including coded data indicative of an identity of the interface surface and of at least one reference point of the interface surface. The user places a sensing device into an operative position relative to the interface surface. In this operative position, the sensing device senses indicating data indicative of: the identity of the interface surface; and a position of the sensing device relative to the interface surface, using at least some of the coded data. The computer system receives the indicating data from the sensing device, and uses the indicating data to identify at least one interactive element relating to the computer software. The computer software is then operated in accordance with instructions associated with the at least one interactive element.

Abstract: A method for assisting a visually impaired person with a document job. The method includes scanning a document that includes at least one sheet, detecting at least one characteristic of the scanned document, and providing a signal identifying the at least one characteristic.

Abstract: A gesture recognition system enabling control of a robotic device through gesture command by a user is provided, comprising a robotic unit, a video or infrared camera affixed to the robotic unit, computing means, and high and low level of control gesture recognition application code capable of enabling the system to locate points of left hand, right hand, upper torso and lower torso of the user in the video imagery and convert it to waveform data, correlate the waveform data to user command data, and form corresponding control voltage command(s) for production of electric current voltage(s) to drive one or more of the electric motors or actuators of the robotic device to thereby control same. In addition, a computer software program is provided for use in the gesture recognition system described above.

Abstract: A method of operating a reading machine includes receiving an image and receiving an user-initiated command. The reading machine interprets the command to determine the portion of the image to process.

Abstract: A gesture recognition simulation system and method is provided. In one embodiment, a gesture recognition simulation system includes a three-dimensional display system that displays a three-dimensional image of at least one simulated object having at least one functional component. A gesture recognition interface system is configured to receive an input gesture associated with a sensorless input object from a user. The gesture recognition simulation system further comprises a simulation application controller configured to match a given input gesture with a predefined action associated with the at least one functional component. The simulation application controller could invoke the three dimensional display system to display a simulated action on at least a portion of the at least one simulated object associated an input gesture and a predefined action match.