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 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: A device for assisting a user to perform a transaction on a machine is described. The device receives data that specifies a transaction mode to use for processing an image and accesses a knowledge base to provide data to configure the device for the transaction mode, the data including data specific to the transaction mode. The device receives an image or images of a portion of a machine that the user will use to perform the transaction and processes the image or images to identify a pattern of controls on the machine and to detect the presence of a user-controlled pointing item over controls on the machine. The device announces to the user the name or function of the control closest to an end of the user-controlled pointing item.

Abstract: Techniques for operating a reading machine are disclosed. The techniques include forming an N-dimensional features vector based on features of an image, the features corresponding to characteristics of at least one object depicted in the image, representing the features vector as a point in n-dimensional space, where n corresponds to N, the number of features in the features vector and comparing the point in n-dimensional space to a centroid that represents a cluster of points in the n-dimensional space corresponding to a class of objects to determine whether the point belongs in the class of objects corresponding to the centroid.

Abstract: A user of an accessibility device is taught to properly use the device with a test image such that the accessibility device captures the entirety of or a large portion of a test image. In training the user, the device processes test image's information located within the device's field of view. Based on this processed information, the device indicates to the user if the device should be re-positioned such that a larger portion of the test image comes within the device's field of view.

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: A handheld device includes an image input device capable of acquiring images, circuitry to send a representation of the image to a remote computing system that performs at least one processing function related to processing the image and circuitry to receive from the remote computing system data based on processing the image by the remote system.

Abstract: A reading machine includes an image input device including a lens and a polarizer disposed over the lens, a flash and a second polarizer disposed over the flash. The image input device also includes a computing device coupled to the image input device for capturing images, the computing device, including a processor to execute instructions and a computer program product residing on a computer readable medium, the computer program product comprising instructions for causing the processor to process the captured images to recognize features in the captured images.

Abstract: A computer executable process for simultaneous visual depiction of plural text hierarchies of a visually displayable machine readable text, including provisions for a visual cue as to a location of a user select text within the simultaneous visual depiction of plural text hierarchies is provided. A text hierarchy is extracted for a reader select text of a machine read text accessible by at least a data processing portion of a data processing and display system. Units of a select element of elements of the text hierarchy are formatted for display and displayed upon a display of the data processing and display system. A portion of text of the machine read text present in the select unit of a select element of elements of the text hierarchy is selected such that when said selected portion of text is present in a particular hierarchical representation, units the select element of elements of the text hierarchy are selectively of moved or positioned.

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: Reading product fabrication methods and devices are provided. Characteristic of the methods is the extraction of text specific attributes from machine readable text, and varying the text presentation in accordance with the attributes. Parts of speech and punctuation of a sentence are identified, with folding rules, which use the parts of speech to determine folding points, applied. The sentence is divided into text segments based upon the folding points, and horizontal displacement rules applied to create displayed text characterized by a cascading appearance.

Abstract: A reading device includes a computing device and an image input device coupled to the computing device for capturing low resolution images and high resolution images. The reading machine also includes a computer program product residing on a computer readable medium. The medium is in communication with the computing device and includes instructions to operate in a plurality of modes to optimize performance for specific uses of the reading device and process low and high resolution images during operation of at least one of the plurality of modes.

Abstract: A device for assisting a user to perform a transaction on a machine is described. The device receives data that specifies a transaction mode to use for processing an image and accesses a knowledge base to provide data to configure the device for the transaction mode, the data including data specific to the transaction mode. The device receives an image or images of a portion of a machine that the user will use to perform the transaction and processes the image or images to identify a pattern of controls on the machine and to detect the presence of a user-controlled pointing item over controls on the machine. The device announces to the user the name or function of the control closest to an end of the user-controlled pointing item.

Abstract: A portable reading device includes a computing device and a computer readable medium storing a computer program product to receive an image and select a section of the image to process. The product processes the section of the image with a first process and when the first process is finished processing the section of the image, process a result of the first process with a second process. While the second process is processing, repeats the first process on another section of the image.

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: A reading machine that operates in various modes includes image correction processing is described. The reading machine operates in different modes that optimize performance for specific uses of the reading machine. The reading machine receives data that specifies a mode to use for processing an image. The reading machine accesses a knowledge base to provide data to the machine for the specified mode, with the data including specific target visual elements that are expected to be encountered in processing images for the specified mode. The reading machine captures one or several images and processes the one or several images to identify one or more of the target elements in the image using information obtained from the knowledge base.

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 filter for removing contaminants from compressed gas is disclosed. The filter features an inverse flow regime wherein gas entering the filter first flows downwardly and then reverses direction before encountering any filter media. The filter has a connection head with a gas inlet, a gas outlet and oppositely disposed openings separated by a central partition. The openings are sealingly enclosed by elongated tubular housings which releasably attach to the head. The gas inlet communicates with one side of the partition and the outlet communicates with the opposite side. A plurality of individual filter elements are arranged on either side of the partition and filter out aerosol, vapor and particulate contaminants from the compressed gas. The filter elements are releasably mounted to the central partition and can be removed and replaced independently of one another.

Abstract: A moisture removal device for compressed gas lines and the like includes a connection head having a gas inlet and a gas outlet. An elongated housing having an internal cavity is attached to the connection head with the use of a clamp ring. The elongated tube and head are sealed to each other with the aid of O-rings preventing the escape of the compressed gases. Internal of the housing is a cartridge containing desiccant media for the removal of water vapor from a compressed gas. The cartridge is sealed and supported to the connection head with the use of a centrally threaded rod and O-rings located between the cartridge and the connection head. The external body of the desiccant cartridge is impermeable to gas and forces compressed gas from the inlet of the connection head to the bottom of the elongated housing.

Abstract: A moisture removal device for compressed air lines and the like includes a connection head having a gas inlet and a gas outlet. An elongated housing having an internal cavity is threaded to the connection head and sealed thereto with O-rings such that a central distribution tube is coupled to one of the inlet and the outlet and an open end of the housing is coupled to the other. The housing contains desiccant material for removing moisture from the gas, held captive in the housing by a retention screen across the open end. The distribution tube is impermeable between its end coupled to the connection head and one or more openings at the opposite end of the housing. The gas thus flows from the gas inlet through the entire bed of desiccant material and is discharged through the gas outlet in the connection head.