Hewlett-packard Company

Microsoft Technology Licensing, LLC

Hewlett-packard Development Company, L.p.

Dan S Johnson

Steven L Webb

Michael J Steinle

Pablo Luis Sala

Kurt Eugene Spears

Mark E Wanger

Robert Gregory Gann

Kevin J Youngers

Carl Edward Picciotto

Greg A Degi

Mark D Seaman

Steven G Henry

Scott Mail

Patricia D Lopez

Michael D Erickson

Gregory A Brake

Wayne G Phillips

Nancy K Mundelius

Shaz Naqvi

A method for touch classification includes obtaining frame data representative of a plurality of frames captured by a touch-sensitive device, analyzing the frame data to define a respective blob in each frame of the plurality of frames, the blobs being indicative of a touch event, computing a plurality of feature sets for the touch event, each feature set specifying properties of the respective blob in each frame of the plurality of frames, and determining a type of the touch event via machine learning classification configured to provide multiple non-bimodal classification scores based on the plurality of feature sets for the plurality of frames, each non-bimodal classification score being indicative of an ambiguity level in the machine learning classification.

Touch classification

Systems and methods of creating a touch sensitive surface structure comprising a piezo structure in communication with a deformable surface such that the piezo structure, or any suitable pressure sensing device, is capable of sensing pressure from a touch upon the deformable surface and communicating that pressure signal to an actuating circuit. The actuating circuit, upon receiving a suitable pressure signal, sends a piezo actuating signal to the piezo structure. The piezo structure, upon receiving the piezo actuating signal, is capable of communicating a mechanical signal to the deformable surface, sufficient for a person's finger to feel a 'click' and/or haptic sensation. In one embodiment, the piezo actuating signal comprises a first slow charging portion and a second fast discharging portion, sufficient for the piezo structure to communicate the click and/or haptic sensation.

Piezo-actuated virtual buttons for touch surfaces

The present invention provides a compact, portable system for capturing two dimensional images from printed and related media, as well as three dimensional scenic images, such as photographs, combining the optical features of scanning and photography. A compact, portable image capturing system is provided that is relatively simple and inexpensive, which is easy to operate, rugged, reliable, integrating the navigational and text-gathering functionalities seamlessly, transparently, and reliably, and not prone to optical misalignment, or cessation of scanning and loss of information, obviating much of the repetition of scanning efforts required by the conventional art. The present invention provides a compact, portable system for capturing both two dimensional images from printed and related media, and three dimensional scenic images, such as photographs, while providing constant user feedback of the image quality and effectiveness, during the imaging process.

Compact portable 2D/ 3D image capture system

An image scanner uses optical targets within the scanner to characterize imperfections of a lens system and to partially compensate for the imperfections using digital image processing. In one sample embodiment, a series of two-dimensional optical targets are placed outside the document scanning area. Each individual target is suitable for obtaining an estimate of the point-spread function for a small segment of the scan line. Each point-spread function is then used to compute a convolution kernel for the corresponding segment of the scan line. Alternatively, each point-spread function may be used in an iterative solution for a modified image. In an alternative embodiment, a two-dimensional known random pattern is provided for a target. Cross-correlation of a portion of the known random pattern with the scanned image of the same portion of known random pattern provides an estimate of the point-spread function for the portion of the scan line corresponding to the portion of the known random pattern. Providing a series of targets or continuous random target over the width of the scan line, within the scanner, enables determination of the point-spread function as a function of position for an assembled lens, at the humidity and temperature appropriate for the scan. As a result, a smaller, lower cost lens can be used and some the lens aberrations can be removed from the final scanned image.

Optical image scanner with internal measurement of point-spread function and compensation for optical aberrations

A multiple image scanner that performs a single scan of a document containing different types of images (e.g., text and graphics) and sends multiple renditions of the same document from the scanner to a host computer (e.g., one high resolution gray scale image and one low resolution high bit depth color image; or one high resolution, low bit depth gray scale or monochrome image and one low resolution, high bit depth gray scale or monochrome image; or one high resolution, low bit depth color image and one low resolution, high bit depth color image), thus greatly reducing the total amount of data sent to and processed by the host computer.

Multiple image scanner

A process for compensation for real time changes of magnification in an optics system for an image scanner. Targets having high-contrast edges, on both sides of an image to be scanned, are scanned along with the image. If magnification changes, the number of pixels between the targets may change. The pixels between the targets are filtered to generate a fixed number of pixels. Photosensor sensitivity compensation values may be separated into factory compensation values and scanner pre-scan compensation values. Factory compensation values are applied before filtering. Differences between factory compensation values and pre-scan compensation values are applied after filtering.

Image scanner with compensation for magnification changes

A method of adjusting the resolution of a scan based on the scan area or the scan window size. The smaller the scan window size, the higher the scan resolution would be. The final scan resolution is a function of an initial resolution, a resolution modifier, a printer factor, and an image factor. The resolution modifier, the printer factor and the image factor are dependent on the scan window size, the system printer, and the scan image type respectively.

Adaptive resolution scanning

A method for image processing combining a device-specific image processing kernel operation with a general image processing kernel operation. Device specific parameters are sent from a host computer to an imaging device. The imaging device selects appropriate device-specific convolution coefficients. The host computer selects additional kernel operations. In a first example embodiment, the device-specific coefficients are then uploaded to the host computer and the host computer convolves the host-specified operations with the device-specific operations. The combined kernel is then downloaded to the imaging device. In an alternative embodiment, the host-specified operations are downloaded to the imaging device for combining. The combined kernels are then used by the imaging device for convolution operations on an image. As a result, host computer software can modify a kernel operation within an imaging device with minimal knowledge of device-specific parameters such as native resolution.

Image processing system with alterable local convolution kernel

An imaging system for applying separate color tonemaps comprises an optical scanning assembly configured to scan an object and produce image data having a first resolution that corresponds to a color characteristic. A memory device associated with the imaging system stores a look-up table that corresponds to a predetermined transfer function. An image data processor operatively associated with the memory device and the optical scanning assembly alters the resolution of the image data having the first resolution to produce image data having a second resolution, the second resolution being less than the first resolution, and also applies the image data having the second resolution to the look-up table to look up LowPoint image data having a third resolution, the third resolution being greater than the second resolution.

Method and apparatus for applying tonal correction to image data

A method of scanning an object at a predetermined resolution along the scanning direction with color scanner apparatus having M linear photosensors positioned in parallel, spaced-apart relation and being exposed for a predetermined exposure time, may comprise the steps of calculating an exposure delay time for each of (M-1) slave linear photosensors. Then, at a start scan time, a master linear photosensor is exposed to light from the illuminated scan line for the predetermined exposure time. However, the slave linear photosensors are not necessarily exposed at the start scan time. Instead, the first exposure for each of the slave linear photosensors is delayed for a time equivalent to the exposure delay time calculated for each respective slave linear photosensor.

Variable resolution color image scanner having an exposure delay between

Disclosed is a system of optical character recognition that first segments a page image into character images. A set of features is extracted and compared to proto-features from a template in order to classify a character, and convert it into a character code. This comparison is performed by comparing each feature of a character image to each proto-feature of each template to create a match rating list which is sorted in descending order. The top match rating and any close ratings are selected and output. To create the ratings, the angles and lengths of the features and proto-features are compared and then the result is normalized to a specific range of values.

Noise tolerant optical character recognition system

Disclosed is a method of optical character recognition that first segments a graphical page image into word images. The method obtains a set of features by extracting smaller outlines of the dark regions in the word images, and then further dissecting each of the smaller outlines into small sections called micro-features. Micro-features are simply sections of character outlines, therefore, they can easily be extracted from the outlines of an entire word without any knowledge about character segmentation boundaries. Micro-features are extracted from an outline by finding the local extremities of the outline and then defining a micro-feature between each pair of sequential extremities. Once extracted, the micro-features are compared to micro-features from an ideal character in order to classify a character, and convert it into a character code.

A solution to accurately aligning a read-write head over a previously written data track on both a write protected and not write protected tape is disclosed. A control unit, preferably a programmed microprocessor, electronically provides a sequence of control outputs to move the tape and step the head to locate an edge of the tape. The control unit then moves the head a fixed distance to be over a selected data track. A threshold circuit controls the readout of data from the head of the tape in such a way as to improve edge find reliability.

Growing community of inventors

Greeley, CO, United States of America

Dan S Johnson