Abstract: In a method of image signal processing, defective pixels are determined on-the-fly in a digital image representation based on a comparison of a pixel under evaluation with its surrounding pixels, with reference to a known resolving capability of a lens-sensor arrangement that captured the digital image representation. In response to the determination of defective pixels, the defective pixels are corrected.

Abstract: A method and system for image chroma suppression of an image sensor system. Chroma suppression is performed to reduce the false color phenomena. The amount of chroma suppression is performed based on the strength of spatial frequency for a current processing pixel measured during edge detection. In determining the strength of spatial frequency of the current processing pixel, only a small number of green pixel values are needed, regardless of whether or not the current processing pixel is a green pixel within the Bayer pattern. As such, line buffers from the color interpolation module of an image sensor system can also be used for the purpose of chroma suppression.

Abstract: Method and system for a single-chip camera where an image sensor is a single-chip digital color imaging device that incorporates a sensor array that captures still or full-motion video and converts the images to digital data. Moreover, the image sensor employs a built-in correlated double sampler, an internal analog-to-digital converter, and a timing circuitry. Output from the sensor is an 8-bit or more raw data, horizontal sync signals, and vertical sync signals. The output raw data may then be fed into a compression circuit that generates packets of compressed output data. The compressed data is transmitted with a USB transceiver using isochronous packets. The packets are then received, decompressed, and color processed by a host PC.

Abstract: An automatic white balancing method and system. A modification of “color in perspective” white balancing technique is implemented. Rather than a default projection plane used by the typical white balancing technique, the projection plane for a RGB space is automatically selected to allows the projected reference gamuts in the projection plane to be as disjoined as possible, thereby making them as uncorrelated as possible. In turn, automatic white balancing is performed using the color temperature associated with the projected reference gamut most correlated with the projected gamut of an image sensor.

Abstract: A fingerprint recognition method includes iterative gamma correction that compensates moisture effect, feature extraction operations, directional morphological filtering that effectively links broken ridges and breaks smeared ridges, adaptive image alignment by local minutia matching, global matching by relaxed rigid transform, and statistical matching with Gaussian weighting functions.

Abstract: An interactive presentation control system, used with a display computer, a computer-controlled image projector, a laser pointer, and a projection screen, comprises a digital camera and a control module. The display computer generates electronic images which are projected onto the projection screen as presentation images. During operation, a presenter uses the laser pointer to trace out a pre-established gesture spatial pattern onto the presentation image. The digital camera acquires these presentation images from which images a processing section in the control module analyzes and identifies the gesture spatial pattern. The identified gesture spatial pattern is compared to a set of pre-established patterns to find a match and to subsequently select a correlated display command.

Abstract: An apparatus and method for calibrating a computer-generated projected image to the displayed image viewed on the computer screen. Four or more calibration spots, at least three of which are collinear, arrayed in a predetermined pattern in both the displayed and the projected images, are optically imaged and electronically discriminated in the projected image, their coordinates ascertained and related to the predetermined pattern so as to derive transformation coefficients used in the process of converting a location on the projected image to the corresponding location in the displayed image.

Abstract: Features characterizing at least two significant portions or regions of the printed pattern on a model document are extracted from a scanned-in image of the model document. Statistical characteristics of each significant region are calculated from the extracted features and saved in a memory. In addition, geometrical relationships, e.g. distances and angles, between the regions are also saved in a memory. The geometrical relationships are represented by the coordinates of the regions in a predetermined coordinate system, e.g. the x-y coordinate system corresponding to the scan area on the platen of a scanner. When a new or trial document is scanned and examined through a search window, features are extracted from the search window blocks and compared to the statistical characteristics of the model document previously stored in memory. If there is a match, the coordinates of the search window having the matching features in the trial document are recorded in a candidate list.

Abstract: A face recognition system is provided comprising an input process or circuit, such as a video camera for generating an image of a person. A face detector process or circuit determines if a face is present in a image. A face position registration process or circuit determines a position of the face in the image if the face detector process or circuit determines that the face is present. A feature extractor process or circuit is provided for extracting at least two facial features from the face. A voting process or circuit compares the extractor facial features with a database of extracted facial features to identify the face.

Abstract: A source image containing both relatively low frequency information (i.e. graphics, pictures and background) and relatively high frequency information (i.e. text) are input to an image processing unit. This image processing unit can be embodied in functional units of an output device such as an LCD projector or may be part of a personal computer connected to the output device, or may even be part of an input device that provides the source image. The source image will be in one resolution and the output device will have a different, generally lower, resolution. The source image is segmented into a black text image and a white text image (i.e. portions of the source image formed as image blocks or tiles). The black text image and the white text image are then subtracted from the source image to form a background image. Then, the background image, the black text image and the white text image are filtered separately using different filters for each. The filtered or down-sampled images are then merged.

Abstract: A system for automatically detecting and recognizing the identity of a deformable object such as a human face, within an arbitrary image scene. The system comprises an object detector implemented as a probabilistic DBNN, for determining whether the object is within the arbitrary image scene and a feature localizer also implemented as a probabilistic DBNN, for determining the position of an identifying feature on the object such as the eyes. A feature extractor is coupled to the feature localizer and receives coordinates sent from the feature localizer which are indicative of the position of the identifying feature and also extracts from the coordinates information relating to other features of the object such as the eyebrows and nose, which are used to create a low resolution image of the object. A probabilistic DBNN based object recognizer for determining the identity of the object receives the low resolution image of the object inputted from the feature extractor to identify the object.