Seiko Epson Corporation

Jincheng Huang

Anoop Kumar Bhattacharjya

Joseph S Shu

Onur Gonen Guleryuz

A method for creating a caricature image from a digital image is provided. The method initiates with capturing digital image data. The method includes locating a facial region within the captured image data. Then, a facial feature template matching a facial feature of the facial region is selected. Next, the facial feature template is substituted for the facial feature. Then, the facial feature template is transformed into a caricature or non-realistic image. A computer readable medium, an image capture device capable of creating a caricature from a captured image and an integrated circuit are also provided.

Method and apparatus for converting a photo to a caricature image

A hybrid compression scheme in which one or more compression schemes are applied to a scanned document depending on its content. Based on the scanned document data itself and edge-map version thereof, a color test is performed to determine if the document is text or a drawing. If only a few colors are detected, the entire document is compressed by a photo compression technique at full resolution. If more than a few colors are present, the document is most likely a mixed mode document, in which case the entire document undergoes segmentation, a process in which text and drawing regions are separated from the background. The mask of the text and/or drawing regions are coded by a bi-level compression technique, whereas background is down-sampled, if necessary, and then compressed by a photo compression technique. A wrapper module is used to wrap the compressed stream(s) into a single file for easy browsing or transmitting.

Segmentation-based hybrid compression scheme for scanned documents

The appearance of edges in an image is improved through precise placement of subpixels within pixel cells that are located on or near edges in an image. Image data is examined to identify a 'target pixel' near the edge of an object that represents the object and is adjacent to a 'background pixel' that represents only background. The target pixel may represent both the object and its background or it may represent the object only. A &#x201c;second pixel&#x201d;, adjacent to the target pixel and representing the object, is also identified. The second pixel may represent both the object and its background or it may represent the object only. The target pixel's location with respect to the second pixel is analyzed to determine the placement of a subpixel within the target pixel cell and the placement of a subpixel within the second pixel cell, such that the edge of the object is well-defined and the density of the object is preserved. A vertical smoothing process can additionally be performed to improve further the appearance of edges in the image. The technique is particularly advantageous for printing a halftoned object represented by pixels that are not saturated.

PWM rendering for color/gray-scale text and graphics for laser printer

A method for generating a dispersed cluster screen defining a stable environment for printing an image is provided. The method initiates with generating a pattern of cluster centroids. Then a cluster growth sequence is defined. Next, a cluster is grown around the cluster centroid according to the cluster growth sequence. A computer readable medium having program instructions for generating a dispersed cluster screen and an image forming device configured to print an image according to a dispersed cluster screen technique are also provided.

Method and apparatus for generating dispersed cluster screen

A superpattern generator uses a first halftone pattern representing a first gray level and a second halftone pattern representing a second gray level to generate a larger pattern or 'superpattern'. In a preferred implementation, the superpattern generator generates a grid of elements to be used as a template for the superpattern, calculates a distance value representing the 'distance' from the first gray level to a desired gray level T, determines how many elements of the grid represent the first halftone pattern and how many represent the second halftone pattern based on the distance value, superimposes a dither matrix on the grid and assigns values representing the first halftone pattern or the second halftone pattern to pixels within the elements of the grid by examining threshold values in the dither matrix. This process is repeated for various values of Tto generate a set of superpatterns representing a set of gray levels intermediate to the first gray level and the second gray level.

Mixed screen design for multi-mode document

A dither matrix generator defines a three-dimensional array of pixels referred to as the 'cluster array' in which each pixel is designated based on its value as a 'cluster pixel' or a &#x201c;void pixel&#x201d;. The dither matrix generator also defines a three-dimensional array referred to as the &#x201c;dither matrix,&#x201d; and assigns rank values to the dither matrix in two stages. In the first stage, the dither matrix generator identifies the largest cluster in the cluster array, identifies a cluster pixel located in the largest cluster, assigns a rank value to the element in the dither matrix corresponding to the cluster pixel and removes the cluster pixel from the cluster array. The process is repeated until the cluster array contains no cluster pixels. In the second stage, the dither matrix generator resets the pixels in the cluster array to their initial values, identifies the largest void in the cluster array, identifies a void pixel within the largest void, assigns a rank value to the element in the dither matrix corresponding to the void pixel and inserts a cluster pixel in the location of the void pixel. The process is repeated until the cluster array contains only cluster pixels.

Growing community of inventors

Sunnyvale, CA, United States of America

Jincheng Huang