Abstract: A method for detecting objects in a digital image includes the steps of generating a first segmentation map of the digital image according to a non-object specific criterion, generating a second segmentation map of the digital image according to an object specific criterion, and detecting objects in the digital image using both the first and second segmentation maps. In a preferred embodiment of the invention, the non-object specific criterion is a color homogeneity criterion and the object specific criterion is an object specific color similarity, wherein the object specific color is skin color and the method further comprises the step of detecting red-eye in the detected skin color regions.

Abstract: A digital image processing method for detecting human figures in a digital color image, comprising the steps of: providing a digital color image having pixels representing RGB values; segmenting the image into non-overlapping regions of homogeneous color or texture; detecting candidate regions of human skin color; detecting candidate regions of human faces; and for each candidate face region, constructing a human figure by grouping regions in the vicinity of the face region according to a pre-defined graphical model of the human figure, giving priority to human skin color regions.

Abstract: A method of producing an image of at least a portion of a digital image that includes pixels includes computing a belief map of the digital image, by using the pixels of the digital image to determine a series of features and using such features to assign the probability of the location of a main subject of the digital image in the belief map determining a crop window having a shape and a zoom factor, which determine a size of the crop window and cropping the digital image to include a portion of the image of high subject content in response to the belief map and the crop window.

Abstract: A method and computer program/system for cropping a digital image includes inputting a belief map of a photographic image, (a belief value at a location in the belief map indicates an importance of a photographic subject at the same location in the photographic image), selecting a zoom factor and a crop window, clustering regions of the belief map to identify background portions, secondary portions and main portions, positioning the crop window such that the crop window is centered around a main portion having a highest belief value, moving the crop window such that the crop window is included completely within the image, moving the crop window such that a sum of belief values is at a maximum, and cropping the image according to the crop window.

Abstract: A digital image processing method determines the extent of blocking artifacts in a digital image by first forming a column difference image and averaging the values in the columns in the column difference image to produce a column difference array. The average of the values in the column difference array that are separated by one block width are computed to produce a block averaged column difference array. Then, the peak value in the block averaged column difference array is located, and the mean value of the block averaged column difference array (excluding the peak value) is calculated to produce a column base value, and the ratio between the peak value and the base value are computed to produce a column ratio. The foregoing steps are repeated in the row direction to produce a row ratio. Finally, the column and row ratios are employed as a measure of the extent of blocking artifacts in the digital image.

Abstract: A digital image processing method reduces noise and blocking artifacts in a digital image by first converting the RGB values of the digital image pixels to Y, Cb and Cr components, then detecting the block boundaries in the Y, Cb and Cr image components, and estimating the noise in the Y, Cb and Cr image components. One or more noise tables are constructed for the Y, Cb and Cr image components. An adaptive Huber-Markov-random-field-model-based filter (HMRF) is applied to the Y, Cb and Cr image components, wherein the adaptive feature of the HMRF employs the detected block boundaries and the noise tables to produce filtered Y, Cb and Cr image components. Finally, the filtered Y, Cb and Cr image components are converted to RGB components.

Abstract: A method and system for segmenting textures in an image includes computing multiresolution simultaneous autoregressive (MSAR) features in the image, preparing an uncertainty map of the MSAR features (the uncertainty map including high confidence pixels and low confidence pixels), computing wavelet features in the image, preparing a classifier based on the high confidence pixels and the wavelet features, and reclassifying the low confidence pixels based on the classifier to obtain the final segmentation.

Abstract: A method for determining the orientation of a digital image, includes the steps of: employing a semantic object detection method to detect the presence and orientation of a semantic object; employing a scene layout detection method to detect the orientation of a scene layout; and employing an arbitration method to produce an estimate of the image orientation from the orientation of the detected semantic object and the detected orientation of the scene layout.

Abstract: A method for processing a digital color image includes the steps of: providing a subject matter detector for distinguishing between target and background subject matters; applying the subject matter detector to the image to produce a belief map indicating the degree of belief that pixels in the image belong to target subject matter; providing an image enhancement operation that is responsive to a control signal for controlling the degree of image enhancement; and applying image enhancement to the digital image by varying the control signal according to the belief map to produce an enhanced image.

Abstract: A digital image processing method for generating a low resolution, low bit depth digital image from a higher resolution, higher bit depth input color digital image, includes the steps of: generating a gray scale image from the input color digital image; generating a valley image; filtering the valley image with a rank order filter to produce a filtered valley image; thresholding the filtered valley image to generate a binary valley image; generating a shadow image and a highlight image from the gray scale image; combining the shadow image, the highlight image, and the binary valley image to produce a combined binary image; and sub-sampling the combined binary image to a desired low resolution.

Abstract: A method of producing an image of least a portion of a photographic image onto a photographic receiver including receiving a digital image corresponding to the photographic image, the digital image comprising pixels, and locating the relative optical position of a photographic image, the lens, and the photographic receiver in response to pixels of the digital image and illuminating a portion of the photographic image of high subject content to produce an image of such portion onto the photographic receiver.

Abstract: Disclosed is a method for detecting subject matter regions in a digital color image having pixels of (red, green, blue) values, comprising the steps of: assigning to each pixel a belief value as belonging to the subject matter region based on color and texture features; forming spatially contiguous candidate subject matter regions by thresholding the belief values; analyzing the spatially contiguous regions based on one or more unique characteristics of the subject matter to determine the probability that a region belongs to the subject matter; and generating a map of detected subject matter regions and associated probability that the regions belongs to the subject matter.

Abstract: A method for producing a compressed bit-stream from a digital image includes the steps of a) processing the digital image to produce a main subject belief map containing a continuum of belief values relating to the importance of subject and background regions in the image, b) performing a spatio-frequency transformation on the digital image to produce an array of transform coefficients, c) deriving a distortion-weighting factor for each transform coefficient from the belief map, and d) producing a compressed bit stream using an image compression system that is responsive to the distortion-weighting factors. The specific image compression system may be selected from a variety of image compression systems, including JPEG compression, JPEG2000 compression or vector quantization.

Abstract: A method of processing a digital image, including the steps of: applying an initial scene balance algorithm to the digital image to produce an initial scene balanced digital image; detecting skin colored pixels in the initial scene balanced digital image; calculating a brightness adjustment amount based on a statistic of the detected skin colored pixels; and applying the brightness adjustment amount to the scene balanced digital image to produce a processed digital image having improved overall brightness.

Abstract: A method, image recognition system, computer program, etc., for determining image orientation. The invention classifies potential sky pixels in the image by color, identifies spatially contiguous regions of the potential sky pixels, identifies actual sky regions by eliminating ones of the spatially contiguous regions that have a texture above a predetermined texture threshold, computes desaturation gradients of the actual sky regions, classifies the image as one of portrait and landscape based on average absolute values of horizontal and vertical desaturation gradient of pixels within each of the actual sky regions, determines orientation of the image based on a polarity of the average horizontal and vertical desaturation gradients, and confirms that the actual sky regions are true sky regions by comparing the desaturation gradients with a predetermined desaturation gradient for sky.

Abstract: A digital image processing method for locating human eyes in a digital image, includes the steps of detecting a skin colored region in the image; detecting human iris color pixels in the skin colored region; forming initial estimates of eye positions using the locations of the detected iris color pixels in the skin colored region; estimating the size of each eye based on the distance between the estimated initial eye positions; forming a first search window for one eye, the center of the window being the estimated initial position for the one eye and the size of the window being proportional to the estimated size of the one eye; and employing a template to locate an eye in the first search window.

Abstract: Disclosed is a method for converting an input digital color image having a set of possible input colors to an output digital color image having a set of palette colors, the number of palette colors being less than the number of possible input colors, wherein the set of palette colors is determined based on the distribution of colors in the input digital image boosted by a distribution of important colors contained in the input digital image.

Abstract: Disclosed is a method for converting an input digital color image having a set of possible input colors to an output digital color image having a set of palette colors, the number of palette colors being less than the number of possible input colors, wherein the set of palette colors is determined based on the distribution of colors in the input digital image supplemented by a distribution of important colors.

Abstract: A method for multitone processing an N level digital image to produce an M level digital image wherein M<N, includes the steps of: determining M reconstruction levels based on the gray level distribution of the N level image; and applying multilevel dithering to the N level digital image using the M reconstruction levels to produce the M level digital image.

Abstract: A method, image recognition system, computer program, etc., for detecting sky regions in an image comprise classifying potential sky pixels in the image by color, extracting connected components of the potential sky pixels, eliminating ones of the connected components that have a texture above a predetermined texture threshold, computing desaturation gradients of the connected components, and comparing the desaturation gradients of the connected components with a predetermined desaturation gradient for sky to identify true sky regions in the image.