Abstract: An image processing apparatus for tracking faces in an image stream iteratively receives an acquired image from the image stream including one or more face regions. The acquired image is sub-sampled at a specified resolution to provide a sub-sampled image. An integral image is then calculated for a least a portion of the sub-sampled image. Fixed size face detection is applied to at least a portion of the integral image to provide a set of candidate face regions. Responsive to the set of candidate face regions produced and any previously detected candidate face regions, the resolution is adjusted for sub-sampling a subsequent acquired image.

Abstract: A smart-focusing technique includes identifying an object of interest, such as a face, in a digital image. A focus-generic classifier chain is applied that is trained to match both focused and unfocused faces and/or data from a face tracking module is accepted. Multiple focus-specific classifier chains are applied, including a first chain trained to match substantially out of focus faces, and a second chain trained to match slightly out of focus faces. Focus position is rapidly adjusted using a MEMS component.

Abstract: A smart-focusing technique includes identifying an object of interest, such as a face, in a digital image. A focus-generic classifier chain is applied that is trained to match both focused and unfocused faces and/or data from a face tracking module is accepted. Multiple focus-specific classifier chains are applied, including a first chain trained to match substantially out of focus faces, and a second chain trained to match slightly out of focus faces. Focus position is rapidly adjusted using a MEMS component.

Abstract: A method of tracking a face in a reference image stream using a digital image acquisition device includes acquiring a full resolution main image and an image stream of relatively low resolution reference images each including one or more face regions. One or more face regions are identified within two or more of the reference images. A relative movement is determined between the two or more reference images. A size and location are determined of the one or more face regions within each of the two or more reference images. Concentrated face detection is applied to at least a portion of the full resolution main image in a predicted location for candidate face regions having a predicted size as a function of the determined relative movement and the size and location of the one or more face regions within the reference images, to provide a set of candidate face regions for the main image.

Abstract: Classifier chains are used to determine quickly and accurately if a window or sub-window of an image contains a right face, a left face, a full face, or does not contain a face. After acquiring a digital image, an integral image is calculated based on the acquired digital image. Left-face classifiers are applied to the integral image to determine the probability that the window contains a left face. Right-face classifiers are applied to the integral image to determine the probability that the window contains a right face. If the probability of the window containing a right face and a left face are both greater than threshold values, then it is determined that the window contains a full face. Alternatively, if only one of the probabilities exceeds a threshold value, then it may be determined that the window contains only a left face or a right face.

Abstract: Classifier chains are used to determine quickly and accurately if a window or sub-window of an image contains a right face, a left face, a full face, or does not contain a face. After acquiring a digital image, an integral image is calculated based on the acquired digital image. Left-face classifiers are applied to the integral image to determine the probability that the window contains a left face. Right-face classifiers are applied to the integral image to determine the probability that the window contains a right face. If the probability of the window containing a right face and a left face are both greater than threshold values, then it is determined that the window contains a full face. Alternatively, if only one of the probabilities exceeds a threshold value, then it may be determined that the window contains only a left face or a right face.

Abstract: An image acquisition device includes a flash and optical system for capturing digital images. A face tracker identifies face regions within a series of one or more relatively low resolution reference images, and predicts face regions within a main digital image. A face analyzer determines one or more partial face regions within the one or more face regions each including at least one eye. A red-eye filter modifies an area within the main digital image indicative of a red-eye phenomenon based on an analysis of one or more partial face regions within the one or more face regions identified and predicted by the face tracker.

Abstract: A method of tracking a face in a reference image stream using a digital image acquisition device includes acquiring a full resolution main image and an image stream of relatively low resolution reference images each including one or more face regions. One or more face regions are identified within two or more of the reference images. A relative movement is determined between the two or more reference images. A size and location are determined of the one or more face regions within each of the two or more reference images. Concentrated face detection is applied to at least a portion of the full resolution main image in a predicted location for candidate face regions having a predicted size as a function of the determined relative movement and the size and location of the one or more face regions within the reference images, to provide a set of candidate face regions for the main image.

Abstract: An image processing apparatus for tracking faces in an image stream iteratively receives an acquired image from the image stream including one or more face regions. The acquired image is sub-sampled at a specified resolution to provide a sub-sampled image. An integral image is then calculated for a least a portion of the sub-sampled image. Fixed size face detection is applied to at least a portion of the integral image to provide a set of candidate face regions. Responsive to the set of candidate face regions produced and any previously detected candidate face regions, the resolution is adjusted for sub-sampling a subsequent acquired image.

Abstract: A database includes an identifier and associated parameters for each of a number of faces to be recognized. A new acquired image from an image stream is received potentially including one or more face regions. Face detection is applied to at least a portion of the acquired image to provide a set of candidate face regions each having a given size and a respective location. Using the database, face recognition is selectively applied to at least one of the candidate face regions to provide an identifier for a face recognized in a candidate face region. A portion of the image is stored including the recognized face in association with at least one image of the image stream.

Abstract: A method operable in a digital image acquisition system having no photographic film is provided. The method comprises receiving a relatively low resolution image of a scene from an image stream, wherein the scene potentially includes one or more faces. At least one high quality face classifier is applied to the image to identify relatively large and medium sized face regions and at least one relaxed face classifier is applied to the image to identify relatively small sized face regions. A relatively high resolution image of nominally the same scene is received and at least one high quality face classifier is applied to the identified small sized face regions in the higher resolution version of said image.

Abstract: An image processing apparatus for tracking faces in an image stream iteratively receives an acquired image from the image stream potentially including one or more face regions. The acquired image is sub-sampled at a specified resolution to provide a sub-sampled image. An integral image is then calculated for a least a portion of the sub-sampled image. Fixed size face detection is applied to at least a portion of the integral image to provide a set of candidate face regions. Responsive to the set of candidate face regions produced and any previously detected candidate face regions, the resolution is adjusted for sub-sampling a subsequent acquired image.

Abstract: A color filter enhancement method for a portable digital image acquisition device includes digitally exposing color pixels of a color sensor array for a first digital exposure duration and digitally exposing white pixels of a color sensor array for a second digital exposure time shorter than the first digital exposure duration. A color filter enhanced digital image is generated using data from both the color pixels exposed for the first digital exposure duration and the white pixels exposed for the second digital exposure duration.

Abstract: A method for red-eye detection in an acquired digital image includes acquiring a first image, and analyzing one or more partial face regions within the first image. One or more characteristics of the first image are determined. One or more corrective processes are identified including red eye correction that can be beneficially applied to the first image according to the one or more characteristics. The one or more corrective processes are applied to the first image.

Abstract: A method for red-eye detection in an acquired digital image includes acquiring a first image, and analyzing one or more partial face regions within the first image. One or more characteristics of the first image are determined. One or more corrective processes are identified including red eye correction that can be beneficially applied to the first image according to the one or more characteristics. The one or more corrective processes are applied to the first image.

Abstract: A method of making an image in a digital camera comprises capturing a digital image of a scene into which the camera user is to be inserted, and superimposing a symbol (subject locator) onto the scene image representing at least a part of a human subject. The subject locator is scaled to a desired size and moved to a desired position relative to the scene image. Next a digital image of the user is captured, and at least the part of the user image represented by the subject locator is extracted. The part of the user image represented by the subject locator is scaled (before or after extraction) to substantially the same size as the subject locator and inserted into the first image at the position of the subject locator.

Abstract: A technique for detecting large and small non-red eye flash defects in an image is disclosed. The method comprises selecting pixels of the image which have a luminance above a threshold value and labeling neighboring selected pixels as luminous regions. A number of geometrical filters are applied to the luminous regions to remove false candidate luminous regions.

Abstract: A smart-focusing technique includes identifying an object of interest, such as a face, in a digital image. A focus-generic classifier chain is applied that is trained to match both focused and unfocused faces and/or data from a face tracking module is accepted. Multiple focus-specific classifier chains are applied, including a first chain trained to match substantially out of focus faces, and a second chain trained to match slightly out of focus faces. Focus position is rapidly adjusted using a MEMS component.

Abstract: A smart-focusing technique includes identifying an object of interest, such as a face, in a digital image. A focus-generic classifier chain is applied that is trained to match both focused and unfocused faces and/or data from a face tracking module is accepted. Multiple focus-specific classifier chains are applied, including a first chain trained to match substantially out of focus faces, and a second chain trained to match slightly out of focus faces. Focus position is rapidly adjusted using a MEMS component.

Abstract: A template matching module is configured to program a processor to apply multiple differently-tuned object detection classifier sets in parallel to a digital image to determine one or more of an object type, configuration, orientation, pose or illumination condition, and to dynamically switch between object detection templates to match a determined object type, configuration, orientation, pose, blur, exposure and/or directional illumination condition.