Abstract: The present invention is to provide a method of restoring closed-eye portrait photo, which comprises the steps of detecting the locations and range of the eyes of a portrait photo being taken, retrieving a patch of a designated range of the eyes area and its neighboring area which represents the expression of the eyes and its neighboring area, determining whether the eyes of said patch are open or closed by using an eyes state classifier, temporarily storing said patch as an open-eye templet when it is determined that the eyes are open, detecting the locations and range of the eyes of a subsequently taken portrait photo, calculating an eyes restoration area when it is determined that the eyes are closed, replacing the closed-eye patch with said open-eye templet, and performing fusion operation toward said eyes restoration area to ensure that each portrait photo generated is with the eyes opened.

Abstract: A method for simulating an image captured at a long exposure time (“simulated image”), includes (1) capturing each of first, second, and third images at a short exposure time, (2) determining a first relative motion between the first and the second images, (3) transforming the first image to remove the first relative motion, (4) determining a second relative motion between the third and the second images, (5) transforming the third image to remove the second relative motion, and (6) combining the first, the second, and the third images to form the simulated image. Relative motions between images are determined by matching blocks at multiple resolutions to determine corresponding points between the images. Transformation to remove relative motion is determined by fitting corresponding points between the images using a minimum square error (MSE) algorithm in a random sample consensus (RANSAC) framework.

Abstract: The present invention is to provide a method for enabling Blue-ray Disc Java (BD-J) to effectively obtain context of a corresponding application, namely an Xlet, while playing BD-J title, which comprises the steps of setting up source file attribute of each class by adding an Xlet context ID as an unique code to the class when loading all classes into a cache of the BD-J; looking up back onto a call stack to search for Xlet class of the current BD-J title when searching for Xlet context; and then obtaining the Xlet context through the Xlet context ID according to the source file attribute. Thus, the method of the present invention enables BD-J to normally play the BD-J title in the Blue-ray Disc Read Only Memory (BD-ROM) and, at the same time, effectively improves the playing performance.

Abstract: A method of automatically detecting and tracking successive frames in a region of interesting by an electronic imaging device includes: decomposing a frame into intensity, color and direction features according to human perceptions; filtering an input image by a Gaussian pyramid to obtain levels of pyramid representations by down sampling; calculating the features of pyramid representations; using a linear center-surround operator similar to a biological perception to expedite the calculation of a mean value of the peripheral region; using the difference of each feature between a small central region and the peripheral region as a measured value; overlaying the pyramid feature maps to obtain a conspicuity map and unify the conspicuity maps of the three features; obtaining a saliency map of the frames by linear combination; and using the saliency map for a segmentation to mark an interesting region of a frame in the large region of the conspicuity maps.

Abstract: A method for digitally magnifying images applied to an electronic device includes the steps of: reading in a preview image inputted into the electronic device; executing a 2-fold image magnifying process to the preview image; executing a fuzziness removing process to the preview image; segmenting the preview image into a background area and a text area, executing a correspondingly text strengthening process to the text area; and determining if the preview image is magnified up to a predetermined amplification factor; if yes, outputting the preview image after being magnified to a display screen for displaying the preview image; and otherwise, going back to re-execute the 2-fold image magnifying process to the magnified preview image, and then executing the fuzziness removing process and the text strengthening process, in order to generate the preview image magnified about 4-fold or more.

Abstract: A method for estimating noise according to a multiresolution model is applied to an imaging device and comprises steps of: using an imaging sensor of the imaging device to capture a series of images of a scene under different imaging conditions; processing the images with a multiresolution transformation process to obtain a series of sub-images corresponding to different frequency layers; processing a series of the sub-images of the images that are in a same frequency layer to generate an averaged image; determining a difference between each of the sub-images in the same frequency layer and the averaged image corresponding to that frequency layer, and calculating the differences and the averaged image to obtain noise level functions of the imaging sensor in the different frequency layers under the different imaging conditions; and defining the noise level functions of the imaging sensor as noise samples for establishing an a priori model database.

Abstract: The present invention is to provide a parallel filtering method, which is implemented to an interpolation filter and comprises the steps of separating coefficients of the interpolation filter into two sets comprising the positive and negative coefficients respectively for parallelly filtering a plurality of input data pixels packed into data words inputted to the interpolation filter concurrently to obtain a first result data word, and clipping and shifting the first result data word to obtain a final output data word containing packed half-pel pixels for parallelly and efficiently filtering data stream of video without increasing the complexity, cost, size and power consumption of circuitry of an electronic video apparatus.

Abstract: A method for detecting a facial area on a color image includes (a) placing a search window on the color image, (b) determining if a center pixel of the search window is a skin color pixel, indicating that the search window is a possible facial area candidate, (c) applying a 3-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (d) applying a 4-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (e) if steps (b), (c), (d) all determine that the search window is a possible facial area candidate, applying an AdaBoost filter to the search window to determine if the search window is a facial area candidate, and (f) if step (e) determines that the search window is a facial area candidate, saving the location of the search window.

Abstract: A JPEG encoding process may generate entropy encoded data indexing auxiliary information. With the assistance of such auxiliary information, a quick JPEG decoder is implemented to significantly improve the performance of processing large sized JPEG images on the mobile systems with limited computation power.

Abstract: The present invention discloses a method of automatically detecting and tracking a face by an electronic capturing device that alternatively uses a face detecting algorithm to quickly locate a face in a frame based on a skin color model and a face tracking algorithm to locate a face in subsequent frames by a nonparametric technique and a mean shift algorithm. If the face tracking algorithm cannot track and locate a face correctly, the face detecting algorithm will be used again to detect a face position in another new frame until the face position is located successfully, and then the face tracking algorithm will be used again for detecting and locating the face position in subsequent frames. After this method has detected a face position, a variable focal lens is used to slowly and smoothly refocus the frame including a face region, so as to obtain a clear face image.

Abstract: A method for enhancing a video includes applying a linear histogram stretch, a gamma correction, and sigma row, column, and temporal filters to the video.

Abstract: The present invention is to provide a denoise method on Gaussian/Laplacian image pyramid, which integrates Pyramid analysis/synthesis algorithm, MMSE (minimum mean square error) filter and NL (non local) filter on the image pyramid to reconstruct and output a denoised image of an original input image through a plurality of iterative procedures, and utilizes an auto-adaptive noise estimation algorithm to find parameter of noise level used by the NL filter, so as to be easily embedded in mobile or handheld devices for obtaining better noise removing and anti-shaking results and remove noise much faster than the conventional denoise method, but only with less quality loss.

Abstract: A method for removing a red eye from an image includes (1) calculating a weighted red value for each pixel in the image from red, green, and blue color values and a luminance value of each pixel in the image, (2) selecting a plurality of pixels in the image having weighted red values greater than a threshold as red eye pixels, and (3) correcting some of the red eye pixels to remove the red eye from the image. The weighted red value for a pixel is calculated as follows: f = c 1 ? r + c 2 ? g + c 3 ? b Y , wherein f is the weighted red value, r is the red color value, g is the green color value, b is the blue color value, c1 is a first weight given to the red color value, c2 is a second weigh given to the green color value, c3 is a third weight given to the blue color value, and Y is the luminance.

Abstract: A method for color matching a first image and a second image, wherein a first region of the first image and a second region of the second image overlap, includes removing overlapping pixels in the first and the second regions that have pixel values are too different, generating a first histogram of the first region, generating a second histogram of the second region, determining corresponding pixel values in the first and the second histograms, determining parameters of an optoelectronic conversion function that matches the corresponding pixel values, and color matching the second image to the first image by applying the optoelectronic conversion function with the determined parameters to the second image.

Abstract: A method for image separating, said method being applied to an electronic apparatus to separate a foreground and a background of an image displayed on said apparatus, comprising the steps of scanning pixels in said image, applying arithmetic algorithm on said pixels and forming a plurality of segments on said image by defining pixels adjacent to each other and similar in color as one segment; examining foreground label and background label marked by an user; merging segments labeled by said foreground label into a foreground region and segments labeled by said background label into a background region, and applying arithmetic algorithm on an unlabeled segment to merge with an adjacent segment, foreground region or background region having the least difference in color; repeating said merging step until all segments are merged into a foreground region or a background region, thereby separating said image into a foreground region and a background region.

Abstract: A method is provided for cloning a facial feature template image into an original image including a face to form a new image. The method includes detecting the face and facial features in the original image, reducing the original and the template images, cloning the reduced template image into the reduced original image to form a new image, enlarging the new image, and displaying the enlarged new image. The method may use Poisson cloning where a resulting system of linear equations is solved by applying a Thomas algorithm to determine an initial solution and applying a Conjugate Gradient algorithm using the initial solution to determine a final solution to the system of linear equations.

Abstract: A method is provided for approximating a quadratic Bezier curve represented by two anchor points and a control point that are fixed-point binary numbers. If a first flatness of a line formed between the two anchor points of the Bezier curve is less than a threshold, the method includes replacing the Bezier curve with an edge between the two anchor points. If the first flatness is not less than the threshold, the method includes subdividing the Bezier curve into halves and determining a second flatness of one of the halves. The first flatness is approximated by a triangular area formed by the two anchor points and the control point, and the triangular area is approximated by multiplication and subtraction operations. The second flatness of the half is approximated as the triangular area divided by 8, where the division by 8 is determined by shifting 3 bits to the right.

Abstract: A method for driving virtual facial expressions by automatically detecting facial expressions of a face image is applied to a digital image capturing device. The method includes the steps of detecting a face image captured by the image capturing device and images of a plurality of facial features with different facial expressions to obtain a key point position of each facial feature on the face image; mapping the key point positions to a virtual face as the key point positions of corresponding facial features on the virtual face; dynamically tracking the key point of each facial feature on the face image; estimating the key point positions of each facial feature of the current face image according to the key point positions of each facial feature on a previous face image; and correcting the key point positions of the corresponding facial features on the virtual face.

Abstract: A method is provided to automatically arrange scanned images so they can be stitched into a composite image. Initially the scanned images are reduced to low resolution and a gradient filter is applied. One scanned image is selected as a possible first image in a stitching order. The possible first image is rotated to one angle and correlated with remaining scanned images rotated to two corresponding angles. Only four scanned images that best correlate with the possible first image and pass a threshold are saved as possible second images in the order. The steps are repeated for subsequent places in the order and for the possible first image at other angles. The method is repeated for other possible first images to form other orders. At the end, a path through one of the orders that produces the best sum of correlation values is set as the correct stitching order.

Abstract: A method is provided to automatically determine “exciting” segments from a video. The method includes calculating image features of each frame in the video, determining a difference for each pair of adjacent frames, calculating a sum of differences for each group of frames in the video, and selecting a number of the groups with high sums as exciting segments of the video. The differences between pairs of adjacent frames are used as a criterion for measuring a degree of “excitement” for determining the highlights in the video.