Abstract: A method of correcting an image with perspective distortion and creating an artificial image with perspective distortion is disclosed. First, image data including a distorted object image are received. Next, the user inputs an operational instruction for setting a plurality of distortion parameters pertaining to the image data, which include a distorted side of the distorted object image, a central line and a distortion ratio. Thus, a plurality of coordinates of corners of the distorted object image are calculated according to these distortion parameters and a transformation matrix is determined according to the calculated coordinates of the corners of the distorted object image. Finally, the distorted object image is transformed to a corrected object image according to the transformation matrix.

Abstract: A method for filtering documents. The method comprises steps of (a) filtering the documents using a sensitivity and calculating the number of the documents blocked by the filtering, (b) receiving the number of documents mistakenly blocked by the filtering to calculate the error rate, (c) increasing (decreasing) the sensitivity by a displacement, (d) repeating steps (a) and (b) with the new sensitivity, (e) if the error rate reduces, going back to step (a) and keeping increasing (decreasing) the sensitivity; if the error rate is raised, going back to step (a) but decreasing (increasing) the sensitivity instead.

Abstract: A region-based image recognition method. First, an input image is segmented into a plurality of regions, and the color feature, texture feature, shape feature, position feature and size feature of each region are extracted. Then, the regions are classified by inputting its features into a classifier. The classifier can be a set of decision rules, a neural network model, or a Bayesian classifier.

Abstract: A method of screening a group of images. First, a parameter table is provided, and a number of images to be screened and an expected objective or non-objective group recognition rate are received. Then, an item-set corresponding to the number of images and the objective or non-objective group recognition rate is selected from the parameter table. A single-image recognition method is set with the parameters recorded in the selected item-set, and then the images are screened by the single-image recognition method. Finally, the group of images is identified as an objective group if the number of objective images detected is equal to or larger than the least number of objective images recorded in the selected item-set.

Abstract: A method of correcting an image with perspective distortion and creating an artificial image with perspective distortion is disclosed. First, image data including a distorted object image are received. Next, the user inputs an operational instruction for setting a plurality of distortion parameters pertaining to the image data, which include a distorted side of the distorted object image, a central line and a distortion ratio. Thus, a plurality of coordinates of corners of the distorted object image are calculated according to these distortion parameters and a transformation matrix is determined according to the calculated coordinates of the corners of the distorted object image. Finally, the distorted object image is transformed to a corrected object image according to the transformation matrix.

Abstract: A method of interactive image retrieval based on user-specified regions. First, a sample image is provided. Next, the system automatically divides the sample image into a plurality of regions and extracts their features. Then, the user selects one or more sample regions and defines corresponding logic operators between them; a composite query is constructed and input for image retrieval. Finally, the system searches the image database to find the images containing regions corresponding with the composite query. Compared with the conventional image retrieval methods, the present invention allows users to select sample regions and exclude undesirable regions intuitively so that more accurate image retrieval can be attained in a more straightforward way.