Abstract: A pointing information extraction unit extracts pointing information indicating a pointing position and a pointing time on a slide from a slide file used in a lecture and a video file of a lecture video using a pointing device. A word information generation unit analyzes a text sentence extracted from the slide file to generate a word information file indicating a word and a position thereof. A word pointing information generation unit estimates a word closest to the pointing position on the slide to generate a word pointing information file with the pointing time assigned. A fill-in-the-blank word extraction unit extracts a word having a pointing time equal to or longer than a predetermined time from the word pointing information as a fill-in-the-blank word file. A fill-in-the-blank test question is generated by setting the fill-in-the-blank word of the slide information as a blank region.

Abstract: It is judged for each pixel in an inputted multilevel image whether the pixel is a background pixel, and the pixel is locally binarized if it is judged not to be a background pixel. Then, it is judged whether the pixel belongs to a background or a stroke, such as of a character, ruled line, etc., and a binary image is generated.

Abstract: A rather expanded binary image and a rather blurry binary image are generated from a multiple-valued image. A ruled line candidate area is extracted from the rather expanded binary image, and the extracted ruled line candidate area is verified using the rather blurry binary image.

Abstract: An information processing apparatus extracts a plurality of strokes from a multilevel image, and generates a stroke binary image. Next, the image processing apparatus extracts feature amounts indicating the thickness and the smoothed graylevel of a stroke in a neighboring region of a target pixel by using each pixel belonging to each of the strokes as the target pixel. Then, the apparatus generates a target stroke binary image from the stroke binary image based on the distribution of the extracted feature amounts.

Abstract: A document image search apparatus generates a text by performing the character recognition of a document image and determines a re-process scope. Then, the apparatus generates a candidate character lattice from the re-recognition result of the re-process scope, generates character strings from the candidate character lattice and adds the character strings to the text. Then, the apparatus performs index search using the text with the character strings added.

Abstract: A key word is first and automatically extracted from a character string group to be recognized, and entered. Then, a character is recognized by segmenting an individual character from a character string image to be recognized, and a character string corresponding to the extracted/entered key word id extracted. Then, a word area delimited by a key word is extracted from the character string image, and a word is recognized. Furthermore, a word recognition result is verified, and a final character string recognition result is output.

Abstract: A table image processing device processes a table image and a memory medium stores a processing program. The table image processing device processes precisely a table image containing a round corner and includes a device extracting a line extracting a longitudinal line and lateral line out of an input image, a device finding a potential match of a round corner region extracting an oblique line which commences from a terminal of a line found by the line extracting device, and finding the potential match of the round corner region, a device extracting a cell containing the potential match of the round corner found by the potential match of the round corner region finding device, and a device deciding the round corner part deciding the round corner from the cells found by the device extracting the cells.

Abstract: Precise grayscale character segmentation apparatus and method. The precise grayscale character segmentation apparatus comprises an adjustment and segmentation unit for adjusting and segmenting an inputted low resolution text line image undergone coarse segmentation, so as to generate an adjusted character image; a character image binarization unit for generating a binary character image from the character image inputted therein; a noise removal unit for removing noise information in the binary character image generated by the binarization unit; and a final character image segmentation unit for generating a precisely segmented character image from the binary character image from which noise has been removed.

Abstract: After an original image, including half-tone dot meshed characters are inputted and a prescribed process is applied to the original image, black pixel connection patterns are extracted from a target process area. If the density of the extracted pattern exceeds prescribed density, it is judged that the pattern is half-tone dot meshed and both the respective average values and standard deviations of the vertical/horizontal sizes of the connection pattern are calculated. Then, respective threshold values are calculated based on both the respective average values and standard deviations, and half-tone dot patterns are eliminated. Furthermore, a pattern, the outline of which is long compared with an included black pixel, of all the remaining connection patterns is eliminated as an unnecessary pattern. Lastly, projections attached to a character are deleted and character extraction is terminated.

Abstract: A multilevel image into which a color or a black-and-white image is converted is input, and a slightly indistinct binary image generating unit generates a slightly indistinct binary image that includes a slightly indistinct line pattern and does not include background noise. Additionally, a shape-preserved binary image generating unit generates a binary image that preserves the shape of a line pattern and includes background noise. These images are ANDed for each pixel, so that a binary image that preserves the shape of the line pattern and does not include the background noise is generated.

Abstract: A document layout analysis program capable of extracting an appropriate set of text blocks from a given document image even in the case where the document layout is so complicated that conventional extraction methods with a single extraction condition would not work well. A plurality of different extraction conditions are stored in an extraction condition memory for use in extracting text blocks from a given document image. In accordance with those extraction conditions, a text block extractor extracts a plurality of sets of text blocks from the document image. A text block consolidator produces a consolidated set of text blocks by performing character recognition on each extracted text block, evaluating validity of each text block based on a result of the character recognition, and selecting most valid text blocks from among the plurality of sets of text blocks.

Abstract: A pattern segmentation apparatus and a pattern recognition apparatus can improve the segmentation precision of a character touching pattern. The pattern segmentation apparatus includes a feature amount extraction unit for extracting the feature amount of an image, a feature amount setting unit for setting the feature amount of a category, a feature amount comparison unit for comparing the feature amount of the category with the feature amount of the image, and a segmentation unit for segmenting a portion corresponding to the feature amount of the category from the image based on the comparison result.

Abstract: A grayscale character dictionary generation apparatus, comprising a first synthetic grayscale degraded character image generation unit for generating first synthetic grayscale degraded character images using binary character images inputted therein; a clustering unit for dividing each category of the first synthetic grayscale degraded character images generated by the first synthetic grayscale degraded character image generation unit into a plurality of clusters; a template generation unit for generating template for each of the clusters; a transformation matrix generation unit for generating transformation matrix in relation to each of the templates; and a second synthetic grayscale degraded character dictionary generation unit for obtaining character feature of every grayscale degraded character of each of the clusters using the transformation matrix, and for constructing eigenspace of each category of the synthetic grayscale degraded character, which is the second synthetic grayscale character dictionary.

Abstract: A projection set of geodesic lines which are parallel with each other on a curved surface of a paper face is extracted from an image in which a paper face has been imaged by an image-pickup device, using the paper face contents as a clue; and also a projection set of ruling lines which form a ruled surface corresponding to the curved surface of the paper face is extracted from the projection set of geodesic lines. Then, the curved surface of the paper face is estimated from the projection set of the geodesic lines and ruling lines, and distortion of the image is corrected based on this curved surface of the paper face. If this is done, correspondence with various types of diverse distortions becomes possible, and distortion correction can be performed even when only one part of the paper face appears in the image.

Abstract: An information processing apparatus extracts a plurality of strokes from a multilevel image, and generates a stroke binary image. Next, the image processing apparatus extracts feature amounts indicating the thickness and the smoothed graylevel of a stroke in a neighboring region of a target pixel by using each pixel belonging to each of the strokes as the target pixel. Then, the apparatus generates a target stroke binary image from the stroke binary image based on the distribution of the extracted feature amounts.

Abstract: Character recognition apparatus and method for recognizing characters in an image, of which the character recognition apparatus comprises a text line extraction unit for extracting a plurality of text lines from an input image, a feature recognition unit for recognizing one or more features of each of the text lines, a synthetic pattern generation unit for generating synthetic character images for each of the text lines by using the features recognized by the feature recognition unit and the original character images, a synthetic dictionary generation unit for generating a synthetic dictionary for each of the text lines by using the synthetic character images, and a text line recognition unit for recognizing characters in each of the text lines by using the synthetic dictionary.

Abstract: A method and apparatus for generating a degraded dictionary automatically is presented in this invention. Herein, a degraded pattern generating means generates a plurality of degraded patterns from an original character image, based on a plurality of degradation parameters. A degraded dictionary generating means generates a plurality of degraded dictionaries corresponding to the plurality of degradation parameters, based on the plurality of degradation patterns. Finally, a dictionary matching means selects one of the plurality of dictionaries which matches the degradation level of a test sample set best, as the final degraded dictionary. In this invention, various degraded patterns can be generated by means of simple scaling and blurring process for establishing degraded dictionaries. Therefore, the invention can be implemented simply and easily.

Abstract: A method and apparatus for generating a degraded character image at various levels of degradation automatically is presented in this invention. The method comprises rendering the character image on a scene plane; translating and rotating the scene plane according to various parameters; determining a projection region of the character image on an image plane according to various parameters; generating a pixel region mask; and generating a final degraded image by super-sampling. Thus various degraded character images are generated on various conditions of degradation. The generated synthetic characters can be used for performance evaluation and training data augmentation in optical character recognition (OCR).

Abstract: A three-dimensional curved-surface model can be estimated by using both two-dimensional outlines obtained from a piece of image photographed from the top and a restriction that the paper is rectangular. Then, only the three-dimensional distortion in the image can be corrected based on the obtained three-dimensional curved-surface model.

Abstract: Video frames that contain text areas are selected from given video frames by removing redundant frames and non-text frames, the text areas in the selected frames are located by removing false strokes, and text lines in the text areas are extracted and binarized.