摘要:
A text input method based on gesture recognition, comprising: collecting image information containing a target object; determining the target object according to the image information, and acquiring a writing surface and a movement trace of the target object; extracting the movement trace of the target object in the writing surface as a writing trace and outputting same; and performing character recognition according to the writing trace, and outputting a character recognition result.
摘要:
There is provided an input/output-integrated image reading device that is thin and easy to carry, recognizes text and images with high accuracy, and enables instantaneous and real-time comparison of a read image with a conversion result, such as translation. An image reading device (101) is provided with an image data reading unit (202) that reads an original document, a recognition unit (201) that recognizes text or images on the read original document, a conversion unit (201) that converts display information of read text or images, and a displaying unit (204) that displays display information of text or images that have been subjected to the conversion processing. The image data reading unit (202) and the displaying unit (204) are each in a sheet-like shape, and the device is overall in a sheet-like shape.
摘要:
The inputted character candidate display section (1213)/inputted character string candidate display section (1214) cause candidates of a character/ character string, which is predicted as an intended character/character string to be inputted by the user, to be displayed as inputted character candidates/inputted character string candidate, and the converted character string candidate display section (1215) causes converted character string candidates, which have been obtained by converting the inputted character string candidate, to be displayed.
摘要:
A line-direction deciding device that can decide the direction of lines in an image having a complicated layout of characters as well as line directions other than vertical and horizontal line directions. The present invention provides a line-direction deciding device that extracts character elements (image components) from an image, examines in which direction the character elements are most densely distributed and decides by majority the direction of lines of characters within a processable area as well as an image inclination correcting device that corrects an image for inclination according to a processing result made by the line-direction deciding device provided with image-inclination detecting means.
摘要:
According to one arrangement, an information processing device (10) includes means (132) for performing a process for displaying an image and information related to a size of a recognition target, and means (134) for recognizing a recognition target from the image. The information related to the size of the recognition target includes visual information of the recognition target.
摘要:
Embodiments of the present application relate to a method, apparatus, and system for registering a user identity. The method includes receiving handwriting information associated with handwriting entered by a user, computing a degree of complexity of the first handwriting information, and in the event that the degree of complexity of the first handwriting information satisfies one or more preset conditions, associating the first handwriting information with identity registration information corresponding to the user.
摘要:
A character recognition system receives an unknown character and recognizes the character based on a pre-trained recognition model. Prior to recognizing the character, the character recognition system may pre-process the character to rotate the character to a normalized orientation. By rotating the character to a normalized orientation in both training and recognition stages, the character recognition system releases the pre-trained recognition model from considering character prototypes in different orientations and thereby speeds up recognition of the unknown character. In one example, the character recognition system rotates the character to the normalized orientation by aligning a line between a sum of coordinates of starting points and a sum of coordinates of ending points of each stroke of the character with a normalized direction.
摘要:
An efficient and simple approach to encoding ideographic characters as sequences of input strokes or stroke categories is shown in Figure 5. Each character (53) is represented by one or more sequences of one or more components (55). Each component corresponds to a plurality of alternative stroke sequences, each of which is associated with a probability that it will be the sequence which the user enters to specify the given component or character. The probability associated with the user's preferred stroke sequence is automatically increased by the system when the character is selected, thus, automatically adapting to a user's preferences.
摘要:
An automatic language determining apparatus automatically determines the particular Asian language of the text image of a document when the gross script-type is known to be, or is determined to be, an Asian script-type. A connected component generating means (28) generates connected components from the pixels comprising the text image. A character cell generating means generates a character cell surrounding at least one connected component. An optical density determining means determines the optical density, in absolute numbers or percentage of pixels, of the pixels within each character cell. A script feature determining means first generates a histogram, then converts, by linear discriminate analysis, the histogram to a point in a new coordinate space. A language determining means (36) compares the determined point of the text portion in the new coordinate space to predetermined regimes in the new coordinate space corresponding to at least one Asian language to determine the particular Asian language of the text image.