Abstract: A document image processing system includes an extraction portion, an estimation portion, a calculation portion, a substitution portion, and a generation portion. The extraction portion extracts first and second document elements of an inputted document image and a preprint data. The estimation portion estimates first and second representative colors due to first and second document elements in a color space, respectively. The calculation portion calculates first and second planes to separate the color space into first and second sub-spaces which each includes each of the first and second representative colors, respectively. The substitution portion substitutes a color of a first pixel of the first document elements with the first representative color and a color of a second pixel of the second document elements with the second representative color. The generation portion subtracts each of the substituted first pixel from each of the substituted second pixel to generate a difference image.

Abstract: A recognition object detecting portion detects a recognition object existing in each of images which are captured in series at different time points by a camera. Images of the detected recognition object are stored in a memory. A recognition object condition judging portion determines whether image areas of the recognition object are recognizable. A movement amount detecting portion detects a movement amount of the recognition object by using the image areas of the recognition object stored in the memory. A sub-area detecting portion detects a sub-area to be recognized, by using the image areas of the recognition object read out from the memory, in accordance with the movement amount of the recognition object. A recognition portion performs recognition processing on the sub-areas. A recognition result integration portion integrates recognition results of the sub-areas including recognized characters and/or recognized patterns and the corresponding reliabilities, respectively.

Abstract: To improve recognition accuracy of a traveling direction of a vehicle by accurately detecting a marking on a road surface which is photographed by a camera while a road environment where a vehicle travels is changing. A car navigation system 100 detects an image of a light-irradiated portion which is unnecessary for the recognition of a road marking, in an image behind a vehicle captured by a camera 6 mounted on the vehicle, clips out image areas in a predetermined shape excluding the detected image area, and sequentially stores the clipped images in a storage unit 7b. Then, the new clipped image and the clipped image already stored in the storage unit 7b are combined, and an image of a road marking is detected and recognized from the composite image.

Abstract: A document image processing system includes an extraction portion, a presumption portion, a calculation portion, a substitution portion, and a generation portion. The extraction portion extracts first and second document elements of an inputted document image and a preprint data. The presumption portion presumes first and second representative colors due to first and second document elements in a color space, respectively. The calculation portion calculates first and second planes to separate the color space into first and second sub-spaces which each includes each of the first and second representative colors, respectively. The substitution portion substitutes a color of a first pixel of the first document elements with the first representative color and a color of a second pixel of the second document elements with the second representative color. The generation portion subtracts each of the substituted first pixel from each of the substituted second pixel to generate a difference image.

Abstract: An inputting device which includes an image input section for inputting an image of a containing areas in which information to be inputted is filled in and patterns representing at least reference positions to define the positions of corresponding areas and size information of corresponding areas; a memory section for storing the image of the input by the image input section; a pattern recognizing section for detecting the reference positions from the patterns in the image which is stored in the memory section and recognizing size information of the areas; an area specifying section for specifying the positions of the areas from the reference positions detected by the pattern recognizing section and the size information of the areas; and an area inputting section for inputting images in the areas defined by the area specifying section.

Abstract: A document image processing system is provided with an input portion to input a document image. An extraction portion extracts document elements of the document image from pixels of the inputted document image. A presumption portion presumes representative colors of the extracted document elements in a color space. A calculation portion calculated a plane to separate the presumed representative colors in the color space. A substitution portion substitutes colors of the pixels of each of the document elements existing in a region separated by the calculated plane in the color space with each of the representative colors existing in the same region.

Abstract: A recognition object detecting portion detects a recognition object existing in each of images which are captured in series at different time points by a camera. Images of the detected recognition object are stored in a memory. A recognition object condition judging portion determines whether image areas of the recognition object are recognizable. A movement amount detecting portion detects a movement amount of the recognition object by using the image areas of the recognition object stored in the memory. A sub-area detecting portion detects a sub-area to be recognized, by using the image areas of the recognition object read out from the memory, in accordance with the movement amount of the recognition object. A recognition portion performs recognition processing on the sub-areas. A recognition result integration portion integrates recognition results of the sub-areas including recognized characters and/or recognized patterns and the corresponding reliabilities, respectively.

Abstract: To improve recognition accuracy of a traveling direction of a vehicle by accurately detecting a marking on a road surface which is photographed by a camera while a road environment where a vehicle travels is changing. A car navigation system 100 detects an image of a light-irradiated portion which is unnecessary for the recognition of a road marking, in an image behind a vehicle captured by a camera 6 mounted on the vehicle, clips out image areas in a predetermined shape excluding the detected image area, and sequentially stores the clipped images in a storage unit 7b. Then, the new clipped image and the clipped image already stored in the storage unit 7b are combined, and an image of a road marking is detected and recognized from the composite image.

Abstract: A cellular phone body 10 includes a memory 12, a CPU 18, a camera 15, and a display 17. The CPU 18 displays on the display 17 a pointer P in a manner to overlap an image of an photographic subject photographed by the camera 15, and judges whether or not to save in an image data saving area 12f of the memory 12 the image of the photographic subject imaged by the camera 15 and buffered in a first buffer 12c of the memory 12, based on information of a move locus of the pointer P moving on the image of the photographic subject along a movement of the cellular phone body at a time of imaging the photographic subject with the camera 15.

Abstract: An inputting device which includes an image input section for inputting an image of a containing areas in which information to be inputted is filled in and patterns representing at least reference positions to define the positions of corresponding areas and size information of corresponding areas; a memory section for storing the image of the input by the image input section; a pattern recognizing section for detecting the reference positions from the patterns in the image which is stored in the memory section and recognizing size information of the areas; an area specifying section for specifying the positions of the areas from the reference positions detected by the pattern recognizing section and the size information of the areas; and an area inputting section for inputting images in the areas defined by the area specifying section.

Abstract: A cellular phone body 10 includes a memory 12, a CPU 18, a camera 15, and a display 17. The CPU 18 displays on the display 17 a pointer P in a manner to overlap an image of an photographic subject photographed by the camera 15, and judges whether or not to save in an image data saving area 12f of the memory 12 the image of the photographic subject imaged by the camera 15 and buffered in a first buffer 12c of the memory 12, based on information of a move locus of the pointer P moving on the image of the photographic subject along a movement of the cellular phone body at a time of imaging the photographic subject with the camera 15.

Abstract: The present invention presents an image processing apparatus having an input unit for inputting image data of an original image, a discriminating unit for extracting a predetermined region by using a feature of pixel of the input image data, and for discriminating an attribute of the region, a determining unit for determining the type of the image data on the basis of the distribution of the attributes of the regions, and a processing unit for processing the image data as specified depending on the type of the determined image data. In this constitution, image processing conforming to the accurate discrimination result can be applied to image data.

Abstract: A document processing apparatus includes a division section for dividing a document image into a plurality of regions or connection components. A recognition section recognizes the type of a region in units of divided regions and edit section edits region data while displaying the recognition result. A shaping section then shapes the document image by using the edited region data.