IMAGE PROCESSING APPARATUS

• US 20160150118A1
• Filed: 11/11/2015
• Published: 05/26/2016
• Est. Priority Date: 11/21/2014
• Status: Active Grant

• Current Assignee: KYOCERA Document Solutions, Inc. (Kyocera Corporation)
• Original Assignee: Kyocera Document Solutions America Incorporated (Kyocera Corporation)
• Inventors: Okumura, Ryuichi
• Granted Patent: US 9,451,118 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/146 Aligning or centring of the image pick-up or image-field
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: H04N 1/207 Simultaneous scanning of the original picture and the reproduced picture with a common scanning device
• CPC Class Codes: H04N 1/2104 for one or a few pictures
• CPC Class Codes: H04N 2201/0094 Multifunctional device, i.e. a device capable of all of reading, reproducing, copying, facsimile transception, file transception

Abstract

For calculating a zooming ratio for a scanned image of an original document that includes a handwritten object, in each of the primary and the secondary scanning direction, the zooming ratio calculating unit generates projection images of black objects in an original image of the original document and the scanned image, identifies the smallest and largest pixel positions in the projection image of the original image, identifies the corresponding smallest and largest pixel positions in the projection image of the scanned image, and calculates the zooming ratio on the basis of a two distances between the smallest and the largest pixel positions of the original image and the scanned image. After zooming the scanned image by the zooming ratio, an image of the handwritten object is extracted on the basis of the zoomed scanned image and the original image.

Claims

1. An image processing apparatus, comprising:

a scanned image obtaining unit configured to use an image scanning device and thereby obtain a scanned image of an original document in which a handwritten object has been written;

an original image obtaining unit configured to obtain original image printing data that was used for printing the original document;

a zooming ratio calculating unit configured to calculate a zooming ratio for the scanned image on the basis of the scanned image and an original image obtained from the original image printing data;

a zoom processing unit configured to perform zooming of the scanned image by the zooming ratio calculated by the zooming ratio calculating unit; and

a handwritten image extracting unit configured to extract an image of the handwritten object from the scanned image zoomed by the zoom processing unit on the basis of the scanned image zoomed by the zoom processing unit and the original image;

wherein the zooming ratio calculating unit (a) generates projection images of a black object in the original image in a primary scanning direction and a secondary scanning direction, (b) generates projection images of a black object in the scanned image in the primary scanning direction and the secondary scanning direction, (c) in the primary scanning direction, identifies a smallest value and a largest value of pixel positions in the projection image of the original image, identifies a smallest value and a largest value of pixel positions in the projection image of the scanned image corresponding to the smallest value and the largest value of the original image, and calculates a zooming ratio in the primary scanning direction on the basis of a distance between the smallest value and the largest value of the original image and a distance between the smallest value and the largest value of the scanned image, and (d) in the secondary scanning direction, identifies a smallest value and a largest value of pixel positions in the projection image of the original image, identifies a smallest value and a largest value of pixel positions in the projection image of the scanned image corresponding to the smallest value and the largest value of the original image, and calculates a zooming ratio in the secondary scanning direction on the basis of a distance between the smallest value and the largest value of the original image and a distance between the smallest value and the largest value of the scanned image.

2. The image processing apparatus according to claim 1 wherein in order to identify the smallest value and the largest value of pixel positions in the projection image of the scanned image,

(e1) if the projection image of the scanned image exists at a pixel position having the smallest value of the original image, the zooming ratio calculating unit identifies a pixel position having the smallest value of the existing projection image of the scanned image as the smallest value of the scanned image corresponding to the smallest value of the original image,

(e2) if the projection image of the scanned image exists at a pixel position having the largest value of the original image, the zooming ratio calculating unit identifies a pixel position having the largest value of the existing projection image of the scanned image as the largest value of the scanned image corresponding to the largest value of the original image,

(f1) if the projection image of the scanned image does not exist at a pixel position having the smallest value of the original image, the zooming ratio calculating unit identifies a pixel of the projection image in the scanned image as a pixel having the smallest value of the scanned image corresponding to the smallest value of the original image, the pixel of the projection image in the scanned image being nearest to and larger than a pixel position having the smallest value of the original image, and

(f2) if the projection image of the scanned image does not exist at a pixel position having the largest value of the original image, the zooming ratio calculating unit identifies a pixel of the projection image in the scanned image as a pixel having the largest value of the scanned image corresponding to the largest value of the original image, the pixel of the projection image in the scanned image being nearest to and smaller than a pixel position having the largest value of the original image.

3. The image processing apparatus according to claim 1 wherein the handwritten image extracting unit extracts the image of the handwritten object from the scanned image zoomed by the zoom processing unit on the basis of a difference between the scanned image zoomed by the zoom processing unit and the original image.

4. The image processing apparatus according to claim 1 wherein the handwritten image extracting unit masks in the scanned image zoomed by the zoom processing unit a color that exists in the original image on the basis of color distribution of the original image and thereby extracts the image of the handwritten object from the scanned image zoomed by the zoom processing unit.

5. The image processing apparatus according to claim 1 wherein the handwritten image extracting unit has a first operation mode and a second operation mode, selects the first operation mode or the second operation mode, and extracts the image of the handwritten object from the scanned image zoomed by the zoom processing unit in the selected operation mode;

wherein the first operation mode extracts the image of the handwritten object from the scanned image zoomed by the zoom processing unit on the basis of a difference between the scanned image zoomed by the zoom processing unit and the original image; and

the second operation mode masks in the scanned image zoomed by the zoom processing unit a color that exists in the original image on the basis of color distribution of the original image and thereby extracts the image of the handwritten object from the scanned image zoomed by the zoom processing unit.

6. The image processing apparatus according to claim 5 wherein the handwritten image extracting unit selects the first operation mode for the original image as a monochrome image and selects the second operation mode for the original image as a color image.