JP2012022575A5

JP2012022575A5 -

Info

Publication number: JP2012022575A5
Application number: JP2010161000A
Authority: JP
Filing date: 2010-07-15
Publication date: 2013-08-29
Anticipated expiration: 2030-07-15

Description

本発明に係る画像処理装置は、複数の入力画像から複数の文字領域を抽出する抽出手段と、前記抽出手段で抽出された複数の文字領域それぞれの歪みを補正する歪み補正手段と、前記歪み補正手段で歪み補正した後の複数の文字領域間の所定の画像特徴の差分が小さくなるように、前記複数の文字領域それぞれに対して補正すべき補正量を決定する決定手段と、前記決定手段で決定された補正量を用いて、前記歪み補正後の複数の文字領域に対して補正を行う画像間補正手段とを備えることを特徴とする。 An image processing apparatus according to the present invention includes an extraction unit that extracts a plurality of character regions from a plurality of input images, a distortion correction unit that corrects distortion of each of the plurality of character regions extracted by the extraction unit, and the distortion correction Determining means for determining a correction amount to be corrected for each of the plurality of character areas so that a difference in predetermined image features between the plurality of character areas after distortion correction by the means is reduced; and And an inter-image correction unit that performs correction on the plurality of character regions after the distortion correction using the determined correction amount.

Claims

Extracting means for extracting a plurality of character regions from a plurality of input images;
Distortion correcting means for correcting distortion of each of the plurality of character regions extracted by the extracting means;
Determining means for determining a correction amount to be corrected for each of the plurality of character areas so that a difference in predetermined image features between the plurality of character areas after distortion correction by the distortion correction means is reduced;
An image processing apparatus comprising: an inter-image correction unit that corrects the plurality of character regions after the distortion correction using the correction amount determined by the determination unit.

The image processing apparatus according to claim 1, wherein the predetermined image feature includes a background color of the plurality of character regions after the distortion correction.

The image processing apparatus according to claim 1, wherein the predetermined image feature includes a position of a character image included in the plurality of character regions after the distortion correction.

The determining unit classifies the plurality of character regions after the distortion correction into a plurality of groups, and determines the correction amount for reducing the difference between the predetermined image features for each of the classified groups. The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus.

The image processing apparatus according to claim 4, wherein the group is classified based on an average value of background colors of the plurality of character regions after the distortion correction.

The image processing apparatus according to claim 4, wherein the group is classified based on a position and a size of a character image included in each of the plurality of character regions after the distortion correction.

7. The apparatus according to claim 1, further comprising an output unit that outputs an electronic file including a plurality of character regions after the difference between the image features is corrected by the inter-image correction unit. The image processing apparatus according to item.

Image determining means for determining whether the input image is a character center or a non-character center using a ratio of a total area of the extracted one or more character regions to an area of the input image;
For the input image determined to be a non-character center by the image determination means, information about the character region included in the input image is given as metadata,
The image processing apparatus according to claim 7, wherein the electronic file includes an input image to which the metadata is assigned.

When the image determination unit determines that the character center is set, the ratio of the area of the extracted character area to the area of the input image is equal to or greater than a first threshold value. Representative character area determination means for determining
The image processing apparatus according to claim 7, wherein the electronic file includes the determined representative character area as an output image.

The image processing apparatus according to claim 9, wherein the electronic file includes text data of a character area other than the representative character area as metadata.

The representative character region determination means is a case where there is no character region in which the ratio of the area of the extracted character region to the area of the input image is equal to or greater than the first threshold value, and from the first threshold value 11. The method according to claim 9, wherein when there are a plurality of character regions after the distortion correction that is a ratio equal to or greater than a small second threshold, the plurality of character regions after the distortion correction are determined as representative character regions. The image processing apparatus described.

The image processing apparatus according to claim 11, wherein the electronic file includes an image in which the determined representative character regions are arranged according to a predetermined layout as an output image.

An extraction step in which the extraction means extracts a plurality of character regions from a plurality of input images;
A distortion correcting unit that corrects distortion of each of the plurality of character regions extracted by the extracting unit;
Determining a correction amount to be corrected for each of the plurality of character regions so that a difference between predetermined image features between the plurality of character regions after the distortion correction is reduced;
An image processing apparatus, comprising: an inter-image correction unit that corrects the plurality of character regions after the distortion correction using the determined correction amount.

Computer
Extraction means for extracting a plurality of character regions from a plurality of input images;
Distortion correcting means for correcting distortion of each of the plurality of character regions extracted by the extracting means;
A determining unit that determines a correction amount to be corrected for each of the plurality of character regions so that a difference between predetermined image features between the plurality of character regions after distortion correction by the distortion correction unit is reduced;
An inter-image correction unit that corrects a plurality of character regions after the distortion correction using the correction amount determined by the determination unit;
Program to function as.