JP2011123737A5

JP2011123737A5 -

Info

Publication number: JP2011123737A5
Application number: JP2009281747A
Authority: JP
Filing date: 2009-12-11
Publication date: 2013-01-31
Anticipated expiration: 2029-12-11

Description

本発明は、テンプレート画像を被探索画像内で走査し、パターンマッチングを行う物体認識装置において、前記被探索画像から所定数のテンプレート画像片に分割されている前記テンプレート画像と同一のサイズの部分画像を抜き出し、前記各テンプレート画像片に対応して前記所定数の部分画像片に分割する部分画像分割手段と、前記テンプレート画像片と前記部分画像片とのそれぞれの相関値を求め、所定閾値以上となる前記相関値の個数を集計して集計値を求める演算手段と、前記被探索画像の全体を走査した結果、前記演算手段により得られた集計値のうち、予め設定された第１所定値以上となる集計値の中から最大値となる集計値を１つ抽出し、その集計値に対応する部分画像の位置を合致位置と認識する認識手段と、前記認識手段により前記合致位置が認識された際の集計値が、前記所定数よりも小さい値で且つ前記第１所定値よりも大きい値に設定された第２所定値以下の場合は、前記テンプレート画像を、前記認識手段で認識された前記合致位置に対応する部分画像に置き換える更新手段と、を備えたことを特徴とするものである。 The present invention, the template image is scanned within the search image, the object recognition apparatus for performing pattern matching part before Symbol the template image and the same size that is divided into a predetermined number of the template image pieces from the search image extracting an image, and the partial image dividing unit operable to correspond to each template image pieces divided into partial image sections of the predetermined number, obtains the respective correlation value between the template image piece and the partial image sections, or greater than a predetermined threshold value A calculation unit for totaling the number of the correlation values to obtain a total value, and a first predetermined value set in advance among the total values obtained by the calculation unit as a result of scanning the entire searched image A recognizing means for extracting one of the maximum values from the total values as described above and recognizing the position of the partial image corresponding to the total value as a matching position; When the total value when the matching position is recognized is less than the second predetermined value set to a value smaller than the predetermined number and larger than the first predetermined value, the template image is Update means for replacing with a partial image corresponding to the matching position recognized by the recognition means.

また、本発明は、テンプレート画像を被探索画像内で走査し、パターンマッチングを行う物体認識装置において、前記被探索画像から所定数のテンプレート画像片に分割されている前記テンプレート画像と同一のサイズの部分画像を抜き出し、前記各テンプレート画像片に対応して前記所定数の部分画像片に分割する部分画像分割手段と、前記テンプレート画像片と前記部分画像片とのそれぞれの相関値を求め、所定閾値以上となる前記相関値の個数を集計して集計値を求める演算手段と、前記被探索画像の全体を走査した結果、前記演算手段により得られた集計値のうち、予め設定された第１所定値以上となる集計値の中から最大値となる集計値を１つ抽出し、その集計値に対応する部分画像の位置を合致位置と認識する認識手段と、今回の走査で前記認識手段により前記合致位置が認識された際の集計値が、前記所定数よりも小さい値で且つ前記第１所定値よりも大きい値に設定された第２所定値以下であって、過去の走査で前記認識手段により前記合致位置が認識された際の集計値と今回の走査で前記認識手段により前記合致位置が認識された際の集計値との差分値が、予め設定された第３所定値以下の場合は、前記テンプレート画像を、今回の走査で前記認識手段により認識された前記合致位置に対応する部分画像に置き換える更新手段と、を備えたことを特徴とするものである。 Further, the present invention is that the template image is scanned within the search image, the object recognition apparatus for performing pattern matching before Symbol the template image and the same size that is divided into a predetermined number of the template image pieces from the search image the extracted partial image, obtains the respective correlation value between said each template image piece partial image dividing means for dividing the partial image sections of the predetermined number in response to the template image piece and the partial image section, predetermined A calculation means for calculating the total value by counting the number of correlation values that are equal to or greater than a threshold value, and a preset first value among the total values obtained by the calculation means as a result of scanning the entire searched image. A recognizing unit that extracts one total value that is the maximum value from the total values that are equal to or greater than a predetermined value, and recognizes the position of the partial image corresponding to the total value as a matching position; The total value when the matching position is recognized by the recognition means in scanning is equal to or less than a second predetermined value set to a value smaller than the predetermined number and larger than the first predetermined value, A difference value between a total value when the matching position is recognized by the recognition unit in the past scan and a total value when the matching position is recognized by the recognition unit in the current scan is set in advance. 3 When the value is equal to or smaller than a predetermined value, the image processing apparatus includes updating means for replacing the template image with a partial image corresponding to the matching position recognized by the recognition means in the current scan.

Claims

In an object recognition device that scans a template image in a searched image and performs pattern matching ,
Portion to split from front Symbol the search image extracted by the same size of the partial image and the template image are divided into a predetermined number of template image piece, the said predetermined number of partial image sections corresponding to each template image pieces Image segmentation means;
Calculating means for obtaining a correlation value between each of the template image piece and the partial image piece;
As a result of scanning the entire image to be searched, one total value that is the maximum value is extracted from the total values that are equal to or greater than the first predetermined value that is set in advance, among the total values obtained by the calculation means. Recognizing means for recognizing the position of the partial image corresponding to the total value as a matching position;
When the total value when the matching position is recognized by the recognition means is equal to or smaller than the second predetermined value set to a value smaller than the predetermined number and larger than the first predetermined value, the template An object recognizing apparatus comprising: an updating unit that replaces an image with a partial image corresponding to the matching position recognized by the recognizing unit.

In an object recognition device that scans a template image in a searched image and performs pattern matching ,
Portion to split from front Symbol the search image extracted by the same size of the partial image and the template image are divided into a predetermined number of template image piece, the said predetermined number of partial image sections corresponding to each template image pieces Image segmentation means;
Calculating means for obtaining a correlation value between each of the template image piece and the partial image piece, and calculating a total value by counting the number of the correlation values equal to or greater than a predetermined threshold;
As a result of scanning the entire image to be searched, one total value that is the maximum value is extracted from the total values that are equal to or greater than the first predetermined value that is set in advance, among the total values obtained by the calculation means. Recognizing means for recognizing the position of the partial image corresponding to the total value as a matching position;
The total value when the matching position is recognized by the recognition means in the current scan is less than or equal to a second predetermined value set to a value smaller than the predetermined number and larger than the first predetermined value. Thus, a difference value between the total value when the matching position is recognized by the recognition unit in the previous scan and the total value when the matching position is recognized by the recognition unit in the current scan is set in advance. And an update unit that replaces the template image with a partial image corresponding to the matching position recognized by the recognition unit in a current scan when the value is equal to or less than a third predetermined value. apparatus.

The object recognition apparatus according to claim 1, further comprising a template image dividing unit that divides the template image into a predetermined number of template image pieces.

When there are a plurality of aggregate values that are maximum values among the aggregate values that are equal to or greater than the first predetermined value, the recognizing unit calculates a total value of correlation values that are used when the aggregate values that are the maximum values are aggregated. each calculated, the object according to the in each sum, any one of claims 1 to 3, characterized in that to recognize that the matching position a position of the partial image corresponding to the total value of the maximum value Recognition device.

When calculating the correlation values of the template image piece and the partial image piece in order, the calculating means is configured such that the number of correlation values that are smaller than the predetermined threshold is from the predetermined number to the first predetermined value. the exceeding a difference value obtained by subtracting, object recognition according to any one of claims 1 to 4, characterized in that aborting the calculation of the correlation value with the rest of the template image piece and the partial image section apparatus.

In an object recognition method that scans a template image in a searched image and performs pattern matching,
Partial image dividing means, said extracting a partial image of the template image and the same size that is divided into a predetermined number of the template image pieces from the search image, the partial image of the predetermined number corresponding to each template image pieces A partial image dividing step for dividing the image into pieces;
A calculating step of calculating a correlation value of each of the template image piece and the partial image piece, calculating a total value by counting the number of the correlation values that are equal to or greater than a predetermined threshold; and
As a result of the recognition means scanning the entire searched image, the aggregate value that is the maximum value among the aggregate values that are equal to or greater than the first predetermined value set in advance among the aggregate values obtained in the calculation step. A step of recognizing the position of the partial image corresponding to the total value as a matching position,
The update means has a total value when the matching position is recognized in the recognition step is equal to or smaller than a second predetermined value set to a value smaller than the predetermined number and larger than the first predetermined value. In this case, the object recognition method includes: an update step of replacing the template image with a partial image corresponding to the matching position recognized in the recognition step.

In an object recognition method that scans a template image in a searched image and performs pattern matching,
Partial image dividing means, said extracting a partial image of the template image and the same size that is divided into a predetermined number of the template image pieces from the search image, the partial image of the predetermined number corresponding to each template image pieces A partial image dividing step for dividing the image into pieces;
A calculating step of calculating a correlation value of each of the template image piece and the partial image piece, calculating a total value by counting the number of the correlation values that are equal to or greater than a predetermined threshold; and
As a result of the recognition means scanning the entire searched image, the aggregate value that is the maximum value among the aggregate values that are equal to or greater than the first predetermined value set in advance among the aggregate values obtained in the calculation step. A step of recognizing the position of the partial image corresponding to the total value as a matching position,
A second value in which the updating means is set to a value smaller than the predetermined number and larger than the first predetermined value when the matching position is recognized in the recognition step in the current scan. A total value when the matching position is recognized in the recognition step in the past scan and a total value when the matching position is recognized in the recognition step in the current scan An update step of replacing the template image with a partial image corresponding to the matching position recognized in the recognition step in the current scan when the difference value is equal to or less than a preset third predetermined value. An object recognition method characterized by that.

8. The object recognition method according to claim 6, wherein the template image dividing means further includes a template image dividing step of dividing the template image into a predetermined number of template image pieces prior to the calculating step. .

In the recognizing step , when there are a plurality of aggregate values that are maximum values among the aggregate values that are equal to or greater than the first predetermined value , the recognition unit is used to aggregate the aggregate values that are maximum values. 9. The total value of correlation values is calculated, and the position of the partial image corresponding to the total value that is the maximum value among the total values is recognized as a matching position . The object recognition method according to item 1 .

In the calculation step , when the calculation means sequentially calculates the correlation values of the template image piece and the partial image piece, the number of correlation values that are smaller than the predetermined threshold is the predetermined number. If you exceed a difference value obtained by subtracting the first predetermined value from any of claims 6 to 9, characterized in that aborting the calculation of the correlation value between the the rest of the template image piece partial image piece 1 Item recognition method according to item.

The program for making a computer perform each step of the object recognition method of any one of Claims 6 thru | or 10 .