JP3732096B2 - Securities imprint verification method - Google Patents

Securities imprint verification method Download PDF

Info

Publication number
JP3732096B2
JP3732096B2 JP2001037849A JP2001037849A JP3732096B2 JP 3732096 B2 JP3732096 B2 JP 3732096B2 JP 2001037849 A JP2001037849 A JP 2001037849A JP 2001037849 A JP2001037849 A JP 2001037849A JP 3732096 B2 JP3732096 B2 JP 3732096B2
Authority
JP
Japan
Prior art keywords
imprint
securities
representative
image
seal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
JP2001037849A
Other languages
Japanese (ja)
Other versions
JP2002245461A (en
Inventor
英二 巻本
展充 浅野
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Omron Terminal Solutions Corp
Original Assignee
Hitachi Omron Terminal Solutions Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Omron Terminal Solutions Corp filed Critical Hitachi Omron Terminal Solutions Corp
Priority to JP2001037849A priority Critical patent/JP3732096B2/en
Publication of JP2002245461A publication Critical patent/JP2002245461A/en
Application granted granted Critical
Publication of JP3732096B2 publication Critical patent/JP3732096B2/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Landscapes

  • Collating Specific Patterns (AREA)

Description

【0001】
【発明の属する技術分野】
本発明は、小切手等の有価証券に押されている代表者印、署名印をあらかじめ登録されているマスター印影画像と照合を行い、その有価証券の信頼度(照合率)を算出する有価証券印影照合方法に関する。
【0002】
【従来の技術】
銀行等の金融機関では、大型コンピュータを保有する集中センターを設置し、これに各支店の顧客情報を蓄積させ、この集中センターと支店の端末装置を通信回線で接続したネットワークを形成している。
【0003】
各支店において、顧客が小切手等の有価証券を持参した場合には、その有価証券が有効なものであるかを判断する為に、有価証券に押されている署名印や代表者印をあらかじめ登録されているマスター印影と照合を行う。
その方法としては、まず、各支店のオペレータが支店の端末装置を使用し、登録されているマスター印影を検索する。口座番号などを検索キーとして、支店のコンピュータ、または、集中センターのコンピュータから該当するマスター印影を検索し、該当する顧客のデータが存在する場合には、そのマスター印影が端末装置のディスプレイに表示される。
オペレータはディスプレイに表示された印影と実際に有価証券に押されている印影とを目視等により照合することにより、その印影が適正なものであるかを判定している。
近年では、この印影照合作業を補助する機能として、コンピュータ処理により、マスター印影と照合対象印影との位置・角度を合わせて表示させたり、2つの印影の類似度を算出して表示させ、オペレータに依存する作業を軽減させている。なお、特開平11−96362号公報には印影照合装置に関する技術が記載されている。
【0004】
【発明が解決しようとする課題】
従来の方式では、小切手等の有価証券の印影を照合する場合、署名印と代表者印のそれぞれで印影エリアの位置指定が必要であり、オペレータへの負担が大きく、作業に時間がかかっていた。また、類似度(照合率)による真贋判定においても、署名印影と代表者印影が重なった場合にはその照合率が大きく低下し、信頼性に問題があった。
【0005】
本発明は、前述の問題点に鑑みなされたもので、従来に比べて高速かつ高精度に照合し、信頼性の高い印影照合処理を提供することを課題とする。
【0006】
【課題を解決するための手段】
前述した課題を解決するために、小切手等の有価証券に押されている印影を照合する際の印影検出処理において、照合対象印影は有価証券の右下部周辺に押される可能性が高いことを利用して、右下部から照合対象印影を探し、登録されているマスター印影画像と照合する構成を採用する。
また、有価証券画像内から代表者印影を探し出し、次に、署名印影は代表者印影と並んで左側に押される可能性が高いことを利用して、得られた代表者印影位置の左側周辺で署名印影を探索し、登録されている署名印影画像と照合する構成を採用する。
【0007】
【発明の実施の形態】
以下、本発明の一実施例として、銀行等の金融機関向けの印影照合装置について説明する。印影照合装置では、あらかじめ登録されている顧客の届け出印鑑の印影(以下「マスター印影」という)と、顧客等によって持ち込まれた手形、小切手等の有価証券に押印されている印影(以下「被照合印影」という)とを照合して正当な利用者であるかの判断材料にしている。本装置は届け出印影と小切手等の有価証券に押印されている署名印影と代表者印影をマスター印影と一致して重なるように位置/回転角度あわせをして合成した印影画像を出力し、また、それらの印影の類似の度合いを定量的に出力し、その有価証券の真贋判定の材料にするものである。
【0008】
図1は本発明を実現する有価証券印影照合装置100の一実施例の構成図である。金融機関等には預金者の届け出印(マスター印影)がスキャナ等で読み込んだイメージデータとしてマスター印影画像データベース101に登録されている。取り引きの際には金融機関に持ち込まれた手形や小切手、各種用紙をスキャナ等の被照合印影画像入力装置102を介して取り込む。取り込まれた被照合印影を含む有価証券画像と口座番号等から検索した対応するマスター印影画像が画像入力部103に入る。次に、代表者印影照合部104にて印影検出処理部105、赤色成分抽出処理部106を用いて有価証券画像から代表者印影を抽出し、位置/角度合わせ処理部107にてマスター印影とその位置/角度を合わせる。次の署名印影照合部108でも同様に印影検出処理部105において署名印影を抽出し、位置/角度合わせ処理部107にてマスター印影と位置/角度を合わせる。
【0009】
照合処理部109では、位置/角度が合わされた代表者印影、署名印影についてそれぞれマスター印影と照合を行う。類似度統合処理部110では、照合処理部109にて算出された代表者印影と署名印影の類似度を統合し、その有価証券の信頼度(照合率)を算出し、印影の重ね合せ画像等とともに照合結果出力装置111に表示させる。
【0010】
オペレータは照合結果出力装置111に表示された印影の重ねあわせ画像や照合率等のデータを参考に持ち込まれた有価証券が正当なものであるかどうかを判定する。以下、有価証券印影照合装置100による自動照合処理を説明する。
【0011】
図2は、有価証券印影照合装置100による自動照合処理を示すフロー図である。まず、画像入力装置を起動し、持ち込まれた有価証券をスキャンする(201)。また、ここで対応するマスター印影画像もマスター印影画像データベースから入力する(202)。続いて、入力された有価証券カラー画像、マスター画像から代表者印影を検出する。
【0012】
図3はこの代表者印影検出処理が示されたフロー図である。ここでは、まず、カラー画像入力(301)の後、主成分分析による赤色部分抽出処理を行う(302)。ここでは、有価証券に押されている代表者印影の色が赤である場合を想定している。カラー画像データの赤成分、緑成分、青成分の分布情報から3次元的な主成分分析を行い、分類することで図5のように赤色の代表者印影を含む画像(図5(B))とそれ以外の署名印影や罫線や地紋、文字などを含む画像(図5(C))に分離させることができる。そして、得られた赤色抽出画像(図5(B))について2値化処理を行い、代表者印影を含む2値画像を生成する(303)。
【0013】
次に、この2値画像から代表者印影の位置を検出する。その方法としては、まず、2値画像からモザイク化処理を行い、階調のモザイク画像を作成する。例えばここでは8×8画素のエリア内の黒画素数をモザイク画像1画素の階調値(0〜64)とする。同様に、マスター印影画像についてもモザイク化処理を行う。図6にモザイク画像の例を示す。(A)は有価証券、(B),(C)はマスター画像である(304)。モザイク化した画像を用いて1ブロックずつずらしながら重ね合せのパターンマッチングを行い、それぞれの画素での階調値の差を足し合わせた相違度が最も小さかったエリアを代表者印影が存在するエリアと判定する。ここでの処理において、ターゲットである代表者印影が有価証券画像の右下に存在する可能性が高いことを考慮して右下からマッチング処理を行う。これにより、高速かつ高精度に代表者印影エリアを検出できる(305)。
【0014】
次に、得られた代表者印影周辺エリアにおいて元画像を用いて回転させながらパターンマッチングを行い、詳細な位置・角度を合わせる(306)。得られた代表者印影の位置座標、回転角度から、マスター印影、被照合印影について角度を合わせた正規化画像を生成する(307)。以上により、まず有価証券中の代表者印影を検出する。検出に失敗した場合は照合不能として照合処理を終了する(204)。次に、同様に有価証券中の署名印影を登録されているマスター印影を用いて検出する。図4はこの署名印影検出処理が示されたフロー図である。ここでは、まず、(302)の処理において生成した赤成分以外を抽出した画像(図5(C))を入力する(401)。そして、その画像に対して2値化処理を行い、署名印影を含む2値画像を生成する(402)。次にこの画像を用いて署名印影を抽出する。ここではすでに代表者印の位置座標がわかっており、署名印影は代表者印影と並んで左側に押される可能性が高いことを考慮し、図7に示すように、代表者印影のエリアを含む左側周辺部を署名印影探索エリアとする。これにより署名印影の検出処理の高速化を図ることができる(403)。このエリアにおいて代表者印影と同様にパターンマッチングを行い、署名印影の位置、角度を合わせる(404)。得られた署名印影の位置座標、回転角度から、マスター印影、被照合印影について角度を合わせた正規化画像を生成する(405)。次に、位置・角度をあわせた代表者印影、署名印影について照合を行い、それぞれの類似度を算出する(207)。
【0015】
照合の方法は例えばドット毎のマッチングにより類似度Simを求める。具体的には、各々の画像の画素数をNm,Ntおよび、双方に共通する画素数Ncとした時、以下の式で定義する。
【0016】
【数1】

Figure 0003732096
この類似度は0≦Sim≦1であり、完全に一致するものが1である。類似度の算出方式についてはこの他にも印影画像の輪郭や濃度勾配のベクトルを用いた方式など様々な方法が考えられる。
【0017】
次に、代表者印影と署名印影それぞれの類似度を統合し、その有価証券の信頼度(照合率)を算出する(208)。その方法としては、代表者印影と署名印影の類似度をある比率で掛け合わせる。例えば、代表者印影と署名印影の重なりがない場合は両方の類似度の平均を有価証券の照合率とする。代表者印影と署名印影に重なりが生じている場合はその重なり具合に応じて掛け合わせの比率を変更させることでより信頼性の高い照合率を算出できる。掛け合わせ比率として例えば以下のように設定する。
(1)重なりがない場合は、署名印:代表者印=5:5
(2)重なりエリアが代表者印の2割未満の場合は、署名印:代表者印=6:4
(3)重なりエリアが代表者印の2割以上4割未満の場合は、署名印:代表者印=7:3
(4)重なりエリアが代表者印の4割以上の場合は、署名印:代表者印=8:2
【0018】
【発明の効果】
本発明により、小切手等の有価証券の照合対象印影が右下部周辺に存在する可能性が高いことを利用して、右下部から印影を探索することで印影照合処理の高速化を図ることができる。
【図面の簡単な説明】
【図1】有価証券印影照合装置構成図
【図2】実施例の処理手順
【図3】代表者印影照合処理手順
【図4】署名印影照合処理手順
【図5】主成分分析による赤色抽出の説明図
【図6】代表者印影探索処理の説明図
【図7】署名印影探索処理の説明図
【符号の説明】
100:有価証券印影照合装置、101:マスター印影画像データベース、102:被照合印影画像入力装置、103:画像入力部、104:代表者印影照合部、105:印影検出処理部、106:赤色成分抽出処理部、107:角度/位置合わせ処理部、108:署名印影処理部、109:照合処理部、110:類似度統合処理部、111:照合結果出力装置、201〜207:実施例の処理手順、301〜307:代表者印影照合処理手順、401〜405:署名印影照合処理手順[0001]
BACKGROUND OF THE INVENTION
The present invention compares a representative seal and signature stamp pressed on a securities such as a check with a master imprint image registered in advance, and calculates the reliability (matching rate) of the securities. The verification method
[0002]
[Prior art]
A financial institution such as a bank establishes a centralized center having a large computer, stores customer information of each branch in this, and forms a network in which the centralized center and branch terminal devices are connected by a communication line.
[0003]
In each branch, when a customer brings securities such as a check, in order to judge whether the securities are valid, the signature stamp or representative stamp on the securities is registered in advance. Check with the master seal imprinted.
As a method, first, an operator at each branch searches for a registered master seal by using a branch terminal device. Using the account number as a search key, the corresponding master seal stamp is searched from the branch office computer or centralized center computer. If the corresponding customer data exists, the master seal stamp is displayed on the terminal device display. The
The operator determines whether or not the imprint is appropriate by collating the imprint displayed on the display with the imprint actually pressed on the securities by visual inspection or the like.
In recent years, as a function that assists in this imprint collation operation, the position and angle of the master imprint and the collation target imprint are displayed by computer processing, or the similarity between the two imprints is calculated and displayed. Reducing dependent work. Japanese Patent Application Laid-Open No. 11-96362 describes a technique related to an imprint checking device.
[0004]
[Problems to be solved by the invention]
In the conventional method, when checking the imprint of securities such as checks, it is necessary to specify the position of the imprint area for each of the signature stamp and the representative stamp, which places a heavy burden on the operator and takes time. . Further, even in the authenticity determination based on the similarity (collation rate), when the signature imprint and the representative imprint overlap, the collation rate is greatly lowered, and there is a problem in reliability.
[0005]
The present invention has been made in view of the above-described problems, and an object of the present invention is to provide a highly reliable seal collation process that collates at a higher speed and with higher accuracy than in the past.
[0006]
[Means for Solving the Problems]
In order to solve the above-mentioned problem, in the imprint detection process when checking imprints pressed on securities such as checks, it is highly likely that the target imprint will be pressed around the lower right corner of the securities. Then, a configuration is adopted in which a collation target imprint is searched from the lower right and collated with a registered master imprint image.
In addition, the representative imprint is searched for in the securities image, and then the signature imprint is likely to be pushed to the left side along with the representative imprint, and around the left side of the obtained representative imprint position. A configuration is adopted in which a signature stamp is searched and collated with a registered signature seal image.
[0007]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, as one embodiment of the present invention, an imprint verification apparatus for a financial institution such as a bank will be described. In the stamp verification device, the registered seal stamp of the customer (hereinafter referred to as “master seal stamp”) and the stamp imprinted on securities such as bills and checks brought in by the customer (hereinafter referred to as “verified”). "Indicium" is used to determine whether the user is a legitimate user. This device outputs a seal image that is a composite of the registered seal and signature stamp imprinted on securities such as checks and the representative seal imprinted by matching the position / rotation angle so as to coincide with the master seal. The degree of similarity between these impressions is quantitatively output and used as a material for authenticity determination of the securities.
[0008]
FIG. 1 is a block diagram of an embodiment of a securities imprint verification device 100 for realizing the present invention. In a financial institution or the like, a depositor's registered seal (master seal) is registered in the master seal image database 101 as image data read by a scanner or the like. At the time of transaction, bills, checks, and various papers brought into the financial institution are taken in via a collated seal image input device 102 such as a scanner. A securities image including the captured image to be verified and a corresponding master seal image retrieved from the account number and the like enter the image input unit 103. Next, the representative imprint collating unit 104 extracts the representative imprint from the securities image using the imprint detection processing unit 105 and the red component extraction processing unit 106, and the position / angle matching processing unit 107 extracts the master imprint and its imprint. Adjust the position / angle. Similarly, in the next signature imprint verification unit 108, the signature imprint is extracted in the imprint detection processing unit 105, and the position / angle matching processing unit 107 matches the position / angle with the master imprint.
[0009]
The verification processing unit 109 performs verification with the master seal for each of the representative seal and the signature seal whose positions / angles are matched. The similarity integration processing unit 110 integrates the similarity between the representative seal and the signature seal stamp calculated by the verification processing unit 109, calculates the reliability (matching rate) of the securities, and superimposes the seal stamp image, etc. At the same time, it is displayed on the collation result output device 111.
[0010]
The operator determines whether the brought-in securities are valid with reference to data such as the superimposed image of the seal imprint displayed on the verification result output device 111 and data such as the verification rate. Hereinafter, the automatic collation process by the securities stamp imprint collation apparatus 100 will be described.
[0011]
FIG. 2 is a flowchart showing an automatic matching process performed by the securities imprint matching device 100. First, the image input apparatus is activated, and the securities brought in are scanned (201). The corresponding master seal image is also input from the master seal image database (202). Subsequently, a representative seal is detected from the input securities color image and master image.
[0012]
FIG. 3 is a flowchart showing the representative seal detection process. Here, first, after a color image input (301), red part extraction processing by principal component analysis is performed (302). Here, it is assumed that the representative seal imprinted on the securities is red. An image including a red representative imprint as shown in FIG. 5 by performing three-dimensional principal component analysis from the distribution information of the red component, green component, and blue component of color image data (FIG. 5B). And an image including other signature seals, ruled lines, background patterns, characters, and the like (FIG. 5C). Then, the obtained red extracted image (FIG. 5B) is binarized to generate a binary image including the representative seal (303).
[0013]
Next, the position of the representative seal is detected from this binary image. As the method, first, a mosaic process is performed from a binary image to create a gradation mosaic image. For example, here, the number of black pixels in an area of 8 × 8 pixels is set as the gradation value (0 to 64) of one pixel of the mosaic image. Similarly, a mosaic process is also performed on the master imprint image. FIG. 6 shows an example of a mosaic image. (A) is a securities, and (B) and (C) are master images (304). Using the mosaiced image, overlay pattern matching is performed while shifting one block at a time, and the area with the smallest difference is the area where the representative imprint is present. judge. In this process, the matching process is performed from the lower right in consideration of the high possibility that the target representative seal is present in the lower right of the securities image. Thereby, the representative imprint area can be detected at high speed and with high accuracy (305).
[0014]
Next, pattern matching is performed while rotating the obtained representative imprint peripheral area using the original image, and the detailed position and angle are matched (306). Based on the position coordinates and the rotation angle of the obtained representative imprint, a normalized image is generated by matching the angles of the master imprint and the check target imprint (307). As described above, first, a representative seal in the securities is detected. If the detection fails, the collation process is terminated because the collation is impossible (204). Next, the signature imprint in the securities is similarly detected using the registered master imprint. FIG. 4 is a flowchart showing the signature seal detection process. Here, first, an image (FIG. 5C) obtained by extracting components other than the red component generated in the processing of (302) is input (401). Then, a binarization process is performed on the image to generate a binary image including a signature seal (402). Next, a signature seal is extracted using this image. Here, the position coordinates of the representative seal are already known, and considering that the signature stamp is likely to be pushed to the left side along with the representative stamp, as shown in FIG. 7, the area of the representative seal is included. The left periphery is the signature seal search area. As a result, the speed of the signature seal detection process can be increased (403). In this area, pattern matching is performed in the same manner as the representative seal, and the position and angle of the signature seal are matched (404). Based on the position coordinates and rotation angle of the obtained signature seal stamp, a normalized image is generated by matching the angles of the master seal stamp and the check target seal stamp (405). Next, collation is performed for the representative seal and signature seal that match the position and angle, and the respective similarities are calculated (207).
[0015]
As a collation method, for example, similarity Sim is obtained by matching for each dot. Specifically, when the number of pixels of each image is Nm, Nt and the number of pixels Nc common to both, it is defined by the following formula.
[0016]
[Expression 1]
Figure 0003732096
This similarity is 0 ≦ Sim ≦ 1, and 1 is a perfect match. There are various other methods for calculating the similarity, such as a method using a contour of an imprint image or a vector of density gradient.
[0017]
Next, the similarity between the representative seal and the signature seal is integrated, and the reliability (collation rate) of the securities is calculated (208). As the method, the similarity between the representative seal and the signature seal is multiplied by a certain ratio. For example, when there is no overlap between the representative seal and the signature seal, the average of both similarities is used as the verification rate of the securities. If there is an overlap between the representative seal and the signature seal, a more reliable verification rate can be calculated by changing the multiplication ratio according to the overlap. For example, the multiplication ratio is set as follows.
(1) When there is no overlap, signature stamp: representative stamp = 5: 5
(2) When the overlap area is less than 20% of the representative mark, signature mark: representative mark = 6: 4
(3) When the overlap area is 20% or more and less than 40% of the representative mark, the signature mark: representative mark = 7: 3
(4) When the overlap area is 40% or more of the representative mark, signature mark: representative mark = 8: 2
[0018]
【The invention's effect】
By utilizing the fact that there is a high possibility that a check target imprint of a security such as a check exists in the lower right area according to the present invention, it is possible to speed up the imprint verification process by searching for the imprint from the lower right part. .
[Brief description of the drawings]
1 is a block diagram of a securities imprint collation apparatus. FIG. 2 is a processing procedure of an embodiment. FIG. 3 is a representative imprint collation processing procedure. FIG. 4 is a signature imprint collation processing procedure. Explanatory diagram [FIG. 6] Explanatory diagram of representative imprint search processing [FIG. 7] Explanatory diagram of signature imprint search processing [Explanation of symbols]
100: Securities imprint collation device, 101: Master imprint image database, 102: Checked imprint image input device, 103: Image input unit, 104: Representative imprint collation unit, 105: Imprint detection processing unit, 106: Red component extraction Processing unit 107: Angle / position alignment processing unit 108: Signature imprint processing unit 109: Collation processing unit 110: Similarity integration processing unit 111: Collation result output device 201-207: Processing procedure of the embodiment 301 to 307: Representative imprint collation processing procedure, 401 to 405: Signature imprint collation processing procedure

Claims (2)

あらかじめ登録してあるマスター印影と画像読み取り装置により入力された有価証券に押印されている印影とを照合する印影照合装置において、照合を行うために登録されているマスター印影画像から照合対象印影をマッチング等の手法を用いてその位置を探し出す際に、入力された有価証券画像の右下部周辺から探索し、
前記得られた照合対象の署名印影と代表者印影をあらかじめ登録してあるそれぞれのマスター印影と比較し、その有価証券が有効であるかを判定する処理において、各々個別に算出した署名印影と代表者印影の2つの印影の類似度を、それぞれの重なり具合に応じた比率で掛け合わせることによって該有価証券の照合率を算出することを特徴とする有価証券印影照合方法。
Matching the target imprint from the master imprint image registered for collation in the imprint collation device that collates the master imprint registered in advance with the imprint imprinted on the securities input by the image reader. When searching for the position using a method such as, search from the lower right corner of the input securities image ,
In the process of comparing the obtained signature imprint to be verified and the representative imprint with each of the master imprints registered in advance, and determining whether the securities are valid, the signature imprint and the representative individually calculated A securities imprint matching method, wherein a matching rate of the securities is calculated by multiplying the similarity of two imprints of the person's seal by a ratio corresponding to the degree of overlap.
前記登録されている代表者マスター印影画像を用いて小切手等の有価証券画像内から照合対象の代表者印影を探し出し、得られた代表者印影位置をもとにして照合対象である署名印影を見つけ、照合処理を行うことを特徴とする請求項1記載の有価証券印影照合方法。  The registered representative master imprint image is used to find the representative imprint to be verified from the securities image such as a check, and the signature imprint to be verified is found based on the obtained representative imprint position. 2. The securities imprint verification method according to claim 1, wherein verification processing is performed.
JP2001037849A 2001-02-15 2001-02-15 Securities imprint verification method Expired - Fee Related JP3732096B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2001037849A JP3732096B2 (en) 2001-02-15 2001-02-15 Securities imprint verification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2001037849A JP3732096B2 (en) 2001-02-15 2001-02-15 Securities imprint verification method

Publications (2)

Publication Number Publication Date
JP2002245461A JP2002245461A (en) 2002-08-30
JP3732096B2 true JP3732096B2 (en) 2006-01-05

Family

ID=18900918

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2001037849A Expired - Fee Related JP3732096B2 (en) 2001-02-15 2001-02-15 Securities imprint verification method

Country Status (1)

Country Link
JP (1) JP3732096B2 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7626715B2 (en) * 2003-05-02 2009-12-01 Infoprint Solutions Company, Llc Joined front end and back end document processing
JP2005025488A (en) * 2003-07-02 2005-01-27 Hitachi Ltd System for certification of written information on check
JP7400386B2 (en) * 2019-11-20 2023-12-19 富士フイルムビジネスイノベーション株式会社 Information processing device and information processing program
JP2021086366A (en) * 2019-11-27 2021-06-03 富士フイルムビジネスイノベーション株式会社 Information processing apparatus and information processing program
JP7452120B2 (en) 2020-03-12 2024-03-19 富士通株式会社 Image processing method, image processing program, and image processing device

Also Published As

Publication number Publication date
JP2002245461A (en) 2002-08-30

Similar Documents

Publication Publication Date Title
CN110598699B (en) Anti-counterfeiting bill authenticity distinguishing system and method based on multispectral image
CN101491074B (en) Document authentication using template matching with fast masked normalized cross-correlation
US8190901B2 (en) Layered security in digital watermarking
US20060282383A1 (en) Payment methods and systems enhanced with image comparison for detecting fraudulent checks
CN108734235A (en) A kind of personal identification method and system for electronic prescription
CN107437293A (en) A kind of bill anti-counterfeit discrimination method based on bill global characteristics
CN108596177A (en) A kind of the area of computer aided discriminating method and system of motor vehicle VIN code rubbing films
CN106599923B (en) Method and device for detecting seal anti-counterfeiting features
JP3732096B2 (en) Securities imprint verification method
Gautam Indian currency detection using image recognition technique
Abdulqader et al. Detection of tamper forgery image in security digital mage
Lamsal et al. Counterfeit paper banknote identification based on color and texture
CN112215225A (en) KYC certificate verification method based on computer vision technology
JP2003109007A (en) Device, method and program for classifying slip form and image collating device
Thaiparnit et al. Tracking vehicles system based on license plate recognition
Su et al. Automatic seal imprint verification systems using edge difference
Alkawaz et al. An overview of advanced optical flow techniques for copy move video forgery detection
JP2004104530A (en) Tickets issuing apparatus, tickets issuing method and user confirmation device, user confirmation method
Rehman et al. Machine learning based image forgery detection using natural scene statistics
JP4486351B2 (en) Seal verification device, seal verification method and seal verification program
JP5190312B2 (en) Seal verification device
JP6039944B2 (en) Form type discriminating apparatus and form type discriminating method
JP2898970B1 (en) 3D seal registration / collation device
JP2002049763A (en) Method and device for automatically collating note and check
Rarani et al. Indian Currency Note Recognition System using YOLO v3 Methodology

Legal Events

Date Code Title Description
A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20050221

A711 Notification of change in applicant

Free format text: JAPANESE INTERMEDIATE CODE: A712

Effective date: 20050223

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20050301

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20050426

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20051004

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20051011

R150 Certificate of patent or registration of utility model

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20091021

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20091021

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20101021

Year of fee payment: 5

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20111021

Year of fee payment: 6

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20121021

Year of fee payment: 7

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20121021

Year of fee payment: 7

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20131021

Year of fee payment: 8

LAPS Cancellation because of no payment of annual fees