WO2018111080A1 - Recognising signatures on cheques in order to verify authenticity - Google Patents
Recognising signatures on cheques in order to verify authenticity Download PDFInfo
- Publication number
- WO2018111080A1 WO2018111080A1 PCT/MX2016/000162 MX2016000162W WO2018111080A1 WO 2018111080 A1 WO2018111080 A1 WO 2018111080A1 MX 2016000162 W MX2016000162 W MX 2016000162W WO 2018111080 A1 WO2018111080 A1 WO 2018111080A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- signature
- image
- stroke
- strokes
- algorithm
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
Definitions
- the present invention has its preponderant field of application in the field of banking security, more specifically in the verification of authenticity of signatures in official documents for the withdrawal of money from accounts, such as checks.
- Patent No. US20060002593 details in its invention an information processing apparatus that detects the sampling rate of a coordinate input device (digitizer) and normalizes the writing data that is entered from the base coordinate input device at the sampling rate detected. Standardized writing data is also used for signature verification or for the recognition of handwritten characters.
- Patent No. US20060262352 describes a mixed media reality system (MMR) and associated techniques.
- MMR mixed media reality system
- the MMR system provides mechanisms to form a mixed media document that includes media of at least two types (printed paper and digital content).
- the MMR system provides a match-processing of images in a document to compare with data in a database.
- Patent No. US20060050962 claims a system, process and software for recognizing manuscript characters, where character data is obtained that includes information indicative of at least one manuscript character. Character data includes a set of segmentation points for the handwritten character. A score for each particular character of a previously stored character set can then be provided, based on a comparison between the character data and the particular character previously stored.
- US7869634 a signature authentication system of a user electronically introduced into the system by a mouse or other manual input device is provided that provides an output indicative of its location when manipulated by the user.
- the system serves to extract angle and distance data that relate different parts of the user's signature entered into the system and to store corresponding angle and distance data relative to a reference signature previously entered into the system during a training procedure.
- the extracted data is then compared by the system with the reference data stored by the system and, when appropriate, an indicative output of an appropriate match between the entered signature and the reference signature is provided depending on the result of the comparison.
- This system provides a dynamic online biometric verification system that can be customized for multiple Internet-based applications that require secure authentication.
- the system does not require specialized equipment at the point of use, which allows access from any computer capable of the Internet with a mouse and browser compatible with Java, for example.
- the invention US20100303356 provides a method for an Optical Character Recognition (OCR) system that provides recognition of characters that are partially hidden by outputs due to, for example, a stamp print, handwritten signatures, etc.
- OCR Optical Character Recognition
- the method establishes a set of template images recognized from the image of the text that is being processed by the OCR system, in which the effect of the crossed out section is modeled on the template images before comparing these images with the image of a visually impaired crossed out character.
- the modeled template image that has the highest similarity with the crossed out character with visual impairments is the correct identification for the instance of the visually impaired character.
- the invention CN 103593673 is based on the online handwritten signature authentication method for dynamic threshold, pertaining to the field of information security, the method of the present invention is used to coordinate the online information model of signature, pressure, Integrated speed and consider several factors to improve the accuracy of a firm.
- the method of the present invention uses a signature segment discrimination policy, and in accordance with the signature and writing habits, two strategy options are presented for the automatic segmentation of the segment method that can improve the signing process.
- the threshold signature method of the present invention is determined in the test procedure to help reflect the bias characteristics of each signature, taking into account the stability characteristics of each person's signature.
- U.S. Pat. No. 4710822 describes a method for image processing in which a figure is divided into a plurality of blocks.
- Each block comprises a variety of image elements that are classified into a first group consisting of image elements of densities not less than a reference density and a second group consisting of image elements of densities lower than the reference density.
- a representative density of image elements of the first group and the second group in each block is obtained.
- An image discrimination is performed according to the representative densities and then a threshold value determination is made according to the representative densities and the result of the image discrimination.
- Image discrimination and determination of threshold values are carried out using histograms made from the representative density of image elements of the first group in each block and the representative density of image elements of the second group in each block.
- the image information is then converted into binary serials according to the threshold value.
- a character recognition identifier is developed based on the function and the level of confidence that are determined for an unknown symbol. If the confidence level is within a range intermediate, the feature-based identification is confirmed by matching the unknown character with a reference template corresponding to the feature-based identification. If the confidence level is below the intermediate range, template matching character recognition is replaced instead of feature-based identification. If template match recognition identifies more than one symbol, corresponding templates from a second set of templates that have thicker character strokes are used to resolve ambiguity.
- Patent US5859929A mentions an effective system and method for reliably identifying guidelines, governed lines and the like, in text images, to distinguish those portions of lines that touch or intersect character strokes in the image.
- the system facilitates the removal of guide segments between character strokes without deleting character strokes.
- the system works effectively on both machine printed text and handmade text.
- a text image has the most separate characters for more efficient subsequent OCR processing.
- a binary method used in an OCR system to determine the pixels of a text is presented, checking for each pixel the difference between its value and the values of a plurality of pixels located at a predetermined distance thereof is greater than a relative threshold corresponding to the difference in intensities between the text and the background of the image.
- the image is sub-sampled at a corresponding rate of at least two pixels to detect text cores and then binar ⁇ zar the image pixels only in mosaics of wide sides of the stroke containing text cores, using in each frame an absolute threshold estimated in said picture.
- the determination of pixels in a text includes, for each pixel analyzed, the verification that any of the differences between the value of the analyzed pixel and the value of the two pixels located at each intersection of a circle with each of the row line , column line and both lines at the angle of 45 degrees, is greater than the relative threshold at which said circle is centered on the position of the analyzed pixel and has a radius equal to the width of the stroke.
- US8320674B2 shows a procedure to recognize a text from an image or a video, accurately locating the position of the text. If the localized text is low resolution it can be extracted, improved and binar ⁇ zar. Finally, OCR technology can be applied to binar ⁇ zado text for recognition.
- a method of interpreting visual information with alphanumeric characters is presented in WO2011080361 A1.
- the method begins with a digital image, converted to grayscale, segmented so that a black and white image formed by a plurality of particles is obtained; filtering said plurality of particles removes particles that do not contain information associated with a character of the original image; a dilated image is obtained to select segments, trying that each segment corresponds to a character of the original image. Finally, the information of these segments is interpreted by means of a character recognition algorithm.
- FIG 1 shows the scheme of the problem.
- Figure 2 shows important characteristics in a signature.
- Figure 3 shows the graph of the density per stroke unit.
- Figure 4 shows the process flow chart. With respect to the figures listed, the first one presents the general scheme of the problem: in a banking legal document, such as a check, a signature is stamped and it is desired to verify the authenticity of the rubric identifying significant characteristics, such as the number of lines which make it up, the beginning and end of each of them and the curvature in the sections that are not straight, as shown in figure 2.
- Each signature is made up of strokes and each stroke of stroke units of 1 mm in length
- Figure 3 shows a graph for recording the number of pixels in each of these units. The density of pixels per stroke unit allows equivalence to be made with respect to the stroke velocity, if the density is constant then it is interpreted as a constant velocity. If changes in density are observed in the graph, then changes in the signature stroke speed are identified.
- Figure 4 shows the process for verifying the authenticity of a signature, considering a first step where the signature is characterized, followed by the image pre-processing method to finally verify the authenticity.
Abstract
The verification of the authenticity of a signature captured on an official bank document is an important activity given that the chance of fraud is high. The invention relates to a method for characterising signatures and confirming their authenticity.
Description
RECONOCIMIENTO DE FIRMAS EN CHEQUES PARA VERIFICAR RECOGNITION OF SIGNATURES IN CHECKS TO VERIFY
AUTENTICIDAD CAMPO TÉCNICO DE LA INVENCIÓN AUTHENTICITY TECHNICAL FIELD OF THE INVENTION
La presente invención tiene su campo de aplicación preponderante en el ámbito de la seguridad bancaria, más específicamente en la verificación de autenticidad de firmas en documentos oficiales para el retiro de dinero de cuentas, como los cheques. The present invention has its preponderant field of application in the field of banking security, more specifically in the verification of authenticity of signatures in official documents for the withdrawal of money from accounts, such as checks.
ANTECEDENTES DE LA INVENCIÓN BACKGROUND OF THE INVENTION
La verificación de la autenticidad de una firma es una preocupación constante en diferentes sectores de las instituciones financieras, en especial las referidas a los cheques de instituciones bancarías. Los avances tecnológicos han propiciado el desarrollo de procedimientos para la corroboración de la autenticidad de rúbricas, a continuación, se presenta una relación de patentes que muestran los esfuerzos por lograr resolver este problema. The verification of the authenticity of a firm is a constant concern in different sectors of financial institutions, especially those referring to checks of banking institutions. Technological advances have led to the development of procedures for the corroboration of the authenticity of rubrics, then a list of patents that show the efforts to solve this problem is presented.
La patente No. US20060002593, detalla en su invención un aparato de procesamiento de información que detecta la velocidad de muestreo de un dispositivo de entrada (digitalizador) de coordenadas y normaliza los datos de escritura que se introducen desde el dispositivo de entrada de coordenadas en base a la velocidad de muestreo detectada. Los datos estandarizados de escritura se utilizan además para la verificación de firma o para el reconocimiento de caracteres manuscritos. Patent No. US20060002593, details in its invention an information processing apparatus that detects the sampling rate of a coordinate input device (digitizer) and normalizes the writing data that is entered from the base coordinate input device at the sampling rate detected. Standardized writing data is also used for signature verification or for the recognition of handwritten characters.
En la patente No. US20060262352 Se describe un sistema de realidad de medios mixtos (MMR) y técnicas asociadas. El sistema MMR proporciona mecanismos para formar un documento de medios mixtos que incluye medios de al menos dos tipos (papel impreso y contenido digital). El sistema MMR proporciona un procesamiento de coincidencia (Matching) de imágenes de un documento para comparar con datos de una base de datos. Patent No. US20060262352 describes a mixed media reality system (MMR) and associated techniques. The MMR system provides mechanisms to form a mixed media document that includes media of at least two types (printed paper and digital content). The MMR system provides a match-processing of images in a document to compare with data in a database.
La patente No. US20060050962 reclama un sistema, proceso y software para reconocer caracteres manuscritos, en donde se obtienen datos de caracteres que incluyen información indicativa de al menos un carácter manuscrito. Los datos de caracteres incluyen un conjunto de puntos de segmentación para el
carácter manuscrito. A continuación, se puede proporcionar una puntuación para cada carácter particular de un conjunto de caracteres almacenados previamente, basándose en una comparación entre los datos del carácter y el carácter particular previamente almacenado. Patent No. US20060050962 claims a system, process and software for recognizing manuscript characters, where character data is obtained that includes information indicative of at least one manuscript character. Character data includes a set of segmentation points for the handwritten character. A score for each particular character of a previously stored character set can then be provided, based on a comparison between the character data and the particular character previously stored.
En la invención US7869634 se proporciona un sistema de autenticación de la firma de un usuario introducida electrónicamente en el sistema por un ratón u otro dispositivo manual de entrada que proporciona una salida indicativa de su ubicación cuando es manipulada por el usuario. El sistema sirve para extraer datos de ángulo y distancia que relacionan diferentes partes de la firma del usuario introducidas en el sistema y para almacenar datos de ángulo y distancia correspondientes relativos a una firma de referencia introducida previamente en el sistema durante un procedimiento de entrenamiento. Los datos extraídos son luego comparados por el sistema con los datos de referencia almacenados por el sistema y, cuando es apropiado, se proporciona una salida indicativa de una coincidencia apropiada entre la firma introducida y la firma de referencia dependiendo del resultado de la comparación. Dicho sistema proporciona un sistema dinámico de verificación biométrica en linea que se puede personalizar para múltiples aplicaciones basadas en Internet que requieren autenticación segura. El sistema no requiere equipo especializado en el punto de uso, lo que permite el acceso desde cualquier computadora capaz de Internet con un ratón y navegador compatible con Java, por ejemplo. In the invention US7869634 a signature authentication system of a user electronically introduced into the system by a mouse or other manual input device is provided that provides an output indicative of its location when manipulated by the user. The system serves to extract angle and distance data that relate different parts of the user's signature entered into the system and to store corresponding angle and distance data relative to a reference signature previously entered into the system during a training procedure. The extracted data is then compared by the system with the reference data stored by the system and, when appropriate, an indicative output of an appropriate match between the entered signature and the reference signature is provided depending on the result of the comparison. This system provides a dynamic online biometric verification system that can be customized for multiple Internet-based applications that require secure authentication. The system does not require specialized equipment at the point of use, which allows access from any computer capable of the Internet with a mouse and browser compatible with Java, for example.
La invención US20100303356 proporciona un método para un sistema de Reconocimiento óptico de Caracteres (OCR) que proporciona reconocimiento de caracteres que están parcialmente ocultos por salidas debido a, por ejemplo, una impresión de un sello, firmas manuscritas, etc. El método establece un conjunto de imágenes de plantilla reconocidos a partir de la imagen del texto que está siendo procesado por el sistema OCR, en el que el efecto de la sección tachada es modelado en las imágenes de plantilla antes de comparar estas imágenes con la imagen de un personaje tachado visualmente deteriorado. La imagen de plantilla modelada que tiene la similitud más alta con el personaje tachado con impedimentos visuales es la identificación correcta para la instancia de personaje con discapacidad visual.
La invención CN 103593673 se basa en el método de autenticación de firma manuscrita en línea para umbral dinámico, perteneciente al campo de segundad de información, el método de la presente invención se utiliza para para coordinar el modelo de información en linea de firma, presión, velocidad integrada y considerar varios factores para mejorar la exactitud de una firma. El método de la presente invención utiliza una política de discriminación de segmentos de firma, y de acuerdo con la firma y hábitos de escritura, se presentan dos opciones de estrategias para la segmentación automática del método de segmento que puede mejorar el proceso de firma. El método de firma de umbral de la presente invención se determina en el procedimiento de prueba para ayuda a reflejar las características de sesgo de cada firma, teniendo en cuenta las características de estabilidad de la firma de cada persona. The invention US20100303356 provides a method for an Optical Character Recognition (OCR) system that provides recognition of characters that are partially hidden by outputs due to, for example, a stamp print, handwritten signatures, etc. The method establishes a set of template images recognized from the image of the text that is being processed by the OCR system, in which the effect of the crossed out section is modeled on the template images before comparing these images with the image of a visually impaired crossed out character. The modeled template image that has the highest similarity with the crossed out character with visual impairments is the correct identification for the instance of the visually impaired character. The invention CN 103593673 is based on the online handwritten signature authentication method for dynamic threshold, pertaining to the field of information security, the method of the present invention is used to coordinate the online information model of signature, pressure, Integrated speed and consider several factors to improve the accuracy of a firm. The method of the present invention uses a signature segment discrimination policy, and in accordance with the signature and writing habits, two strategy options are presented for the automatic segmentation of the segment method that can improve the signing process. The threshold signature method of the present invention is determined in the test procedure to help reflect the bias characteristics of each signature, taking into account the stability characteristics of each person's signature.
En la invención U.S. Pat. No. 4710822 se describe un método para el procesamiento de imágenes en el que una figura se divide en una pluralidad de bloques. Cada bloque comprende una diversidad de elementos de la imagen que se clasifican en un primer grupo consistente en elementos de imagen de densidades no inferiores a una densidad de referencia y un segundo grupo consistente en elementos de imagen de densidades inferiores a la densidad de referencia. Se obtiene una densidad representativa de elementos de imagen del primer grupo y del segundo grupo en cada bloque. Una discriminación de imagen se efectúa de acuerdo con las densidades representativas y, a continuación, se efectúa una determinación de un valor umbral de acuerdo con las densidades representativas y el resultado de la discriminación de imagen. La discriminación de imagen y la determinación de valores de umbral se llevan a cabo usando histogramas hechos a partir de la densidad representativa de elementos de imagen del primer grupo en cada bloque y la densidad representativa de elementos de imagen del segundo grupo en cada bloque. La información de la imagen se convierte entonces en seriales binarias de acuerdo con el valor de umbral. In the invention U.S. Pat. No. 4710822 describes a method for image processing in which a figure is divided into a plurality of blocks. Each block comprises a variety of image elements that are classified into a first group consisting of image elements of densities not less than a reference density and a second group consisting of image elements of densities lower than the reference density. A representative density of image elements of the first group and the second group in each block is obtained. An image discrimination is performed according to the representative densities and then a threshold value determination is made according to the representative densities and the result of the image discrimination. Image discrimination and determination of threshold values are carried out using histograms made from the representative density of image elements of the first group in each block and the representative density of image elements of the second group in each block. The image information is then converted into binary serials according to the threshold value.
En la patente US 5077805A se desarrolla un identificador de reconocimiento de caracteres basado en la función y el nivel de confianza que se determinan para un símbolo desconocido. Si el nivel de confianza está dentro de un rango
intermedio, la identificación basada en características se confirma haciendo coincidir el carácter desconocido con una plantilla de referencia correspondiente a la identificación basada en características. Si el nivel de confianza está por debajo del rango intermedio, el reconocimiento de caracteres de coincidencia de plantillas se sustituye en lugar de la identificación basada en características. Si el reconocimiento de coincidencia de plantilla identifica más de un símbolo, se emplean plantillas correspondientes de un segundo conjunto de plantillas que tienen trazos de caracteres más gruesos para resolver la ambigüedad. In US patent 5077805A a character recognition identifier is developed based on the function and the level of confidence that are determined for an unknown symbol. If the confidence level is within a range intermediate, the feature-based identification is confirmed by matching the unknown character with a reference template corresponding to the feature-based identification. If the confidence level is below the intermediate range, template matching character recognition is replaced instead of feature-based identification. If template match recognition identifies more than one symbol, corresponding templates from a second set of templates that have thicker character strokes are used to resolve ambiguity.
En la patente US5859929A se menciona un sistema y un método eficaces para la identificación de manera fiable directrices, líneas gobernadas y similares, en imágenes de texto, para distinguir aquellas porciones de líneas que tocan o intersecan trazos de carácter en la imagen. El sistema facilita la eliminación de segmentos de guía entre trazos de carácter sin borrar trazos del carácter. El sistema funciona eficazmente tanto en el texto impreso en máquina como en el texto hecho a mano. Una imagen de texto tiene la mayoría de los caracteres separados para un procesamiento OCR posterior más eficaz. Patent US5859929A mentions an effective system and method for reliably identifying guidelines, governed lines and the like, in text images, to distinguish those portions of lines that touch or intersect character strokes in the image. The system facilitates the removal of guide segments between character strokes without deleting character strokes. The system works effectively on both machine printed text and handmade text. A text image has the most separate characters for more efficient subsequent OCR processing.
En la patente US6438265B1, se presenta un método binario utilizado en un sistema OCR para determinar los píxeles de un texto, comprobando para cada píxel la diferencia entre su valor y los valores de una pluralidad de píxeles situados a una distancia predeterminada de la misma sea mayor que un umbral relativo correspondiente a la diferencia de intensidades entre el texto y el fondo de la imagen. Se submuestrea la imagen a una velocidad correspondiente al menos de dos píxeles para detectar núcleos de texto y después binarízar los píxeles de imagen solamente en mosaicos de vanos lados de ancho del trazo que contengan núcleos de texto, utilizando en cada cuadro un umbral absoluto estimado en dicho cuadro. La determinación de píxeles en un texto incluye, para cada pixel analizado, la comprobación de que cualquiera de las diferencias entre el valor del píxel analizado y el valor de los dos píxeles situados en cada intersección de un círculo con cada uno de la línea de fila, línea de columna y ambas líneas en el ángulo de 45 grados, es mayor que el umbral relativo en el que dicho círculo está centrado en la posición del pixel analizado y tiene un radio igual al ancho del trazo.
En la patente US8320674B2 se muestra un procedimiento para reconocer un texto a partir de una imagen o un vídeo, localizando con precisión la posición del texto. Si el texto localizado es de baja resolución se puede extraer, mejorar y binarízar. Finalmente, la tecnología OCR se puede aplicar al texto binarízado para su reconocimiento. In US6438265B1, a binary method used in an OCR system to determine the pixels of a text is presented, checking for each pixel the difference between its value and the values of a plurality of pixels located at a predetermined distance thereof is greater than a relative threshold corresponding to the difference in intensities between the text and the background of the image. The image is sub-sampled at a corresponding rate of at least two pixels to detect text cores and then binarízar the image pixels only in mosaics of wide sides of the stroke containing text cores, using in each frame an absolute threshold estimated in said picture. The determination of pixels in a text includes, for each pixel analyzed, the verification that any of the differences between the value of the analyzed pixel and the value of the two pixels located at each intersection of a circle with each of the row line , column line and both lines at the angle of 45 degrees, is greater than the relative threshold at which said circle is centered on the position of the analyzed pixel and has a radius equal to the width of the stroke. US8320674B2 shows a procedure to recognize a text from an image or a video, accurately locating the position of the text. If the localized text is low resolution it can be extracted, improved and binarízar. Finally, OCR technology can be applied to binarízado text for recognition.
En la patente US4594732A se describe un método y un aparato para determinar el paso de un carácter de un grupo alineado de imágenes sobre la superficie de un papel, donde el grupo contiene varios caracteres que se tocan o se fusionan entre sí. Los bloques de letras separables se extraen del grupo alineado de caracteres y el tamaño y ubicación de cada uno se detecta y almacena. Basándose en esta información, se determina un intervalo permisible para una anchura de bloque de una letra y se determina la anchura de bloques de letras que ocurre con mayor frecuencia en ese intervalo permisible. Basándose en la anchura del bloque de letras que ocurre con mayor frecuencia. Se determina un intervalo efectivo para determinar el paso de la letra y se emplea un método numérico para estimar el tono de la letra. In US4594732A a method and an apparatus for determining the passage of a character of an aligned group of images on the surface of a paper are described, where the group contains several characters that touch or merge with each other. Separable letter blocks are extracted from the aligned group of characters and the size and location of each is detected and stored. Based on this information, an allowable range for a block width of one letter is determined and the width of letter blocks that occurs most frequently in that allowable range is determined. Based on the width of the block of letters that occurs most frequently. An effective interval is determined to determine the pitch of the letter and a numerical method is used to estimate the tone of the letter.
En la patente WO2011080361 A1 se presenta un método de interpretación de información visual con caracteres alfanuméricos. El método inicia con una imagen digital, convertida a escala de grises se segmenta de forma que se obtiene una imagen en blanco y negro formada por una pluralidad de partículas; al filtrar dicha pluralidad de partículas se eliminan partículas que no contienen información asociada a un carácter de la imagen original; se obtiene una imagen dilatada para seleccionar segmentos, tratando de que cada segmento corresponda a un carácter de la imagen original. Finalmente se interpreta la información de dichos segmentos mediante un algoritmo de reconocimiento de caracteres. A method of interpreting visual information with alphanumeric characters is presented in WO2011080361 A1. The method begins with a digital image, converted to grayscale, segmented so that a black and white image formed by a plurality of particles is obtained; filtering said plurality of particles removes particles that do not contain information associated with a character of the original image; a dilated image is obtained to select segments, trying that each segment corresponds to a character of the original image. Finally, the information of these segments is interpreted by means of a character recognition algorithm.
DESCRIPCIÓN DETALLADA DE LA INVENCIÓN DETAILED DESCRIPTION OF THE INVENTION
Los detalles característicos de la presente invención, se muestran claramente en la siguiente descripción y en las figuras que se acompañan, las cuales se
mencionan a manera de ejemplo, por lo que no deben considerarse como una limitante para dicha invención. The characteristic details of the present invention are clearly shown in the following description and in the accompanying figures, which are they are mentioned by way of example, so they should not be considered as a limitation for said invention.
Breve descripción de las figuras: Brief description of the figures:
La figura 1 muestra el esquema del problema. Figure 1 shows the scheme of the problem.
La figura 2 muestra características importantes en una firma. Figure 2 shows important characteristics in a signature.
La figura 3 muestra la gráfica de la densidad por unidad de trazo. Figure 3 shows the graph of the density per stroke unit.
La figura 4 muestra el diagrama de flujo del proceso. Con respecto a las figuras enlistadas, en la primera se presenta el esquema general del problema: en un documento legal bancarío, como un cheque, se estampa una firma y se desea verificar la autenticidad de la rúbrica identificando características significativas, como el número de trazos que la componen, el inicio y final de cada uno de ellos y la curvatura en las secciones que no son rectas, como se observa en la figura 2. Cada firma se compone de trazos y cada trazo de unidades de trazo de 1 mm de longitud, en la figura 3 se muestra una gráfica para el registro del número de pixeles en cada una de estas unidades. La densidad de pixeles por unidad de trazo permite realizar la equivalencia respecto a la velocidad de trazo, si la densidad es constante entonces se interpreta como una velocidad constante. Si en la gráfica se observan cambios en la densidad, entonces se identifican cambios en la velocidad de trazo de la firma. En la figura 4 se presentan el proceso para la verificación de la autenticidad de una firma, considerando un primer paso donde se caracteriza la firma, seguido del método de pre-procesamiento de imágenes para finalmente comprobar la autenticidad.
Figure 4 shows the process flow chart. With respect to the figures listed, the first one presents the general scheme of the problem: in a banking legal document, such as a check, a signature is stamped and it is desired to verify the authenticity of the rubric identifying significant characteristics, such as the number of lines which make it up, the beginning and end of each of them and the curvature in the sections that are not straight, as shown in figure 2. Each signature is made up of strokes and each stroke of stroke units of 1 mm in length , Figure 3 shows a graph for recording the number of pixels in each of these units. The density of pixels per stroke unit allows equivalence to be made with respect to the stroke velocity, if the density is constant then it is interpreted as a constant velocity. If changes in density are observed in the graph, then changes in the signature stroke speed are identified. Figure 4 shows the process for verifying the authenticity of a signature, considering a first step where the signature is characterized, followed by the image pre-processing method to finally verify the authenticity.
Claims
1. Un método implementado mediante un dispositivo electrónico en una institución financiera con el fin de verificar la autenticidad de una firma plasmada en un cheque, caracterizado por: 1. A method implemented by an electronic device in a financial institution in order to verify the authenticity of a signature embodied in a check, characterized by:
• Un dispositivo electrónico para la captura de la imagen; • An electronic device for image capture;
• Un método para análisis e identificación de trazos; • A method for analysis and identification of strokes;
• Un método para caracterización de trazos; • A method for characterizing strokes;
• Un método de pre-procesamiento de imágenes; • An image pre-processing method;
2. El sistema de conformidad con la reivindicación No. 1 , donde un dispositivo electrónico es utilizado para la captura de la imagen de un cheque para su análisis; 2. The system according to claim No. 1, wherein an electronic device is used to capture the image of a check for analysis;
3. El sistema de conformidad con la reivindicación No. 2, donde el dispositivo de captura tiene la capacidad de disminuir el reflejo directo de la tinta en el papel para un mejor análisis de los trazos de la firma; 3. The system according to claim No. 2, wherein the capture device has the ability to decrease the direct reflection of the ink on the paper for a better analysis of the signature strokes;
4. El sistema de conformidad con la reivindicación No. 1 , donde se registra la firma de un usuario en diferentes tipos de papel y artículos de escritura para considerar un número suficientemente grande de combinaciones posibles de escenarios donde, en un momento dado, las condiciones pudieran modificar los trazos de una firma; 4. The system according to claim No. 1, wherein a user's signature is registered on different types of paper and writing articles to consider a sufficiently large number of possible combinations of scenarios where, at any given time, the conditions they could modify the strokes of a signature;
5. El sistema de conformidad con la reivindicación No. 4, donde se identifica y mide el ángulo de inclinación de la firma; 5. The system according to claim No. 4, wherein the inclination angle of the signature is identified and measured;
6. El sistema de conformidad con la reivindicación No. 5, donde un algoritmo analiza las firmas recabadas para la identificación y caracterización de trazos; 6. The system according to claim No. 5, wherein an algorithm analyzes the signatures collected for the identification and characterization of strokes;
7. El sistema de conformidad con la reivindicación No. 6, donde un algoritmo identifica la forma de un trazo como circular, elíptica o rectangular; 7. The system according to claim No. 6, wherein an algorithm identifies the shape of a stroke as circular, elliptical or rectangular;
8. El sistema de conformidad con la reivindicación No. 7, donde se define el trazo de una firma como un segmento de línea continua, con principio y fin; 8. The system according to claim No. 7, wherein the signature of a signature is defined as a continuous line segment, with beginning and end;
9. El sistema de conformidad con la reivindicación No. 8, donde un algoritmo identifica curvaturas y dimensiones relativas a cada trazo identificado;
9. The system according to claim No. 8, wherein an algorithm identifies curvatures and dimensions relative to each identified stroke;
10. El sistema de conformidad con la reivindicación No. 9, donde un algoritmo detecta e identifica los puntos de inflexión de cada trazo; 10. The system according to claim No. 9, wherein an algorithm detects and identifies the inflection points of each stroke;
11. El sistema de conformidad con la reivindicación No. 10, donde se define una unidad de trazo o trazo unitario como el segmento de línea con una longitud igual a 1mm; 11. The system according to claim No. 10, wherein a unit or stroke unit is defined as the line segment with a length equal to 1mm;
12. El sistema de conformidad con la reivindicación No. 11, donde un algoritmo analiza la densidad de pixeles por unidad de trazo, es decir, contabiliza el número de pixeles por trazo unitario; 12. The system according to claim No. 11, wherein an algorithm analyzes the density of pixels per stroke unit, that is, counts the number of pixels per unit stroke;
13. El sistema de conformidad con la reivindicación No. 12, donde un algoritmo detecta el cambio en la densidad normalizada de pixeles por unidad de trazo para la cuantificación de la velocidad de trazo; 13. The system according to claim No. 12, wherein an algorithm detects the change in the standard density of pixels per stroke unit for quantification of the stroke rate;
14. El sistema de conformidad con la reivindicación No. 13, donde el número de pixeles por unidad de trazo se representa en una gráfica de dispersión para representar los cambios en la velocidad de trazo; 14. The system according to claim No. 13, wherein the number of pixels per stroke unit is represented in a scatter plot to represent changes in stroke speed;
15. El sistema de conformidad con la reivindicación No. 14, donde al identificar las características de los trazos en las firmas registradas se determina un patrón de referencia: 15. The system according to claim No. 14, wherein identifying the characteristics of the strokes in the registered signatures determines a reference standard:
16. El sistema de conformidad con la reivindicación No. 1, donde el sistema de pre-procesamiento se utiliza para aislar la firma en la imagen del cheque; 16. The system according to claim No. 1, wherein the pre-processing system is used to isolate the signature in the image of the check;
17. El sistema de conformidad con la reivindicación No. 16, donde un algoritmo se utiliza para dimensionar y alinear la imagen del cheque: 17. The system according to claim No. 16, wherein an algorithm is used to size and align the image of the check:
18. El sistema de conformidad con la reivindicación No. 17, donde el dispositivo de captura identifica y autentifica la clave del banco emisor;18. The system according to claim No. 17, wherein the capture device identifies and authenticates the issuing bank's password;
19. El sistema de conformidad con la reivindicación No. 18, donde un algoritmo identifica y elimina la imagen del fondo del cheque de la firma para su eliminación; 19. The system according to claim No. 18, wherein an algorithm identifies and removes the background image of the signature check for disposal;
20. El sistema de conformidad con la reivindicación No. 19, donde un algoritmo identifica y elimina la línea de referencia debajo de la firma; 20. The system according to claim No. 19, wherein an algorithm identifies and removes the reference line below the signature;
21. El sistema de conformidad con la reivindicación No. 20, donde se extrae la imagen de la firma;
21. The system according to claim No. 20, wherein the signature image is extracted;
22. El sistema de conformidad con la reivindicación No. 21, donde el método de análisis utiliza la estandarización de la imagen de la firma para la comparación con la firma de referencia; 22. The system according to claim No. 21, wherein the analysis method uses the standardization of the signature image for comparison with the reference signature;
23. El sistema de conformidad con la reivindicación No. 22, donde la firma extraída del cheque se somete a pruebas de comparación para la identificación de los trazos previamente caracterizados en la firma del usuario; 23. The system according to claim No. 22, wherein the signature extracted from the check is subjected to comparison tests for the identification of the strokes previously characterized in the user's signature;
24. El sistema de conformidad con la reivindicación No. 23, donde un algoritmo calcula el porcentaje de coincidencia entre los trazos de la firma en el cheque con la de referencia; 24. The system according to claim No. 23, wherein an algorithm calculates the percentage of coincidence between the signature strokes on the check with the reference one;
25. El sistema de conformidad con la reivindicación No. 1 , donde la autenticidad de una firma se obtiene al contabilizar, al menos, el 98% de las características identificadas;
25. The system in accordance with claim No. 1, wherein the authenticity of a firm is obtained by accounting for at least 98% of the characteristics identified;
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/MX2016/000162 WO2018111080A1 (en) | 2016-12-16 | 2016-12-16 | Recognising signatures on cheques in order to verify authenticity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/MX2016/000162 WO2018111080A1 (en) | 2016-12-16 | 2016-12-16 | Recognising signatures on cheques in order to verify authenticity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2018111080A1 true WO2018111080A1 (en) | 2018-06-21 |
Family
ID=62559561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/MX2016/000162 WO2018111080A1 (en) | 2016-12-16 | 2016-12-16 | Recognising signatures on cheques in order to verify authenticity |
Country Status (1)
| Country | Link |
|---|---|
| WO (1) | WO2018111080A1 (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2684469A1 (en) * | 1991-11-29 | 1993-06-04 | Thomson Csf | Automatic process for recognising handwritten signatures by image analysis and device intended for its implementation |
| US20020073029A1 (en) * | 2000-12-12 | 2002-06-13 | Telefonaktiebolaget Lm Ericsson (Publ) | System and method of authorizing an electronic commerce transaction |
| US20160140540A1 (en) * | 2014-11-03 | 2016-05-19 | Square, Inc. | Background ocr during card data entry |
-
2016
- 2016-12-16 WO PCT/MX2016/000162 patent/WO2018111080A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2684469A1 (en) * | 1991-11-29 | 1993-06-04 | Thomson Csf | Automatic process for recognising handwritten signatures by image analysis and device intended for its implementation |
| US20020073029A1 (en) * | 2000-12-12 | 2002-06-13 | Telefonaktiebolaget Lm Ericsson (Publ) | System and method of authorizing an electronic commerce transaction |
| US20160140540A1 (en) * | 2014-11-03 | 2016-05-19 | Square, Inc. | Background ocr during card data entry |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778586A (en) | Offline handwriting signature verification method and system | |
| US7542593B1 (en) | Offline signature verification using high pressure regions | |
| CN106874968B (en) | Second-generation identity card authenticity identification method | |
| US20180033020A1 (en) | System and apparatus for detecting forgery features on identification documents | |
| Abramova et al. | Detecting copy–move forgeries in scanned text documents | |
| Bulatov et al. | Towards a unified framework for identity documents analysis and recognition | |
| Randhawa et al. | Off-line signature verification with concentric squares and slope based features using support vector machines | |
| Hao et al. | Printer identification using page geometric distortion on text lines | |
| Roy et al. | Offline signature verification using grid based and centroid based approach | |
| CN116612538A (en) | Online confirmation method of electronic contract content | |
| Gunjal et al. | Offline signature verification using feature point extraction | |
| WO2018111080A1 (en) | Recognising signatures on cheques in order to verify authenticity | |
| Mahanta et al. | A study on handwritten signature | |
| Nadia et al. | Personal identification based on texture analysis of Arabic handwriting text | |
| Vishnu et al. | Principal component analysis on Indian currency recognition | |
| Ahmed et al. | Comparative analysis of global feature extraction methods for off-line signature recognition | |
| Yadav et al. | Comparative analysis of offline signature verification system | |
| Ravi et al. | Concatenation of spatial and transformation features for off-line signature identification | |
| Dewangan | Real Time Recognition of Handwritten Devnagari Signatures without Segmentation Using Artificial Neural Network | |
| Kore et al. | Writer verification using spatial domain features under different ink width conditions | |
| Jain et al. | A comparative study of various methods for offline signature verification | |
| Kulkarni et al. | Review on authentication mechanisms of digital signatures used for certification | |
| Bashir et al. | Techniques of detecting forgery in identity documents | |
| Bharadwaja | The analysis of online and offline signature verification techniques to counter forgery | |
| KR102181243B1 (en) | Electronic device for generating verification model used to verify a user's signature |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16924079 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 16924079 Country of ref document: EP Kind code of ref document: A1 |