Ir al contenido principal

Fuzzy shape-memory snakes for the automatic off-line signature verification problem

Publicado en Fuzzy Sets and Systems

This paper introduces an adapted fuzzy snake approach for efficiently solving some of the practical constraints in the off-line signature verification problem. Our method is called fuzzy shape-memory snakes due to its resemblance to shape-memory alloys, which are metals that in high-temperature conditions can remember their original shape. In our approach, the snake also “remembers” its geometry during its iterative adjustment to a test signature. Off-line signature verification aims to establish the degree of genuineness of a given test signature when compared to a reference signature. Due to the shape and size variability in signatures of the same subject, a system with tolerance to imprecision and also with some “memory” of its initial configured shape, would be very useful for this complex verification problem. To our knowledge, snakes and other active contour models have not been previosly applied to the offline signature verification problem. We consider that they could be properly adapted to be useful for this task. Consequently, we have developed a fuzzy snake framework for signature verification which takes into account some practical constraints of this problem when applied to bank checks. Over other signature verification systems, our approach has the advantage of using only one training signature per person. We introduce the fuzziness for the considered signature verification problem in a double direction. First, when iteratively adjusting a shape-memory snake (which is obtained from the training signature) to a considered test signature. Second, when measuring the similarity degree between the snake and the test signature after the adjustment (or verification task) using a Takagi–Sugeno fuzzy inference system, which is trained with three signature features (coincidence, distance and energy) provided by the adjustment. Some advantages of our approach are that: some involved parameters in the internal (shape) snake energy are now eliminated, and a more efficient and natural snake adjustment to the test signature is achieved. This paper also provides a study of the biometric classification errors when comparing our off-line signature verification approach to other non-fuzzy ones using the same signature database.

Entradas populares de este blog

Multiview 3D human pose estimation using improved least-squares and LSTM networks

Publicado en Neurocomputing En este artículo se presenta un método para estimar la pose del cuerpo humano en 3D a partir de múltiples vistas 2D utilizando aprendizaje profundo. El sistema está formado una sucesión de subsistemas. Primeramente, se obtienen las poses 2D usando una red de neuronas profunda que detecta los puntos claves de un esqueleto simplificado del cuerpo en las vistas disponibles. Luego, se recosntruyen las coordenadas 3D de cada punto utilizando una propuesta original, basada en optimización de mínimos cuadrados, que analiza la calidad de las anteriores detecciones 2D para decidir si aceptarlas o no. Una vez que se dispone de las poses 3D, se estima la posición completa del cuerpo, teniendo en cuenta la historia pasada para refinarla mediante una red LSTM. En la parte experimental, el artículo ofrece unos resultados competitivos cuando se compara con trabajos representativos de la literatura. In this paper we present a deep learning based method to estimate the

ASTRID - Análisis y Transcripción Semántica para Imágenes de Documentos Manuscritos

Ministerio de Ciencias, innovación y universidades Advances in the development of methods for automatically extracting and understanding the content of handwritten digitized documents will continue being an important need for our society. This project addresses three challenging computational problems related to automatic handwritten text processing of document images: (1) document layout extraction over unstructured documents, (2) continuous handwritten text recognition under unrestricted conditions and (3) offline verification of human signatures using advanced deep neural models, respectively. The proposed solutions to previous problems will be adapted to several applications presenting a socio-economic interest. In particular: the analysis and transcription of historical documents, and some demographic prediction problems based on use of handwriting (for example, recognizing the gender or handedness of a person). In this project, we will emphasize the application of developments

SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities

Publicado en Sensors    Este trabajo compara una red SSD con una red YOLO para el problema de detección del paneles de publicidad exterior en entornos urbanos reales.  La detección de paneles de publicidad en imágenes ofrece importantes aplicaciones tanto en el mundo real como en el virtual. Por ejemplo, aplicaciones como Google Street View podrían utilizarla para actualizar o personalizar la publicidad que aparece en las imagenes de las calles.  En nuestros experimentos, tanto las redes SSD como las redes YOLO han producido resultados interesantes ante diferentes tamaños de paneles, condiciones de iluminación, perspectivas de visión, oclusiones parciales, fondos complejos y múltiples paneles en cada escenas.  Debido a la dificultad de encontrar imágenes anotadas para el problema considerado, creamos nuestro propio conjunto de datos para llevar a cabo los experimentos.  La mayor fortaleza del modelo SSD fue la casi eliminación de los casos de Falsos Positivos (FP), situación que es pr