Reconocimiento de objetos de forma libre a partir de los datos de rango de una vista parcial usando cono curvaturas ponderadas

Salamanca, Santiago; Adán, Antonio; Cerrada, Carlos; Adán, Miguel; Merchán, Pilar; Tejado, Inés

doi:10.1016/s1697-7912(07)70195-4

Cited by 5 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some plots have been rotated to enhance data visualization. Complementary tests of this recognition procedure have been carried out in slightly different environments, for example in (Salamanca et al, 2007). Nevertheless, no significant performance differences can be extracted from the analysis of the obtained results in all these cases.…”

Section: Resultsmentioning

confidence: 99%

“…For this task the new characteristic WCC, which is computed from the partial spherical model, is proposed. The specific partial modelling technique applied is not going to be explained in detail here, and a deeper analysis can be found in (Salamanca et al, 2000). Nevertheless, some preliminary concepts must be introduced to present and explain the power of this feature.…”

Section: First Stage: Robust Determination Of the Point Of Viewmentioning

confidence: 99%

“…Fig. 4 illustrates some aspects of this procedure, but a more detailed explanation can be found at (Salamanca et al, 2000).…”

Section: Definition 3 We Call Modeling Wave Set Associated To T To Tmentioning

confidence: 99%

See 2 more Smart Citations

Experiences in Recognizing Free-Shaped Objects from Partial Views by Using Weighted Cone Curvatures

Cerrada¹,

Salamanca²,

Adán³

et al. 2011

Object Recognition

Self Cite

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: First Stage: Robust Determination Of the Point Of Viewmentioning

confidence: 99%

See 1 more Smart Citation

Experiences in Recognizing Free-Shaped Objects from Partial Views by Using Weighted Cone Curvatures

Cerrada¹,

Salamanca²,

Adán³

et al. 2011

Object Recognition

Self Cite

View full text Add to dashboard Cite

“…Then, if the goal is recognize them, a good solution is an object recognition method considering free form objects. The most methods like that use local feature to describe the objects in a faster way [5][6][7][8]. These methods, detects visually distinctive points in images called: interest points, salient points, keypoints or corner points.…”

Section: Introductionmentioning

confidence: 99%

Free Form Object Recognition Module using A-KAZE and GCS

Flores-Rodrıguez¹,

Trujillo-Romero²

2016

RCS

View full text Add to dashboard Cite

This paper presents an object recognition module development. This module uses a local feature approach to identify keypoints in free form objects and an unsupervised artificial neural network (ANN) to associate the nearest ones and get clusters of each object learned. The module uses A-KAZE feature descriptor and Growing Cell Structure (GCS) ANN. The module is validated using an own data base, with twenty real objects and twenty different images each one. Here is presented a variety of experiments using from five to fifteen trainning images per object and the rest of them for evaluation. This method gets good results with 100% of discrimination between objects and up to 80% of correct classification.

show abstract

“…Uno de los tratamientos que se aplica en la etapa de procesado es el de rellenado de huecos. Con este paso se persigue la obtención de una malla hermética, es decir, totalmente cerrada, que resulta de gran utilidad en multitud de aplicaciones: fabricación con sistemas de prototipado rápido, caracte-rización de superficies, reconocimiento de objetos (Salamanca et al (2009),Adán and Huber (2011)), etc.…”

unclassified

Relleno de huecos en mallas 3D completas mediante algoritmos de restauración de imagen

Hernández

Miño

Somolinos

et al. 2012

Revista Iberoamericana de Automática e Informática Industrial R

View full text Add to dashboard Cite

En este artículo se propone un método para rellenar huecos en objetos 3D. La idea principal es la de utilizar un algoritmo de restauración de imágenes para reconstruir las partes que se han de completar. Para ello es necesario hacer una transformación de los datos de la superficie 3D en datos de imagen 2D. Por tanto, el algoritmo propuesto parte de una etapa inicial de identificación de huecos. A continuación se hace la selección, para cada hueco, de una porción de malla representativa. Seguidamente se calcula el punto de vista o plano de proyección adecuado para obtener una imagen de rango de esa porción de malla. A la imagen de rango obtenida se le aplica el algoritmo de restauración de imagen. Finalmente, se aplica una transformación inversa 2D a 3D y se integra el resultado con la malla inicial. Se trata de un algoritmo robusto, válido para diversos tipos de huecos y diferentes tamaños de los mismos.

show abstract

Reconocimiento de objetos de forma libre a partir de los datos de rango de una vista parcial usando cono curvaturas ponderadas

Cited by 5 publications

References 11 publications

Experiences in Recognizing Free-Shaped Objects from Partial Views by Using Weighted Cone Curvatures

Experiences in Recognizing Free-Shaped Objects from Partial Views by Using Weighted Cone Curvatures

Free Form Object Recognition Module using A-KAZE and GCS

Relleno de huecos en mallas 3D completas mediante algoritmos de restauración de imagen

Contact Info

Product

Resources

About