Combined edge detection using wavelet transform and signal registration

Heric, D.; Zazula, Damjan

doi:10.1016/j.imavis.2006.05.008

Cited by 52 publications

(31 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Basados en el operador convencional del algoritmo de Canny y en muchas otras técnicas como la lógica difusa, la transformada Wavelet, control de escala lineal y filtrado morfológico o lineal sugeridos en los artículos de : (Patel, Dhiraj, Sagar, & More, 2013), (Xia, Yao, Chang, & Zhong, 2010), (Demigny, 2002), (Xu, Weaver, & Healy, 1994), (Heric & Zazula, 2007), (Elder & Zucker, 1998), nuestro artículo propone realizar una variación del filtro morfológico presentando en (Deng, Wang, & Yang, 2013), donde se reemplaza el filtro gaussiano que presenta la debilidad de la selección manual de la varianza para realizar la reducción del ruido. Este estudio utiliza en los experimentos imágenes cross-espectrales fusionadas para evaluar las variantes propuestas.…”

Section: Enfoque Gqmunclassified

Detección de Contornos utilizando el Algoritmo Canny en Imágenes Cross-Espectrales Fusionadas

Suárez

Villavicencio

2017

Enfoque UTE

View full text Add to dashboard Cite

Considerando que las imágenes de diferentes espectros proporcionan una amplia información que ayuda mucho en el proceso de identificación y distinción de objetos que tienen firmas espectrales únicas. En este trabajo se evalúa el uso de imágenes cross-espectrales en el proceso de detección de bordes. Este estudio evalua el detector de bordes Canny con dos variantes. La primera se refiere al uso de imágenes cross-espectrales fusionadas, y la segunda al uso de filtros morfológicos. Para garantizar la calidad de los datos utilizados en este estudio se aplicó el marco de trabajo GQM (Goal-Question-Metrics), la cual fue utilizada como marco de trabajo para reducir el ruido y aumentar la entropía en las imágenes. Después de realizar los experimentos. Las métricas obtenidas en los experimentos confirman que la cantidad y calidad de los bordes detectados aumenta significativamente después de la inclusión de un filtro morfológico y un canal de espectro infrarrojo cercano en las imágenes fusionadas.

show abstract

Section: Enfoque Gqmunclassified

Detección de Contornos utilizando el Algoritmo Canny en Imágenes Cross-Espectrales Fusionadas

Suárez

Villavicencio

2017

Enfoque UTE

View full text Add to dashboard Cite

show abstract

“…Sobel), Gaussian based (e.g. LoG), multi-resolution [17], non-linear [18], wavelet based [19], statistical [20], machine learning based [21], contextual [22] and line edge [23] methods.…”

Section: Edge Detectionmentioning

confidence: 99%

Illumination Invariant Facial Pose Classification

Jaiswal¹,

Kumar²,

Agrawal³

2012

IJCA

View full text Add to dashboard Cite

In this paper, we compared the performance of various combinations of edge operators and linear subspace methods to determine the best combination for pose classification. To evaluate the performance, we have carried out experiments on CMU-PIE database which contains images with wide variation in illumination and pose. We found that the performance of pose classification depends on the choice of edge operator and linear subspace method. The best classification accuracy is obtained with Prewitt edge operator and Eigenfeature regularization method. In order to handle illumination variation, we used adaptive histogram equalization as a preprocessing step resulting into significant improvement in performance except for Roberts operator.

show abstract

“…There are several different wavelets that have gained popularity throughout the development of wavelet analysis. The most important of these is the Harr wavelet, which is the simplest and preferred wavelet in many applications [22]. Equation (1) can be discretized by restraining a and b to a discrete lattice (a = 2 b & a > 0) to give the DWT, which can be expressed as follows.…”

Section: Discrete Wavelet Transformmentioning

confidence: 99%

A Novel Method for Magnetic Resonance Brain Image Classification Based on Adaptive Chaotic Pso

Zhang¹,

Wang²,

Wu³

2010

PIER

117

View full text Add to dashboard Cite

Abstract-Automated and accurate classification of magnetic resonance (MR) brain images is an integral component of the analysis and interpretation of neuroimaging. Many different and innovative methods have been proposed to improve upon this technology. In this study, we presented a forward neural network (FNN) based method to classify a given MR brain image as normal or abnormal. This method first employs a wavelet transform to extract features from images, and then applies the technique of principle component analysis (PCA) to reduce the dimensions of features. The reduced features are sent to an FNN, and these parameters are optimized via adaptive chaotic particle swarm optimization (ACPSO). K-fold stratified cross validation was used to enhance generalization. We applied the proposed method on 160 images (20 normal, 140 abnormal), and found that the classification accuracy is as high as 98.75% while the computation time per image is only 0.0452 s.

show abstract

Combined edge detection using wavelet transform and signal registration

Cited by 52 publications

References 20 publications

Detección de Contornos utilizando el Algoritmo Canny en Imágenes Cross-Espectrales Fusionadas

Detección de Contornos utilizando el Algoritmo Canny en Imágenes Cross-Espectrales Fusionadas

Illumination Invariant Facial Pose Classification

A Novel Method for Magnetic Resonance Brain Image Classification Based on Adaptive Chaotic Pso

Contact Info

Product

Resources

About