Automatic feature selection for biological shape classification in Σynergos

Bruno, Odemir Martinez; César, Roberto M.; Consularo, Luís Augusto; Costa, Luciano da F.

doi:10.1109/sibgra.1998.722774

Cited by 9 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…the probability of each grey-level occurring in that image [22]. The geometrical information can then be analysed from the histogram by allowing the image to undergo a filtering process where the output depends on a neighbourhood around each pixel in the original image [5]. In order to avoid images being embedded within windows of different size, which will influence the outcome of the histogram analysis, each neuron has been represented inside its Ferret box [11], ie.…”

Section: Blurred Histogram Entropy and Momentmentioning

confidence: 99%

Automated Morphometric Analysis of the Cat Retinal Α/Y, Β/X and Δ Ganglion Cells Using Wavelet Statistical Moment and Clustering Algorithms

Jelinek

César²,

Leandro³

et al. 2004

J. Integr. Neurosci.

View full text Add to dashboard Cite

Computational morphological analysis comprises the development of measures (indicators) that describe different form attributes of a neuron and provides additional parameters for classification algorithms. Our work addressed the problem of small group sizes often encountered in neuromorphological and neurophysiological research, automated classification tasks (unsupervised learning) and introduced a new morphological measure: the wavelet statistical moment. We analysed cat alpha/Y, beta/X and delta Golgi-stained retinal ganglion cells using six different shape features (circularity, 2(nd) statistical moment and entropy of Gaussian blurred images, wavelet statistical moment, number of terminations and the fractal dimension). This allowed us to compare the sensitivity of the methods in uniquely describing morphological attributes of these cells.

show abstract

Section: Blurred Histogram Entropy and Momentmentioning

confidence: 99%

Automated Morphometric Analysis of the Cat Retinal Α/Y, Β/X and Δ Ganglion Cells Using Wavelet Statistical Moment and Clustering Algorithms

Jelinek

César²,

Leandro³

et al. 2004

J. Integr. Neurosci.

View full text Add to dashboard Cite

show abstract

“…The multiscale entropy [8,9] can be used to complement the degeneracy of the traditional entropy, which is invariant to any spatial permutation of the mosaic values (the entropy ultimately depends only on the image value histogram which, as a first order statistics, does not depend on the spatial positions). More specifically, the multiscale entropy can be defined as follows…”

mentioning

confidence: 99%

Statistical mechanics characterization of neuronal mosaics

Costa

Rocha

Lima

2005

Applied Physics Letters

View full text Add to dashboard Cite

The spatial distribution of neuronal cells is an important requirement for achieving proper neuronal function in several parts of the nervous system of most animals. For instance, specific distribution of photoreceptors and related neuronal cells, particularly the ganglion cells, in mammal's retina is required in order to properly sample the projected scene. This work presents how two concepts from the areas of statistical mechanics and complex systems, namely the lacunarity and the multiscale entropy (i.e. the entropy calculated over progressively diffused representations of the cell mosaic), have allowed effective characterization of the spatial distribution of retinal cells. * Electronic address: luciano@if.sc.usp.br 1

show abstract

“…A vision research software environment, called Synergos, has been implemented (see [ 5 ] ) , which includes computational tools for searching and storing WWW images.…”

Section: 2mentioning

confidence: 99%

Improved face×non-face discrimination using Fourier descriptors through feature selection

Dampos¹,

Feris²,

César³

Proceedings 13th Brazilian Symposium on Computer Graphics and Image Processing (Cat. No.PR00878)

Self Cite

View full text Add to dashboard Cite

This work presents a new method to discriminate face from non-face images using Fourier descriptors. The first step of our approach consists in applying a horizontal edge detection filter in the input image, followed by the extraction of a ID signal from the computed edge map. Then we calculate the Fourier descriptors from this signal and classify the image using statistical classifiers. In order to improve our results, we applied a feature selection algorithm. Preliminary performance assessment results have shown that this approach is superior than traditional transform based methods. Besides, these results showed that our method might be used to develop a fast face detection system. 28 0-7695-0878-WOO $10.00 0 2000 IEEE

show abstract

Automatic feature selection for biological shape classification in Σynergos

Cited by 9 publications

References 13 publications

Automated Morphometric Analysis of the Cat Retinal Α/Y, Β/X and Δ Ganglion Cells Using Wavelet Statistical Moment and Clustering Algorithms

Automated Morphometric Analysis of the Cat Retinal Α/Y, Β/X and Δ Ganglion Cells Using Wavelet Statistical Moment and Clustering Algorithms

Statistical mechanics characterization of neuronal mosaics

Improved face×non-face discrimination using Fourier descriptors through feature selection

Contact Info

Product

Resources

About