Daniel Acevedo | National Council of Scientific and Technological Research (CONICET) (original) (raw)
Conference Presentations by Daniel Acevedo
We present a new lossless compressor for multispectral images having few bands. The mentioned com... more We present a new lossless compressor for multispectral images having few bands. The mentioned compressor takes into account variations in spectral correlation in order to determine the appropriate spectral and
spatial prediction to be performed. The algorithm exploits 2 different facts. On one hand, highly correlated bands may be efficiently compressed with fast computations. On the other hand, a class–conditioned wavelet–based compressor, which is more time-consuming, has given very high compression ratios, even in the case of lowly correlated bands. Our correlation-dependent hybrid algorithm yields high compression ratios, outperforming state-of-the-art lossless compressors, and has reasonable execution times.
Papers by Daniel Acevedo
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021
The present work corresponds to the application of techniques of data mining and deep training of... more The present work corresponds to the application of techniques of data mining and deep training of neural networks (deep learning) with the objective of classifying images of moles in ‘Melanomas’ or ‘No Melanomas’. For this purpose an ensemble of three classifiers will be created. The first corresponds to a convolutional network VGG-16, the other two correspond to two hybrid models. Each hybrid model is composed of a VGG-16 input network and a Support Vector Machine (SVM) as a classifier. These models will be trained with Fisher Vectors (FVs) calculated with the descriptors that are the output of the convolutional network aforementioned. The difference between these two last classifiers lies in the fact that one has segmented images as input of the VGG-16 network, while the other uses non-segmented images. Segmentation is done by means of an U-NET network. Finally, we will analyze the performance of the hybrid models: The VGG-16 network and the ensemble that incorporates the three cl...
SPIE Proceedings, 2005
We present a lossless compressor for multispectral Landsat images that exploits interband and int... more We present a lossless compressor for multispectral Landsat images that exploits interband and intraband correlations. The compressor operates on blocks of 256 × 256 pixels, and performs two kinds of predictions. For bands 1, 2, 3, 4, 5, 6.2 and 7, the compressor performs an integer-to-integer wavelet transform, which is applied to each block separately. The wavelet coefficients that have not yet been encoded are predicted by means of a linear combination of already coded coefficients that belong to the same orientation and spatial location in the same band, and coefficients of the same location from other spectral bands. A fast block classification is performed in order to use the best weights for each landscape. The prediction errors or differences are finally coded with an entropy-based coder. For band 6.1, we do not use wavelet transforms, instead, a median edge detector is applied to predict a pixel, with the information of the neighbouring pixels and the equalized pixel from band 6.2. This technique exploits better the great similarity between histograms of bands 6.1 and 6.2. The prediction differences are finally coded with a context-based entropy coder. The two kinds of predictions used reduce both spatial and spectral correlations, increasing the compression rates. Our compressor has shown to be superior to the lossless compressors Winzip, LOCO-I, PNG and JPEG2000.
publicaciones.dc.uba.ar
Abstract???We present a new lossless compressor for multispectral images having few bands. The me... more Abstract???We present a new lossless compressor for multispectral images having few bands. The mentioned compressor takes into account variations in spectral correlation in order to determine the appropriate spectral and spatial prediction to be performed. The ...
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Http Digital Bl Fcen Uba Ar, 2011
This paper addresses a license plate detection and recognition (LPR) task on still images of truc... more This paper addresses a license plate detection and recognition (LPR) task on still images of trucks. The main contribution of our LPR system is the fusion of different segmentation algorithms used to improve the license plate detection. We also compare the performance of two kinds of classifiers for optical character recognition (OCR): one based on the a contrario framework using
Lecture Notes in Computer Science, 2010
This paper addresses a license plate detection and recognition (LPR) task on still images of truc... more This paper addresses a license plate detection and recognition (LPR) task on still images of trucks. The main contribution of our LPR system is the fusion of different segmentation algorithms used to improve the license plate detection. We also compare the performance of two kinds of classifiers for optical character recognition (OCR): one based on the a contrario framework using the shape contexts as features and the other based on a SVM classifier using the intensity pixel values as features.
Lecture Notes in Computer Science, 2014
In this work we analyze and implement several audio features. We emphasize our analysis on the ZC... more In this work we analyze and implement several audio features. We emphasize our analysis on the ZCR feature and propose a modification making it more robust when signals are near zero. They are all used to discriminate the following audio classes: music, speech, environmental sound. An SVM classifier is used as a classification tool, which has proven to be efficient for audio classification. By means of a selection heuristic we draw conclusions of how they may be combined for fast classification.
Lecture Notes in Computer Science, 2014
Proceedings of Spie the International Society For Optical Engineering, 2006
Inspired by previous work on the modelling of wavelet coefficients, and on the observed differenc... more Inspired by previous work on the modelling of wavelet coefficients, and on the observed differences between distributions of wavelet coefficients belonging to different landscapes, we present a lossless compressor of multi-spectral images based on the prediction of wavelet coefficients, conditioned to the landscape. This compressor operates blockwise. The wavelet transform is applied to each block, and detail coefficients from the two finest scales are predicted by means of a linear combination of other coefficients, which may belong to the same band as the predicted coefficient, or to a previously coded band. The weights for the lineal combination are estimated on-line: for each detail subband, the compressor is trained on all the detail coefficients belonging to the same class. In addition, a different band ordering is considered for each block. Differences in prediction are coded with a conditional entropy coder. Preliminary results reveal that we obtain more accurate predictions.
2010 20th International Conference on Pattern Recognition, 2010
This paper presents a texture descriptor based on the fine detail coefficients at three resolutio... more This paper presents a texture descriptor based on the fine detail coefficients at three resolution levels of a traslation invariant undecimated wavelet transform. First, we consider vertical and horizontal wavelet detail coefficients at the same position as the components of a bivariate random vector, and the magnitude and angle of these vectors are computed. The magnitudes are modeled by a Generalized Gamma distribution. Their parameters, together with the circular histograms of angles, are used to characterize each texture image of the database. The Kullback-Leibler divergence is used as the similarity measurement. Retrieval experiments, in which we compare two wavelet transforms, are carried out on the Brodatz texture collection. Results reveal the good performance of this wavelet-based texture descriptor obtained via the Generalized Gamma distribution.
XVIII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'05), 2005
We present a lossless compressor for multispectral images that exploits interband correlations. E... more We present a lossless compressor for multispectral images that exploits interband correlations. Each band is divided into blocks, to which a wavelet transform is applied. The wavelet coefficients are predicted by means of a linear combination of coefficients belonging to the same orientation and spatial location. The prediction errors are then encoded with an entropy -based coder. Our original contributions are i) the inclusion, among the candidates for prediction, of coefficients of the same location from other spectral bands, ii) the calculation of weights tuned to the landscape being processed, iii) a fast block classification and a different band-ordering for each landscape. Our compressor reduces the size of an image to about a fourth of its original size. Our method is equivalent to LOCO-I, on 3 of the images tested it was superior. It is superior to other lossless compressors: WinZip, JPEG2000 and PNG.
Satellite Data Compression, Communications, and Archiving III, 2007
We present a lossless compressor for multispectral images that combines two classical tools: wave... more We present a lossless compressor for multispectral images that combines two classical tools: wavelets and neural networks. Due to their huge dimensions, images are split into small blocks and the wavelet transform that maps integers to integers is applied to each block -and each band- to decorrelate it. In order to increase even more the compression rates achieved by the wavelet transform, coefficients in the two finest scales are predicted by means of neural networks, which use causal information (ie, coefficients already coded) to get nonlinear estimates. In this work, we add coefficients from other spectral bands to compute the prediction, besides those coefficients belonging to the same band, which lie in a causal neighbourhood. The differences are then coded with a context based arithmetic coder. Several options regarding initialization, training and architecture of the neural networks are analyzed. Comparison results with other lossless compressors (with respect to the coding time and the bitrates achieved) are given.
Lecture Notes in Computer Science, 2012
Satellite Data Compression, Communications, and Archiving II, 2006
Inspired by previous work on the modelling of wavelet coefficients, and on the observed differenc... more Inspired by previous work on the modelling of wavelet coefficients, and on the observed differences between distributions of wavelet coefficients belonging to different landscapes, we present a lossless compressor of multi-spectral images based on the prediction of wavelet coefficients, conditioned to the landscape. This compressor operates blockwise. The wavelet transform is applied to each block, and detail coefficients from the two finest scales are predicted by means of a linear combination of other coefficients, which may belong to the same band as the predicted coefficient, or to a previously coded band. The weights for the lineal combination are estimated on-line: for each detail subband, the compressor is trained on all the detail coefficients belonging to the same class. In addition, a different band ordering is considered for each block. Differences in prediction are coded with a conditional entropy coder. Preliminary results reveal that we obtain more accurate predictions.
Advances in Wavelet Theory and Their Applications in Engineering, Physics and Technology, 2012
Lecture Notes in Computer Science, 2007
This paper presents a novel texture descriptor based on the wavelet transform. First, we will con... more This paper presents a novel texture descriptor based on the wavelet transform. First, we will consider vertical and horizontal coefficients at the same position as the components of a bivariate random vector. The magnitud and angle of these vectors are computed and its histograms are analyzed. This empirical magnitud histogram is modelled by using a gamma distribution (pdf). As a result, the feature extraction step consists of estimating the gamma parameters using the maxima likelihood estimator and computing the circular histograms of angles. The similarity measurement step is done by means of the well-known Kullback-Leibler divergence. Finally, retrieval experiments are done using the Brodatz texture collection obtaining a good performance of this new texture descriptor. We compare two wavelet transforms, with and without downsampling, and show the advantage of the second one, which is translation invariant, for the construction of our texture descriptor.
Data Compression Conference (dcc 2008), 2008
We present a nonlinear lossless compressor for multispectral images that exploits both intraband ... more We present a nonlinear lossless compressor for multispectral images that exploits both intraband and interband correlations. A 2-dimensional wavelet transform is performed on each image band, and then the interband and remaining intraband correlations are exploited via an affine prediction of the wavelet coefficients, conditioning it to class information.
We present a new lossless compressor for multispectral images having few bands. The mentioned com... more We present a new lossless compressor for multispectral images having few bands. The mentioned compressor takes into account variations in spectral correlation in order to determine the appropriate spectral and
spatial prediction to be performed. The algorithm exploits 2 different facts. On one hand, highly correlated bands may be efficiently compressed with fast computations. On the other hand, a class–conditioned wavelet–based compressor, which is more time-consuming, has given very high compression ratios, even in the case of lowly correlated bands. Our correlation-dependent hybrid algorithm yields high compression ratios, outperforming state-of-the-art lossless compressors, and has reasonable execution times.
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021
The present work corresponds to the application of techniques of data mining and deep training of... more The present work corresponds to the application of techniques of data mining and deep training of neural networks (deep learning) with the objective of classifying images of moles in ‘Melanomas’ or ‘No Melanomas’. For this purpose an ensemble of three classifiers will be created. The first corresponds to a convolutional network VGG-16, the other two correspond to two hybrid models. Each hybrid model is composed of a VGG-16 input network and a Support Vector Machine (SVM) as a classifier. These models will be trained with Fisher Vectors (FVs) calculated with the descriptors that are the output of the convolutional network aforementioned. The difference between these two last classifiers lies in the fact that one has segmented images as input of the VGG-16 network, while the other uses non-segmented images. Segmentation is done by means of an U-NET network. Finally, we will analyze the performance of the hybrid models: The VGG-16 network and the ensemble that incorporates the three cl...
SPIE Proceedings, 2005
We present a lossless compressor for multispectral Landsat images that exploits interband and int... more We present a lossless compressor for multispectral Landsat images that exploits interband and intraband correlations. The compressor operates on blocks of 256 × 256 pixels, and performs two kinds of predictions. For bands 1, 2, 3, 4, 5, 6.2 and 7, the compressor performs an integer-to-integer wavelet transform, which is applied to each block separately. The wavelet coefficients that have not yet been encoded are predicted by means of a linear combination of already coded coefficients that belong to the same orientation and spatial location in the same band, and coefficients of the same location from other spectral bands. A fast block classification is performed in order to use the best weights for each landscape. The prediction errors or differences are finally coded with an entropy-based coder. For band 6.1, we do not use wavelet transforms, instead, a median edge detector is applied to predict a pixel, with the information of the neighbouring pixels and the equalized pixel from band 6.2. This technique exploits better the great similarity between histograms of bands 6.1 and 6.2. The prediction differences are finally coded with a context-based entropy coder. The two kinds of predictions used reduce both spatial and spectral correlations, increasing the compression rates. Our compressor has shown to be superior to the lossless compressors Winzip, LOCO-I, PNG and JPEG2000.
publicaciones.dc.uba.ar
Abstract???We present a new lossless compressor for multispectral images having few bands. The me... more Abstract???We present a new lossless compressor for multispectral images having few bands. The mentioned compressor takes into account variations in spectral correlation in order to determine the appropriate spectral and spatial prediction to be performed. The ...
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Http Digital Bl Fcen Uba Ar, 2011
This paper addresses a license plate detection and recognition (LPR) task on still images of truc... more This paper addresses a license plate detection and recognition (LPR) task on still images of trucks. The main contribution of our LPR system is the fusion of different segmentation algorithms used to improve the license plate detection. We also compare the performance of two kinds of classifiers for optical character recognition (OCR): one based on the a contrario framework using
Lecture Notes in Computer Science, 2010
This paper addresses a license plate detection and recognition (LPR) task on still images of truc... more This paper addresses a license plate detection and recognition (LPR) task on still images of trucks. The main contribution of our LPR system is the fusion of different segmentation algorithms used to improve the license plate detection. We also compare the performance of two kinds of classifiers for optical character recognition (OCR): one based on the a contrario framework using the shape contexts as features and the other based on a SVM classifier using the intensity pixel values as features.
Lecture Notes in Computer Science, 2014
In this work we analyze and implement several audio features. We emphasize our analysis on the ZC... more In this work we analyze and implement several audio features. We emphasize our analysis on the ZCR feature and propose a modification making it more robust when signals are near zero. They are all used to discriminate the following audio classes: music, speech, environmental sound. An SVM classifier is used as a classification tool, which has proven to be efficient for audio classification. By means of a selection heuristic we draw conclusions of how they may be combined for fast classification.
Lecture Notes in Computer Science, 2014
Proceedings of Spie the International Society For Optical Engineering, 2006
Inspired by previous work on the modelling of wavelet coefficients, and on the observed differenc... more Inspired by previous work on the modelling of wavelet coefficients, and on the observed differences between distributions of wavelet coefficients belonging to different landscapes, we present a lossless compressor of multi-spectral images based on the prediction of wavelet coefficients, conditioned to the landscape. This compressor operates blockwise. The wavelet transform is applied to each block, and detail coefficients from the two finest scales are predicted by means of a linear combination of other coefficients, which may belong to the same band as the predicted coefficient, or to a previously coded band. The weights for the lineal combination are estimated on-line: for each detail subband, the compressor is trained on all the detail coefficients belonging to the same class. In addition, a different band ordering is considered for each block. Differences in prediction are coded with a conditional entropy coder. Preliminary results reveal that we obtain more accurate predictions.
2010 20th International Conference on Pattern Recognition, 2010
This paper presents a texture descriptor based on the fine detail coefficients at three resolutio... more This paper presents a texture descriptor based on the fine detail coefficients at three resolution levels of a traslation invariant undecimated wavelet transform. First, we consider vertical and horizontal wavelet detail coefficients at the same position as the components of a bivariate random vector, and the magnitude and angle of these vectors are computed. The magnitudes are modeled by a Generalized Gamma distribution. Their parameters, together with the circular histograms of angles, are used to characterize each texture image of the database. The Kullback-Leibler divergence is used as the similarity measurement. Retrieval experiments, in which we compare two wavelet transforms, are carried out on the Brodatz texture collection. Results reveal the good performance of this wavelet-based texture descriptor obtained via the Generalized Gamma distribution.
XVIII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'05), 2005
We present a lossless compressor for multispectral images that exploits interband correlations. E... more We present a lossless compressor for multispectral images that exploits interband correlations. Each band is divided into blocks, to which a wavelet transform is applied. The wavelet coefficients are predicted by means of a linear combination of coefficients belonging to the same orientation and spatial location. The prediction errors are then encoded with an entropy -based coder. Our original contributions are i) the inclusion, among the candidates for prediction, of coefficients of the same location from other spectral bands, ii) the calculation of weights tuned to the landscape being processed, iii) a fast block classification and a different band-ordering for each landscape. Our compressor reduces the size of an image to about a fourth of its original size. Our method is equivalent to LOCO-I, on 3 of the images tested it was superior. It is superior to other lossless compressors: WinZip, JPEG2000 and PNG.
Satellite Data Compression, Communications, and Archiving III, 2007
We present a lossless compressor for multispectral images that combines two classical tools: wave... more We present a lossless compressor for multispectral images that combines two classical tools: wavelets and neural networks. Due to their huge dimensions, images are split into small blocks and the wavelet transform that maps integers to integers is applied to each block -and each band- to decorrelate it. In order to increase even more the compression rates achieved by the wavelet transform, coefficients in the two finest scales are predicted by means of neural networks, which use causal information (ie, coefficients already coded) to get nonlinear estimates. In this work, we add coefficients from other spectral bands to compute the prediction, besides those coefficients belonging to the same band, which lie in a causal neighbourhood. The differences are then coded with a context based arithmetic coder. Several options regarding initialization, training and architecture of the neural networks are analyzed. Comparison results with other lossless compressors (with respect to the coding time and the bitrates achieved) are given.
Lecture Notes in Computer Science, 2012
Satellite Data Compression, Communications, and Archiving II, 2006
Inspired by previous work on the modelling of wavelet coefficients, and on the observed differenc... more Inspired by previous work on the modelling of wavelet coefficients, and on the observed differences between distributions of wavelet coefficients belonging to different landscapes, we present a lossless compressor of multi-spectral images based on the prediction of wavelet coefficients, conditioned to the landscape. This compressor operates blockwise. The wavelet transform is applied to each block, and detail coefficients from the two finest scales are predicted by means of a linear combination of other coefficients, which may belong to the same band as the predicted coefficient, or to a previously coded band. The weights for the lineal combination are estimated on-line: for each detail subband, the compressor is trained on all the detail coefficients belonging to the same class. In addition, a different band ordering is considered for each block. Differences in prediction are coded with a conditional entropy coder. Preliminary results reveal that we obtain more accurate predictions.
Advances in Wavelet Theory and Their Applications in Engineering, Physics and Technology, 2012
Lecture Notes in Computer Science, 2007
This paper presents a novel texture descriptor based on the wavelet transform. First, we will con... more This paper presents a novel texture descriptor based on the wavelet transform. First, we will consider vertical and horizontal coefficients at the same position as the components of a bivariate random vector. The magnitud and angle of these vectors are computed and its histograms are analyzed. This empirical magnitud histogram is modelled by using a gamma distribution (pdf). As a result, the feature extraction step consists of estimating the gamma parameters using the maxima likelihood estimator and computing the circular histograms of angles. The similarity measurement step is done by means of the well-known Kullback-Leibler divergence. Finally, retrieval experiments are done using the Brodatz texture collection obtaining a good performance of this new texture descriptor. We compare two wavelet transforms, with and without downsampling, and show the advantage of the second one, which is translation invariant, for the construction of our texture descriptor.
Data Compression Conference (dcc 2008), 2008
We present a nonlinear lossless compressor for multispectral images that exploits both intraband ... more We present a nonlinear lossless compressor for multispectral images that exploits both intraband and interband correlations. A 2-dimensional wavelet transform is performed on each image band, and then the interband and remaining intraband correlations are exploited via an affine prediction of the wavelet coefficients, conditioning it to class information.
2009 16th IEEE International Conference on Image Processing (ICIP), 2009
This work presents a novel contribution in the field of shape recognition, in general, and in the... more This work presents a novel contribution in the field of shape recognition, in general, and in the Shape Context technique, in particular. We propose to address the problem of deciding if two shape context descriptors match or not using an a con-trario approach. Its key advantage ...