The Experts below are selected from a list of 26382 Experts worldwide ranked by ideXlab platform
Curtis L Baker - One of the best experts on this subject based on the ideXlab platform.
-
modeling second order boundary perception a machine learning approach
PLOS Computational Biology, 2019Co-Authors: Christopher Dimattina, Curtis L BakerAbstract:Visual Pattern detection and discrimination are essential first steps for scene analysis. Numerous human psychophysical studies have modeled visual Pattern detection and discrimination by estimating linear templates for classifying noisy stimuli defined by spatial variations in pixel intensities. However, such methods are poorly suited to understanding sensory processing mechanisms for complex visual stimuli such as second-order boundaries defined by spatial differences in contrast or Texture. We introduce a novel machine learning framework for modeling human perception of second-order visual stimuli, using image-computable hierarchical neural network models fit directly to psychophysical trial data. This framework is applied to modeling visual processing of boundaries defined by differences in the contrast of a carrier Texture Pattern, in two different psychophysical tasks: (1) boundary orientation identification, and (2) fine orientation discrimination. Cross-validation analysis is employed to optimize model hyper-parameters, and demonstrate that these models are able to accurately predict human performance on novel stimulus sets not used for fitting model parameters. We find that, like the ideal observer, human observers take a region-based approach to the orientation identification task, while taking an edge-based approach to the fine orientation discrimination task. How observers integrate contrast modulation across orientation channels is investigated by fitting psychophysical data with two models representing competing hypotheses, revealing a preference for a model which combines multiple orientations at the earliest possible stage. Our results suggest that this machine learning approach has much potential to advance the study of second-order visual processing, and we outline future steps towards generalizing the method to modeling visual segmentation of natural Texture boundaries. This study demonstrates how machine learning methodology can be fruitfully applied to psychophysical studies of second-order visual processing.
-
modeling second order boundary perception a machine learning approach
bioRxiv, 2018Co-Authors: Christopher Dimattina, Curtis L BakerAbstract:Background: Visual Pattern detection and discrimination are essential first steps for scene analysis. Numerous human psychophysical studies have modeled visual Pattern detection and discrimination by estimating linear templates for classifying noisy stimuli defined by spatial variations in pixel intensities. However, such methods are poorly suited to understanding sensory processing mechanisms for complex visual stimuli such as second-order boundaries defined by spatial differences in contrast or Texture. Methodology / Principal Findings: We introduce a novel machine learning framework for modeling human perception of second-order visual stimuli, using image-computable hierarchical neural network models fit directly to psychophysical trial data. This framework is applied to modeling visual processing of boundaries defined by differences in the contrast of a carrier Texture Pattern, in two different psychophysical tasks: (1) boundary orientation identification, and (2) fine orientation discrimination. Cross-validation analysis is employed to optimize model hyper-parameters, and demonstrate that these models are able to accurately predict human performance on novel stimulus sets not used for fitting model parameters. We find that, like the ideal observer, human observers take a region-based approach to the orientation identification task, while taking an edge-based approach to the fine orientation discrimination task. How observers integrate contrast modulation across orientation channels is investigated by fitting psychophysical data with two models representing competing hypotheses, revealing a preference for a model which combines multiple orientations at the earliest possible stage. Our results suggest that this machine learning approach has much potential to advance the study of second-order visual processing, and we outline future steps towards generalizing the method to modeling visual segmentation of natural Texture boundaries. Conclusions / Significance: This study demonstrates how machine learning methodology can be fruitfully applied to psychophysical studies of second-order visual processing.
Yongsheng Zhang - One of the best experts on this subject based on the ideXlab platform.
-
surface engineering design of alumina molybdenum fibrous monolithic ceramic to achieve excellent lubrication in a high vacuum environment
Tribology Letters, 2018Co-Authors: Hengzhong Fan, Yongsheng ZhangAbstract:Al2O3/Mo fibrous monolithic ceramics are potential candidates for space applications because of their excellent mechanical properties and low density. This study aims at achieving low friction and long life of this material in a high vacuum environment. Three-dimensional composite-lubricating layers were fabricated by considering Texture Pattern as storage dimples and MoS2 synthesized via hydrothermal method as lubricant. The tribological properties were studied sliding against Si3N4 ceramic and GCr15 bearing steel balls under high vacuum condition. Results showed that the lubricating properties of the Al2O3/Mo fibrous monolithic ceramics were improved greatly by the micro-Texture and MoS2 solid lubricant; the friction coefficients were as low as approximately 0.08 and 0.04, respectively, when Si3N4 ceramic and GCr15 bearing steel balls acted as the pairing materials. It was also demonstrated that the low friction coefficient can be realized with various normal loads and sliding speeds, indicating the composite-lubricating layers have good adaptation of working conditions. This excellent performance of the material is mainly because of MoS2 stored in dimples can be easily dragged onto the friction surface to form lubricating and transferring films during the friction process. This work is an extension of studies that were previously published in Tribology Letters journal.
-
surface engineering design of alumina molybdenum fibrous monolithic ceramic to achieve continuous lubrication from room temperature to 800 c
Tribology Letters, 2017Co-Authors: Hengzhong Fan, Junjie Song, Yongsheng ZhangAbstract:Al2O3/Mo fibrous monolithic ceramics are potential candidates for high-temperature applications because of their excellent high-temperature self-lubricated and fracture properties. This study aims at achieving the good self-lubricating ability at a wide temperature variation from room temperature (RT) to 800 °C and avoiding the abrasive wear of the material at the starting moment of the friction test. Three-dimensional composite-lubricating layers were formed by considering Texture Pattern as storage dimples and burnishing BaSO4 solid lubricant (SL) on the Textured surface of Al2O3/Mo fibrous monolithic ceramics. The friction properties and wear mechanisms were studied from RT to 800 °C in a continuous heating process. The results show that the synergy effect of micro-Texture, BaSO4 SL and oxidation products derived from Mo containing MoO3 improved the lubricating performances of the material at each temperature stage, thus realizing continuous lubrication in a wide temperature range. It is demonstrated that the friction coefficient of Textured surface coated with BaSO4 SL was kept lower 0.57 when subjected to dry sliding against Al2O3 ceramic pin at the temperature from RT to 800 °C, and it even can be as low as 0.30 at 600 and 800 °C. This work is an extension of study that was previously published in Tribology Letters journal.
-
surface engineering design of al2o3 mo self lubricating structural ceramics part ii continuous lubrication effects of a three dimensional lubricating layer at temperatures from 25 to 800 c
Wear, 2016Co-Authors: Yuan Fang, Junjie Song, Yongsheng Zhang, Litian HuAbstract:Abstract Al 2 O 3 /Mo self-lubricating structural ceramics with laminated-structure are potential candidates for high-temperature applications because of their excellent self-lubricating and mechanical performances. This study aims at revealing the mechanisms of how a three-dimensional lubricating layer affects the tribological properties of Al 2 O 3 /Mo laminated composites at temperatures from 25 to 800 °C. A three-dimensional lubricating layer was formed by considering Texture Pattern as storage dimples and coating solid lubricants (SLs) on the Textured surface of Al 2 O 3 /Mo laminated composite. The friction properties and wear mechanisms at temperature from 25 to 800 °C in a continuous heating process were studied. It is found that the synergy effect of micro-Textures and SLs influence the tribological properties of material. Moreover, the tribochemical reaction of SLs stored in the micro-dimples at high temperature improves the lubricating ability of materials, thus realizing continuous lubrication within a wide temperature range. We demonstrated that the friction coefficient of Textured surface that coated with MoS 2 /CaF 2 –BaF 2 SLs was kept lower than 0.50 when subjected to dry sliding wear against Al 2 O 3 ceramic pin at 25–800 °C, and it was even lower than 0.15 and 0.35 at 25–200 °C and 800 °C, respectively. This work is an extension of studies that were previously published in Wear journal.
Carlos Garciaresua - One of the best experts on this subject based on the ideXlab platform.
-
automatic classification of the interferential tear film lipid layer using colour Texture analysis
Computer Methods and Programs in Biomedicine, 2013Co-Authors: Beatriz Remeseiro, M. Penas, A. Mosquera, N Barreira, Jorge Novo, Carlos GarciaresuaAbstract:The tear film lipid layer is heterogeneous among the population. Its classification depends on its thickness and can be done using the interference Pattern categories proposed by Guillon. This papers presents an exhaustive study about the characterisation of the interference phenomena as a Texture Pattern, using different feature extraction methods in different colour spaces. These methods are first analysed individually and then combined to achieve the best results possible. The principal component analysis (PCA) technique has also been tested to reduce the dimensionality of the feature vectors. The proposed methodologies have been tested on a dataset composed of 105 images from healthy subjects, with a classification rate of over 95% in some cases.
Christopher Dimattina - One of the best experts on this subject based on the ideXlab platform.
-
modeling second order boundary perception a machine learning approach
PLOS Computational Biology, 2019Co-Authors: Christopher Dimattina, Curtis L BakerAbstract:Visual Pattern detection and discrimination are essential first steps for scene analysis. Numerous human psychophysical studies have modeled visual Pattern detection and discrimination by estimating linear templates for classifying noisy stimuli defined by spatial variations in pixel intensities. However, such methods are poorly suited to understanding sensory processing mechanisms for complex visual stimuli such as second-order boundaries defined by spatial differences in contrast or Texture. We introduce a novel machine learning framework for modeling human perception of second-order visual stimuli, using image-computable hierarchical neural network models fit directly to psychophysical trial data. This framework is applied to modeling visual processing of boundaries defined by differences in the contrast of a carrier Texture Pattern, in two different psychophysical tasks: (1) boundary orientation identification, and (2) fine orientation discrimination. Cross-validation analysis is employed to optimize model hyper-parameters, and demonstrate that these models are able to accurately predict human performance on novel stimulus sets not used for fitting model parameters. We find that, like the ideal observer, human observers take a region-based approach to the orientation identification task, while taking an edge-based approach to the fine orientation discrimination task. How observers integrate contrast modulation across orientation channels is investigated by fitting psychophysical data with two models representing competing hypotheses, revealing a preference for a model which combines multiple orientations at the earliest possible stage. Our results suggest that this machine learning approach has much potential to advance the study of second-order visual processing, and we outline future steps towards generalizing the method to modeling visual segmentation of natural Texture boundaries. This study demonstrates how machine learning methodology can be fruitfully applied to psychophysical studies of second-order visual processing.
-
modeling second order boundary perception a machine learning approach
bioRxiv, 2018Co-Authors: Christopher Dimattina, Curtis L BakerAbstract:Background: Visual Pattern detection and discrimination are essential first steps for scene analysis. Numerous human psychophysical studies have modeled visual Pattern detection and discrimination by estimating linear templates for classifying noisy stimuli defined by spatial variations in pixel intensities. However, such methods are poorly suited to understanding sensory processing mechanisms for complex visual stimuli such as second-order boundaries defined by spatial differences in contrast or Texture. Methodology / Principal Findings: We introduce a novel machine learning framework for modeling human perception of second-order visual stimuli, using image-computable hierarchical neural network models fit directly to psychophysical trial data. This framework is applied to modeling visual processing of boundaries defined by differences in the contrast of a carrier Texture Pattern, in two different psychophysical tasks: (1) boundary orientation identification, and (2) fine orientation discrimination. Cross-validation analysis is employed to optimize model hyper-parameters, and demonstrate that these models are able to accurately predict human performance on novel stimulus sets not used for fitting model parameters. We find that, like the ideal observer, human observers take a region-based approach to the orientation identification task, while taking an edge-based approach to the fine orientation discrimination task. How observers integrate contrast modulation across orientation channels is investigated by fitting psychophysical data with two models representing competing hypotheses, revealing a preference for a model which combines multiple orientations at the earliest possible stage. Our results suggest that this machine learning approach has much potential to advance the study of second-order visual processing, and we outline future steps towards generalizing the method to modeling visual segmentation of natural Texture boundaries. Conclusions / Significance: This study demonstrates how machine learning methodology can be fruitfully applied to psychophysical studies of second-order visual processing.
Beatriz Remeseiro - One of the best experts on this subject based on the ideXlab platform.
-
automatic classification of the interferential tear film lipid layer using colour Texture analysis
Computer Methods and Programs in Biomedicine, 2013Co-Authors: Beatriz Remeseiro, M. Penas, A. Mosquera, N Barreira, Jorge Novo, Carlos GarciaresuaAbstract:The tear film lipid layer is heterogeneous among the population. Its classification depends on its thickness and can be done using the interference Pattern categories proposed by Guillon. This papers presents an exhaustive study about the characterisation of the interference phenomena as a Texture Pattern, using different feature extraction methods in different colour spaces. These methods are first analysed individually and then combined to achieve the best results possible. The principal component analysis (PCA) technique has also been tested to reduce the dimensionality of the feature vectors. The proposed methodologies have been tested on a dataset composed of 105 images from healthy subjects, with a classification rate of over 95% in some cases.
-
statistical comparison of classifiers applied to the interferential tear film lipid layer automatic classification
Computational and Mathematical Methods in Medicine, 2012Co-Authors: Beatriz Remeseiro, Manuel G. Penedo, M. Penas, A. Mosquera, Jorge Novo, Eva YebrapimentelAbstract:The tear film lipid layer is heterogeneous among the population. Its classification depends on its thickness and can be done using the interference Pattern categories proposed by Guillon. The interference phenomena can be characterised as a colour Texture Pattern, which can be automatically classified into one of these categories. From a photography of the eye, a region of interest is detected and its low-level features are extracted, generating a feature vector that describes it, to be finally classified in one of the target categories. This paper presents an exhaustive study about the problem at hand using different Texture analysis methods in three colour spaces and different machine learning algorithms. All these methods and classifiers have been tested on a dataset composed of 105 images from healthy subjects and the results have been statistically analysed. As a result, the manual process done by experts can be automated with the benefits of being faster and unaffected by subjective factors, with maximum accuracy over 95%.