The Experts below are selected from a list of 51903 Experts worldwide ranked by ideXlab platform
Alan L Yuille - One of the best experts on this subject based on the ideXlab platform.
-
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Chenxi Liu, Liang-chieh Chen, Alan L Yuille, Florian Schroff, Hartwig Adam, Wei Hua, Li Fei-feiAbstract:Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale Image classification. In this paper, we study NAS for Semantic Image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense Image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes Images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for Semantic Image segmentation, attains state-of-the-art performance without any ImageNet pretraining.
-
CVPR - Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
2019 IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019Co-Authors: Chenxi Liu, Liang-chieh Chen, Alan L Yuille, Florian Schroff, Hartwig Adam, Wei Hua, Li Fei-feiAbstract:Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale Image classification. In this paper, we study NAS for Semantic Image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense Image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes Images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for Semantic Image segmentation, attains state-of-the-art performance without any ImageNet pretraining.
-
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
International Conference on Learning Representations, 2016Co-Authors: Liang-chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L YuilleAbstract:Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as Image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "Semantic Image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Qualitatively, our "DeepLab" system is able to localize segment boundaries at a level of accuracy which is beyond previous methods. Quantitatively, our method sets the new state-of-art at the PASCAL VOC-2012 Semantic Image segmentation task, reaching 71.6% IOU accuracy in the test set. We show how these results can be obtained efficiently: Careful network re-purposing and a novel application of the 'hole' algorithm from the wavelet community allow dense computation of neural net responses at 8 frames per second on a modern GPU.
-
CVPR - Attention to Scale: Scale-Aware Semantic Image Segmentation
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016Co-Authors: Liang-chieh Chen, Yi Yang, Jiang Wang, Alan L YuilleAbstract:Incorporating multi-scale features in fully convolutional neural networks (FCNs) has been a key element to achieving state-of-the-art performance on Semantic Image segmentation. One common way to extract multi-scale features is to feed multiple resized input Images to a shared deep network and then merge the resulting features for pixelwise classification. In this work, we propose an attention mechanism that learns to softly weight the multi-scale features at each pixel location. We adapt a state-of-the-art Semantic Image segmentation model, which we jointly train with multi-scale input Images and the attention model. The proposed attention model not only outperforms averageand max-pooling, but allows us to diagnostically visualize the importance of features at different positions and scales. Moreover, we show that adding extra supervision to the output at each scale is essential to achieving excellent performance when merging multi-scale features. We demonstrate the effectiveness of our model with extensive experiments on three challenging datasets, including PASCAL-Person-Part, PASCAL VOC 2012 and a subset of MS-COCO 2014.
-
weakly and semi supervised learning of a deep convolutional network for Semantic Image segmentation
International Conference on Computer Vision, 2015Co-Authors: George Papandreou, Liangchieh Che, Kevi Murphy, Alan L YuilleAbstract:Deep convolutional neural networks (DCNNs) trained on a large number of Images with strong pixel-level annotations have recently significantly pushed the state-of-art in Semantic Image segmentation. We study the more challenging problem of learning DCNNs for Semantic Image segmentation from either (1) weakly annotated training data such as bounding boxes or Image-level labels or (2) a combination of few strongly labeled and many weakly labeled Images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for Semantic Image segmentation model training under these weakly supervised and semi-supervised settings. Extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 Image segmentation benchmark, while requiring significantly less annotation effort. We share source code implementing the proposed system at https://bitbucket.org/deeplab/deeplab-public.
George Papandreou - One of the best experts on this subject based on the ideXlab platform.
-
rethinking atrous convolution for Semantic Image segmentation
arXiv: Computer Vision and Pattern Recognition, 2017Co-Authors: Liang-chieh Chen, George Papandreou, Florian Schroff, Hartwig AdamAbstract:In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of Semantic Image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with Image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 Semantic Image segmentation benchmark.
-
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
International Conference on Learning Representations, 2016Co-Authors: Liang-chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L YuilleAbstract:Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as Image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "Semantic Image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Qualitatively, our "DeepLab" system is able to localize segment boundaries at a level of accuracy which is beyond previous methods. Quantitatively, our method sets the new state-of-art at the PASCAL VOC-2012 Semantic Image segmentation task, reaching 71.6% IOU accuracy in the test set. We show how these results can be obtained efficiently: Careful network re-purposing and a novel application of the 'hole' algorithm from the wavelet community allow dense computation of neural net responses at 8 frames per second on a modern GPU.
-
weakly and semi supervised learning of a deep convolutional network for Semantic Image segmentation
International Conference on Computer Vision, 2015Co-Authors: George Papandreou, Liangchieh Che, Kevi Murphy, Alan L YuilleAbstract:Deep convolutional neural networks (DCNNs) trained on a large number of Images with strong pixel-level annotations have recently significantly pushed the state-of-art in Semantic Image segmentation. We study the more challenging problem of learning DCNNs for Semantic Image segmentation from either (1) weakly annotated training data such as bounding boxes or Image-level labels or (2) a combination of few strongly labeled and many weakly labeled Images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for Semantic Image segmentation model training under these weakly supervised and semi-supervised settings. Extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 Image segmentation benchmark, while requiring significantly less annotation effort. We share source code implementing the proposed system at https://bitbucket.org/deeplab/deeplab-public.
-
weakly and semi supervised learning of a deep convolutional network for Semantic Image segmentation
International Conference on Computer Vision, 2015Co-Authors: George Papandreou, Liang-chieh Chen, Kevin Murphy, Alan L YuilleAbstract:Deep convolutional neural networks (DCNNs) trained on a large number of Images with strong pixel-level annotations have recently significantly pushed the state-of-art in Semantic Image segmentation. We study the more challenging problem of learning DCNNs for Semantic Image segmentation from either (1) weakly annotated training data such as bounding boxes or Image-level labels or (2) a combination of few strongly labeled and many weakly labeled Images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for Semantic Image segmentation model training under these weakly supervised and semi-supervised settings. Extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 Image segmentation benchmark, while requiring significantly less annotation effort. We share source code implementing the proposed system at https://bitbucket.org/deeplab/deeplab-public.
-
weakly and semi supervised learning of a dcnn for Semantic Image segmentation
arXiv: Computer Vision and Pattern Recognition, 2015Co-Authors: George Papandreou, Liang-chieh Chen, Kevin Murphy, Alan L YuilleAbstract:Deep convolutional neural networks (DCNNs) trained on a large number of Images with strong pixel-level annotations have recently significantly pushed the state-of-art in Semantic Image segmentation. We study the more challenging problem of learning DCNNs for Semantic Image segmentation from either (1) weakly annotated training data such as bounding boxes or Image-level labels or (2) a combination of few strongly labeled and many weakly labeled Images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for Semantic Image segmentation model training under these weakly supervised and semi-supervised settings. Extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 Image segmentation benchmark, while requiring significantly less annotation effort. We share source code implementing the proposed system at this https URL
Liang-chieh Chen - One of the best experts on this subject based on the ideXlab platform.
-
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Chenxi Liu, Liang-chieh Chen, Alan L Yuille, Florian Schroff, Hartwig Adam, Wei Hua, Li Fei-feiAbstract:Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale Image classification. In this paper, we study NAS for Semantic Image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense Image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes Images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for Semantic Image segmentation, attains state-of-the-art performance without any ImageNet pretraining.
-
CVPR - Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
2019 IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019Co-Authors: Chenxi Liu, Liang-chieh Chen, Alan L Yuille, Florian Schroff, Hartwig Adam, Wei Hua, Li Fei-feiAbstract:Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale Image classification. In this paper, we study NAS for Semantic Image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense Image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes Images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for Semantic Image segmentation, attains state-of-the-art performance without any ImageNet pretraining.
-
rethinking atrous convolution for Semantic Image segmentation
arXiv: Computer Vision and Pattern Recognition, 2017Co-Authors: Liang-chieh Chen, George Papandreou, Florian Schroff, Hartwig AdamAbstract:In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of Semantic Image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with Image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 Semantic Image segmentation benchmark.
-
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
International Conference on Learning Representations, 2016Co-Authors: Liang-chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L YuilleAbstract:Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as Image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "Semantic Image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Qualitatively, our "DeepLab" system is able to localize segment boundaries at a level of accuracy which is beyond previous methods. Quantitatively, our method sets the new state-of-art at the PASCAL VOC-2012 Semantic Image segmentation task, reaching 71.6% IOU accuracy in the test set. We show how these results can be obtained efficiently: Careful network re-purposing and a novel application of the 'hole' algorithm from the wavelet community allow dense computation of neural net responses at 8 frames per second on a modern GPU.
-
CVPR - Attention to Scale: Scale-Aware Semantic Image Segmentation
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016Co-Authors: Liang-chieh Chen, Yi Yang, Jiang Wang, Alan L YuilleAbstract:Incorporating multi-scale features in fully convolutional neural networks (FCNs) has been a key element to achieving state-of-the-art performance on Semantic Image segmentation. One common way to extract multi-scale features is to feed multiple resized input Images to a shared deep network and then merge the resulting features for pixelwise classification. In this work, we propose an attention mechanism that learns to softly weight the multi-scale features at each pixel location. We adapt a state-of-the-art Semantic Image segmentation model, which we jointly train with multi-scale input Images and the attention model. The proposed attention model not only outperforms averageand max-pooling, but allows us to diagnostically visualize the importance of features at different positions and scales. Moreover, we show that adding extra supervision to the output at each scale is essential to achieving excellent performance when merging multi-scale features. We demonstrate the effectiveness of our model with extensive experiments on three challenging datasets, including PASCAL-Person-Part, PASCAL VOC 2012 and a subset of MS-COCO 2014.
Kevin Murphy - One of the best experts on this subject based on the ideXlab platform.
-
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
International Conference on Learning Representations, 2016Co-Authors: Liang-chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L YuilleAbstract:Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as Image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "Semantic Image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Qualitatively, our "DeepLab" system is able to localize segment boundaries at a level of accuracy which is beyond previous methods. Quantitatively, our method sets the new state-of-art at the PASCAL VOC-2012 Semantic Image segmentation task, reaching 71.6% IOU accuracy in the test set. We show how these results can be obtained efficiently: Careful network re-purposing and a novel application of the 'hole' algorithm from the wavelet community allow dense computation of neural net responses at 8 frames per second on a modern GPU.
-
weakly and semi supervised learning of a deep convolutional network for Semantic Image segmentation
International Conference on Computer Vision, 2015Co-Authors: George Papandreou, Liang-chieh Chen, Kevin Murphy, Alan L YuilleAbstract:Deep convolutional neural networks (DCNNs) trained on a large number of Images with strong pixel-level annotations have recently significantly pushed the state-of-art in Semantic Image segmentation. We study the more challenging problem of learning DCNNs for Semantic Image segmentation from either (1) weakly annotated training data such as bounding boxes or Image-level labels or (2) a combination of few strongly labeled and many weakly labeled Images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for Semantic Image segmentation model training under these weakly supervised and semi-supervised settings. Extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 Image segmentation benchmark, while requiring significantly less annotation effort. We share source code implementing the proposed system at https://bitbucket.org/deeplab/deeplab-public.
-
weakly and semi supervised learning of a dcnn for Semantic Image segmentation
arXiv: Computer Vision and Pattern Recognition, 2015Co-Authors: George Papandreou, Liang-chieh Chen, Kevin Murphy, Alan L YuilleAbstract:Deep convolutional neural networks (DCNNs) trained on a large number of Images with strong pixel-level annotations have recently significantly pushed the state-of-art in Semantic Image segmentation. We study the more challenging problem of learning DCNNs for Semantic Image segmentation from either (1) weakly annotated training data such as bounding boxes or Image-level labels or (2) a combination of few strongly labeled and many weakly labeled Images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for Semantic Image segmentation model training under these weakly supervised and semi-supervised settings. Extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 Image segmentation benchmark, while requiring significantly less annotation effort. We share source code implementing the proposed system at this https URL
-
ICCV - Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
2015 IEEE International Conference on Computer Vision (ICCV), 2015Co-Authors: George Papandreou, Liang-chieh Chen, Kevin Murphy, Alan L YuilleAbstract:Deep convolutional neural networks (DCNNs) trained on a large number of Images with strong pixel-level annotations have recently significantly pushed the state-of-art in Semantic Image segmentation. We study the more challenging problem of learning DCNNs for Semantic Image segmentation from either (1) weakly annotated training data such as bounding boxes or Image-level labels or (2) a combination of few strongly labeled and many weakly labeled Images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for Semantic Image segmentation model training under these weakly supervised and semi-supervised settings. Extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 Image segmentation benchmark, while requiring significantly less annotation effort. We share source code implementing the proposed system at https://bitbucket.org/deeplab/deeplab-public.
M.g. Strintzis - One of the best experts on this subject based on the ideXlab platform.
-
A Comparati ve Study of Object-level Spatial Context Techniques for Semantic Image Analysis
2011Co-Authors: Carsten Saathoff, Vasileios Mezaris, Ioannis Kompatsiaris, Hugo Jair Escalante, M.g. StrintzisAbstract:In this paper, three approaches to utilizing object- level spatial contextual information for Semantic Image analysis are presented and comparatively evaluated. Contextual informa- tion is in the form of fuzzy directional relations between Image regions. All techniques, namely a Genetic Algorithm (GA), a Binary Integer Programming (BIP) and an Energy-Based Model (EBM), are applied in order to estimate an optimal Semantic Image interpretation, after an initial set of region classification results is computed using solely visual features. Aim of this paper is the in-depth investigation of the advantages of each technique and the gain of a better insight on the use of spatial context. For this purpose, an appropriate evaluation framework, which includes several different combinations of low-level features and classification algorithms, has been developed. Extensive experi- ments on six datasets of varying problem complexity have been conducted for investigating the influence of typical factors (such as the utilized visual features, the employed classifier, the number of supported concepts, etc.) on the performance of each spatial context technique, while a detailed analysis of the obtained results is also given.
-
A Comparative Study of Object-level Spatial Context Techniques for Semantic Image Analysis
Computer Vision and Image Understanding, 2011Co-Authors: G. Th. Papadopoulos, Carsten Saathoff, Vasileios Mezaris, Ioannis Kompatsiaris, Hugo Jair Escalante, M.g. StrintzisAbstract:In this paper, three approaches to utilizing object-level spatial contextual information for Semantic Image analysis are presented and comparatively evaluated. Contextual information is in the form of fuzzy directional relations between Image regions. All techniques, namely a Genetic Algorithm (GA), a Binary Integer Programming (BIP) and an Energy-Based Model (EBM), are applied in order to estimate an optimal Semantic Image interpretation, after an initial set of region classification results is computed using solely visual features. Aim of this paper is the in-depth investigation of the advantages of each technique and the gain of a better insight on the use of spatial context. For this purpose, an appropriate evaluation framework, which includes several different combinations of low-level features and classification algorithms, has been developed. Extensive experiments on six datasets of varying problem complexity have been conducted for investigating the influence of typical factors (such as the utilized visual features, the employed classifier, and the number of supported concepts) on the performance of each spatial context technique, while a detailed analysis of the obtained results is also given.
-
WIAMIS - Comparative evaluation of spatial context techniques for Semantic Image analysis
2009 10th Workshop on Image Analysis for Multimedia Interactive Services, 2009Co-Authors: G. Th. Papadopoulos, Carsten Saathoff, Marcin Grzegorzek, Vasileios Mezaris, Ioannis Kompatsiaris, Steffen Staab, M.g. StrintzisAbstract:In this paper, two approaches to utilizing contextual information in Semantic Image analysis are presented and comparatively evaluated. Both approaches make use of spatial context in the form of fuzzy directional relations. The first one is based on a Genetic Algorithm (GA), which is employed in order to decide upon the optimal Semantic Image interpretation by treating Semantic Image analysis as a global optimization problem. On the other hand, the second method follows a Binary Integer Programming (BIP) technique for estimating the optimal solution. Both spatial context techniques are evaluated with several different combinations of classifiers and low-level features, in order to demonstrate the improvements attained using spatial context in a number of different Image analysis schemes.
-
A Genetic Algorithm Approach to Ontology-driven Semantic Image Analysis
IET International Conference on Visual Information Engineering (VIE 2006), 2006Co-Authors: P. Panagi, G. Th. Papadopoulos, Ioannis Kompatsiaris, Stamatia Dasiopoulou, M.g. StrintzisAbstract:In this paper, a hybrid approach coupling ontologies and a genetic algorithm is presented for realizing knowledge-assisted Semantic Image analysis. The employed domain knowledge considers both high-level information referring to objects of the domain of interest and their spatial relations, and low-level information in terms of prototypical low-level visual descriptors. To account for the inherent in visual information ambiguity, fuzzy spatial relations have been employed and the corresponding domain ontology definitions are obtained though training. A genetic algorithm is applied to decide the most plausible annotation. Experiments with Images from the beach vacation domain demonstrate the performance of the proposed approach.
