The Experts below are selected from a list of 37407 Experts worldwide ranked by ideXlab platform
Zhuowen Tu - One of the best experts on this subject based on the ideXlab platform.
-
holistically nested edge detection
International Journal of Computer Vision, 2017Co-Authors: Zhuowen TuAbstract:We develop a new edge detection algorithm that addresses two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning. Our proposed method, holistically-nested edge detection (HED), performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets. HED automatically learns rich hierarchical representations (guided by deep supervision on side responses) that are important in order to resolve the challenging ambiguity in edge and Object Boundary detection. We significantly advance the state-of-the-art on the BSDS500 dataset (ODS F-score of 0.790) and the NYU Depth dataset (ODS F-score of 0.746), and do so with an improved speed (0.4 s per image) that is orders of magnitude faster than some CNN-based edge detection algorithms developed before HED. We also observe encouraging results on other Boundary detection benchmark datasets such as Multicue and PASCAL-Context.
-
Holistically-Nested Edge Detection
International Journal of Computer Vision, 2017Co-Authors: Saining Xie, Zhuowen TuAbstract:We develop a new edge detection algorithm that tackles two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning. Our proposed method, holistically-nested edge detection (HED), performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets. HED automatically learns rich hierarchical representations (guided by deep supervision on side responses) that are important in order to approach the human ability resolve the challenging ambiguity in edge and Object Boundary detection. We significantly advance the state-of-the-art on the BSD500 dataset (ODS F-score of .782) and the NYU Depth dataset (ODS F-score of .746), and do so with an improved speed (0.4 second per image) that is orders of magnitude faster than some recent CNN-based edge detection algorithms.
Zhenjiang Miao - One of the best experts on this subject based on the ideXlab platform.
-
sketch based image retrieval through hypothesis driven Object Boundary selection with hlr descriptor
IEEE Transactions on Multimedia, 2015Co-Authors: Shu Wang, Jian Zhang, Tony X Han, Zhenjiang MiaoAbstract:The appearance gap between sketches and photo- realistic images is a fundamental challenge in sketch-based image retrieval (SBIR) systems. The existence of noisy edges on photo- realistic images is a key factor in the enlargement of the appearance gap and significantly degrades retrieval performance . To bridge the gap, we propose a framework consisting of a new line segment -based descriptor named histogram of line relationship (HLR) and a new noise impact reduction algorithm known as Object Boundary selection . HLR treats sketches and extracted edges of photo- realistic images as a series of piece-wise line segments and captures the relationship between them. Based on the HLR, the Object Boundary selection algorithm aims to reduce the impact of noisy edges by selecting the shaping edges that best correspond to the Object boundaries. Multiple hypotheses are generated for descriptors by hypothetical edge selection. The selection algorithm is formulated to find the best combination of hypotheses to maximize the retrieval score; a fast method is also proposed. To reduce the distraction of false matches in the scoring process, two constraints on spatial and coherent aspects are introduced . We tested the HLR descriptor and the proposed framework on public datasets and a new image dataset of three million images, which we recently collected for SBIR evaluation purposes. We compared the proposed HLR with state-of-the-art descriptors (SHoG, GF-HOG). The experimental results show that our HLR descriptor outperforms them. Combined with the Object Boundary selection algorithm, our framework significantly improves SBIR performance.
Shu Wang - One of the best experts on this subject based on the ideXlab platform.
-
sketch based image retrieval through hypothesis driven Object Boundary selection with hlr descriptor
IEEE Transactions on Multimedia, 2015Co-Authors: Shu Wang, Jian Zhang, Tony X Han, Zhenjiang MiaoAbstract:The appearance gap between sketches and photo- realistic images is a fundamental challenge in sketch-based image retrieval (SBIR) systems. The existence of noisy edges on photo- realistic images is a key factor in the enlargement of the appearance gap and significantly degrades retrieval performance . To bridge the gap, we propose a framework consisting of a new line segment -based descriptor named histogram of line relationship (HLR) and a new noise impact reduction algorithm known as Object Boundary selection . HLR treats sketches and extracted edges of photo- realistic images as a series of piece-wise line segments and captures the relationship between them. Based on the HLR, the Object Boundary selection algorithm aims to reduce the impact of noisy edges by selecting the shaping edges that best correspond to the Object boundaries. Multiple hypotheses are generated for descriptors by hypothetical edge selection. The selection algorithm is formulated to find the best combination of hypotheses to maximize the retrieval score; a fast method is also proposed. To reduce the distraction of false matches in the scoring process, two constraints on spatial and coherent aspects are introduced . We tested the HLR descriptor and the proposed framework on public datasets and a new image dataset of three million images, which we recently collected for SBIR evaluation purposes. We compared the proposed HLR with state-of-the-art descriptors (SHoG, GF-HOG). The experimental results show that our HLR descriptor outperforms them. Combined with the Object Boundary selection algorithm, our framework significantly improves SBIR performance.
Changhong Wang - One of the best experts on this subject based on the ideXlab platform.
-
gradient vector flow active contours with prior directional information
Pattern Recognition Letters, 2010Co-Authors: Shuqun Zhang, Qingshuang Zeng, Changhong WangAbstract:Active contours, or snakes, have been widely used in image processing and computer vision for image segmentation and Object tracking. However, they usually have poor performance in segmenting images with complex Object shape and complex background, and also in dealing with the issue of weak-edge-leakage. To guide the front of active contour toward the desired Object Boundary and prevent it from moving over the weak edges with strong neighbors, we present a novel external force field, referred to as gradient and direction vector flow (G&DVF), which integrates the gradient vector flow (GVF) and the prior directional information provided by a user. The proposed method is sufficiently general and simple to implement. The experiments conducted on image segmentation demonstrate that the proposed method is insensitive to image clutters/noise and capable of driving the fronts of active contours to conform to complex shapes and addressing the issue of weak-edge-leakage in some cases.
Daniel L Rubin - One of the best experts on this subject based on the ideXlab platform.
-
robust noise region based active contour model via local similarity factor for image segmentation
Pattern Recognition, 2017Co-Authors: Qiang Chen, Luis De Sisternes, Zexuan Ji, Ze Ming Zhou, Daniel L RubinAbstract:Abstract Image segmentation using a region-based active contour model could present difficulties when its noise distribution is unknown. To overcome this problem, this paper proposes a novel region-based model for the segmentation of Objects or structures in images by introducing a local similarity factor, which relies on the local spatial distance within a local window and local intensity difference to improve the segmentation results. By using this local similarity factor, the proposed method can accurately extract the Object Boundary while guaranteeing certain noise robustness. Furthermore, the proposed algorithm completely avoids the pre-processing steps typical of region-based contour model segmentation, resulting in a higher preservation of image details. Experiments performed on synthetic images and real word images demonstrate that the proposed algorithm, as compared with the state-of-art algorithms, is more efficient and robust to higher noise level manifestations in the images.
