Deep Learning Shape Priors for Object Segmentation

Chen, Fei; Yu, Huimin; Hu, Rong; Zeng, Xunxun

doi:10.1109/cvpr.2013.244

Cited by 66 publications

(50 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, each binary shape is the contour of a top-view drawing for a certain type of aircraft, with pixel values of the inner of the aircraft contour being filled with 255 and the outer of the aircraft contour being filled with 0, which can be seen in most of the shape prior-based method [3,12]. For example, Figure 5 shows the top-view drawing of an aircraft's and the corresponding binary shape.…”

Section: Shape Prior Descriptionmentioning

confidence: 99%

“…Here, a classical probabilistic shape representation method [12,16] is used as the basic function and is modified via combining the shape term and the scattering term, which is defined as follows:…”

Section: Pose Reconstruction and Optimizationmentioning

confidence: 99%

“…Inside, u is the processed image and Ω τ is the scattering region, which is Ω τ = {x : q ≥ τ} with τ a selected threshold. Reconstruction results are obtained by optimize the energy function with an iterative minimization procedure, in which the approximate inference of DBM [12] is introduced for the calculation of each layer of hidden units, and split Bregman, a traditional algorithm for convex optimization, is used to calculate the shape. Details of the optimization process are summarized in Algorithm 1, while Algorithm 2 is the details of Split Bregman method to solve the problem of minimizing q in Algorithm 1 step 2.3.…”

Section: Pose Reconstruction and Optimizationmentioning

confidence: 99%

“…However, the calculation of P(v; θ) is difficult. Therefore, approximate inference is used via an efficient Gibbs sampling, which is detailed in [8,12] and is shown in Figure 9. The energy function of the three-layered shape model is defined as:…”

Section: Shape Prior Modelsmentioning

confidence: 99%

See 3 more Smart Citations

Aircraft Reconstruction in High-Resolution SAR Images Using Deep Shape Prior

Dou

Diao

Sun

et al. 2017

IJGI

View full text Add to dashboard Cite

Contour shapes are important features. An accurate contour shape of a target can provide important prior information for applications, such as target recognition, which can improve the accuracy of target interpretation. In this paper, a synthetic aperture radar (SAR) target reconstruction method is proposed, which can be used to reconstruct the target by using shape priors to perform an accurate extraction of the contour shape feature. The method is divided into two stages. In the deep shape prior extraction stage, a generative deep learning modelling method is used to obtain deep shape priors. In the reconstruction stage, a novel coarse-to-fine pose estimation method combined with an optimization algorithm is proposed, which integrates deep shape priors into the process of reconstruction. Specifically, to address the issue of object rotation, candidate poses are obtained using the coarse pose estimation method, which avoids an exhaustive search of each pose. In addition, an energy function composed of a scattering term and shape term to combine the fine pose estimation, is constructed and optimized via an iterative optimization algorithm to achieve the goal of object reconstruction. To the best of our knowledge, this is the first time shape priors have been used to extract shape features of SAR targets. Experiments are conducted on a data set acquired by TerraSAR-X images and the results demonstrate the high accuracy and robustness of the proposed method.

show abstract

Section: Shape Prior Descriptionmentioning

confidence: 99%

Section: Pose Reconstruction and Optimizationmentioning

confidence: 99%

Section: Pose Reconstruction and Optimizationmentioning

confidence: 99%

Section: Shape Prior Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Aircraft Reconstruction in High-Resolution SAR Images Using Deep Shape Prior

Dou

Diao

Sun

et al. 2017

IJGI

View full text Add to dashboard Cite

show abstract

“…The labels for this layer are then pooled into a raster structure, enabling them to use a RBM to provide shape priors. Another attempt is to combine Deep Boltzmann Machines shape prior with a variational segmentation model [7], showing the effectiveness of strong shape priors for simple object segmentation. In all of the above approaches, the only inference pathway between the image features x and the hidden variables h representing shapes leads through the labels assigned to image pixels y while the shape only works as a prior.…”

Section: Related Workmentioning

confidence: 99%

Max-Margin Boltzmann Machines for Object Segmentation

Yang

Safar

Yang

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

We present Max-Margin Boltzmann Machines (MMBMs) for object segmentation. MMBMs are essentially a class of Conditional Boltzmann Machines that model the joint distribution of hidden variables and output labels conditioned on input observations. In addition to image-to-label connections, we build direct image-to-hidden connections to facilitate global shape prediction, and thus derive a simple Iterated Conditional Modes algorithm for efficient maximum a posteriori inference. We formulate a max-margin objective function for discriminative training, and analyze the effects of different margin functions on learning. We evaluate MMBMs using three datasets against state-of-the-art methods to demonstrate the strength of the proposed algorithms.

show abstract

Enhancing level set brain tumor segmentation using fuzzy shape prior information and deep learning

Khosravanian

Rahmanimanesh

Keshavarzi

et al. 2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) brain tumor segmentation is a crucial task for clinical treatment. However, it is challenging owing to variations in type, size, and location of tumors. In addition, anatomical variation in individuals, intensity non-uniformity, and noises adversely affect brain tumor segmentation. To address these challenges, an automatic region-based brain tumor segmentation approach is presented in this paper which combines fuzzy shape prior term and deep learning. We define a new energy function in which an Adaptively Regularized Kernel-Based Fuzzy C-Means (ARKFCM) Clustering algorithm is utilized for inferring the shape of the tumor to be embedded into the level set method. In this way, some shortcomings of traditional level set methods such as contour leakage and shrinkage have been eliminated. Moreover, a fully automated method is achieved by using U-Net to obtain the initial contour, reducing sensitivity to initial contour selection. The proposed method is validated on the BraTS 2017 benchmark dataset for brain tumor segmentation. Average values of Dice, Jaccard, Sensitivity and specificity are 0.93 ± 0.03, 0.86 ± 0.06, 0.95 ± 0.04, and 0.99 ± 0.003, respectively. Experimental results indicate that the proposed method outperforms the other state-of-theart methods in brain tumor segmentation.

show abstract

Deep Learning Shape Priors for Object Segmentation

Abstract: In this paper we introduce a new shape-driven approach for object segmentation.

Cited by 66 publications

References 20 publications

Aircraft Reconstruction in High-Resolution SAR Images Using Deep Shape Prior

Aircraft Reconstruction in High-Resolution SAR Images Using Deep Shape Prior

Max-Margin Boltzmann Machines for Object Segmentation

Enhancing level set brain tumor segmentation using fuzzy shape prior information and deep learning

Contact Info

Product

Resources

About