Automatic and accurate segmentation of bladder walls and tumors in magnetic resonance imaging (MRI) is a challenging task, due to significant bladder shape variations, strong intensity inhomogeneity in urine and very high variability across tumors appearance. To tackle such issues, we propose to leverage the representation capacity of an improved U-Net networks using stacked dilated convolutions. The proposed structure includes stacked dilated convolutions to increase the receptive field without incurring gridding artifacts. In addition, we embed stacked dilated convolution network into the U-Net architecture, thus enabling extracting multi-scale features for segmentation of multi structures with different shapes and scales. Finally, we apply a focal loss function to make all classes contribute equally to the loss function in our model. Evaluations on T2-weighted MRI show the proposed model achieves a higher level of accuracy than state-of-the-art methods, with a mean Dice similarity coefficient of 0.95, 0.81 and 0.66 for inner wall, outer wall and tumor region segmentation, respectively. These results demonstrate a strong agreement with reference standards and a high performance gain compared with existing methods.
Object detection based on deep learning algorithms has been an important yet challenging research field in computer vision. The feature pyramid network has become a dominant network architecture in many detection applications because of its powerful feature learning ability for objects with varying scales. To address the challenges in detecting small and densely packed objects, this paper proposes an innovative object detection approach by combining the path aggregation scheme and the feature pyramid network into a unified framework. Specifically, we add a bottom-up branch with lateral connection onto the existing feature pyramid network and apply adaptive feature fusion strategy, which improves the detection performance for small and densely arranged objects in remote sensing images. Experiment results show that our proposed path aggregated feature pyramid network can improve the detection performance for diverse objects in aerial images.
We propose a fast multiscale face detector that boosts a set of SVM-based hierarchy classifiers constructed with two
heterogeneous features, i.e. Multi-block Local Binary Patterns (MB-LBP) and Speeded Up Robust Features (SURF), at
different image resolutions. In this hierarchical architecture, simple and fast classifiers using efficient MB-LBP
descriptors remove large parts of the background in low and intermediate scale layers, thus only a small percentage of
background patches look similar to faces and require a more accurate but slower classifier that uses distinctive SURF
descriptor to avoid false classifications in the finest scale. By propagating only those patterns that are not classified as
background, we can quickly decrease the amount of data need to be processed. To lessen the training burden of the
hierarchy classifier, in each scale layer, a feature selection scheme using Binary Particle Swarm Optimization (BPSO)
searches the entire feature space and filters out the minimum number of discriminative features that give the highest
classification rate on a validation set, then these selected distinctive features are fed into the SVM classifier. We
compared detection performance of the proposed face detector with other state-of-the-art methods on the CMU+MIT
face dataset. Our detector achieves the best overall detection performance. The training time of our algorithm is 60 times
faster than the standard Adaboost algorithm. It takes about 70 ms for our face detector to process a 320×240 image,
which is comparable to Viola and Jones' detector.
A novel contourlet-based local feature descriptor, called Local Contourlet Binary Pattern (LCBP), is developed in this
paper. LCBP provides a multiscale and multidirectional representation for images since it integrates contourlet transform
with local binary pattern operators. Allowing for the characteristics of marginal and conditional distributions of LCBP as
well as simplicity of the model itself, we model LCBP coefficients using a two-state HMT that is in accordance with the
intra-band, inter-band and inter-direction distributions of LCBP coefficients. Based on the LCBP-HMT model, we
further propose an object recognition method that extracts parameters of the LCBP-HMT model as features and
classifies the query sample by comparing the Kullback-Liebler distance between features of the query sample and that of
the prototype objects. Experimental results illustrate the superiority of the LCBP over traditional wavelet features and
raw statistical features of contourlet coefficients in terms of the discrimination performance.
A set of new invariant moment descriptors - wavelet moment invariants, which combine wavelet multiresolution analysis and moments invariants target recognition method, are proposed in this paper and their invariance also have been proved. Wavelet moment invariants take both advantages of the wavelet inherent property of multiresolution analysis and moment invariants quality of invariant to translation, scaling changes and rotation. Furthermore, studies of the effect of using different wavelet functions and their orders are carried out. Experimental results show that wavelet moment invariants derived from the wavelet function having proper vanishing moments, symmetry and compact support have the best discrimination performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.