While convolutional neural networks have shown promise in medical image registration, their inherent complexity limits their registration speed, particularly for surgical applications. Additionally, traditional feature-based matching methods struggle with multi-modal forearm image registration due to the simplicity of forearm skin textures. To address these issues, we propose a robust forearm feature point extraction method based on the forearm’s structural invariance. We combine this method with thin plate spline interpolation to achieve multi-modal forearm registration. Our approach introduces the Forearm Feature Representation Curve (FFRC) and the Multi-Modal Image Registration Framework (FAM) for aligning forearm images with digital anatomical models. FFRC identifies feature points based on forearm structural characteristics, and FAM employs FFRC for matching point pre-screening before applying an affine transformation. For deformable registration which adds Thin Plate Spline (FAM-TPS) uses the matched points as control points. In our experiments, both FAM and FAM-TPS demonstrate high registration accuracy, with FAM-TPS outperforming conventional feature-based methods. Our framework excels at registering forearm images with varying rotation angles, and we have observed a strong correlation between the feature curve’s peak value and the rotation angle. These results affirm the effectiveness of our approach in achieving precise and resilient registration.
Salient object detection(SOD) is particularly important especially for applications like autonomous driving which requires real-time inference speed and high performance. Most of the previous works however focus on global object accuracy but not on the connection of local objects. In this paper, we first process the cityscapes dataset into a saliency detection dataset, which focuses on distinguishing between moving objects on the road and moving objects on the sidewalk. In order to enable the saliency detection network to learn the connection between the target categories, we propose a gated convolution(GCov), which can control the input of the feature layer. For the evaluation of SOD, we combine a variety of loss functions to form a mixed loss. Equipped with the GCov and mixed loss, the proposed architecture is able to effectively distinguish the difference in the semantics of the location for the targets of the same category. Experimental results on the dataset show that our method has competitive results compared with other saliency detection networks.
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.