With all-weather, all-time imaging characteristics of synthetic aperture radar (SAR), SAR image is applied widely. However, because of the SAR imaging mechanism, speckle noise is inevitably present in SAR images. In the translationinvariant second-generation bandelet transform (TIBT) domain, SAR image despeckling algorithm using edge detection and feature clustering (CFCM-TIBT) combines edge detection and fuzzy C-main clustering (FCM) operation is an efficient way to reduce speckle noise. However, the edges will be blurred by the algorithm. In order to improve the edge preservation ability and reduce false edge phenomenon. A new algorithm, named enhanced edge detection for SAR images despeckling in TIBT domain (CRFCM-TIBT), is proposed in this letter. It combines CFCM-TIBT and an improved edge detector, named C-RBED, which consists of Canny edge detector and rate-based edge detector (RBED). CRFCM-TIBT better realizes the extraction and separation of details that benefits from the ability of eliminating false edge pixels of C-RBED. The process of CRFCM-TIBT: C-RBED is first utilized to calculate and compare edge direction map (EDM) and edge strong map (ESM) several times. Then, TIBT and FCM are used to decompose and despeckle the edge-removed image, respectively. Finally, add the removed edges to the reconstructed image. In the two scenarios of Bedfordshire and Horse track, the Equivalent Look Number (ENL) and Edge Preservation Index (ESI) of this algorithm are better than traditional Lee filtering, FCM-TIBT and CFCM-TIBT. The experimental results show from the evaluation indicators and visual effects that the method proposed in this paper significantly improves ESI while ensuring a better ENL.
Synthetic aperture radar (SAR) target recognition is an important part of SAR image interpretation. It has been widely used in the field of national defense and national economy. At present, the feature extraction based on convolution is a local operation in space and time. The convolution kernel extracts the features in the local region with a certain step size. The global information of the picture can only be obtained by increasing the number of convolution layers. However, this method will not only increase the difficulty of model training but also makes the optimization of the network more difficult, and even leads to over fitting. Therefore, this paper proposes a SAR image target recognition algorithm based on GoogLeNet -NB, which combines accurate and effective GoogLeNet framework and non-local block(NB). By adding NB to GoogLeNet framework, we can capture more context information, enhance the correlation between pixels and regions, and improve the representation ability of the network. In order to verify the effectiveness of NB, NB is added in different positions of GoogLeNet framework for experimental comparison. Finally, MSTAR database is used to verify the algorithm. The experimental results show that the recognition effect of the GoogLeNet -NB algorithm model proposed in this paper is better than the traditional Alexnet algorithm and GoogLeNet algorithm. In the adding NB in different positions of GoogLeNet framework, adding NB in the front position of GoogLeNet can reduce the loss of information in the training process and obtain more global information. Therefore, GoogLeNet-preNB algorithm has certain advantages over GoogLeNet-postNB algorithm.
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.