Small Target Recognition Using Dynamic Time Warping and Visual Attention

2020 ◽  
Author(s):  
Xinpeng Zhang ◽  
Jigang Wu ◽  
Min Meng
Keyword(s):  
Visual Attention ◽  
Gabor Wavelet ◽  
Local Contrast ◽  
Small Target ◽  
Time Warping ◽  
The Public ◽  
The Arts ◽  
Dynamic Time ◽  
Small Targets ◽  
Public Datasets

Abstract Microaneurysm is a kind of small targets in color retinal image, and it is an essential work to recognize the small target for the early diagnosis of diabetic retinopathy. This paper proposes an efficient method to accurately recognize microaneurysm. A symmetric extended curvature Gabor wavelet is presented to generate candidate objects, where some novel features are extracted for classification. A kind of statistic features is generated to distinguish between microaneurysm and thin vessels, in terms of the shape similarity of cross-section profiles. Furthermore, the visual attention-based features are proposed to compute local contrast of small targets in complex background. Random undersampling with AdaBoost (RUSBoost) classifier is employed to discriminate true microaneurysm from an overwhelming amount of candidate objects. Experimental results demonstrate that the proposed method achieves significant sensitivity and accuracy on the public datasets, in comparison to the state-of-the-arts.

scholarly journals DTW–RADON-BASED SHAPE DESCRIPTOR FOR PATTERN RECOGNITION

2013 ◽  
Vol 27 (03) ◽  
pp. 1350008 ◽  
Author(s):  
K. C. SANTOSH ◽  
BART LAMIROY ◽  
LAURENT WENDLING
Keyword(s):  
Pattern Recognition ◽  
Dynamic Time Warping ◽  
Recognition Performance ◽  
Shape Descriptor ◽  
Shape Descriptors ◽  
Time Warping ◽  
Recognition Method ◽  
Dynamic Time ◽  
Public Datasets ◽  
Comprehensive Study

In this paper, we present a pattern recognition method that uses dynamic programming for the alignment of Radon features. The key characteristic of the method is to use dynamic time warping (DTW) to match corresponding pairs of the Radon features for all possible projections. Thanks to DTW, we avoid compressing the feature matrix into a single vector which would otherwise miss information. To reduce the possible number of matchings, we rely on a initial normalization based on the pattern orientation. A comprehensive study is made using major state-of-the-art shape descriptors over several public datasets of shapes such as graphical symbols (both printed and hand-drawn), handwritten characters and footwear prints. In all tests, the method proves its generic behavior by providing better recognition performance. Overall, we validate that our method is robust to deformed shape due to distortion, degradation and occlusion.

scholarly journals Infrared Small Target Detection via Modified Random Walks

2018 ◽  
Vol 10 (12) ◽  
pp. 2004 ◽  
Author(s):  
Chaoqun Xia ◽  
Xiaorun Li ◽  
Liaoying Zhao
Keyword(s):  
Random Walks ◽  
Target Detection ◽  
Detection Algorithm ◽  
Local Contrast ◽  
Small Target ◽  
Global Uniqueness ◽  
Dimensional Image ◽  
Small Target Detection ◽  
Small Targets ◽  
Infrared Small Target

Infrared small target detection under intricate background and heavy noise is one of the crucial tasks in the field of remote sensing. Conventional algorithms can fail in detecting small targets due to the low signal-to-noise ratios of the images. To solve this problem, an effective infrared small target detection algorithm inspired by random walks is presented in this paper. The novelty of our contribution involves the combination of the local contrast feature and the global uniqueness of the small targets. Firstly, the original pixel-wise image is transformed into an multi-dimensional image with respect to the local contrast measure. Secondly, a reconstructed seeds selection map (SSM) is generated based on the multi-dimensional image. Then, an adaptive seeds selection method is proposed to automatically select the foreground seeds potentially placed in the areas of the small targets in the SSM. After that, a confidence map is constructed using a modified random walks (MRW) algorithm to represent the global uniqueness of the small targets. Finally, we segment the targets from the confidence map by utilizing an adaptive threshold. Extensive experimental evaluation results on a real test dataset demonstrate that our algorithm is superior to the state-of-the-art algorithms in both target enhancement and detection performance.

scholarly journals Detection of Small Target Using Schatten 1/2 Quasi-Norm Regularization with Reweighted Sparse Enhancement in Complex Infrared Scenes

2019 ◽  
Vol 11 (17) ◽  
pp. 2058 ◽  
Author(s):  
Fei Zhou ◽  
Yiquan Wu ◽  
Yimian Dai ◽  
Peng Wang
Keyword(s):  
Target Detection ◽  
Low Rank ◽  
Small Target ◽  
L1 Norm ◽  
Small Target Detection ◽  
Detection Algorithms ◽  
The Arts ◽  
Rank Matrix ◽  
Adaptive Penalty ◽  
Small Targets

In uniform infrared scenes with single sparse high-contrast small targets, most existing small target detection algorithms perform well. However, when encountering multiple and/or structurally sparse targets in complex backgrounds, these methods potentially lead to high missing and false alarm rate. In this paper, a novel and robust infrared single-frame small target detection is proposed via an effective integration of Schatten 1/2 quasi-norm regularization and reweighted sparse enhancement (RS1/2NIPI). Initially, to achieve a tighter approximation to the original low-rank regularized assumption, a nonconvex low-rank regularizer termed as Schatten 1/2 quasi-norm (S1/2N) is utilized to replace the traditional convex-relaxed nuclear norm. Then, a reweighted l1 norm with adaptive penalty serving as sparse enhancement strategy is employed in our model for suppressing non-target residuals. Finally, the small target detection task is reformulated as a problem of nonconvex low-rank matrix recovery with sparse reweighting. The resulted model falls into the workable scope of inexact augment Lagrangian algorithm, in which the S1/2N minimization subproblem can be efficiently solved by the designed softening half-thresholding operator. Extensive experimental results on several real infrared scene datasets validate the superiority of the proposed method over the state-of-the-arts with respect to background interference suppression and target extraction.

scholarly journals Gated Object-Attribute Matching Network for Detailed Image Caption

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Jing Yun ◽  
ZhiWei Xu ◽  
GuangLai Gao
Keyword(s):  
Visual Attention ◽  
Matching Network ◽  
The Public ◽  
Attribute Matching ◽  
Public Datasets ◽  
Object Attribute ◽  
Image Caption ◽  
Semantic Attributes

Image caption enables computers to generate a text description of images automatically. However, the generated description is not good enough recently. Computers can describe what objects are in the image but cannot give more details about these objects. In this study, we present a novel image caption approach to give more details when describing objects. In detail, a visual attention-based LSTM is used to find the objects, as well as a semantic attention-based LSTM is used for giving semantic attributes. At last, a gated object-attribute matching network is used to match the objects to their semantic attributes. The experiments on the public datasets of Flickr30k and MSCOCO demonstrate that the proposed approach improved the quality of the image caption, compared with the most advanced methods at present.

Template Protection and Renewability for Dynamic Time Warping Based Biometric Signature Verification

2009 ◽  
Vol 1 (4) ◽  
pp. 40-57 ◽  
Author(s):  
Emanuele Maiorana ◽  
Patrizio Campisi ◽  
Alessandro Neri
Keyword(s):  
Dynamic Time Warping ◽  
Time Warping ◽  
The Public ◽  
Protection Scheme ◽  
Signature Database ◽  
Template Protection ◽  
On Line ◽  
Authentication System ◽  
Matching Strategy ◽  
Dynamic Time

In this article, the authors propose a protected on-line signature based biometric authentication system, where the original signature templates are protected by transforming them in a non-invertible way. Recovering the original biometrics from the stored data is thus computationally as hard as random guessing them. The transformed templates are compared employing a Dynamic Time Warping (DTW) matching strategy. The reported experimental results, evaluated on the public MCYT signature database, show that the achievable recognition rates are only slightly affected by the proposed protection scheme, which is able to guarantee the desired security and renewability for the considered biometrics.

Sign in / Sign up

Export Citation Format

Share Document