Fine-grained image classification has the characteristic of large inter-class differences and small intra-class differences. The challenge lies in the fact that different subclasses have similar structures and minimal differences. The key to distinguishing different subclasses lies in differentiating certain components of the image subject, such as the beak, claws, and tail of a bird, and there is also a certain relationship between these components. With the application of Transformer in visual processing, researchers have discovered the inherent advantages of Transformer in establishing dependencies. This paper fully considers the characteristics of Transformer in mining contextual relationships and proposes a fine-grained image classification algorithm based on Transformer and patch-selection mechanism for extracting component features.
The purpose of visual tracking is to associate the target object in a continuous video frame. In recent years, the method based on the kernel correlation filter has become the research hotspot. However, the algorithm still has some problems such as video capture equipment fast jitter, tracking scale transformation. In order to improve the ability of scale transformation and feature description, this paper has carried an innovative algorithm based on the multi feature fusion and multi-scale transform. The experimental results show that our method solves the problem that the target model update when is blocked or its scale transforms. The accuracy of the evaluation (OPE) is 77.0%, 75.4% and the success rate is 69.7%, 66.4% on the VOT and OTB datasets. Compared with the optimal one of the existing target-based tracking algorithms, the accuracy of the algorithm is improved by 6.7% and 6.3% respectively. The success rates are improved by 13.7% and 14.2% respectively.
Super-resolution image reconstruction is an effective method to improve the image quality. It has important research significance in the field of image processing. However, the choice of the dictionary directly affects the efficiency of image reconstruction. A sparse representation theory is introduced into the problem of the nearest neighbor selection. Based on the sparse representation of super-resolution image reconstruction method, a super-resolution image reconstruction algorithm based on multi-class dictionary is analyzed. This method avoids the redundancy problem of only training a hyper complete dictionary, and makes the sub-dictionary more representatives, and then replaces the traditional Euclidean distance computing method to improve the quality of the whole image reconstruction. In addition, the ill-posed problem is introduced into non-local self-similarity regularization. Experimental results show that the algorithm is much better results than state-of-the-art algorithm in terms of both PSNR and visual perception.
It is difficult to get ideal effect that research on target enhancement and segmentation are developed by simply using
features of edge, texture and gray in complex background. Studies on target enhancement and segmentation have always
been the research focus for a long time. Considering known regular shape target in complex background, an approach of
target enhancement and segment based on shape feature is proposed. According to analyze the shape of regular target
such as line and arc, first, Top-hat is used to enhance target. Then, threshold segmentation method, thinning and
deburring are following. Third, a new image is acquired by the Hough transform which can find points in edge image
similar with target in shape and property. The very points would be reserved. Moreover, the new image acquired is the
initial condition of reconstruction, the original image is limit condition, and target enhancement is achieved by grayscale
morphological reconstruction. Finally, binaryzation processing of image was used to segment target. Experimental
results demonstrate that the proposed algorithm has an encouraging 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.