Search

Offline signature verification is a widely used biometric method in finance, law, and administrative procedures. However, existing deep convolutional neural network models perform poorly on signature datasets that span different regions and ethnic people, while also suffering from problems such as large parameter counts and slow inference speeds. To address these issues, we propose an improved residual network model (FC-ResNet). This model introduces a convolutional block attention module into the classical residual network to adapt to the diversity and variability of signatures, while also compressing the model for lightweight deployment. Due to the lack of public, offline handwritten signature datasets for ethnic people, we collected a large-scale offline handwritten signature dataset, including genuine signatures and forged signatures in Chinese, Uyghur, Kazakh, and Kirgiz, totaling 38,400 images. Our FC-ResNet model achieved an accuracy of over 96% for each language in our self-built dataset, as well as accuracy rates of 96.21%, 98.42%, and 97.28% on the public datasets CEDAR, BHSig-B, and BHSig-H, respectively. Based on the above experimental results, our proposed model demonstrates great potential for both public and self-built signature datasets, while also exhibiting significant advantages in lightweight model deployment. We believe that this work can provide a feasible solution for ethnic people signature verification. [ABSTRACT FROM AUTHOR]

Implicit sentiment identification is a significant classical task in text analysis. Graph neural networks (GNNs) have recently been successful in implicit sentiment identification, but the current approaches still suffer from two problems. On the one hand, there is a lack of structural information carried by the single-view graph structure of implicit sentiment texts to accurately capture obscure sentiment expressions. On the other hand, the predefined fixed graph structure may contain some noisy edges that cannot represent semantic information using an accurate topology, which can seriously impair the performance of implicit sentiment analysis. To address these problems, we introduce a knowledge-fusion-based iterative graph structure learning framework (KIG). Specifically, for the first problem, KIG constructs graph structures based on three views, namely, co-occurrence statistics, cosine similarity, and syntactic dependency trees through prior knowledge, which provides rich multi-source information for implicit sentiment analysis and facilitates the capture of implicit obscure sentiment expressions. To address the second problem, KIG innovatively iterates the three original graph structures and searches for their implicit graph structures to better fit the data themselves to optimize the downstream implicit sentiment analysis task. We compared our method with the mainstream implicit sentiment identification methods on two publicly available datasets, and ours outperformed both benchmark models. The accuracy, recall, and F1 values of KIG on the Pun of the Day dataset reached 89.2%, 93.7%, and 91.1%, respectively. Extensive experimental results demonstrate the superiority of our proposed method for the implicit sentiment identification task. [ABSTRACT FROM AUTHOR]

In multilingual scene text understanding, script identification is an important prerequisite step for text image recognition. Due to the complex background of text images in natural scenes, severe noise, and common symbols or similar layouts in different language families, the problem of script identification has not been solved. This paper proposes a new script identification method based on ConvNext improvement, namely EA-ConvNext. Firstly, the method of generating an edge flow map from the original image is proposed, which increases the number of scripts and reduces background noise. Then, based on the feature information extracted by the convolutional neural network ConvNeXt, a coordinate attention module is proposed to enhance the description of spatial position feature information in the vertical direction. The public dataset SIW-13 has been expanded, and the Uyghur script image dataset has been added, named SIW-14. The improved method achieved identification rates of 97.3%, 93.5%, and 92.4% on public script identification datasets CVSI-2015, MLe2e, and SIW-13, respectively, and 92.0% on the expanded dataset SIW-14, verifying the superiority of this method. [ABSTRACT FROM AUTHOR]

Problems such as complex image backgrounds, low image quality, diverse text forms, and similar or common character layouts in different script categories in natural scenes pose great challenges to scene script identification. This paper proposes a new Res2Net-based improved script identification method, namely FAS-Res2Net. In the feature extraction part, the feature pyramid network (FPN) module is introduced, which is beneficial to aggregate the geometric feature information extracted by the shallow network and the semantic feature information extracted by the deep network. Integrating the Adaptive Spatial Feature Fusion (ASFF) module is beneficial to obtain local feature information for optimal weight fusion. In addition, the global feature information of the image is extracted by introducing the swin transformer coding block, which makes the extracted feature information more abundant. In the classification part, the convolutional classifier is used to replace the traditional Linear classification, and the classification confidence of each category is output, which improves the identification efficiency. The improved algorithm achieved identification rates of 94.7% and 96.0% on public script identification datasets SIW-13 and CVSI-2015, respectively, which verified the superiority of the method. [ABSTRACT FROM AUTHOR]

Target tracking algorithms based on deep learning have achieved good results in public datasets. Among them, the network tracking algorithm based on Siamese tracking has a high accuracy and fast speed, which has attracted significant attention. However, the Siamese tracker uses the AlexNet network as its backbone and the network layers are relatively shallow, so it does not make full use of the ability of the deep neural network. If only the backbones of target tracking are replaced, there will be no obvious improvement, such as in the cases of ResNet and Inception. Therefore, this paper designs a wider and deeper network structure. At a wider level, a mechanism that can adaptively adjust the receptive field (RF) size is designed. Firstly, multiple branches are divided by the split operator, and each branch has a different size of kernel corresponding to a different size of RF; then, the fuse operator is used to fuse the information of each branch to obtain the selection weights; and finally, according to the selection, the aggregation feature map is weighted. At a deeper level, a new kind of residual models is designed. The channel is simplified by pruning in order to improve the tracking speed. According to the above, a wider and deeper Siamese network was proposed in this paper. The experimental results show that the structure proposed in this paper achieves a good tracking effect and real-time performance on six kinds of datasets. The proposed tracker achieves an SUC and Prec of LaSOT of 0.569 and 0.571, respectively. [ABSTRACT FROM AUTHOR]

Most children's mice are designed based on appearance, without consideration of the child's comfort skeletal structure. This paper proposes a mouse design more suitable for children, considering ergonomic, physiological and psychological factors. The characteristics of children's hands and fingers were summarised and statistically analysed to propose a design built on improving the traditional mouse to better suit children's use. Experimental data analysis showed that the proposed mouse is more suitable for children's palm sizes, making the user more comfortable, and increasing practical value. Abbreviations: Traditional mouse(TM); new mouse(NM) [ABSTRACT FROM AUTHOR]

Analysis is one of the importent steps of computer forensics. The most popular analyzing tools, such as EnCase and FTK, are suitable for processing information in English or in Chinese. If the original evidence is in other scripts such as Uyghur, Kazakh, Kyrgyz (hereafter: UKK), it will be much more difficult to identify, filter, and fulfill other kinds of analyzing. In this paper, the variety of UKK characters, the diversity of its encoding scheme and the particularity of the denotation for UKK in different documents are analyzed in detail. Then, it is designed and implemented the efficient tool for digital evidences in UKK according to the nature of UKK and its encoding situation. Finally, the convenience and efficiency of the system is proved by the many experiments and actual applications. [ABSTRACT FROM AUTHOR]

Text representation is an essential part of text classification. The BOW is the most common approach for text representation. But an obvious disadvantage of BOW method is word independent assumption which ignores the more evidential information for text classification. LDA (Latent Dirichlet Allocation) is a recently proposed model which extracts latent topics from text data and widely used in text mining. However, the input to the LDA is also the BOW representation of a document collection, where word counts are preserved but word order is lost. In order to improve the topic quality of Uyghur text learned by LDA, we present a novel method to extract discriminative and semantically complete Uyghur bigrams from the Uyghur text corpus statistically, and integrate top-ranked bigrams into BOW representation of Uyghur text collection before learning the LDA topic model. We construct a text classification method based on the bigram incorporated topic representation of Uyghur text set. Experiments on Uyghur text collection showed that inclusion of Uyghur Bigrams in LDA topic model, improves the topic quality and classification performance of Uyghur text. [ABSTRACT FROM AUTHOR]

Document images of various scripts must be identified and processed in today's international environment. As the front-end technology of Optical Character Recognition (OCR), script identification is an indispensable part of automatic document image analysis. Aiming at the nature of rich texture features of document images, a 3-level Nonsubsampled Contourlet Transform (NSCT) was used to extract 30- dimensional texture features in this paper. A Support Vector Machine (SVM) and K Nearest Neighbor (KNN) classifier were used for classification. A total of 10,000 document images in 10 kinds of Central Asian scripts--Arabic, Russian, Tibetan, Chinese, Uyghur, English, Mongolian, Kyrgyzstan, Kazakhstan, and Turkish--were classified. The identification efficiency of SVM and KNN was analyzed and compared, with the result that the SVM classifier obtained 99.5% average accuracy, a higher accuracy than KNN, during the experiment. The validity of the proposed method was proved by comparing the Wavelet Transforms (WT) and Local Binary Patterns (LBP) of these two script-identification methods. [ABSTRACT FROM AUTHOR]