In recent years,anomaly detection has attracted much attention in industrial production.As traditional anomaly detection methods usually rely on direct comparison of samples,they often ignore the intrinsic relationshi...In recent years,anomaly detection has attracted much attention in industrial production.As traditional anomaly detection methods usually rely on direct comparison of samples,they often ignore the intrinsic relationship between samples,resulting in poor accuracy in recognizing anomalous samples.To address this problem,a knowledge distillation anomaly detection method based on feature reconstruction was proposed in this study.Knowledge distillation was performed after inverting the structure of the teacher-student network to avoid the teacher-student network sharing the same inputs and similar structure.Representability was improved by using feature splicing to unify features at different levels,and the merged features were processed and reconstructed using an improved Transformer.The experimental results show that the proposed method achieves better performance on the MVTec dataset,verifying its effectiveness and feasibility in anomaly detection tasks.This study provides a new idea to improve the accuracy and efficiency of anomaly detection.展开更多
In the daily application of an iris-recognition-at-a-distance(IAAD)system,many ocular images of low quality are acquired.As the iris part of these images is often not qualified for the recognition requirements,the mor...In the daily application of an iris-recognition-at-a-distance(IAAD)system,many ocular images of low quality are acquired.As the iris part of these images is often not qualified for the recognition requirements,the more accessible periocular regions are a good complement for recognition.To further boost the performance of IAAD systems,a novel end-to-end framework for multi-modal ocular recognition is proposed.The proposed framework mainly consists of iris/periocular feature extraction and matching,unsupervised iris quality assessment,and a score-level adaptive weighted fusion strategy.First,ocular feature reconstruction(OFR)is proposed to sparsely reconstruct each probe image by high-quality gallery images based on proper feature maps.Next,a brand new unsupervised iris quality assessment method based on random multiscale embedding robustness is proposed.Different from the existing iris quality assess-ment methods,the quality of an iris image is measured by its robustness in the embedding space.At last,the fusion strategy exploits the iris quality score as the fusion weight to coalesce the complementary information from the iris and periocular regions.Extensive experi-mental results on ocular datasets prove that the proposed method is obviously better than unimodal biometrics,and the fusion strategy can significantly improve therecognition performance.展开更多
The emergence of new media in various fields has continuously strengthened the social aspect of social media.Netizens tend to express emotions in social interactions,and many people even use satire,metaphors,and other...The emergence of new media in various fields has continuously strengthened the social aspect of social media.Netizens tend to express emotions in social interactions,and many people even use satire,metaphors,and other techniques to express some negative emotions,it is necessary to detect sarcasm in social comment data.For sarcasm,the more reference data modalities used,the better the experimental effect.This paper conducts research on sarcasm detection technology based on image-text fusion data.To effectively utilize the features of each modality,a feature reconstruction output algorithm is proposed.This algorithm is based on the attention mechanism,learns the low-rank features of another modality through cross-modality,the eigenvectors are reconstructed for the corresponding modality through weighted averaging.When only the image modality in the dataset is used,the preprocessed data has outstanding performance in reconstructing the output model,with an accuracy rate of 87.6%.When using only the text modality data in the dataset,the reconstructed output model is optimal,with an accuracy rate of 85.2%.To improve feature fusion between modalities for effective classification,a weight adaptive learning algorithm is used.This algorithm uses a neural network combined with an attention mechanism to calculate the attention weight of each modality to achieve weight adaptive learning purposes,with an accuracy rate of 87.9%.Extensive experiments on a benchmark dataset demonstrate the superiority of our proposed model.展开更多
In the prosthetic socket design, aimed at the high cost and radiation deficiency caused by CT scanning which is a routine technique to obtain the cross-sectional image of the residual limb, a new ultrasonic scanning m...In the prosthetic socket design, aimed at the high cost and radiation deficiency caused by CT scanning which is a routine technique to obtain the cross-sectional image of the residual limb, a new ultrasonic scanning method is developed to acquire the bones and skin contours of the residual limb. Using a pig fore-leg as the scanning object, an overlapping algorithm is designed to reconstruct the 2D cross-sectional image, the contours of the bone and skin are extracted using edge detection algorithm and the 3D model of the pig fore-leg is reconstructed by using reverse engineering technology. The results of checking the accuracy of the image by scanning a cylinder work pieces show that the extracted contours of the cylinder are quite close to the standard circumference. So it is feasible to get the contours of bones and skin by ultrasonic scanning. The ultrasonic scanning system featuring no radiation and low cost is a kind of new means of cross section scanning for medical images.展开更多
An adaptive blind support vector machine equalizer(ABSVME) is presented in this paper.The method is based upon least square support vector machine(LSSVM),and stems from signal feature reconstruction idea.By oversa...An adaptive blind support vector machine equalizer(ABSVME) is presented in this paper.The method is based upon least square support vector machine(LSSVM),and stems from signal feature reconstruction idea.By oversampling the output of a LSSVM equalizer and exploiting a reasonable decorrelation cost function design,the method achieves fine online channel tracing with Kumar express algorithm and static iterative learning algorithm incorporated.The method is verified through simulation and compared with other nonlinear equalizers.The results show that it provides excellent performance in nonlinear equalization and time-varying channel tracing.Although a constant module equalization algorithm requires that the signal has characteristic of constant module,this method has no such requirement.展开更多
文摘In recent years,anomaly detection has attracted much attention in industrial production.As traditional anomaly detection methods usually rely on direct comparison of samples,they often ignore the intrinsic relationship between samples,resulting in poor accuracy in recognizing anomalous samples.To address this problem,a knowledge distillation anomaly detection method based on feature reconstruction was proposed in this study.Knowledge distillation was performed after inverting the structure of the teacher-student network to avoid the teacher-student network sharing the same inputs and similar structure.Representability was improved by using feature splicing to unify features at different levels,and the merged features were processed and reconstructed using an improved Transformer.The experimental results show that the proposed method achieves better performance on the MVTec dataset,verifying its effectiveness and feasibility in anomaly detection tasks.This study provides a new idea to improve the accuracy and efficiency of anomaly detection.
基金This work was supported by National Natural Science Foundation of China(Nos.62006225,61906199 and 62071468)the Strategic Priority Research Program of Chinese Academy of Sciences(CAS),China(No.XDA 27040700)sponsored by The Beijing Nova Program,China(Nos.Z201100006820050 and Z211100002121010).
文摘In the daily application of an iris-recognition-at-a-distance(IAAD)system,many ocular images of low quality are acquired.As the iris part of these images is often not qualified for the recognition requirements,the more accessible periocular regions are a good complement for recognition.To further boost the performance of IAAD systems,a novel end-to-end framework for multi-modal ocular recognition is proposed.The proposed framework mainly consists of iris/periocular feature extraction and matching,unsupervised iris quality assessment,and a score-level adaptive weighted fusion strategy.First,ocular feature reconstruction(OFR)is proposed to sparsely reconstruct each probe image by high-quality gallery images based on proper feature maps.Next,a brand new unsupervised iris quality assessment method based on random multiscale embedding robustness is proposed.Different from the existing iris quality assess-ment methods,the quality of an iris image is measured by its robustness in the embedding space.At last,the fusion strategy exploits the iris quality score as the fusion weight to coalesce the complementary information from the iris and periocular regions.Extensive experi-mental results on ocular datasets prove that the proposed method is obviously better than unimodal biometrics,and the fusion strategy can significantly improve therecognition performance.
基金funded by National Key Research and Development Program of China(No.2022YFC3302103).
文摘The emergence of new media in various fields has continuously strengthened the social aspect of social media.Netizens tend to express emotions in social interactions,and many people even use satire,metaphors,and other techniques to express some negative emotions,it is necessary to detect sarcasm in social comment data.For sarcasm,the more reference data modalities used,the better the experimental effect.This paper conducts research on sarcasm detection technology based on image-text fusion data.To effectively utilize the features of each modality,a feature reconstruction output algorithm is proposed.This algorithm is based on the attention mechanism,learns the low-rank features of another modality through cross-modality,the eigenvectors are reconstructed for the corresponding modality through weighted averaging.When only the image modality in the dataset is used,the preprocessed data has outstanding performance in reconstructing the output model,with an accuracy rate of 87.6%.When using only the text modality data in the dataset,the reconstructed output model is optimal,with an accuracy rate of 85.2%.To improve feature fusion between modalities for effective classification,a weight adaptive learning algorithm is used.This algorithm uses a neural network combined with an attention mechanism to calculate the attention weight of each modality to achieve weight adaptive learning purposes,with an accuracy rate of 87.9%.Extensive experiments on a benchmark dataset demonstrate the superiority of our proposed model.
基金This project is supported by National Hi-tech Research and Development Program of China(863 Program, No.2002AA421130)Excellent Doctoral Dissertation Fund(No.200026).
文摘In the prosthetic socket design, aimed at the high cost and radiation deficiency caused by CT scanning which is a routine technique to obtain the cross-sectional image of the residual limb, a new ultrasonic scanning method is developed to acquire the bones and skin contours of the residual limb. Using a pig fore-leg as the scanning object, an overlapping algorithm is designed to reconstruct the 2D cross-sectional image, the contours of the bone and skin are extracted using edge detection algorithm and the 3D model of the pig fore-leg is reconstructed by using reverse engineering technology. The results of checking the accuracy of the image by scanning a cylinder work pieces show that the extracted contours of the cylinder are quite close to the standard circumference. So it is feasible to get the contours of bones and skin by ultrasonic scanning. The ultrasonic scanning system featuring no radiation and low cost is a kind of new means of cross section scanning for medical images.
基金Supported by the National Natural Science Foundation of China(60772056)the Postdoctoral Science Foundation of China(20070421094)
文摘An adaptive blind support vector machine equalizer(ABSVME) is presented in this paper.The method is based upon least square support vector machine(LSSVM),and stems from signal feature reconstruction idea.By oversampling the output of a LSSVM equalizer and exploiting a reasonable decorrelation cost function design,the method achieves fine online channel tracing with Kumar express algorithm and static iterative learning algorithm incorporated.The method is verified through simulation and compared with other nonlinear equalizers.The results show that it provides excellent performance in nonlinear equalization and time-varying channel tracing.Although a constant module equalization algorithm requires that the signal has characteristic of constant module,this method has no such requirement.