针对人脸检测中小尺度人脸和遮挡人脸的漏检问题,提出了一种基于改进YOLOv5s-face(you only look once version 5 small-face)的Face5系列人脸检测算法Face5S(face5 small)和Face5M(face5 medium)。使用马赛克(mosaic)和图像混合(mixup...针对人脸检测中小尺度人脸和遮挡人脸的漏检问题,提出了一种基于改进YOLOv5s-face(you only look once version 5 small-face)的Face5系列人脸检测算法Face5S(face5 small)和Face5M(face5 medium)。使用马赛克(mosaic)和图像混合(mixup)数据增强方法,提升算法在复杂场景下检测人脸的泛化性和稳定性;通过改进C3的网络结构和引入可变形卷积(DCNv2)降低算法的参数量,提高算法提取特征的灵活性;通过引入特征的内容感知重组上采样算子(CARAFE),提高多尺度人脸的检测性能;引入损失函数WIoUV3(wise intersection over union version 3),提升算法的小尺度人脸检测性能。实验结果表明,在WIDER FACE验证集上,相较于YOLOv5s-face算法,Face5S算法的平均mAP@0.5提升了1.03%;相较于先进的人脸检测算法ASFD-D3(automatic and scalable face detector-D3)和TinaFace,Face5M算法的平均mAP@0.5分别提升了1.07%和2.11%,提出的Face5系列算法能够有效提升算法对小尺度和部分遮挡人脸的检测性能,同时具有实时性。展开更多
Compactly supported radial basis function can enable the coefficient matrix of solving weigh linear system to have a sparse banded structure, thereby reducing the complexity of the algorithm. Firstly, based on the com...Compactly supported radial basis function can enable the coefficient matrix of solving weigh linear system to have a sparse banded structure, thereby reducing the complexity of the algorithm. Firstly, based on the compactly supported radial basis function, the paper makes the complex quadratic function （Multiquadric, MQ for short） to be transformed and proposes a class of compactly supported MQ function. Secondly, the paper describes a method that interpolates discrete motion capture data to solve the motion vectors of the interpolation points and they are used in facial expression reconstruction. Finally, according to this characteris- tic of the uneven distribution of the face markers, the markers are numbered and grouped in accordance with the density level, and then be interpolated in line with each group. The approach not only ensures the accuracy of the deformation of face local area and smoothness, but also reduces the time complexity of computing.展开更多
An efficient face recognition system with face image representation using averaged wavelet packet coefficients, compact and meaningful feature vectors dimensional reduction and recognition using radial basis function ...An efficient face recognition system with face image representation using averaged wavelet packet coefficients, compact and meaningful feature vectors dimensional reduction and recognition using radial basis function (RBF) neural network is presented. The face images are decomposed by 2-level two-dimensional (2-D) wavelet packet transformation. The wavelet packet coefficients obtained from the wavelet packet transformation are averaged using two different proposed methods. In the first method, wavelet packet coefficients of individual samples of a class are averaged then decomposed. The wavelet packet coefficients of all the samples of a class are averaged in the second method. The averaged wavelet packet coefficients are recognized by a RBF network. The proposed work tested on three face databases such as Olivetti-Oracle Research Lab (ORL), Japanese Female Facial Expression (JAFFE) and Essexface database. The proposed methods result in dimensionality reduction, low computational complexity and provide better recognition rates. The computational complexity is low as the dimensionality of the input pattern is reduced.展开更多
自嘲作为一种言语现象,在不同文化背景下,既可以造成群体间的分裂也可以建立包容性。自嘲行为的使用可以构建积极的自我形象,促进团结。该研究从自嘲行为入手,基于中国知网(CNKI)收录的核心期刊、CSSCI期刊和Web of Science数据库中的...自嘲作为一种言语现象,在不同文化背景下,既可以造成群体间的分裂也可以建立包容性。自嘲行为的使用可以构建积极的自我形象,促进团结。该研究从自嘲行为入手,基于中国知网(CNKI)收录的核心期刊、CSSCI期刊和Web of Science数据库中的期刊论文,对国内外2003—2023年自嘲行为的研究进行述评。研究发现:该研究虽然已经受到国内外学者的关注,但国内研究成果较国外研究成果明显不足,且专门研究较少,存在研究对象覆盖面有限、研究样本量过少、研究方法单一等问题。基于研究现状,未来研究选题可以考虑深化相关研究并扩大研究的样本数量和范围,完善研究方法并运用新的研究理论,丰富自嘲行为的本土化研究,寻求新的研究视角,最终获得对自嘲行为更全面的认识。展开更多
针对人脸检测模型在低照度环境下出现的检测性能明显降低这一问题,提出一种基于图像增强的低照度人脸检测方法。首先,采用图像增强方法对低照度图像预处理,以增强人脸的有效特征信息;其次,在模型主干网络后引入注意力机制,以提升网络对...针对人脸检测模型在低照度环境下出现的检测性能明显降低这一问题,提出一种基于图像增强的低照度人脸检测方法。首先,采用图像增强方法对低照度图像预处理,以增强人脸的有效特征信息;其次,在模型主干网络后引入注意力机制,以提升网络对人脸区域的关注,并同时降低非均匀光照与噪声带来的负面影响;此外,引入注意力边界框损失函数WIoU(Wise Intersection over Union),以提升网络对低质量人脸的检测准确率;最后,使用更有效的特征融合模块代替模型原有结构。在低照度人脸数据集DARK FACE上的实验结果表明,所提方法的平均检测精度AP@0.5相较于原始YOLOv7模型提升了2.4个百分点,精度平均值AP@0.5:0.95提升了1.4个百分点,并且不引入额外参数与计算量。另外,在其他2个低照度人脸数据集上的结果也表明所提方法的有效性与鲁棒性,证明所提方法适用于不同场景下的低照度人脸检测。展开更多
Event-related potential （ERP） studies of cognitive function in Parkinson＇s disease （PD） have focused on P300 and N270. However, little is known regarding face recognition ERP in PD. The present study assessed cog...Event-related potential （ERP） studies of cognitive function in Parkinson＇s disease （PD） have focused on P300 and N270. However, little is known regarding face recognition ERP in PD. The present study assessed cognitive function in PD patients using neuropsychological scales and analyzed N170 of visuospatial function impairment （VFI） in PD. Results showed that Montreal cognitive assessment can be used for assessing cognitive impairment when visuospatial functioning is changed during the early stage of PD. Face recognition has clinical significance for detecting changes in visuospatial functioning. However, N170 is not sensitive for detection of VFI in PD, which implies that VFI does not appear in the stage of structure coding in face recognition. In addition, VFI affects face recognition.展开更多
文摘针对人脸检测中小尺度人脸和遮挡人脸的漏检问题,提出了一种基于改进YOLOv5s-face(you only look once version 5 small-face)的Face5系列人脸检测算法Face5S(face5 small)和Face5M(face5 medium)。使用马赛克(mosaic)和图像混合(mixup)数据增强方法,提升算法在复杂场景下检测人脸的泛化性和稳定性;通过改进C3的网络结构和引入可变形卷积(DCNv2)降低算法的参数量,提高算法提取特征的灵活性;通过引入特征的内容感知重组上采样算子(CARAFE),提高多尺度人脸的检测性能;引入损失函数WIoUV3(wise intersection over union version 3),提升算法的小尺度人脸检测性能。实验结果表明,在WIDER FACE验证集上,相较于YOLOv5s-face算法,Face5S算法的平均mAP@0.5提升了1.03%;相较于先进的人脸检测算法ASFD-D3(automatic and scalable face detector-D3)和TinaFace,Face5M算法的平均mAP@0.5分别提升了1.07%和2.11%,提出的Face5系列算法能够有效提升算法对小尺度和部分遮挡人脸的检测性能,同时具有实时性。
基金Supported by the National Natural Science Foundation of China (No.60875046)by Program for Changjiang Scholars and Innovative Research Team in University(No.IRT1109)+5 种基金the Key Project of Chinese Ministry of Education (No.209029)the Program for Liaoning Excellent Talents in University(No.LR201003)the Program for Liaoning Science and Technology Research in University (No.LS2010008,2009S008,2009S009,LS2010179)the Program for Liaoning Innovative Research Team in University(Nos.2009T005,LT2010005,LT2011018)Natural Science Foundation of Liaoning Province (201102008)by "Liaoning BaiQianWan Talents Program(2010921010,2011921009)"
文摘Compactly supported radial basis function can enable the coefficient matrix of solving weigh linear system to have a sparse banded structure, thereby reducing the complexity of the algorithm. Firstly, based on the compactly supported radial basis function, the paper makes the complex quadratic function （Multiquadric, MQ for short） to be transformed and proposes a class of compactly supported MQ function. Secondly, the paper describes a method that interpolates discrete motion capture data to solve the motion vectors of the interpolation points and they are used in facial expression reconstruction. Finally, according to this characteris- tic of the uneven distribution of the face markers, the markers are numbered and grouped in accordance with the density level, and then be interpolated in line with each group. The approach not only ensures the accuracy of the deformation of face local area and smoothness, but also reduces the time complexity of computing.
文摘An efficient face recognition system with face image representation using averaged wavelet packet coefficients, compact and meaningful feature vectors dimensional reduction and recognition using radial basis function (RBF) neural network is presented. The face images are decomposed by 2-level two-dimensional (2-D) wavelet packet transformation. The wavelet packet coefficients obtained from the wavelet packet transformation are averaged using two different proposed methods. In the first method, wavelet packet coefficients of individual samples of a class are averaged then decomposed. The wavelet packet coefficients of all the samples of a class are averaged in the second method. The averaged wavelet packet coefficients are recognized by a RBF network. The proposed work tested on three face databases such as Olivetti-Oracle Research Lab (ORL), Japanese Female Facial Expression (JAFFE) and Essexface database. The proposed methods result in dimensionality reduction, low computational complexity and provide better recognition rates. The computational complexity is low as the dimensionality of the input pattern is reduced.
文摘自嘲作为一种言语现象,在不同文化背景下,既可以造成群体间的分裂也可以建立包容性。自嘲行为的使用可以构建积极的自我形象,促进团结。该研究从自嘲行为入手,基于中国知网(CNKI)收录的核心期刊、CSSCI期刊和Web of Science数据库中的期刊论文,对国内外2003—2023年自嘲行为的研究进行述评。研究发现:该研究虽然已经受到国内外学者的关注,但国内研究成果较国外研究成果明显不足,且专门研究较少,存在研究对象覆盖面有限、研究样本量过少、研究方法单一等问题。基于研究现状,未来研究选题可以考虑深化相关研究并扩大研究的样本数量和范围,完善研究方法并运用新的研究理论,丰富自嘲行为的本土化研究,寻求新的研究视角,最终获得对自嘲行为更全面的认识。
文摘针对人脸检测模型在低照度环境下出现的检测性能明显降低这一问题,提出一种基于图像增强的低照度人脸检测方法。首先,采用图像增强方法对低照度图像预处理,以增强人脸的有效特征信息;其次,在模型主干网络后引入注意力机制,以提升网络对人脸区域的关注,并同时降低非均匀光照与噪声带来的负面影响;此外,引入注意力边界框损失函数WIoU(Wise Intersection over Union),以提升网络对低质量人脸的检测准确率;最后,使用更有效的特征融合模块代替模型原有结构。在低照度人脸数据集DARK FACE上的实验结果表明,所提方法的平均检测精度AP@0.5相较于原始YOLOv7模型提升了2.4个百分点,精度平均值AP@0.5:0.95提升了1.4个百分点,并且不引入额外参数与计算量。另外,在其他2个低照度人脸数据集上的结果也表明所提方法的有效性与鲁棒性,证明所提方法适用于不同场景下的低照度人脸检测。
文摘Event-related potential （ERP） studies of cognitive function in Parkinson＇s disease （PD） have focused on P300 and N270. However, little is known regarding face recognition ERP in PD. The present study assessed cognitive function in PD patients using neuropsychological scales and analyzed N170 of visuospatial function impairment （VFI） in PD. Results showed that Montreal cognitive assessment can be used for assessing cognitive impairment when visuospatial functioning is changed during the early stage of PD. Face recognition has clinical significance for detecting changes in visuospatial functioning. However, N170 is not sensitive for detection of VFI in PD, which implies that VFI does not appear in the stage of structure coding in face recognition. In addition, VFI affects face recognition.
