The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographica...The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographical regions.This work aimed to construct a computational classification model for classifying Indian regional face images acquired from south and east regions of India,referring to human vision.We have created an Automated Human Intelligence System(AHIS)to evaluate human visual capabilities.Analysis of AHIS response showed that face shape is a discriminative feature among the other facial features.We have developed a modified convolutional neural network to characterize the human vision response to improve face classification accuracy.The proposed model achieved mean F1 and Matthew Correlation Coefficient(MCC)of 0.92 and 0.84,respectively,on the validation set,outperforming the traditional Convolutional Neural Network(CNN).The CNN-Contoured Face(CNN-FC)model is developed to train contoured face images to investigate the influence of face shape.Finally,to cross-validate the accuracy of these models,the traditional CNN model is trained on the same dataset.With an accuracy of 92.98%,the Modified-CNN(M-CNN)model has demonstrated that the proposed method could facilitate the tangible impact in intra-classification problems.A novel Indian regional face dataset is created for supporting this supervised classification work,and it will be available to the research community.展开更多
This paper presents discrete wavelet transform （DWT） and its inverse （IDWT） with Haar wavelets as tools to compute the variable size interpolated versions of an image at optimum computational load. As a human obse...This paper presents discrete wavelet transform （DWT） and its inverse （IDWT） with Haar wavelets as tools to compute the variable size interpolated versions of an image at optimum computational load. As a human observer moves closer to or farther from a scene, the retinal image of the scene zooms in or out, respectively. This zooming in or out can be modeled using variable scale interpolation. The paper proposes a novel way of applying DWT and IDWT in a piecewise manner by non-uniform down- or up-sampling of the images to achieve partially sampled versions of the images. The partially sampled versions are then aggregated to achieve the final variable scale interpolated images. The non-uniform down- or up-sampling here is a function of the required scale of interpolation. Appropriate zero padding is used to make the images suitable for the required non-uniform sampling and the subsequent interpolation to the required scale. The concept of zeroeth level DWT is introduced here, which works as the basis for interpolating the images to achieve bigger size than the original one. The main emphasis here is on the computation of variable size images at less computational load, without compromise of quality of images. The interpolated images to different sizes and the reconstructed images are benchmarked using the statistical parameters and visual comparison. It has been found that the proposed approach performs better as compared to bilinear and bicubic interpolation techniques.展开更多
A shadow detection method using pulse couple neural network inspired by the characters of human visual system is proposed.More precisely,lateral inhibition of human vision and coefficient of variation are combined tog...A shadow detection method using pulse couple neural network inspired by the characters of human visual system is proposed.More precisely,lateral inhibition of human vision and coefficient of variation are combined together to improve the pulse couple neural network.Shadow detection is considered to be a shadow region segmentation problem.Experiment shows that the presented method is consistent with human vision compared to shadow detection methods based on HSV and pulse couple neural network(PCNN) by both subjective and objective assessments.展开更多
Common displays such as CRT or LCD screens have limited capabilities in displaying most color spectra correctly. The main disadvantage of these devices is that they work with three primaries and the colors displayed a...Common displays such as CRT or LCD screens have limited capabilities in displaying most color spectra correctly. The main disadvantage of these devices is that they work with three primaries and the colors displayed are the mixture of these three colours. Consequently these devices can be confusing in testing human color identification, because the spectral distribution of the colors displayed is the combined spectrum of the three primaries. We have developed a new instrument for spectrally correct color vision measurement. This instrument uses light emitting diodes (LEDs) and is capable of producing all spectra of perceivable colors, thus with appropriate test methods this instrument can be a reliable and useful tool in test~ing human color vision and in verifying color vision correction.展开更多
Vision-simulated imagery―the process of generating images that mimic the human visual system―is a valuable tool with a wide spectrum of possible applications, including visual acuity measurements, personalized plann...Vision-simulated imagery―the process of generating images that mimic the human visual system―is a valuable tool with a wide spectrum of possible applications, including visual acuity measurements, personalized planning of corrective lenses and surgeries, vision-correcting displays, vision-related hardware development, and extended reality discomfort reduction. A critical property of human vision is that it is imperfect because of the highly influential wavefront aberrations that vary from person to person. This study provides an overview of the existing computational image generation techniques that properly simulate human vision in the presence of wavefront aberrations. These algorithms typically apply ray tracing with a detailed description of the simulated eye or utilize the point-spread func-tion of the eye to perform convolution on the input image. Based on the description of the vision simulation tech-niques, several of their characteristic features have been evaluated and some potential application areas and research directions have been outlined.展开更多
AIM： To analyze the clinical factors influencing the human vision corrections via the changing of ocular components of human eye in various applications; and to analyze refractive state via a new effective axial leng...AIM： To analyze the clinical factors influencing the human vision corrections via the changing of ocular components of human eye in various applications; and to analyze refractive state via a new effective axial length.METHODS： An effective eye model was introduced by the ocular components of human eye including refractive indexes, surface radius（r1, r2, R1, R2） and thickness（t, T） of the cornea and lens, the anterior chamber depth（S1） and the vitreous length（S2）. Gaussian optics was used to calculate the change rate of refractive error per unit amount of ocular components of a human eye（the rate function M）. A new criterion of myopia was presented via an effective axial length.RESULTS： For typical corneal and lens power of 42 and 21.9 diopters, the rate function Mj（j=1 to 6） were calculated for a 1% change of r1, r2, R1, R2, t, T（in diopters） M1=＋0.485, M2=-0.063, M3=＋0.053, M4=＋0.091, M5=＋0.012, and M6=-0.021 diopters. For 1.0 mm increase of S1 and S2, the rate functions were M7=＋1.35, and M8=-2.67 diopter/mm, respectively. These rate functions were used to analyze the clinical outcomes in various applications including laser in situ keratomileusis surgery, corneal cross linking procedure, femtosecond laser surgery and scleral ablation for accommodation.CONCLUSION： Using Gaussian optics, analytic formulas are presented for the change of refractive power due to various ocular parameter changes. These formulas provide useful clinical guidance in refractive surgery and other related procedures.展开更多
针对现有车牌定位算法准确率不高、步骤多和速度慢等问题,提出一种彩色图像车牌定位方法(License plate locating based on CNN color edge detec tion,LPLCCED).首先利用细胞神经网络(Cell neural network,CNN)模型导出一种与车牌颜色...针对现有车牌定位算法准确率不高、步骤多和速度慢等问题,提出一种彩色图像车牌定位方法(License plate locating based on CNN color edge detec tion,LPLCCED).首先利用细胞神经网络(Cell neural network,CNN)模型导出一种与车牌颜色特征相结合的车牌定位专用边缘检测算法,将车牌的颜色对约束条件融合到边缘检测算法中,本文专用边缘检测算法可以大大缩小车牌初步定位的范围.接下来提出一种针对车牌特征的边缘滤波算法,最后根据车牌结构和纹理特征对候选区域进行判别验证.该流程的各个环节都可以通过硬件实现,为面向智能交通领域的实时车牌识别系统的前期车牌定位处理提供了依据.展开更多
文摘The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographical regions.This work aimed to construct a computational classification model for classifying Indian regional face images acquired from south and east regions of India,referring to human vision.We have created an Automated Human Intelligence System(AHIS)to evaluate human visual capabilities.Analysis of AHIS response showed that face shape is a discriminative feature among the other facial features.We have developed a modified convolutional neural network to characterize the human vision response to improve face classification accuracy.The proposed model achieved mean F1 and Matthew Correlation Coefficient(MCC)of 0.92 and 0.84,respectively,on the validation set,outperforming the traditional Convolutional Neural Network(CNN).The CNN-Contoured Face(CNN-FC)model is developed to train contoured face images to investigate the influence of face shape.Finally,to cross-validate the accuracy of these models,the traditional CNN model is trained on the same dataset.With an accuracy of 92.98%,the Modified-CNN(M-CNN)model has demonstrated that the proposed method could facilitate the tangible impact in intra-classification problems.A novel Indian regional face dataset is created for supporting this supervised classification work,and it will be available to the research community.
文摘This paper presents discrete wavelet transform （DWT） and its inverse （IDWT） with Haar wavelets as tools to compute the variable size interpolated versions of an image at optimum computational load. As a human observer moves closer to or farther from a scene, the retinal image of the scene zooms in or out, respectively. This zooming in or out can be modeled using variable scale interpolation. The paper proposes a novel way of applying DWT and IDWT in a piecewise manner by non-uniform down- or up-sampling of the images to achieve partially sampled versions of the images. The partially sampled versions are then aggregated to achieve the final variable scale interpolated images. The non-uniform down- or up-sampling here is a function of the required scale of interpolation. Appropriate zero padding is used to make the images suitable for the required non-uniform sampling and the subsequent interpolation to the required scale. The concept of zeroeth level DWT is introduced here, which works as the basis for interpolating the images to achieve bigger size than the original one. The main emphasis here is on the computation of variable size images at less computational load, without compromise of quality of images. The interpolated images to different sizes and the reconstructed images are benchmarked using the statistical parameters and visual comparison. It has been found that the proposed approach performs better as compared to bilinear and bicubic interpolation techniques.
基金Projects(61262032,61173122)supported by the National Natural Science Foundation of ChinaProject(12JJ038)supported by the Key Project of Natural Science Foundation of Hunan Province,China+1 种基金Project(2012FJ3100)supported by the Hunan Provincial Science&Technology Department,ChinaProject(12B103)supported by the Youth Project of Hunan Universities and Colleges Science Research,China
文摘A shadow detection method using pulse couple neural network inspired by the characters of human visual system is proposed.More precisely,lateral inhibition of human vision and coefficient of variation are combined together to improve the pulse couple neural network.Shadow detection is considered to be a shadow region segmentation problem.Experiment shows that the presented method is consistent with human vision compared to shadow detection methods based on HSV and pulse couple neural network(PCNN) by both subjective and objective assessments.
文摘Common displays such as CRT or LCD screens have limited capabilities in displaying most color spectra correctly. The main disadvantage of these devices is that they work with three primaries and the colors displayed are the mixture of these three colours. Consequently these devices can be confusing in testing human color identification, because the spectral distribution of the colors displayed is the combined spectrum of the three primaries. We have developed a new instrument for spectrally correct color vision measurement. This instrument uses light emitting diodes (LEDs) and is capable of producing all spectra of perceivable colors, thus with appropriate test methods this instrument can be a reliable and useful tool in test~ing human color vision and in verifying color vision correction.
文摘Vision-simulated imagery―the process of generating images that mimic the human visual system―is a valuable tool with a wide spectrum of possible applications, including visual acuity measurements, personalized planning of corrective lenses and surgeries, vision-correcting displays, vision-related hardware development, and extended reality discomfort reduction. A critical property of human vision is that it is imperfect because of the highly influential wavefront aberrations that vary from person to person. This study provides an overview of the existing computational image generation techniques that properly simulate human vision in the presence of wavefront aberrations. These algorithms typically apply ray tracing with a detailed description of the simulated eye or utilize the point-spread func-tion of the eye to perform convolution on the input image. Based on the description of the vision simulation tech-niques, several of their characteristic features have been evaluated and some potential application areas and research directions have been outlined.
基金Supported by an Internal Research of New Vision Inc.,Taipei,Taiwan
文摘AIM： To analyze the clinical factors influencing the human vision corrections via the changing of ocular components of human eye in various applications; and to analyze refractive state via a new effective axial length.METHODS： An effective eye model was introduced by the ocular components of human eye including refractive indexes, surface radius（r1, r2, R1, R2） and thickness（t, T） of the cornea and lens, the anterior chamber depth（S1） and the vitreous length（S2）. Gaussian optics was used to calculate the change rate of refractive error per unit amount of ocular components of a human eye（the rate function M）. A new criterion of myopia was presented via an effective axial length.RESULTS： For typical corneal and lens power of 42 and 21.9 diopters, the rate function Mj（j=1 to 6） were calculated for a 1% change of r1, r2, R1, R2, t, T（in diopters） M1=＋0.485, M2=-0.063, M3=＋0.053, M4=＋0.091, M5=＋0.012, and M6=-0.021 diopters. For 1.0 mm increase of S1 and S2, the rate functions were M7=＋1.35, and M8=-2.67 diopter/mm, respectively. These rate functions were used to analyze the clinical outcomes in various applications including laser in situ keratomileusis surgery, corneal cross linking procedure, femtosecond laser surgery and scleral ablation for accommodation.CONCLUSION： Using Gaussian optics, analytic formulas are presented for the change of refractive power due to various ocular parameter changes. These formulas provide useful clinical guidance in refractive surgery and other related procedures.
文摘针对现有车牌定位算法准确率不高、步骤多和速度慢等问题,提出一种彩色图像车牌定位方法(License plate locating based on CNN color edge detec tion,LPLCCED).首先利用细胞神经网络(Cell neural network,CNN)模型导出一种与车牌颜色特征相结合的车牌定位专用边缘检测算法,将车牌的颜色对约束条件融合到边缘检测算法中,本文专用边缘检测算法可以大大缩小车牌初步定位的范围.接下来提出一种针对车牌特征的边缘滤波算法,最后根据车牌结构和纹理特征对候选区域进行判别验证.该流程的各个环节都可以通过硬件实现,为面向智能交通领域的实时车牌识别系统的前期车牌定位处理提供了依据.
