Invoice document digitization is crucial for efficient management in industries.The scanned invoice image is often noisy due to various reasons.This affects the OCR(optical character recognition)detection accuracy.In ...Invoice document digitization is crucial for efficient management in industries.The scanned invoice image is often noisy due to various reasons.This affects the OCR(optical character recognition)detection accuracy.In this paper,letter data obtained from images of invoices are denoised using a modified autoencoder based deep learning method.A stacked denoising autoencoder(SDAE)is implemented with two hidden layers each in encoder network and decoder network.In order to capture the most salient features of training samples,a undercomplete autoencoder is designed with non-linear encoder and decoder function.This autoencoder is regularized for denoising application using a combined loss function which considers both mean square error and binary cross entropy.A dataset consisting of 59,119 letter images,which contains both English alphabets(upper and lower case)and numbers(0 to 9)is prepared from many scanned invoices images and windows true type(.ttf)files,are used for training the neural network.Performance is analyzed in terms of Signal to Noise Ratio(SNR),Peak Signal to Noise Ratio(PSNR),Structural Similarity Index(SSIM)and Universal Image Quality Index(UQI)and compared with other filtering techniques like Nonlocal Means filter,Anisotropic diffusion filter,Gaussian filters and Mean filters.Denoising performance of proposed SDAE is compared with existing SDAE with single loss function in terms of SNR and PSNR values.Results show the superior performance of proposed SDAE method.展开更多
We present the analysis of three independent and most widely used image smoothing techniques on a new fractional based convolution edge detector originally constructed by same authors for image edge analysis. The impl...We present the analysis of three independent and most widely used image smoothing techniques on a new fractional based convolution edge detector originally constructed by same authors for image edge analysis. The implementation was done using only Gaussian function as its smoothing function based on predefined assumptions and therefore did not scale well for some types of edges and noise. The experiments conducted on this mask using known images with realistic geometry suggested the need for image smoothing adaptation to obtain a more optimal performance. In this paper, we use the structural similarity index measure and show that the adaptation technique for choosing smoothing function has significant advantages over a single function implementation. The new adaptive fractional based convolution mask can smoothly find edges of various types in detail quite significantly. The method can now trap both local discontinuities in intensity and its derivatives as well as locating Dirac edges.展开更多
Automatic and robust matching of multi-modal images can be challenging owing to the nonlinear intensity differences caused by radiometric variations among these images.To address this problem,a novel dense feature des...Automatic and robust matching of multi-modal images can be challenging owing to the nonlinear intensity differences caused by radiometric variations among these images.To address this problem,a novel dense feature descriptor and improved similarity measure are proposed for enhancing the matching performance.The proposed descriptor is built on a voting scheme of structure tensor that can effectively capture the geometric structural properties of images.It is not only illumination and contrast invariant but also robust against the degradation caused by significant noise.Further,the similarity measure is improved to adapt to the reversal of orientation caused by the intensity inversion between multi-modal images.The proposed dense feature descriptor and improved similarity measure enable the development of a robust and practical templatematching algorithm for multi-modal images.We verify the proposed algorithm with a broad range of multi-modal images including optical,infrared,Synthetic Aperture Radar(SAR),digital surface model,and map data.The experimental results confirm its superiority to the state-of-the-art methods.展开更多
蝗虫显微切片图像在获取的过程中不可避免地会受到噪声污染,其纹理、边缘与噪声又都属于高频分量,单独使用小波变换或偏微分方程(partial differential equation,PDE)扩散的方法都不能在有效去噪的同时保持边缘、纹理等。针对这一问题,...蝗虫显微切片图像在获取的过程中不可避免地会受到噪声污染,其纹理、边缘与噪声又都属于高频分量,单独使用小波变换或偏微分方程(partial differential equation,PDE)扩散的方法都不能在有效去噪的同时保持边缘、纹理等。针对这一问题,提出了基于自适应小波PDE的去噪算法。首先对蝗虫切片含噪图像进行sym5小波软阈值去噪,分解层数根据去噪后图像的PSNR(peak signal to noise ratio)值自适应地选择,阈值门限使用Birge-Massart处罚算法获取。然后在此去噪的基础上进行Perona-Malik(PM)模型去噪,迭代次数根据去噪后图像的PSNR值自适应地选择,梯度阈值根据图像自身的2范数获取。为了验证所提出算法的去噪性能,进行了与常用去噪算法的对比试验。试验结果表明:视觉上,采用本文算法去噪后的图像噪声点较少且边缘、纹理清晰;客观上,采用该文算法去噪后的图像PSNR值比使用维纳滤波高出2 d B左右,比使用中值滤波高出3 d B左右,比使用小波阈值去噪高出2 d B左右,比使用PM模型去噪高出1 d B左右,并且在结构相似性(structural similarity image measurement,SSIM)上采用该文算法去噪后的图像与原始图像的相似度最高。因此,将自适应小波PDE的算法应用于蝗虫切片去噪是可行的、有效的,为其后续处理提供了技术支持。展开更多
该文提出一种基于结构相似性指数(SSIM)的非局部均值(Non Local means,NL-means)滤波的合成孔径雷达(SAR)图像相干斑噪声抑制新方法。该方法用SSIM改进NL-means算法中小块相似性的度量,能利用结构信息来进行相干斑抑制。通过在真实SAR...该文提出一种基于结构相似性指数(SSIM)的非局部均值(Non Local means,NL-means)滤波的合成孔径雷达(SAR)图像相干斑噪声抑制新方法。该方法用SSIM改进NL-means算法中小块相似性的度量,能利用结构信息来进行相干斑抑制。通过在真实SAR图像上的实验表明,与GammaMAP滤波、CHMT算法、BLS-GSM算法、NL-means滤波相比,此方法在有效去除相干斑噪声的同时能更好地保持边缘结构信息。展开更多
文摘Invoice document digitization is crucial for efficient management in industries.The scanned invoice image is often noisy due to various reasons.This affects the OCR(optical character recognition)detection accuracy.In this paper,letter data obtained from images of invoices are denoised using a modified autoencoder based deep learning method.A stacked denoising autoencoder(SDAE)is implemented with two hidden layers each in encoder network and decoder network.In order to capture the most salient features of training samples,a undercomplete autoencoder is designed with non-linear encoder and decoder function.This autoencoder is regularized for denoising application using a combined loss function which considers both mean square error and binary cross entropy.A dataset consisting of 59,119 letter images,which contains both English alphabets(upper and lower case)and numbers(0 to 9)is prepared from many scanned invoices images and windows true type(.ttf)files,are used for training the neural network.Performance is analyzed in terms of Signal to Noise Ratio(SNR),Peak Signal to Noise Ratio(PSNR),Structural Similarity Index(SSIM)and Universal Image Quality Index(UQI)and compared with other filtering techniques like Nonlocal Means filter,Anisotropic diffusion filter,Gaussian filters and Mean filters.Denoising performance of proposed SDAE is compared with existing SDAE with single loss function in terms of SNR and PSNR values.Results show the superior performance of proposed SDAE method.
文摘We present the analysis of three independent and most widely used image smoothing techniques on a new fractional based convolution edge detector originally constructed by same authors for image edge analysis. The implementation was done using only Gaussian function as its smoothing function based on predefined assumptions and therefore did not scale well for some types of edges and noise. The experiments conducted on this mask using known images with realistic geometry suggested the need for image smoothing adaptation to obtain a more optimal performance. In this paper, we use the structural similarity index measure and show that the adaptation technique for choosing smoothing function has significant advantages over a single function implementation. The new adaptive fractional based convolution mask can smoothly find edges of various types in detail quite significantly. The method can now trap both local discontinuities in intensity and its derivatives as well as locating Dirac edges.
基金supported by the National Natural Science Foundations of China(No.61802423)the Natural Science Foundation of Hunan Province,China(No.2019JJ50739)。
文摘Automatic and robust matching of multi-modal images can be challenging owing to the nonlinear intensity differences caused by radiometric variations among these images.To address this problem,a novel dense feature descriptor and improved similarity measure are proposed for enhancing the matching performance.The proposed descriptor is built on a voting scheme of structure tensor that can effectively capture the geometric structural properties of images.It is not only illumination and contrast invariant but also robust against the degradation caused by significant noise.Further,the similarity measure is improved to adapt to the reversal of orientation caused by the intensity inversion between multi-modal images.The proposed dense feature descriptor and improved similarity measure enable the development of a robust and practical templatematching algorithm for multi-modal images.We verify the proposed algorithm with a broad range of multi-modal images including optical,infrared,Synthetic Aperture Radar(SAR),digital surface model,and map data.The experimental results confirm its superiority to the state-of-the-art methods.
文摘蝗虫显微切片图像在获取的过程中不可避免地会受到噪声污染,其纹理、边缘与噪声又都属于高频分量,单独使用小波变换或偏微分方程(partial differential equation,PDE)扩散的方法都不能在有效去噪的同时保持边缘、纹理等。针对这一问题,提出了基于自适应小波PDE的去噪算法。首先对蝗虫切片含噪图像进行sym5小波软阈值去噪,分解层数根据去噪后图像的PSNR(peak signal to noise ratio)值自适应地选择,阈值门限使用Birge-Massart处罚算法获取。然后在此去噪的基础上进行Perona-Malik(PM)模型去噪,迭代次数根据去噪后图像的PSNR值自适应地选择,梯度阈值根据图像自身的2范数获取。为了验证所提出算法的去噪性能,进行了与常用去噪算法的对比试验。试验结果表明:视觉上,采用本文算法去噪后的图像噪声点较少且边缘、纹理清晰;客观上,采用该文算法去噪后的图像PSNR值比使用维纳滤波高出2 d B左右,比使用中值滤波高出3 d B左右,比使用小波阈值去噪高出2 d B左右,比使用PM模型去噪高出1 d B左右,并且在结构相似性(structural similarity image measurement,SSIM)上采用该文算法去噪后的图像与原始图像的相似度最高。因此,将自适应小波PDE的算法应用于蝗虫切片去噪是可行的、有效的,为其后续处理提供了技术支持。
文摘该文提出一种基于结构相似性指数(SSIM)的非局部均值(Non Local means,NL-means)滤波的合成孔径雷达(SAR)图像相干斑噪声抑制新方法。该方法用SSIM改进NL-means算法中小块相似性的度量,能利用结构信息来进行相干斑抑制。通过在真实SAR图像上的实验表明,与GammaMAP滤波、CHMT算法、BLS-GSM算法、NL-means滤波相比,此方法在有效去除相干斑噪声的同时能更好地保持边缘结构信息。
