3D reconstruction of image sequences is an important application in computer graphics and imageprocessing, especially in biomedicalengineering. 3D reconstruction of elastin second harmonic generation (SHG) sequences...
详细信息
An objective blur measure is crucial for a variety of imageprocessing applications, Traditional researches concentrate on a model estimating the amount of spatial high frequency. However, human vision detects blurrin...
详细信息
ISBN:
(纸本)9781509037100
An objective blur measure is crucial for a variety of imageprocessing applications, Traditional researches concentrate on a model estimating the amount of spatial high frequency. However, human vision detects blurriness might be influenced by the texture of image contents. To address the important issue, this paper presents a new objective metric designed as both measuring the inherent smooth texture and predicting the difference induced by blur distortion. The approach is based on the wavelet characterization of Besov function spaces and just noticeable difference of human vision. Then, the just noticeable blur is estimated from the derived psychometric function using the proposed metric and subjective scores. Experimental comparisons with state-of-the-arts quality metrics for public data bases show that the proposed metric achieved high correlation with the general objective quality or subjective metrics.
This paper proposes a new neural fusion algorithm for fast robust image restoration without requiring the optimal regularization parameter. The new neural fusion algorithm is based on a new reduced dimension neural ne...
详细信息
ISBN:
(纸本)9781509037100
This paper proposes a new neural fusion algorithm for fast robust image restoration without requiring the optimal regularization parameter. The new neural fusion algorithm is based on a new reduced dimension neural network (RDNN). The RDNN is guaranteed to obtain an optimal fusion weight. The proposed RDNN-based neural fusion algorithm uses only a very small solution space to compute the optimal fusion weight, unlike existing neural fusion algorithms with solution space dimension being grater than image size. Unlike current image restoration algorithms, the proposed neural fusion algorithm has a low-dimensional solution space Computed results show that the proposed new algorithm has a robust performance against non-Gaussian noise and can obtain a good image estimate at a fast speed by using the non-optimal regularization parameter.
Blur plays an key part in evaluating of camera image quality. It leads to decrease of high frequency information and accordingly changes the image energy. Recent researches in quaternion singular value decomposition s...
详细信息
ISBN:
(纸本)9781509037100
Blur plays an key part in evaluating of camera image quality. It leads to decrease of high frequency information and accordingly changes the image energy. Recent researches in quaternion singular value decomposition show that the quaternion's singular values and associated vectors can capture the distortion of color images, and thus singular values can be utilized to assess the sharpness of camera image. Based on this, a novel blind quality assessment method considering the integral color information and singular values of the blurred camera image is proposed for evaluating the sharpness of camera image. Pure quaternion is utilized to represent pixels of the blurred camera image and the energy of every block are obtained. Results confirm the superiority of the proposed blind algorithm in assessing camera images.
In recent years, a dramatically increasing number of surveillance cameras have been installed to monitor private and public spaces and areas. Video surveillance is seen as an effective way to ensure our security. Ther...
详细信息
ISBN:
(纸本)9781509037100
In recent years, a dramatically increasing number of surveillance cameras have been installed to monitor private and public spaces and areas. Video surveillance is seen as an effective way to ensure our security. Therefore, modeling activity patterns and human behaviors for detection or recognition of peculiar event is a critical technology which has attracted remarkable research interest in the last few years. Various methods have been developed to build intelligent vision systems, this article extensively explain the current improvement made toward video-based human abnormal activity detection and wide applications in various fields range from monitoring in public spaces to personal health rehabilitation.
A quad-head combined aerial camera is first introduced in this paper. Due to its multiple center projection at each exposure station, an image post-processing procedure including camera calibration, matching, self-cal...
详细信息
ISBN:
(纸本)9781509037100
A quad-head combined aerial camera is first introduced in this paper. Due to its multiple center projection at each exposure station, an image post-processing procedure including camera calibration, matching, self-calibration stitching and color balancing is proposed to generate the stitched virtual image, in which the mathematical models of geometric calibration and self-calibration algorithms are primarily derived. The experiments show that the post-processing procedure has been capable of obtaining satisfying stitched virtual images. Besides, the related precisions of a 1:500 scale photogrammetry project has totally meet the requirements of national specifications of surveying and mapping.
This paper proposed a novel image fusion framework based on PCNN in NSCT domain. Compared with the contourlet transform(CT), NSCT has translational invariance and can also overcome the image pseudo Gibbs phenomena aro...
详细信息
ISBN:
(纸本)9781509037100
This paper proposed a novel image fusion framework based on PCNN in NSCT domain. Compared with the contourlet transform(CT), NSCT has translational invariance and can also overcome the image pseudo Gibbs phenomena around singularites. PCNN is evolved from mammal's visual cortex neuron model, and characterized by its pulse synchronization and acquisition of the neurons. Firstly, the source images were decomposed into low-frequency and high-frequency sub-bands, and in the fusion process, the summodified-laplacian(SML) was used to motivate PCNN. In the same time, the coefficients with larger firing times were selected as the fusion coefficients. Finally, the fused image can be obtained by the inverse NSCT. Experimental results show that the method is better than the traditional fusion methods, such as the wavelet transform, the contourlet transform and the PCNN based methods both in subjective appearance and objective criteria.
With the development and application of the computer, the traditional paper documents can be stored and managed effectively after turning into digital images. In electronization of archives, a single camera is insuffi...
详细信息
ISBN:
(纸本)9781509037100
With the development and application of the computer, the traditional paper documents can be stored and managed effectively after turning into digital images. In electronization of archives, a single camera is insufficient to gain a whole image clearly. At present, we generally shoot several images for stitching to obtain a complete and clear image. In document stitching, ghost has a quite large influence on fusion effect. A document stitching method based on optimal seam is proposed in this paper. When tilt correction for the archives is finished and overlapping regions are detected, binary images are extracted with OTSU algorithm. The area without archives is detected in the binary image horizontally and vertically by projection method and then search for feasible seams is made for stitching in the blank area so as to avoid ghost. Finally, the optimal seam is determined from the blank area. The experimental results show that the effect of registration ghost is eliminated and a good blending effect is achieved.
In the paper, we present a method for evaluating the quality of tongue images in Traditional Chinese Medicine (TCM). First, we preprocess the original images to segment the tongue images. Second, geometric features, t...
详细信息
ISBN:
(纸本)9781509037100
In the paper, we present a method for evaluating the quality of tongue images in Traditional Chinese Medicine (TCM). First, we preprocess the original images to segment the tongue images. Second, geometric features, texture features and spectral entropy features and spatial entropy features based on Spatial-Spectral Entropy-based Quality (SSEQ) index of tongue images are extracted respectively to form 17 dimensional feature vector for the tongue image quality assessment. Finally, Support vector machine (SVM) model is used to classify the samples. The experimental result shows that our method has a better effect on the tongue image quality assessment for the objectification of tongue diagnosis.
The brain tumor CT image segmentation frequently suffers from the fuzzy edges, and manual segmentation mainly relies on doctor's clinical experience. For the purpose to accurately segment brain tumor, a method for...
详细信息
ISBN:
(纸本)9781509037100
The brain tumor CT image segmentation frequently suffers from the fuzzy edges, and manual segmentation mainly relies on doctor's clinical experience. For the purpose to accurately segment brain tumor, a method for brain tumor CT image segmentation based on SLIC0 superpixels is proposed. Firstly, the simple linear iterative clustering version with 0 (SLIC0) is employed to generate superpixels;Secondly, region merging is adopted to merge the similar superpixels according to their gray, and finally segment the brain tumor regions. Experiments show that this method can accurately segment the target tumor, and segmentation accuracy can be adjusted by setting the pixel number of superpixels.
暂无评论