【摘 要】
：
针对传统局部二值模式(LBP)及其扩展方法往往会将具有不同视觉特征的局部邻域赋予相同二值模式值的问题,提出了一种新的凹-凸LBP划分方法。首先通过选择最优参数将具有相同二值模式值的邻域划分为凹凸两类,然后分别统计每类特征并组合在一起进行纹理分类。为验证新方法的性能,实验采用3个在纹理分析领域广泛应用的图像库进行分类实验,结果表明,本文方法明显提高了传统LBP方法的分辨能力。
论文部分内容阅读
针对传统局部二值模式(LBP)及其扩展方法往往会将具有不同视觉特征的局部邻域赋予相同二值模式值的问题,提出了一种新的凹-凸LBP划分方法。首先通过选择最优参数将具有相同二值模式值的邻域划分为凹凸两类,然后分别统计每类特征并组合在一起进行纹理分类。为验证新方法的性能,实验采用3个在纹理分析领域广泛应用的图像库进行分类实验,结果表明,本文方法明显提高了传统LBP方法的分辨能力。
其他文献
Anti-aliasing is a well-established technique in computer graphics that reduces the blocky or stair-wise appearance of pixels. This paper provides a comprehensive overview of the anti-aliasing techniq
Image resizing is a key technique for displaying images on different devices, and has attracted much attention in the past few years. This paper reviews the image resizing methods proposed in recent y
Medical image segmentation is of pivotal importance in computer-aided clinical diagnosis. Many factors, including noises, bias field effect, local volume effect, as well as tissue movement may affect
This paper proposes a massively parallel keypoint detection and description(MP-KDD) algorithm for the vision chip with parallel array processors. The MP-KDD algorithm largely reduces the computational
Human weight estimation is useful in a variety of potential applications,e.g.,targeted advertisement,entertainment scenarios and forensic science.However,estimating weight only from color cues is part
Despite the existence of advanced functions in smartphones,most blind people are still using old-fashioned phones with familiar layouts and dependence on tactile buttons.Smartphones support accessibil
Due to the encephalic tissues are highly irregular, three-dimensional(3D) modeling of brain always leads to complicated computing. In this paper, we explore an efficient method for brain surface recon
Generalized morphological operator can generate less statistical bias in the output than classical morphological operator. Comprehensive utilization of spectral and spatial information of pixels, an e
为了利用较少低分辨率视频序列实现多视频超分辨率重建,本文提出一种将时空分别进行重建的算法。首先利用已有方法进行时间重建,再以得到的高时间分辨率的视频序列帧为参考帧,结合输入低分辨率视频序列帧进行空间重建。此外,针对传统重建方法在配准不精确的情况下会产生振铃现象这一问题,提出一种加入自适应惩罚项的改进迭代反投影(IBP)算法。实验结果表明,本文算法在输入低分辨率序列较少的情况下,能较好地实现多视频超
针对目前路面图像滤波算法复杂度高且难以耦合噪声抑制和信号平衡的缺点,提出一种基于非下采样Contourlet变换(NSCT)域压缩采样的滤波算法。首先,使用NSCT对含噪路面病害图像进行分解,得到变换后的低频子带系数和高频子带系数;然后,对高频子带系数建立压缩感知(CS)去噪模型,并采用伪随机傅里叶矩阵对系数进行观测,之后使用分裂Bregman迭代方法对系数进行重构,得到去噪模型重建后的高频子带系