基于小波域的图像椒盐噪声密度估计

提出一种基于小波域的椒盐噪声密度估计方法.利用图像信号在小波域的系数具有稳定近似的分布,以及噪声对小波系数影响的特点,定量地分析了含噪图像的系数幅值直方图与原始图像的系数幅值直方图之间的偏离程度随噪声密度的变化规律,揭示这种变化关系对图像具有强的鲁棒性,从而利用这种关系对噪声进行估计.仿真结果表明,相对于目前方法,提出算法性能更佳,能够获得更准确的估计值和更小的估计偏差.     

基于加权模糊C均值聚类的图像分割算法

模糊C均值(FCM)算法用于灰度图像分割是一种非监督模糊聚类后再标定的过程,适合灰度图像中存在着模糊和不确定性的特点。但是这种算法存在着本质上的缺陷,就是仅利用了图像的灰度信息,而没有考虑像素的空间信息,使得其对于实际的含有噪声的图像分割效果不理想。因此,提出了一种新的加权模糊C均值聚类算法,实践证明,该方法可以有效地、实时地把目标从背景中分割出来,并具有较强的鲁棒性。     

中英色彩语言的诠释

本文运用比较的方法分析了中英两种语言中颜色词的异同，说明由于受历史传统、社会习俗，宗教信仰以及民族心理等因素的影响，不同的民族国家表示颜色的方法和用词不尽相同。了解并掌握这些颜色词及其受文化影响而形成的各种固定用法，对中西文化交流有一定实际意义。     

Chlorophyll,calcite, and suspended sediment concentrations in the Bay of Bengal and the Arabian Sea at the river mouths

Chlorophyll and suspended sediment concentrations (SSC) and sea surface temperature (SST) are important parameters in assessing the productivity of coastal regions. Numerous rivers flow into the eastern (Ganga, Subernarekha, Mahanadi, Godavari, Krishna, Penner, and Kaveri) and western (Narmada, Tapti, and Indus) coasts of the Indian sub-continent. Using IRS P4 (Oceansat-1) Ocean Color Monitor (OCM) and Moderate Resolution Imaging Spectroradiometer (MODIS) data, we have retrieved chlorophyll, calcite, and SSC near the mouth of these rivers for the period during 2000–2004. The maxima of chlorophyll-a concentrations at the river mouth is much higher for the Himalayan and north India rivers (Ganga, Subernarekha, Mahanadi, and Indus) (10–14 mg/m³) compared to rivers in the southern parts of India (Kaveri and Penner) (∼4 mg/m³). The maxima of calcite concentration (∼45 moles/m³), chlorophyll (∼14 mg/m³), and sediment concentrations (∼9 g/m³) near river mouth are found to be influenced by river discharges (Ganga and Brahmaputra) during the monsoon season. The calcite concentration (∼45 moles/m³) at the mouth of Ganga river shows a major peak with the onset of monsoon season (June–July) followed by a maxima in chlorophyll-a with a time lag of 1–2 months. The Krishna, Kaveri, and Penner rivers show low chlorophyll concentrations (3–8 mg/m³), high calcite (0–40 moles/m³), and low SSC (<3 g/m³) compared to Narmada and Tapti rivers (chlorophyll-a 12–14 mg/m³, calcite 0–2 moles/m³, and SSC 13–19 g/m³). The Indus river shows similar behavior (maxima of chlorophyll ∼13 mg/m³ and SSC ∼8 g/m³) with respect to Ganga river except for high calcite concentration during winter months (∼25 moles/m³). The characteristics of the chlorophyll, calcite, and SSC at the mouth of these rivers show spatial and temporal variability along the eastern and westerns coasts of India which are found to differ widely. A comparison of the chlorophyll concentrations using OCM and MODIS data shows low chlorophyll concentrations in the Bay of Bengal as compared to the Arabian Sea.     

基于四元数理论的彩色图像脉冲噪声开关滤波

根据四元数单位变换理论定义了一种新的描述彩色图像像素点间差异的距离,该距离可以同时描述两个彩色像素点在强度和色度上的差异.利用该距离和图像边缘的结构性与方向性,构造了一种基于四元数的开关型彩色图像脉冲噪声滤波器.该滤波器对像素点进行4个方向上的噪声检测并仅对检测为噪声的像素点进行滤波.实验表明:该滤波器能够在去除彩色图像中的相关和非相关噪声的同时保护图像细节,同时具有比传统方法更快的执行速度.     

一种改进的直方图概率多假设多目标跟踪方法

直方图概率多假设跟踪（H-PMHT）方法及其变形泊松分布直方图概率多假设跟踪（P-HPMHT）方法的一个主要缺点是其量测模型仅考虑了背景杂波而没有考虑传感器噪声,从而导致在低信噪比条件下检测概率较低。针对这一问题,提出了一种带传感器噪声模型的H-PMHT方法,通过将传感器噪声引入量测模型,从而明显提高了对低信噪比目标的跟踪检测能力。该方法的计算量与目标数保持线性关系,仍然适用于目标数目较多的情况。仿真实验表明：该方法在误跟踪比率为1‰,信噪比为6 dB时,检测比率可提升近20%,信噪比为3 dB时,可提升近10%。     

基于多尺度梯度及深度神经网络的汉字识别

介绍了一种基于多尺度滑动窗的方法提取文字的梯度直方图特征,并结合深度神经网络对印刷体汉字进行识别.针对梯度直方图的空间关系,使用可伸缩的滑动窗对图像进行分割,在不同尺度上获取文字的特征信息,有效融合汉字的全局特征和局部分块特征.实验采用5层的深度神经网络模型对国标一级3755个印刷体汉字进行分类,并应用Dropout技术防止训练过拟合,提高神经网络的泛化能力.实验准确率达到98.292%,有较好的识别性能,验证了本文多尺度梯度特征及深度神经网络模型在文字识别上的有效性.      

硬笔写生的色彩借鉴与表现--浅谈美术设计专业的速写教学

速写是线的艺术也是黑白的艺术.在教学实践中,应从其它黑白造型艺术(如中国水墨与白描、黑白装饰画、图案、版画等)中吸取营养,让学生借鉴这些造型艺术形式中的黑白美学原则,并熟练运用"线条"和"色彩"两种语言来表现自然.     

基于加强模糊聚类的航空行李图像超像素分割

在自助行李托运系统拍摄的行李图像库中检索错误运输的行李时,图像背景会严重影响检索精度。针对该问题提出了一种加强模糊聚类算法（EnFCM）的超像素分割方法,实现了行李目标区域的提取。通过多尺度形态学重建梯度图像,设计了自适应上限尺度的分水岭超像素预分割算法,得到多个独立的超像素区域。对超像素图像进行直方图统计,并结合分水岭分割参数和实际行李图像内容的类别数量进行超像素的加强模糊聚类,得到行李区域。通过多个实际行李图像的分割实验验证了算法的有效性,平均分割精度达到93%,超过多个典型的分割算法。     

Merged series of normalized water leaving radiances obtained from multiple satellite missions for the Mediterranean Sea

Merging time series of ocean color-derived products provided by independent satellite missions supports related biogeochemical and environmental applications by combining temporally overlapping data sets and by increasing data coverage. The creation of a merged series of normalized water leaving radiances _LWN$L_{\text{WN}}$, the primary ocean color product, is presented for the Mediterranean Sea using the SeaWiFS and MODIS data records. The merging relies on an optically-based technique that combines the available _LWN$L_{\text{WN}}$ signal in a spectrally consistent way. Validation statistics indicate uncertainties associated with the merged _LWN$L_{\text{WN}}$ decreasing from 23% at 412 nm to 12% in the 500- to 555-nm spectral range. The inter-comparison of the sensor-specific products, conducted at the scale of the basin for daily-to-monthly time scales, indicates an overall consistency. The level of differences varies with the wavelength considered and shows a marked seasonal cycle, with differences that tend to be higher in winter. The merged series is remarkably consistent with the sensor-specific data, with average absolute percent differences lower than 10% for all wavelengths below 555 nm. The benefit of merging in terms of sampling frequency over the basin is also illustrated. A merged series of _LWN$L_{\text{WN}}$ data based on the two considered missions provides valid data over 36% of the basin area on a daily basis.