Improved gamut-constrained illuminant estimation by combining modified category correlation

In this paper we propose a new gamut-constrained illuminant estimation framework using an improved category correlation method. Firstly, we obtain a set of feasible illuminations by the original gamut mapping method. Then, the probability of each feasible illumination as the ground truth illuminant is calculated according to its ability to map the corrected image onto specific colors using the improved category correlation method. Differently from the original category correlation method, to decrease the effect of image noise and the computation complexity, instead of using an entire pixel set for estimating the probability of portable illuminant, superpixel segments of an input image are used in our improved method. And the best illuminant estimate is given on the basis of the measure of the degree to which each feasible illumination is consistent with the image data. Experiment results prove that our improved method shows better current state-of-the-art performance Gamut mapping methods.     

基于核优化密度聚类的绿色苹果分割算法

苹果的可见光谱目标的高效、精准识别是实现果园测产或机器自动采摘作业的关键,由于绿色目标果实与枝叶背景颜色较为相近,因此绿色苹果的识别成为新的挑战。再由于果园实际复杂环境因素影响,如光照、阴雨、枝叶遮挡、目标重叠等情况,现有的目标果实识别方案难以满足测产或自动采摘的实时、精准作业需求。为更好地实现果园自然环境中绿色目标果实识别问题,提出一种新的核密度估计优化的聚类分割算法（kernel density clustering, KDC）。新算法首先利用简单的迭代聚类（simple linear iterative cluster, SLIC）算法将目标图像分割成不规则块,集结小区域内近似像素点组成超像素区域,计算单元由像素点转变为超像素区域,有效降低数据复杂度,且SLIC算法简化图像数据时可有效避免目标果实轮廓模糊;基于超像素构造R-B区域均值和G-B区域均值的二维特征分量,建立针对聚类分析的青苹果颜色特征空间。然后借助密度峰值聚类中心计算绿色苹果图像每个数据点的局部密度和局部差异度,为解决分割边界模糊问题,在计算过程中利用核密度估计计算局部密度,确保局部密度在不同复杂场景中的清晰准确表达,以更精准找出被低密度区域分割的高密度区域,实现任意形状的聚类。最后以局部密度和距离构造寻找聚类中心的决策图,该研究采用双排序算法实现聚类中心的自动选择,完成目标果实的高效分割。新算法通过SLIC算法获得图像的超像素区域表示,数据点的局部密度通过核密度估计得到,大幅降低算法的计算量,实现目标图像的高效、精准分割。为更好地验证新算法性能,实验采集多光照、阴雨等环境下的遮挡、重叠等复杂目标图像,以分割效率、分割有效性、假阳性、假阴性等指标进行评价,通过对比k-means聚类算法、meanshift聚类算法、FCM算法和DPCA算法,该研究提出的新算法分割性能均最优。     

An infrared thermal image processing framework based on superpixel algorithm to detect cracks on metal surface

Infrared thermography has been used increasingly as an effective non-destructive technique to detect cracks on metal surface. Due to many factors, infrared thermal image has low definition compared to visible image. The contrasts between cracks and sound areas in different thermal image frames of a specimen vary greatly with the recorded time. An accurate detection can only be obtained by glancing over the whole thermal video, which is a laborious work. Moreover, experience of the operator has a great important influence on the accuracy of detection result. In this paper, an infrared thermal image processing framework based on superpixel algorithm is proposed to accomplish crack detection automatically. Two popular superpixel algorithms are compared and one of them is selected to generate superpixels in this application. Combined features of superpixels were selected from both the raw gray level image and the high-pass filtered image. Fuzzy c-means clustering is used to cluster superpixels in order to segment infrared thermal image. Experimental results show that the proposed framework can recognize cracks on metal surface through infrared thermal image automatically.     

High-contrast imaging based on wavefront shaping to improve low signal-to-noise ratio photoacoustic signals using superpixel method

Photoacoustic(PA) imaging has drawn tremendous research interest for various applications in biomedicine and experienced exponential growth over the past decade. Since the scattering effect of biological tissue on ultrasound is two-to three-orders magnitude weaker than that of light, photoacoustic imaging can effectively improve the imaging depth.However, as the depth of imaging further increases, the incident light is seriously affected by scattering that the generated photoacoustic signal is very weak and the signal-to-noise ratio(SNR) is quite low. Low SNR signals can reduce imaging quality and even cause imaging failure. In this paper, we proposed a new wavefront shaping and imaging method of low SNR photoacoustic signal using digital micromirror device(DMD) based superpixel method. We combined the superpixel method with DMD to modulate the phase and amplitude of the incident light, and the genetic algorithm(GA) was used as the wavefront shaping algorithm. The enhancement of the photoacoustic signal reached 10.46. Then we performed scanning imaging by moving the absorber with the translation stage. A clear image with contrast of 8.57 was obtained while imaging with original photoacoustic signals could not be achieved. The proposed method opens new perspectives for imaging with weak photoacoustic signals.     

动态背景下基于光流场分析的运动目标检测算法

针对现有动态背景下运动目标检测算法的不足,提出一种基于光流场分析的运动目标检测算法.首先根据前背景在光流梯度幅值和光流矢量方向上的差异确定目标的大致边界,然后通过点在多边形内部原理获得边界内部的稀疏像素点,最后以超像素为节点,利用混合高斯模型拟合的表观信息和超像素的时空邻域关系构建马尔可夫随机场模型的能量函数,并通过使目标函数能量最小化得到最终的运动目标检测结果.该算法不需要任何先验假设,能够同时处理动态背景和静态背景两种情况.多组实验结果表明,本文算法在检测的准确性和处理速度上均优于现有算法.     

Vessel boundary extraction based on a global and local deformable physical model with variable stiffness

Reliable and efficient vessel cross-sectional boundary extraction is very important for many medical magnetic resonance (MR) image studies. General purpose edge detection algorithms often fail for medical MR images processing due to fuzzy boundaries, inconsistent image contrast, missing edge features, and the complicated background of MR images. In this regard, we present a vessel cross-sectional boundary extraction algorithm based on a global and local deformable model with variable stiffness. With the global model, the algorithm can handle relatively large vessel position shifts and size changes. The local deformation with variable stiffness parameters enable the model to stay right on edge points at the location where edge features are strong and at the same time, fit a smooth contour at the location where edge features are missing. Directional gradient information is used to help the model to pick correct edge segments. The algorithm was used to process MR cine phase-contrast images of the aorta from 20 volunteers (over 500 images) with excellent results.     

拉普拉斯约束低秩表示的高光谱图像异常检测

伴随高光谱图像的广泛使用,高光谱图像技术得到长足的发展,其中高光谱图像异常检测技术越发受到重视。为了解决传统高光谱图像异常检测技术的实用性和检测效果不佳的问题,提出一种新颖的低秩表示检测算法。对于高光谱图像,大部分背景像元均可以被少量主要的背景像元组合近似地表示,且它们的表示系数将会位于低秩的空间中。在剩下无法被主要背景像元表示的稀疏部分中存在着异常像元,则可以被检测算法提取出来。在低秩表示中,背景像元字典的构建将会影响高光谱图像中背景像元的表示。如直接从现有高光谱图像中提取背景像元构建字典,会导致异常像元对背景像元字典的污染。而利用待检测高光谱图像观测数据和由光谱组成原理可合成的潜在未观测数据来构建背景像元字典,提取出背景像元的主要特征,有利于更好地分离出稀疏异常像元的信息。并且高光谱图像数据存在高维几何结构特点,通过引入拉普拉斯矩阵来约束空间中局部相似的像元对于待检测像元的表示作用,获得更接近于真实的表示系数。实验结果分别在仿真数据和真实数据上验证,与传统方法相比,提出的方法通过有效地突出异常像元提高了检出率和抑制了背景像元,降低了误检率。     

Region-based object and background extraction via active contours

In this paper, we propose a region-based model for the object and background extraction with application to the image with thick or complex boundary. Based on region information of the image, we employ two curves to extract the object and background, respectively, regardless of the boundary. The first curve is used to extract the object. Correspondingly, the second curve is used to extract the background. By employing two level set functions to represent the two curves, we propose a new region-based energy functional. In the proposed model, a distance constraint term is incorporated, which effectively avoid that the two level set functions too away from each other and keep their similar shapes well. Besides, we present a penalty term to maintain the accurate computation and stability evolution. Experiment results demonstrate the desirable performance of the proposed model with application to synthetic and real-world images.     

Improved wavelet transform algorithm for single image dehazing

Image dehazing to single color image remains a longstanding challenge in image processing. Because of light scattered by the suspended particles in the atmosphere, photographs taken in the foggy day look gray and lack visibility. How to improve the capacity for the clear image's structures and colors. Toward this objective, we explored the improved Wavelet Transform algorithm on image haze removal. Here, we propose a improved algorithm on image haze removal. Our method is to first apply wavelet transform to image dehazing, and then use Retinex (SSR) algorithm to enhance the color performance and to improve the color effect after applying wavelet transform to image dehazing, and finally get the desired haze-removed image. Experimental results show that this algorithm is effective and practical, and the effect is ideal.     

Color removal method of considering distance in color space

In a color-to-gray conversion, which only considers lightness components, difference of colors are not appropriately reflected in monochrome images. Gooch et al. have proposed a color removal method that considers the differences of colors. Although the method can obtain good results in many cases, there is room for improvement. In this paper, a new color removal method that introduces a weight to Gooch’s algorithm is proposed. In the proposed method, for combinations of colors of each pixel in an input image, weights are determined by distance in color space. In the proposed method, unimportant color combinations are not considered by weight and color information in an input image is appropriately reflected in a monochrome image. The validity of the proposed method is shown by experiments using some images.     

Saliency detection via two-directional 2DPCA analysis of image patches

Salient object detection is an important and challenging problem in computer vision. In this paper, we present a model of salient region detection based on the fusion of contrast and distribution, computed by two-directional 2DPCA analysis of image patches under the combination of RGB space, LAB space and YCbCr space. First, non-overlap patches of three layers from the image are obtained in the three color spaces respectively and stacked for the combination of the three sapces in a single layer. For every layer, two-directional, two-dimensional PCA are utilized to realize automatic selection of effective features, then based on the high contrast and compact character of salient object, contrast values and distribution values of image patches are fused to get the saliency map. Finally, three saliency maps for three layers are combined to detect salient object. The experimental results on a publicly available database show that the proposed algorithm performs well and are in line with the human eye observation results.     

基于神经网络的低照度彩色图像增强算法

由于低照度彩色图像存在整体亮度低、对比度低、颜色偏暗和信噪比低等特点,所以经典图像增强算法对其增强效果非常有限。提出了一种利用BP神经网络进行彩色图像增强的算法,并将RGB图像转换成HSI图像,以保证增强处理不引起图像的色彩失真。实验证明:该方法显著地改善了低照度彩色图像的视觉效果,提高了图像整体亮度和图像的信噪比,可调节图像的动态范围,能增强图像的对比度和细节,可增加图像信息熵。     

改进灰度世界颜色校正算法

讨论了灰度世界算法,提出了两种改进的灰度世界算法——基于标准差加权的算法和基于图像熵约束的算法,从而避免了当给定图像仅有少量几种颜色或大块单一颜色时的冥法失效问题.通过对算法颜色校正结果进行主观(视觉上)评价,并对算法性能通过使用色差数据进行了客观评价.实验结果表明:改进算法对实际采集的图像和下载的图像都有较好的校正效果.     

基于互结构正则约束的红外偏振图像增强算法

为有效改善红外偏振图像视觉效应,提高红外偏振成像质量,提出了基于互结构正则约束的红外偏振图像增强算法。根据红外偏振特性描述,对Stokes参数Q分量与U分量进行加权邻域梯度融合,获得起偏特征图像,捕获目标边缘、轮廓的偏振特性;提出互结构正则约束模型,以梯度幅值相似算子联合正则约束融合结果与起偏特征图像的边缘结构相似性,及与辐射强度图像的灰度一致性,优化得到增强后的高质量红外偏振图像。实验结果表明,基于互结构正则约束的红外偏振图像增强算法,能有效提高红外偏振图像对比度与清晰度,同时提升复杂背景下人造目标边缘轮廓的偏振显著性,算法快速,工程实时性高.     

Skin layer detection of optical coherence tomography images

In this paper, we present an image processing algorithm to automatically and more precisely detect the boundary between the main skin layers: stratum corneum, epidermis, and dermis. The aim of the proposed skin layer detection algorithm is to assist the dermatologists to measure the epidermal thickness (ET) for skin diseases diagnosis and also to assist pharmacologists so that they can make a better decision for prescribing according to the advancement of the skin disorders characterized with ET change.     

Geometrically robust image watermarking using scale-invariant feature transform and Zernike moments

In order to resist geometric attacks, a robust image watermarking algorithm is proposed using scaleinvariant feature transform (SIFT) and Zernike moments. As SIFT features are invariant to rotation and scaling, we employ SIFT to extract feature points. Then circular patches are generated using the most robust points. An invariant watermark is generated from each circular patch based on Zernike moments.The watermark is embedded into multiple patches for resisting locally cropping attacks. Experimental results show that the proposed scheme is robust to both geometric attacks and signal processing attacks.     

高光谱成像砖红壤中石油烃含量的可视化研究

高光谱成像具有快速无损和图谱合一的特点,每个波段都会呈现一幅图像,每个像素点都显示一条光谱曲线,不仅可以获取样本的光谱信息,还可以表征物体的空间信息,目前在诸多领域展现出极大的应用价值。采用高光谱成像实现土壤中石油烃含量分布的可视化。制备不同石油烃含量的砖红壤样本,分为建模样本和预测样本。采集高光谱图像,为避免图像背景的干扰,采用掩膜的方法进行背景剔除。之后提取建模样本中感兴趣区域的平均光谱,采用连续投影算法筛选特征变量,基于提取的特征变量,一方面建立MLR预测模型,另一方面从预测样本中提取特征波段的高光谱图像。最后,将特征图像上像素点的数据代入模型,得到石油烃的含量分布情况。通过图像处理的方法,不同的含量赋予不同的颜色,实现砖红壤中石油烃含量分布的可视化。研究结果表明,采用高光谱成像与图像处理方法能够初步实现砖红壤中石油烃含量分布的可视化,为以后大范围地识别和反演土壤中石油烃含量提供了基础。     

A non-circular iris localization algorithm using image projection function and gray level statistics

Iris recognition technology identifies an individual from its iris texture with great precision. A typical iris recognition system comprises eye image acquisition, iris segmentation, feature extraction, and matching. However, the system precision greatly depends on accurate iris localization in the segmentation module. In this paper, we propose a reliable iris localization algorithm. First, we locate a coarse eye location in an eye image using integral projection function (IPF). Next, we localize the pupillary boundary in a sub image using a reliable technique based on the histogram-bisection, image statistics, eccentricity, and object geometry. After that, we localize the limbic boundary using a robust scheme based on the radial gradients and an error distance transform. Finally, we regularize the actual iris boundaries using active contours. The proposed algorithm is tested on public iris databases: MMU V1.0, CASIA-IrisV1, and the CASIA-IrisV3-Lamp. Experimental results demonstrate superiority of the proposed algorithm over some of the contemporary techniques.