Model of vegetable freshness perception using luminance cues

Freshness perception is a quality discrimination process that influences our consumer choice and eating behavior, especially of highly perishable products such as vegetables. Previous research used photographic stimuli to investigate the relationship between luminance distribution and freshness perception for a cabbage leaf (C. Arce-Lopera, Masuda, Kimura, et al., 2013) and a strawberry (Carlos Arce-Lopera, Masuda, Kimura, Wada, & Okajima, 2012). In this study, the luminance and chromatic information of the freshness degradation process of four different vegetables (cabbage, strawberry, carrot and spinach) was recorded in a temperature, humidity and light controlled environment. However, instead of a camera, a 2D luminance and chromaticity analyzer (TOPCON UA1000) was chosen as the measurement equipment. Then, using a color management system to guarantee the exact reproduction of the recorded luminance and chromatic data of the real objects, a color and a grayscale version of the stimuli was created. Subsequently, those pictures were randomly presented to subjects who had to rate their perceived freshness using a visual analog scale. The achromatic results did not differ from the chromatic ones suggesting that luminance information is sufficient to enable an accurate estimation of vegetable freshness. Additionally, the original images were digitally manipulated only by modifying their luminance distribution and keeping their color information intact. When the resulting images were presented, using the same psychophysical experimental setting, the results showed that the perceived freshness also changed concordantly with the changes on the asymmetry of the luminance distribution. Finally, a model for vegetable freshness perception that utilizes only luminance cues is presented.     

Wavelet-based hybrid natural image modeling using generalized Gaussian and α-stable distributions

Natural image is characterized by its highly kurtotic and heavy-tailed distribution in wavelet domain. These typical non-Gaussian statistics are commonly described by generalized Gaussian density (GGD) or α-stable distribution. However, each of the two models has its own deficiency to capture the variety and complexity of real world scenes. Considering the statistical properties of GGD and α-stable distributions respectively, in this paper we propose a hybrid statistical model of natural image’s wavelet coefficients which is better in describing the leptokurtosis and heavy tails simultaneously. Based on a clever fusion of GGD and α-stable functions, we establish the optimal parametric hybrid model, and a close-formed Kullback–Leibler divergence of the hybrid model is derived for evaluating model accuracy. Experiment results and comparative studies demonstrate that the proposed hybrid model is closer to the true distribution of natural image’s wavelet coefficients than the single modeling using GGD or α-stable, while is beneficial for applications such as image comparison.     

Image analysis of the porous yttria-stabilized zirconia (YSZ) structure for a lanthanum ferrite-impregnated solid oxide fuel cell (SOFC) electrode

Image analysis and quantification were performed on porous scaffolds for building SOFC cathodes using the two types of YSZ powders. The two powders (U1 and U2) showed different particle size distribution and sinterability at 1300?°C. AC impedance on symmetrical cells was used to evaluate the performance of the electrode impregnated with 35-wt.% La_0.8Sr_0.2FeO₃. For example, at 700?°C, the electrode from U2 powder shows a polarization resistance (R_p) of 0.21?Ω?cm², and series resistance (R_s) of 8.5?Ω?cm² for an YSZ electrolyte of 2-mm thickness, lower than the electrode from U1 powder (0.25?Ω?cm² for R_p and 10?Ω?cm² for R_s) does. The quantitative study on image of the sintered scaffold indicates that U2 powder is better at producing architecture of high porosity or long triple phase boundary (TPB), which is attributed as the reason for the higher performance of the LSF-impregnated electrode.     

Difference Detection Between Two Images for Image Monitoring

In manufacturing industries, images are commonly used for quality control purposes. In such applications, if the quality of the products is good, then their images should be all similar to the image of a good-quality product. Therefore, comparison of images is a fundamental task in image-based quality control. This problem, however, is complicated in the sense that (1) observed images often contain noise, and (2) the related images need to be geometrically matched up first because images of different products could be geometrically mismatched because the relative positions between a camera and different products are often not exactly the same. The first issue requires a statistical method that can remove noise, and the second issue is related to the so-called image registration problem in the image processing literature. In this article, we propose effective methods for detecting difference between two images of products, and our proposed methods can accommodate both noise and geometric mismatch mentioned above. Theoretical results and numerical examples show that they can work effectively in applications.     

基于改进Renyi熵的运动目标图像提取仿真

运动目标图像提取有助于通过计算机视觉实现复杂变化背景下的图像细节分析,现有图像提取方法通常针对某一类图像作为研究对象,致使应用场合受到一定限制。针对运动目标图像的提取应用,提出了改进Renyi熵的运动目标图像提取方法。首先利用直方图对运动图像的YCbCr颜色概率进行估算,根据图像YCbCr颜色计算Renyi熵,然后设计相应的目标函数来确定阈值,并结合中值处理提高算法的抗噪声性能,最后对颜色的Y、Cb与Cr通道分割得到原始中心点,利用迭代处理更新中心点,并搜索出像素的边界阈值,从而实现运动目标图像的提取。通过仿真,分别从提取时间、计算熵值、以及目标图像识别率多个方面进行比较验证,证明了提出的改进Renyi熵的运动目标图像提取方法能够有效应对运动图像复杂多变的背景,提高了处理速度与提取准确度,具有较好的抗干扰能力。     

Face completion with Hybrid Dilated Convolution

Image completion is a challenging task which aims to fill the missing or masked regions in images with plausibly synthesized contents. In this paper, we focus on face image inpainting tasks, aiming at reconstructing missing or damaged regions of an incomplete face image given the context information. We specially design the U-Net architecture to tackle the problem. The proposed U-Net based method combines Hybrid Dilated Convolution (HDC) and spectral normalization to fill in missing regions of any shape with sharp structures and fine-detailed textures. We perform both qualitative and quantitative evaluation on two challenging face datasets. Experimental results demonstrate that our method outperforms previous learning-based inpainting methods. The proposed method can generate realistic and semantically plausible images.     

Turning a Digital Camera into an Absolute 2D Tele‐Colorimeter

We present a simple and effective technique for absolute colorimetric camera characterization, invariant to changes in exposure/aperture and scene irradiance, suitable in a wide range of applications including image‐based reflectance measurements, spectral pre‐filtering and spectral upsampling for rendering, to improve colour accuracy in high dynamic range imaging. Our method requires a limited number of acquisitions, an off‐the‐shelf target and a commonly available projector, used as a controllable light source, other than the reflected radiance to be known. The characterized camera can be effectively used as a 2D tele‐colorimeter, providing the user with an accurate estimate of the distribution of luminance and chromaticity in a scene, without requiring explicit knowledge of the incident lighting power spectra. We validate the approach by comparing our estimated absolute tristimulus values (XYZ data in ) with the measurements of a professional 2D tele‐colorimeter, for a set of scenes with complex geometry, spatially varying reflectance and light sources with very different spectral power distribution.     

A survey on analysis and implementation of state-of-the-art haze removal techniques

Haze is a poor-quality state described by the opalescent appearance of the atmosphere which reduces the visibility. It is caused by high concentrations of atmospheric air pollutants, such as dust, smoke and other particles that scatter and absorb sunlight. The poor visibility can result in the failure of multiple computer vision applications such as smart transport systems, image processing, object detection, surveillance etc. One of the major issues in the field of image processing is the restoration of images that are corrupted due to different degradations. Typically, the images or videos captured in the outside environment have low contrast, colour fade and restricted visibility due to suspended particles of the atmosphere that directly influence the image quality. This can cause difficulty in identifying the objects in the captured hazy images or frames. To address this problem, several image dehazing techniques have been developed in the literature, each of which has its own advantages and limitations, but effective image restoration remains a challenging task. In recent times, various learning (Machine learning & Deep learning) based methods greatly condensed the drawbacks of manual design of haze related features and reduces the difficulty in efficient restoration of images with less computational time and cost. The current state-of-the-art methods for haze free images, mainly from the last decade, are thoroughly examined in this survey. Moreover, this paper systematically summarizes the hardware implementations of various haze removal methods in real time. It is with the hope that this current survey acts as a reference for researchers in this scientific area and to provide a direction for future improvements based on current achievements.     

高光谱图像分类的融合分层深度网络联合稀疏表示算法

在高光谱图像分类领域中每个像素的局部邻域一旦包含来自不同类别的样本,联合稀疏表示将受邻域内字典原子与测试样本之间同谱异类的影响,严重降低分类性能.根据高光谱图像的特点,文中提出融合分层深度网络的联合稀疏表示算法.在光谱和空间特征学习之间交替提取判别性光谱信息和空间信息,构建兼具空谱特征的学习字典,用于联合稀疏表示.在分类过程中将学习字典与测试样本间的相关系数与分类误差融合并决策.在两个高光谱遥感数据集上的实验验证文中算法的有效性.