Single image dehazing using a new color channel

Images with hazy scene suffer from low-contrast, which reduces the visible quality of the scene, thus making object detection a more challenging task. Low-contrast can result from foggy weather conditions during image acquisition. Dehazing is a process of removal of haze from the photography of a hazy scene. Single-image dehazing based on dark channel priors are well-known techniques in this field. However, the performance of such techniques is limited to priors or constraints. Moreover, this type of method fails when images have sky-region. So, a method is proposed, which can restore the visibility of hazy images. First, a hazy image is divided into blocks of size 32 × 32, then the score of each block is calculated to select a block having the highest score. Atmospheric light is calculated from the selected block. A new color channel is considered to remove atmospheric scattering, obtained channel value and atmospheric light are then used to calculate the transmission map in the second step. Third, radiance is computed using a transmission map and atmospheric light. The illumination scaling factor is adopted to enhance the quality of a dehazed image in the final step. Experiments are performed on six datasets namely, I-HAZE, O-HAZE, BSDS500, FRIDA, RESIDE dataset and natural images from Google. The proposed method is compared against 11 state-of-the-art methods. The performance is analyzed using fourteen quantitative evaluation metrics. All the results demonstrate that the proposed method outperforms 11 state-of-the-art methods in most of the cases.     

Droplet Entrainment Analysis in a Flash Evaporator with an Image-Based Measurement Technique

Local droplet sizes and volumes of entrained liquid are captured with an image-based measurement technique for comparison with a conventional, integral method for entrainment analysis. Experiments in a forced circulation flash evaporation were performed for different operating conditions and with two different chemical systems. Droplet size and frequency rise with an increase in thermal energy input. The local readings confirm the trends found by the integral measurement method. The modification of the image-based probe enables the detection of small (≈ 10 µm) and at the same time fast droplets under challenging operating conditions, such as vacuum and superheated feed similar to industrial process conditions.     

Learning shape and texture progression for young child face aging

Face aging (FA) for young faces refers to rendering the aging faces at target age for an individual, generally under 20s, which is an important topic of facial age analysis. Unlike traditional FA for adults, it is challenging to age children with one deep learning-based FA network, since there are deformations of facial shapes and variations of textural details. To alleviate the deficiency, a unified FA framework for young faces is proposed, which consists of two decoupled networks to apply aging image translation. It explicitly models transformations of geometry and appearance using two components: GD-GAN, which simulates the Geometric Deformation using Generative Adversarial Network; TV-GAN, which simulates the Textural Variations guided by the age-related saliency map. Extensive experiments demonstrate that our method has advantages over the state-of-the-art methods in terms of synthesizing visually plausible images for young faces, as well as preserving the personalized features.     

Past is important: Improved image captioning by looking back in time

A major development in the area of image captioning consists of trying to incorporate visual attention in the design of language generative model. However, most previous studies only emphasize its role in enhancing visual composition at the current moment, while neglect its role in global sequence reasoning. This problem appears not only in captioning model, but also in reinforcement learning structure. To tackle this issue, we first propose a Visual Reserved model that enables previous visual context to be considered for the current sequence reasoning. Next, a Attentional-Fluctuation Supervised model is also proposed in reinforcement learning structure. Compared against the traditional strategies that only take non-differentiable Natural Language Processing (NLP) metrics as the incentive standard, the proposed model regards the fluctuation of previous attention matrix as an important indicator to judge the convergence of the captioning model. The proposed methods have been tested on MS-COCO captioning dataset and achieve competitive results evaluated by the evaluation server of MS COCO captioning challenge.     

Secure image encryption scheme using 4D-Hyperchaotic systems based reconfigurable pseudo-random number generator and S-Box

This paper introduces the design of a hardware efficient reconfigurable pseudorandom number generator (PRNG) using two different feedback controllers based four-dimensional (4D) hyperchaotic systems i.e. Hyperchaotic-1 and -2 to provide confidentiality for digital images. The parameter's value of these two hyperchaotic systems is set to be a specific value to get the benefits i.e. all the multiplications (except a few multiplications) are performed using hardwired shifting operations rather than the binary multiplications, which doesn't utilize any hardware resource. The ordinary differential equations (ODEs) of these two systems have been exploited to build a generic architecture that fits in a single architecture. The proposed architecture provides an opportunity to switch between two different 4D hyperchaotic systems depending on the required behavior. To ensure the security strength, that can be also used in the encryption process in which encrypt the input data up to two times successively, each time using a different PRNG configuration. The proposed reconfigurable PRNG has been designed using Verilog HDL, synthesized on the Xilinx tool using the Virtex-5 (XC5VLX50T) and Zynq (XC7Z045) FPGA, its analysis has been done using Matlab tool. It has been found that the proposed architecture of PRNG has the best hardware performance and good statistical properties as it passes all fifteen NIST statistical benchmark tests while it can operate at 79.101-MHz or 1898.424-Mbps and utilize only 0.036 %, 0.23 %, and 1.77 % from the Zynq (XC7Z045) FPGA's slice registers, slice LUTs, and DSP blocks respectively. Utilizing these PRNGs, we design two 16 × 16 substitution boxes (S-boxes). The proposed S-boxes fulfill the following criteria: Bijective, Balanced, Non-linearity, Dynamic Distance, Strict Avalanche Criterion (SAC) and BIC non-linearity criterion. To demonstrate these PRNGs and S-boxes, a new three different scheme of image encryption algorithms have been developed: a) Encryption using S-box-1, b) Encryption using S-box-2 and, c) Two times encryption using S-box-1 and S-box-2. To demonstrate that the proposed cryptosystem is highly secure, we perform the security analysis (in terms of the correlation coefficient, key space, NPCR, UACI, information entropy and image encryption quantitatively in terms of (MSE, PSNR and SSIM)).     

稳产国Ⅵ柴油并兼产喷气燃料技术方案的工业应用

介绍了浙江石油化工有限公司新建的3 Mt/a柴油加氢精制装置，其配套使用中国石化石油化工科学研究院有限公司开发的催化剂级配技术，并实施了可根据原料供应及市场产品需求情况灵活调整切换的2种生产技术方案。1 a的安稳生产运行结果表明:该装置以直馏柴油为主原料，通过分馏塔的馏分切割及其侧线抽出，实现了稳产国Ⅵ柴油并兼产喷气燃料技术方案的工业化应用；在实施以兼产喷气燃料为主的生产技术方案时，通过调整常一线柴油的掺炼量，不仅可以生产含硫量小于10.0 μg/g的精制柴油产品，同时兼产所得到的喷气燃料产品含硫量小于0.5 μg/g，赛波特颜色号值大于30；在实施主产精制柴油组分方案时，通过掺炼质量分数为20%~40%的催化柴油，并使所提炼得到的精制柴油组分含硫量小于6.0 μg/g的前提下，这些精制柴油组分产品既可直接作为满足国Ⅵ柴油产品出厂待售，也可作为柴油调和组分储存待用于产品的进一步优化。     

Image sequence-based risk behavior detection of power operation inspection personnel

A novel image sequence-based risk behavior detection method to achieve high-precision risk behavior detection for power maintenance personnel is proposed in this paper. In this method, the original image sequence data is first separated from the foreground and background. Then, the free anchor frame detection method is used in the foreground image to detect the personnel and correct their direction. Finally, human posture nodes are extracted from each frame of the image sequence, which are then used to identify the abnormal behavior of the human. Simulation experiment results demonstrate that the proposed algorithm has significant advantages in terms of the accuracy of human posture node detection and risk behavior identification.     

Physiochemical structure of semicoke derived from co-carbonization of coal and sawdust blends

The substitution of coal blending with sawdust had been widely investigated for metallurgical coke production. In this paper, the physiochemical structures of the semicoke derived from sawdust/coals blends co-coking were characterized by several analytical techniques including FTIR-ATR, XPS, NMR, OM, and SEM. Meanwhile, the influence of the sawdust on the physicochemical properties of the sawdust/coals blends were also investigated. Results indicated that partial substitution of coal blending with sawdust benefited from the formation of colloid and optical anisotropy due to the positive synergetic effect, whereas high proportion of sawdust (>10 wt%) inhibited the agglomeration of semi-coke. On the other hand, the semicoke consisted primarily of aromatic carbons replaced by the oxygen linked to carbons and aliphatic carbons when the coal blending was replaced by high proportion of sawdust, causing a less polyaromatic graphite-like structure formation in the semicoke.     

安卓平台上的医用图像信息采集系统的开发设计

为了探讨在安卓平台上构建医用图像采集系统的开发个案,分析通过以智能手机、平板电脑为核心安卓设备通过拍照获得化验单数据后进行文本识别并提交智慧医疗系统的解决方案。本文首先通过二值化算法形成低阈值图像数据,使用卷积神经元网络算法对文本进行逐一识别,使用K-means算法对识别后的单字文本进行字段记录值的整合并形成元数据库服务于其他智慧医疗系统模块。在使用9000组数据对神经元网络进行前期训练的前提下,该系统的识别准确率达到了99.5%以上。本系统具有一定的可行性,对未来智慧医疗的系统开发有实践意义。