基于改进残差特征蒸馏的轻量级超分辨率网络

基于深度学习的图像超分辨率算法通常采用递归的方式或参数共享的策略来减少网络参数，这将增加网络的深度，使得运行网络花费大量的时间，从而很难将模型部署到现实生活中。为了解决上述问题，本文设计一种轻量级超分辨率网络，对中间特征的关联性及重要性进行学习，且在重建部分结合高分辨率图像的特征信息。首先，引入层间注意力模块，通过考虑层与层之间的相关性，自适应地分配重要层次特征的权重。其次，使用增强重建模块提取高分辨率图像中更精细的特征信息，以此得到更加清晰的重建图片。通过大量的对比实验表明，本文设计的网络与其他轻量级模型相比，有更小的网络参数量，并且在重建精度和视觉效果上都有一定的提升。     

No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion

This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa.     

SOINN-Based Abnormal Trajectory Detection for Efficient Video Condensation

With the evolution of video surveillance systems, the requirement of video storage grows rapidly; in addition, safe guards and forensic officers spend a great deal of time observing surveillance videos to find abnormal events. As most of the scene in the surveillance video are redundant and contains no information needs attention, we propose a video condensation method to summarize the abnormal events in the video by rearranging the moving trajectory and sort them by the degree of anomaly. Our goal is to improve the condensation rate to reduce more storage size, and increase the accuracy in abnormal detection. As the trajectory feature is the key to both goals, in this paper, a new method for feature extraction of moving object trajectory is proposed, and we use the SOINN (Self-Organizing Incremental Neural Network) method to accomplish a high accuracy abnormal detection. In the results, our method is able to shirk the video size to 10% storage size of the original video, and achieves 95% accuracy of abnormal event detection, which shows our method is useful and applicable to the surveillance industry.     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。     

The use of seed texture features for discriminating different cultivars of stored apples

The aim of this study was to identify the textural features of apple seeds with the highest discriminatory power for distinguishing the seeds of different apple cultivars with the use of discriminative classifiers. The seeds of apple cvs. Gala, Jonagold and Idared were scanned with the use of a flatbed scanner, and the acquired images were processed to calculate textural features from color channels: L, a, b, R, G, B, Y, U, V, H, S, I, X, Y and Z. The selected textures were used to develop discriminative models and distinguish the seeds of the examined apple cultivars. The analyses were performed for color spaces and color channels. The seeds of apple cvs. Gala and Idared were discriminated with 100% accuracy in models based on the textures from Lab and YUV color spaces and color channel L for the Naive Bayes, Multilayer Perceptron and Multi Class classifiers. The discriminatory accuracies of the seeds of all analyzed apple cultivars (Gala, Idared and Jonagold) ranged from 72% to 85%. The discriminatory accuracy of the textures selected from Lab color space for the Naive Bayes classifier reached 85%. The seeds of apple cvs. Gala and Jonagold were discriminated with 78–90% accuracy, and the discriminatory accuracy of the textures from Lab color space and color channel b for the Naive Bayes classifier reached 90%. The seeds of apple cvs. Idared and Jonagold were distinguished with 80–94% accuracy. The models based on textures from Lab color space and color channel b for the Naive Bayes classifier were characterized by 94% discriminatory accuracy. The study demonstrated that textural features are useful for discriminating the seeds of different apple cultivars.     

傣族织锦的艺术特征与传承

文章阐述了傣族织锦的艺术特征及传承发展现状,对其纹样、内涵及应用进行了分析,提出了傣锦传承和发展的措施与方法,为傣锦的保护和传承提供参考。     

显色图像分析技术在水稻叶耳花青甙显色目测分级中的应用

目的基于颜色特征的叶耳花青甙显色分级研究。方法以水稻倒二叶叶耳花青甙显色测试为切入点,在Emgu Cv3.0图像分析软件基础上,对完成图像分割的目标区域提取红绿蓝(red green blue, RGB)、色调饱和度亮度(hue saturation value, HSV)颜色特征,利用SPSS软件对颜色特征和测试分级数据进行相关性、回归等统计分析,建立颜色特征多元回归模型。结果叶耳花青甙显色强度与R(红色)、G(绿色)、B(蓝色)、H(色调)、V(亮度)极显著负相关;所有颜色特征值中,G值与叶耳花青甙显色强度相关性最显著,是一元和多元回归主要自变量; G值建立的一元回归模型中, R~2为0.980;多元回归模型R~2值为0.994。结论回归模型的拟合效果好,用这两个模型均可完成叶耳花青甙显色强度分级。     

伪标签置信选择的半监督集成学习视频语义检测

在视频语义检测中，有标记样本不足会严重影响检测的性能，而且伪标签样本中的噪声也会导致集成学习基分类器性能提升不足。为此，提出一种伪标签置信选择的半监督集成学习算法。首先，在三个不同的特征空间上训练出三个基分类器，得到基分类器的标签矢量；然后，引入加权融合样本所属某个类别的最大概率与次大概率的误差和样本所属某个类别的最大概率与样本所属其他各类别的平均概率的误差，作为基分类器的标签置信度，并融合标签矢量和标签置信度得到样本的伪标签和集成置信度；接着，选择集成置信度高的样本加入到有标签的样本集，迭代训练基分类器；最后，采用训练好的基分类器集成协作检测视频语义概念。该算法在实验数据集UCF11上的平均准确率到达了83.48%，与Co-KNN-SVM算法相比，平均准确率提高了3.48个百分点。该算法选择的伪标签能体现样本所属类别与其他类别的总体差异性，又能体现所属类别的唯一性，可减少利用伪标签样本的风险，有效提高视频语义概念检测的准确率。     

A deep neural network based classifier for brain tumor diagnosis

Classification process plays a key role in diagnosing brain tumors. Earlier research works are intended for identifying brain tumors using different classification techniques. However, the False Alarm Rates (FARs) of existing classification techniques are high. To improve the early-stage brain tumor diagnosis via classification the Weighted Correlation Feature Selection Based Iterative Bayesian Multivariate Deep Neural Learning (WCFS-IBMDNL) technique is proposed in this work. The WCFS-IBMDNL algorithm considers medical dataset for classifying the brain tumor diagnosis at an early stage. At first, the WCFS-IBMDNL technique performs Weighted Correlation-Based Feature Selection (WC-FS) by selecting subsets of medical features that are relevant for classification of brain tumors. After completing the feature selection process, the WCFS-IBMDNL technique uses Iterative Bayesian Multivariate Deep Neural Network (IBMDNN) classifier for reducing the misclassification error rate of brain tumor identification. The WCFS-IBMDNL technique was evaluated in JAVA language using Disease Diagnosis Rate (DDR), Disease Diagnosis Time (DDT), and FAR parameter through the epileptic seizure recognition dataset.