The Video-Based Age and Gender Recognition with Convolution Neural Networks
The paper reviews the problem of age and gender recognition methods for video data using modern deep convolutional neural networks. We present the comparative analysis of classifier fusion algorithms to aggregate decisions for individual frames. We implemented the video-based recognition system with several aggregation methods to improve the age and gender identification accuracy. The experimental comparison of the proposed approach with traditional simple voting using IJB-A, Indian Movies, and Kinect datasets is provided. It is demonstrated that the most accurate decisions are obtained using the geometric mean and mathematical expectation of the outputs at softmax layers of the convolutional neural networks for gender recognition and age prediction, respectively.
In this article, the effectiveness of content services is formalized on the basis of an analysis of the regulatory legal acts regulating the relationship in the market for consuming content services. The use of cloud computing for the widespread introduction of services to assess the consumer quality of content services is considered. The article describes the security aspects and the possibility of implementing security requirements for mobile applications and discusses the proposed circuit-technical options for implementing the principles of building information-safe mobile applications that are reducible to the typical info-communication technological interaction.
Because of rapid mobile technologies expansion, there is a gap between the complexity of mobile applications and the complexity of employed testing techniques. This paper is aimed at reducing the gap from the theoretical point of view. The paper comprises an analysis of mobile applications testing processes, mobile applications testing metrics, along with the full test coverage criterion. It also contains an integral criterion of the testing processes optimization which is based on the idea of summing the corresponding sub-processes times. The presented criterion leads to an assumption of the tests generation approach efficiency. Therefore a partial criterion of the tests generation process is proposed. The mathematical model of this partial criterion is based on the properties of different algebraic expressions. The numerical results section includes processes comparison and some estimates.
The article describes an approach for extraction of user preferences based on the analysis of a gallery of photos and videos on mobile device. It is proposed to firstly use fast SSD-based methods in order to detect objects of interests in offline mode directly on mobile device. Next we perform facial analysis of all visual data: extract feature vectors from detected facial regions, cluster them and select public photos and videos which do not contain faces from the large clusters of an owner of mobile device and his or her friends and relatives. At the second stage, these public images are processed on the remote server using very accurate but rather slow object detectors. Experimental study of several contemporary detectors is presented with the specially designed subset of MS COCO, ImageNet and Open Images datasets.
The EPiC Series in Language and Linguistics publishes high quality collections of papers in language, linguistics and related areas.
A new public dataset of traffic sign images is presented. The dataset is intended for training and testing the algorithms of traffic sign recognition. We describe the dataset structure and guidelines for working with the dataset, comparing it with the previously published traffic sign datasets. The evaluation of modern detection and classification algorithms conducted using the proposed dataset has shown that existing methods of recognition of a wide class of traffic signs do not achieve the accuracy and completeness required for a number of applications.
It has been shown that the activations invoked by an image within the top layers of a large convolutional neural network provide a high-level descriptor of the visual content of the image. In this paper, we investigate the use of such descriptors (neural codes) within the image retrieval application. In the experiments with several standard retrieval benchmarks, we establish that neural codes perform competitively even when the convolutional neural network has been trained for an unrelated classification task (e.g. Image-Net). We also evaluate the improvement in the retrieval performance of neural codes, when the network is retrained on a dataset of images that are similar to images encountered at test time. We further evaluate the performance of the compressed neural codes and show that a simple PCA compression provides very good short codes that give state-of-the-art accuracy on a number of datasets. In general, neural codes turn out to be much more resilient to such compression in comparison other state-of-the-art descriptors. Finally, we show that discriminative dimensionality reduction trained on a dataset of pairs of matched photographs improves the performance of PCA-compressed neural codes even further. Overall, our quantitative experiments demonstrate the promise of neural codes as visual descriptors for image retrieval.
This book focuses on the core areas of computing and their applications in the real world. Presenting papers from the Computing Conference 2020 covers a diverse range of research areas, describing various detailed techniques that have been developed and implemented.
The Computing Conference 2020, which provided a venue for academic and industry practitioners to share new ideas and development experiences, attracted a total of 514 submissions from pioneering academic researchers, scientists, industrial engineers and students from around the globe. Following a double-blind, peer-review process, 160 papers (including 15 poster papers) were selected to be included in these proceedings.
Featuring state-of-the-art intelligent methods and techniques for solving real-world problems, the book is a valuable resource and will inspire further research and technological improvements in this important area.
Because of rapid mobile technologies expansion, there is a gap between the complexity of mobile applications and the complexity of employed testing techniques. This paper is aimed at reducing the gap from the practical point of view. Tests generation techniques are widely spread, but none of them are optimized for mobile applications. This paper proposes an analytical model of tests generation process, which is based on prototypes and takes mobile specificity into consideration. Along with this an analysis of existing tests generation approaches has beenmade. The flowchart of the proposed model has been submitted with the model. The efficiency of the model has been described in the numerical results section.
In this work, we describe the problem of automated pollen recognition using images from lighting microscope. Automated pollen recognition related to such important tasks as honey quality control, air quality control for helping to asthma and allergy patients, paleopalynology, forensic palynology. We describe the problem solution based on machine learning and CUDA. Extracted features and preprocessing steps are described. Results are compared on dataset of 5 specie. The best model is convolutional neural network with 89% of accuracy. Its performance was particularly up twice using CUDA.