Convolutional Neural Network Based Age Estimation From Facial Image And Depth Prediction From Single Image
Download Convolutional Neural Network Based Age Estimation From Facial Image And Depth Prediction From Single Image PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Convolutional Neural Network Based Age Estimation From Facial Image And Depth Prediction From Single Image book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Convolutional Neural Network Based Age Estimation from Facial Image and Depth Prediction from Single Image
Convolutional neural network (CNN), one of the most commonly used deep learning methods, has been applied to various computer vision and pattern recognition tasks, and has achieved state-of-the-art performance. Most recent research work on CNN focuses on the innovations of the structure. This thesis explores both the innovation of structure and final label encoding of CNN. To evaluate the performance of our proposed network structure and label encoding method, two computer vision tasks are conducted, namely age estimation from facial image and depth estimation from a single image. For age estimation from facial image, we propose a novel hierarchical aggregation based deep network to learn aging features from facial images and apply our encoding method to transfer the discrete aging labels into a possibility label, which enables the CNN to conduct a classification task rather than regression task. In contrast to traditional aging features, where identical filter is applied to the en- tire facial image, our deep aging feature can capture both local and global cues in aging. Under our formulation, convolutional neural network (CNN) is employed to extract region specific features at lower layers. Then, low layer features are hierarchically aggregated by using fully connected way to consecutive higher layers. The resultant aging feature is of dimensionality 110, which achieves both good discriminative ability and efficiency. Experimental results of age prediction on the MORPH-II and the FG-NET databases show that the proposed deep aging feature outperforms state-of-the-art aging features by a margin. Depth estimation from a single image is an essential component toward understanding the 3D geometry of a scene. Compared with depth estimation from stereo images, depth map estimation from a single image is an extremely challenging task. This thesis addresses this task by regression with deep features, combined with surface normal constrained depth refinement. The proposed framework consists of two steps. First, we implement a convolutional neural network (CNN) to learn the mapping from multi-scale image patches to depth on the super-pixel level. In this step, we apply the proposed label encoding method to transfer the continuous depth labels to be possibility vectors, which reformulates the regression task to a classification task. Second, we refine predicted depth at the super-pixel level to the pixel level by exploiting surface normal constraints on depth map. Experimental results of depth estimation on the NYU2 dataset show that the proposed method achieves a promising performance and has a better performance compared with methods without the proposed label encoding. The above tasks show the proposed label encoding method has promising performance, which is another direction of CNN structure optimization.
Proceedings of Seventh International Congress on Information and Communication Technology
This book gathers selected high-quality research papers presented at the Seventh International Congress on Information and Communication Technology, held at Brunel University, London, on February 21–24, 2022. It discusses emerging topics pertaining to information and communication technology (ICT) for managerial applications, e-governance, e-agriculture, e-education and computing technologies, the Internet of Things (IoT) and e-mining. Written by respected experts and researchers working on ICT, the book offers a valuable asset for young researchers involved in advanced studies. The work is presented in four volumes.
Proceedings of the Second International Conference on Innovations in Computing Research (ICR’23)
The Second International Conference on Innovations in Computing Research (ICR’23) brings together a diverse group of researchers from all over the world with the intent of fostering collaboration and dissemination of the innovations in computing technologies. The conference is aptly segmented into six tracks: Data Science, Computer and Network Security, Health Informatics and Medical Imaging, Computer Science and Computer Engineering Education, Internet of Things, and Smart Cities/Smart Energy. These tracks aim to promote a birds-of-the-same-feather congregation and maximize participation. The Data Science track covers a wide range of topics including complexity score for missing data, deep learning and fake news, cyberbullying and hate speech, surface area estimation, analysis of gambling data, car accidents predication model, augmenting character designers’ creativity, deep learning for road safety, effect of sleep disturbances on the quality of sleep, deep learning-based path-planning, vehicle data collection and analysis, predicting future stocks prices, and trading robot for foreign exchange. Computer and Network Security track is dedicated to various areas of cybersecurity. Among these are decentralized solution for secure management of IoT access rights, multi-factor authentication as a service (MFAaaS) for federated cloud environments, user attitude toward personal data privacy and data privacy economy, host IP obfuscation and performance analysis, and vehicle OBD-II port countermeasures. The Computer Science and Engineering Education track enfolds various educational areas, such as data management in industry–academia joint research: a perspective of conflicts and coordination in Japan, security culture and security education, training and awareness (SETA), influencing information security management, engaging undergraduate students in developing graphical user interfaces for NSF funded research project, and emotional intelligence of computer science teachers in higher education. On the Internet of Things (IoT) track, the focus is on industrial air quality sensor visual analytics, social spider optimization meta-heuristic for node localization optimization in wireless sensor networks, and privacy aware IoT-based fall detection with infrared sensors and deep learning. The Smart Cities and Smart Energy track spans various areas, which include, among others, research topics on heterogeneous transfer learning in structural health monitoring for high-rise structures and energy routing in energy Internet using the firefly algorithm.