Results 271 to 280 of about 693,698 (310)

Deep Iris Feature Extraction

2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), 2021
Iris recognition refers to the automated process of individual recognition based on the patterns in their irises. Due to its uniqueness, it is a common modality used in biometric recognition. With a technique pioneered by Daugman, it was shown that it enables recognition with very low false match rates. However, existing approaches still offer room for
Andrej Hafner, Peter Peer, Ziga Emersic, Matej Vitek   +3 more
openaire   +1 more source

Deep neural network as deep feature learner

Journal of Intelligent & Fuzzy Systems, 2020
Features play an important role in image processing. But as not all features are comparable, relative features emerged. From the beginning, low-level features, extracted by experts, have been employed to create difficult models for learning the problem of relative attribute.
Pok Man Szeto, Hamid Parvin, Mohammad Reza Mahmoudi, Bui Anh Tuan, Kim-Hung Pho   +4 more
openaire   +1 more source

Deep adaptive feature enrichment

Expert Systems with Applications, 2020
Abstract Features play an important role in the performance of machine learning and classification applications. Usually, separability of classes by using raw or original features are so low, and it is necessary to use complex classifiers with high computational costs or use enrichment modules to increase distinctiveness of features. In this paper, a
Mehran Taghipour-Gorjikolaie, Javad Sadri, Seyed Mohammad Razavi   +2 more
openaire   +2 more sources

Object‐aware deep feature extraction for feature matching

Concurrency and Computation: Practice and Experience, 2023
SummaryFeature extraction is a fundamental step in the feature matching task. A lot of studies are devoted to feature extraction. Recent researches propose to extract features by pre‐trained neural networks, and the output is used for feature matching.
Zuoyong Li, Weice Wang, Taotao Lai, Haiping Xu, Pantea Keikhosrokiani   +4 more
openaire   +1 more source

Learning deep classifiers with deep features

2016 IEEE International Conference on Multimedia and Expo (ICME), 2016
Visual separability between different objects in various image classification tasks is highly uneven. As a consequence, humans need different levels of detailed descriptions to separate objects in multi-granularity similarities. Meanwhile, deep networks, such as convolutional neural networks (C-NNs) have demonstrated great ability in multilevel ...
Jie Lei 0002, Xinhui Song, Li Sun, Mingli Song, Na Li, Chun Chen 0001   +5 more
openaire   +1 more source

Supervised Deep Feature Embedding With Handcrafted Feature

IEEE Transactions on Image Processing, 2019
Image representation methods based on deep convolutional neural networks (CNNs) have achieved the state-of-the-art performance in various computer vision tasks, such as image retrieval and person re-identification. We recognize that more discriminative feature embeddings can be learned with supervised deep metric learning and handcrafted features for ...
Shichao Kan, Yigang Cen, Zhihai He, Zhi Zhang 0005, Linna Zhang, Yanhong Wang   +5 more
openaire   +2 more sources

Speaker verification with deep features

2014 International Joint Conference on Neural Networks (IJCNN), 2014
Due to great success of deep learning in speech recognition, there has been interest of applying deep learning to speaker verification. Previous investigations usually focus on using deep neural network as new classifiers or to extract speaker dependent features.
Yuan Liu, Tianfan Fu, Yuchen Fan 0001, Yanmin Qian, Kai Yu 0004   +4 more
openaire   +1 more source

Evolvable Deep Features

2018
Feature extraction is the first step in building real-life classification engines—it aims at elaborating features to characterize objects that are to be labeled by a trained model. Time-consuming feature extraction requires domain expertise to effectively design features.
Jakub Nalepa, Grzegorz Mrukwa, Michal Kawulok   +2 more
openaire   +1 more source

Deep Semantic Feature Matching

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Estimating dense visual correspondences between objects with intra-class variation, deformations and background clutter remains a challenging problem. Thanks to the breakthrough of CNNs there are new powerful features available. Despite their easy accessibility and great success, existing semantic flow methods could not significantly benefit from these
Nikolai Ufer, Björn Ommer
openaire   +1 more source