Methods of local features extraction in person authentication task by face thermographic image
Annotation
The paper presents a methods of image local features extraction research in relation to people authentication problem by face thermogram. As a part of the study, there were formed two datasets for methods training and testing: photographic images and face images in the long-wavelength infrared specter (LWIR) with various factors. The novelty of this study is due to the approach to collecting datasets to verify the accuracy of authentication methods. The dataset was collected with more realistic conditions that affect the quality of authentication, such as changing facial expressions, wearing glasses, medical masks, applying make-up/cosmetics, changing the lighting and temperature conditions of the environment, rotating the head. The methods core is based on the idea of constructing a vector of image features while reducing the dimension and highlighting the boundaries. Likewise, the methods of this group cope well with extracting features task on images and are widely used in the tasks of authentication by 2D face image, as well as in other computer vision tasks. In this paper, four classical methods of local feature extraction are considered: the method of locally binary templates, Gabor wavelets, scale-invariant feature transformation, and Weber’s local descriptor. The classifiers for the feature vectors comparison in this research are SVM and the simplest Perceptron — the basic methods of machine learning. As part of the study, a comparative analysis of each method was carried out in relation to the collected datasets. The methods were trained and tested on a collected face dataset of over 632,000 images of 152 people. As a result of the comparative analysis, it can be concluded that the method of local binary features demonstrates the best result among the considered methods for both types of data: for face thermograms (for SVM — 0,57, for Perceptron — 0,58), for photographic images (for SVM — 0,71, for Perceptron — 0,73). Furthermore, the SIFT method showed similar results: for face thermograms (for SVM — 0,58, for Perceptron — 0,55), for photographic images (for SVM — 0,72, for Perceptron — 0,74). Gabor filters and Weber local descriptor application demonstrate a low accuracy rate in the authentication task by both types of data. The results of the work can be used in access control and management systems to increase the fault tolerance of person authentication. The appliance of the considered methods are effective in the tasks such as processing thermograms for authentication a person by so-called “secondary” signs, for example, by the veins and vessels on face patterns, in cases of facial expressions and appearance changes.
Keywords
Постоянный URL
Articles in current issue
- Dynamic range restrictions influence of the fiber-optic towed seismic streamer on the seismogram quality
- Control of MIMO linear plants with a guarantee for the controlled signals to stay in a given set
- Elliposoidal estimates of trajectory sensitivity of multi-dimensional processes based on generalized singular values problems
- Nonlinear rheological models and their application to describe the mechanical behavior of highly oriented polymer materials
- Research on the effectiveness of noise reduction when encoding a lossless speech signal
- Lightweight approach for malicious domain detection using machine learning
- Cloud computing simulation model with a sporadic mechanism of parallel task solving control
- Classification of short texts using a wave model
- Algorithm for energy-efficient interaction of wireless sensor network nodes
- Auxiliary arbitrary waveform generator for fiber optic gyroscope
- Constructing twitter corpus of Iraqi Arabic Dialect (CIAD) for sentiment analysis
- A novel framework for the prevention of black-hole in wireless sensors using hybrid convolution network
- Modern variations of McEliece and Niederreiter cryptosystems
- Lightweight ECC and token based authentication mechanism for WSN-IoT
- Model of the acoustic path of a separatecombined optical-acoustic transducer
- Study on received signal strength of femtocell with circular and rectangular microstrip patch antenna designed at 2.55 GHz
- Whirlpool Hash Mutual Biometric Serpent Authentication (WPHMBSA) for secured data access in cloud environment
- IRDFPR-CMDNN: An energy efficient and reliable routing protocol for improved data transmission in MANET
- Influence investigation of electromagnetic-acoustic transducer parameters on thickness measurement accuracy by numerical modeling methods
- Detection of quadcopter propeller failure by machine learning methods
- Throughput modeling of cellular network systems with spatial precoding
- Visual display system of changes in physiological state for patients with chronic disorders
- Method for discovering spatial arm positions with depth sensor data at low-performance devices