scholarly journals A Mobile Computing Method Using CNN and SR for Signature Authentication with Contour Damage and Light Distortion

2018 ◽  
Vol 2018 ◽  
pp. 1-10
Author(s):  
Mei Wang ◽  
Ke Zhai ◽  
Chi Harold Liu ◽  
Yujie Li
Keyword(s):  
Mobile Computing ◽  
Recognition Accuracy ◽  
Computation Time ◽  
Image Authentication ◽  
Affect Image Quality ◽  
Probability Threshold ◽  
Minimum Probability ◽  
Human Feature ◽  
Computing Method ◽  
Mean Filtering

A signature is a useful human feature in our society, and determining the genuineness of a signature is very important. A signature image is typically analyzed for its genuineness classification; however, increasing classification accuracy while decreasing computation time is difficult. Many factors affect image quality and the genuineness classification, such as contour damage and light distortion or the classification algorithm. To this end, we propose a mobile computing method of signature image authentication (SIA) with improved recognition accuracy and reduced computation time. We demonstrate theoretically and experimentally that the proposed golden global-local (G-L) algorithm has the best filtering result compared with the methods of mean filtering, medium filtering, and Gaussian filtering. The developed minimum probability threshold (MPT) algorithm produces the best segmentation result with minimum error compared with methods of maximum entropy and iterative segmentation. In addition, the designed convolutional neural network (CNN) solves the light distortion problem for detailed frame feature extraction of a signature image. Finally, the proposed SIA algorithm achieves the best signature authentication accuracy compared with CNN and sparse representation, and computation times are competitive. Thus, the proposed SIA algorithm can be easily implemented in a mobile phone.

scholarly journals Dynamic load identification algorithm based on Newmark-β and self-filtering

2019 ◽  
Vol 234 (1) ◽  
pp. 96-107
Author(s):  
Fan Yuchuan ◽  
Chunyu Zhao ◽  
Yu Hongye ◽  
Bangchun Wen
Keyword(s):  
Dynamic Load ◽  
Recognition Accuracy ◽  
Computation Time ◽  
The Self ◽  
Iteration Algorithm ◽  
Identification Algorithm ◽  
Load Identification ◽  
Filtering Algorithm ◽  
Recognition Result

In this paper, a dynamic load identification iteration algorithm based on Newmark -β is proposed. Aiming at the problem of excessive iteration error in the process of calculation, a self-filtering algorithm is proposed and added to the load identification algorithm. After adding the self-filtering algorithm, the recognition accuracy of the algorithm has been improved significantly. The recognition result of the proposed method and explicit Newmark- β method is compared by simulations and experiment. The results show that the recognition precision and calculation efficiency of this algorithm are higher, especially in the aspect of calculation efficiency, the proposed method has obvious advantages. Under the same conditions, the proposed method can save a lot of computation time.

scholarly journals Real-Time Recognition Method for 0.8 cm Darning Needles and KR22 Bearings Based on Convolution Neural Networks and Data Increase

2018 ◽  
Vol 8 (10) ◽  
pp. 1857 ◽  
Author(s):  
Jing Yang ◽  
Shaobo Li ◽  
Zong Gao ◽  
Zheng Wang ◽  
Wei Liu
Keyword(s):  
Object Recognition ◽  
Real Time ◽  
High Speed ◽  
Feature Fusion ◽  
Recognition Accuracy ◽  
Computation Time ◽  
Real Data ◽  
Accurate Method ◽  
Recognition Method ◽  
Industrial Object

The complexity of the background and the similarities between different types of precision parts, especially in the high-speed movement of conveyor belts in complex industrial scenes, pose immense challenges to the object recognition of precision parts due to diversity in illumination. This study presents a real-time object recognition method for 0.8 cm darning needles and KR22 bearing machine parts under a complex industrial background. First, we propose an image data increase algorithm based on directional flip, and we establish two types of dataset, namely, real data and increased data. We focus on increasing recognition accuracy and reducing computation time, and we design a multilayer feature fusion network to obtain feature information. Subsequently, we propose an accurate method for classifying precision parts on the basis of non-maximal suppression, and then form an improved You Only Look Once (YOLO) V3 network. We implement this method and compare it with models in our real-time industrial object detection experimental platform. Finally, experiments on real and increased datasets show that the proposed method outperforms the YOLO V3 algorithm in terms of recognition accuracy and robustness.

MODEL-BASED ANALYSIS AND UNDERSTANDING OF CHECK FORMS

1994 ◽  
Vol 08 (05) ◽  
pp. 1053-1080 ◽  
Author(s):  
THIEN MINH HA ◽  
HORST BUNKE
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Accuracy ◽  
Financial Institution ◽  
Computation Time ◽  
Model Matching ◽  
Post Offices ◽  
Fully Automatic ◽  
Sample Set ◽  
Model Based Analysis

Check forms are used by many people in daily life for money remittances. Surprisingly, the processing of these forms at banks and post offices is only partly automated. In this paper, we consider a particular kind of form, viz., the GIRO check forms used in Switzerland. We will describe a fully automatic system which is able to recognise the financial institution, the name and address of the receiver, and the account number on a GIRO check. The system comprises procedures for binarization, segmentation, model matching, and optical character recognition (OCR). Experiments on a sample set of 48 checks have shown promising results in terms of both computation time and recognition accuracy.

scholarly journals Performance Evaluation of Feature Extraction Techniques in Multi-Layer Based Fingerprint Ethnicity Recognition System

2019 ◽  
pp. 1-9
Author(s):  
H. O. Aworinde ◽  
A. O. Afolabi ◽  
A. S. Falohun ◽  
O. T. Adedeji
Keyword(s):  
Feature Extraction ◽  
Correlation Coefficient ◽  
Recognition Accuracy ◽  
Computation Time ◽  
Principal Component ◽  
Kernel Principal Component Analysis ◽  
Extraction Techniques ◽  
Recognition Time ◽  
Memory Space ◽  
Linear Discriminant

This paper is set out to evaluate the performance of feature extraction techniques that can determine ethnicity of an individual using fingerprint biometric technique and deep learning approach. Hence, fingerprint images of one thousand and fifty-four (1054) persons of three different ethnic groups (Yoruba, Igbo and Middle-Belt) in Nigeria were captured. Kernel Principal Component Analysis (K-PCA) and Kernel Linear Discriminant Analysis (KLDA) were used independently for feature extraction while Convolutional Neural Network (CNN) was used for supervised learning of the features and classification. The results showed that out of sixty (60) individual fingerprints tested, eight (8) were classified as Yoruba, forty-eight (48) as Igbo and four (4) as Hausa. The Recognition Accuracy for K-PCA was 93.97% and KLDA was 97.26%. For Average Recognition time, K-PCA used 9.98seconds while KLDA used 10.02seconds. The memory space utilized by K-PCA was 94.57KB while KLDA utilized 52.17KB. T-Test paired sample statistics was carried out on the result obtained; the outcome presented reveal that KLDA outperformed the K-PCA technique in terms of Recognition Accuracy. The relationship between the average recognition time () and threshold value () was found to be polynomial of order four (4) with a high correlation coefficient for KPCA and polynomial of order three (3) with a high correlation coefficient for KLDA. In terms of computation time analysis, KLDA is computationally more expensive than KPCA by reason of processing speed.

scholarly journals A Rapid Beam Pointing Determination and Beam-Pointing Error Analysis Method for a Geostationary Orbiting Microwave Radiometer Antenna in Consideration of Antenna Thermal Distortions

Sensors ◽  
2021 ◽  
Vol 21 (17) ◽  
pp. 5943
Author(s):  
Hualong Hu ◽  
Xiaochong Tong ◽  
He Li
Keyword(s):  
Real Time ◽  
Electromechanical Coupling ◽  
Microwave Radiometer ◽  
Computation Time ◽  
Optical Path ◽  
Microwave Antenna ◽  
Analysis Method ◽  
Pointing Error ◽  
Computing Method ◽  
The Ideal

When observing the Earth’s radiation signal with a geostationary orbiting (GEO) mechanically scanned microwave radiometer, it is necessary to correct the antenna beam pointing (ABP) in real time for the deviation caused by thermal distortions of antenna reflectors with the help of the on-board Image Navigation and Registration (INR) system during scanning of the Earth. The traditional ABP determination and beam-pointing error (BPE) analysis method is based on the electromechanical coupling principle, which usurps time and computing resources and thus cannot meet the requirement for frequent real-time on-board INR operations needed by the GEO microwave radiometer. For this reason, matrix optics (MO), which is widely used in characterizing the optical path of the visible/infrared sensor, is extended to this study so that it can be applied to model the equivalent optical path of the microwave antenna with a much more complicated configuration. Based on the extended MO method, the ideal ABP determination model and the model for determining the actual ABP affected by reflector thermal distortions are deduced for China’s future GEO radiometer, and an MO-based BPE computing method, which establishes a direct connection between the reflector thermal distortion errors (TDEs) and the thermally induced BPE, is defined. To verify the overall performance of the extended MO method for rapid ABP determination, the outputs from the ideal ABP determination model were compared to calculations from GRASP 10.3 software. The experimental results show that the MO-based ABP determination model can achieve the same results as GRASP software with a significant advantage in computational efficiency (e.g., at the lowest frequency band of 54 GHz, our MO-based model yielded a 4,730,000 times faster computation time than the GRASP software). After validating the correctness of the extended MO method, the impacts of the reflector TDEs on the BPE were quantified on a case-by-case basis with the help of the defined BPE computing method, and those TDEs that had a significant impact on the BPE were therefore identified. The methods and results presented in this study are expected to set the basis for the further development of on-board INR systems to be used in China’s future GEO microwave radiometer and benefit the ABP determination and BEP analysis of other antenna configurations to a certain extent.

Influence of the Acoustic Reflex on Vowel Recognition

1986 ◽  
Vol 29 (3) ◽  
pp. 420-424 ◽  
Author(s):  
Michael Dorman ◽  
Ingrid Cedar ◽  
Maureen Hannley ◽  
Marjorie Leek ◽  
Julie Mapes Lindholm
Keyword(s):  
Auditory System ◽  
Sound Pressure ◽  
Dynamic Range ◽  
Recognition Accuracy ◽  
Pressure Level ◽  
Acoustic Reflex ◽  
The Poor ◽  
Stapedial Reflex ◽  
Vowel Recognition ◽  
High Sound

Computer synthesized vowels of 50- and 300-ms duration were presented to normal-hearing listeners at a moderate and high sound pressure level (SPL). Presentation at the high SPL resulted in poor recognition accuracy for vowels of a duration (50 ms) shorter than the latency of the acoustic stapedial reflex. Presentation level had no effect on recognition accuracy for vowels of sufficient duration (300 ms) to elicit the reflex. The poor recognition accuracy for the brief, high intensity vowels was significantly improved when the reflex was preactivated. These results demonstrate the importance of the acoustic reflex in extending the dynamic range of the auditory system for speech recognition.

Methods for Restricting Maximum Exposure Rate in Computerized Adaptative Testing

Methodology ◽  
2007 ◽  
Vol 3 (1) ◽  
pp. 14-23 ◽  
Author(s):  
Juan Ramon Barrada ◽  
Julio Olea ◽  
Vicente Ponsoda
Keyword(s):  
Measurement Accuracy ◽  
Computerized Adaptive Testing ◽  
Computation Time ◽  
Adaptive Testing ◽  
Exposure Rate ◽  
Control Parameters ◽  
The Impact ◽  
Two Alternatives ◽  
Selection Of ◽  
Maximum Exposure

Abstract. The Sympson-Hetter (1985) method provides a means of controlling maximum exposure rate of items in Computerized Adaptive Testing. Through a series of simulations, control parameters are set that mark the probability of administration of an item on being selected. This method presents two main problems: it requires a long computation time for calculating the parameters and the maximum exposure rate is slightly above the fixed limit. Van der Linden (2003) presented two alternatives which appear to solve both of the problems. The impact of these methods in the measurement accuracy has not been tested yet. We show how these methods over-restrict the exposure of some highly discriminating items and, thus, the accuracy is decreased. It also shown that, when the desired maximum exposure rate is near the minimum possible value, these methods offer an empirical maximum exposure rate clearly above the goal. A new method, based on the initial estimation of the probability of administration and the probability of selection of the items with the restricted method ( Revuelta & Ponsoda, 1998 ), is presented in this paper. It can be used with the Sympson-Hetter method and with the two van der Linden's methods. This option, when used with Sympson-Hetter, speeds the convergence of the control parameters without decreasing the accuracy.

Sign in / Sign up

Export Citation Format

Share Document