Improvement of Waveform Analysis Method Based on Polynomial Fitting for Liquid Drop Fingerprint

2014 ◽  
Vol 945-949 ◽  
pp. 2093-2096
Author(s):  
Qing Song ◽  
Dan Qing Du ◽  
Lu Yang ◽  
Gao Jie Meng ◽  
Xue Fei Mao
Keyword(s):  
Bp Neural Network ◽  
Liquid Drop ◽  
Recognition Accuracy ◽  
Smooth Curve ◽  
Waveform Analysis ◽  
Maximum Difference ◽  
Analysis Method ◽  
Accuracy Rate ◽  
Polynomial Fitting ◽  
Waveform Fitting

Waveform analysis method is widely used for feature extraction of liquid drop fingerprint, but it is easily affected by noise. To solve this problem, waveform fitting and analysis method based on polynomial fitting is proposed, though which the waveform of liquid drop fingerprint is fitted to be a smooth curve. Experimental results show that waveform fitting and analysis method is able to reduce the standard deviation and maximum difference of eigenvectors from the same kinds of liquid, and thus increase the recognition accuracy rate of 10 kinds of water based on BP neural network from 86.5% to 100%.

Drop Fingerprint Recognition Method Based on Cluster Analysis and BP Neural Network

2014 ◽  
Vol 543-547 ◽  
pp. 2099-2102 ◽  
Author(s):  
Qing Song ◽  
Dan Qing Du ◽  
Lu Yang ◽  
Gao Jie Meng ◽  
Xue Fei Mao
Keyword(s):  
Neural Network ◽  
Cluster Analysis ◽  
Bp Neural Network ◽  
Liquid Drop ◽  
Recognition Accuracy ◽  
Fingerprint Recognition ◽  
High Similarity ◽  
Recognition Method ◽  
Accuracy Rate ◽  
Accuracy Rates

The eigenvalues of some liquid drop fingerprints are of high similarity, which decreases the recognition accuracy rates of BP neural network. In order to solve this problem, recognition method based on cluster analysis and BP neural network is proposed in this paper. Cluster analysis is used to classify liquid samples according to the similarity of eigenvalues and narrow the recognition range for samples under study. The experimental results have proved that this method is able to increase the recognition accuracy rate from 83.42% to 99.83%.

A study on encoding-based oracle bone script recognition

2020 ◽  
Vol 4 (4) ◽  
pp. 281-290
Author(s):  
Tingzhu Chen ◽  
Yaoyao Qian ◽  
Jingyu Pei ◽  
Shaoteng Wu ◽  
Jiang Wu ◽  
...  
Keyword(s):  
General Public ◽  
Expert Knowledge ◽  
Recognition Accuracy ◽  
Fundamental Problem ◽  
High Accuracy ◽  
Time Range ◽  
Accuracy Rate ◽  
Script Recognition ◽  
Processing Techniques ◽  
Accuracy Speed

Oracle bone script recognition (OBSR) has been a fundamental problem in research on oracle bone scripts for decades. Despite being intensively studied, existing OBSR methods are still subject to limitations regarding recognition accuracy, speed and robustness. Furthermore, the dependency of these methods on expert knowledge hinders the adoption of OBSR systems by the general public and also discourages social outreach of research outputs. Addressing these issues, this study proposes an encoding-based OBSR system that applies image pre-processing techniques to encode oracle images into small matrices and recognize oracle characters in the encoding space. We tested our methods on a collection of oracle bones from the Yin Ruins in XiaoTun village, and achieved a high accuracy rate of 99% within a time range of milliseconds.

scholarly journals Automatic Receipt Recognition System Based on Artificial Intelligence Technology

2022 ◽  
Vol 12 (2) ◽  
pp. 853
Author(s):  
Cheng-Jian Lin ◽  
Yu-Cheng Liu ◽  
Chin-Ling Lee
Keyword(s):  
Character Recognition ◽  
Template Matching ◽  
Recognition Accuracy ◽  
Recognition System ◽  
Character Segmentation ◽  
Small Object ◽  
Labor Costs ◽  
Accuracy Rate ◽  
Artificial Intelligence Technology ◽  
S Model

In this study, an automatic receipt recognition system (ARRS) is developed. First, a receipt is scanned for conversion into a high-resolution image. Receipt characters are automatically placed into two categories according to the receipt characteristics: printed and handwritten characters. Images of receipts with these characters are preprocessed separately. For handwritten characters, template matching and the fixed features of the receipts are used for text positioning, and projection is applied for character segmentation. Finally, a convolutional neural network is used for character recognition. For printed characters, a modified You Only Look Once (version 4) model (YOLOv4-s) executes precise text positioning and character recognition. The proposed YOLOv4-s model reduces downsampling, thereby enhancing small-object recognition. Finally, the system produces recognition results in a tax declaration format, which can upload to a tax declaration system. Experimental results revealed that the recognition accuracy of the proposed system was 80.93% for handwritten characters. Moreover, the YOLOv4-s model had a 99.39% accuracy rate for printed characters; only 33 characters were misjudged. The recognition accuracy of the YOLOv4-s model was higher than that of the traditional YOLOv4 model by 20.57%. Therefore, the proposed ARRS can considerably improve the efficiency of tax declaration, reduce labor costs, and simplify operating procedures.

scholarly journals SEMG Feature Extraction Based on Stockwell Transform Improves Hand Movement Recognition Accuracy

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4457 ◽  
Author(s):  
She ◽  
Zhu ◽  
Tian ◽  
Wang ◽  
Yokoi ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Frequency Analysis ◽  
Recognition Accuracy ◽  
Hand Movement ◽  
Analysis Method ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Analysis Methods ◽  
Movement Recognition ◽  
S Transform

Feature extraction, as an important method for extracting useful information from surfaceelectromyography (SEMG), can significantly improve pattern recognition accuracy. Time andfrequency analysis methods have been widely used for feature extraction, but these methods analyzeSEMG signals only from the time or frequency domain. Recent studies have shown that featureextraction based on time-frequency analysis methods can extract more useful information fromSEMG signals. This paper proposes a novel time-frequency analysis method based on the Stockwelltransform (S-transform) to improve hand movement recognition accuracy from forearm SEMGsignals. First, the time-frequency analysis method, S-transform, is used for extracting a feature vectorfrom forearm SEMG signals. Second, to reduce the amount of calculations and improve the runningspeed of the classifier, principal component analysis (PCA) is used for dimensionality reduction of thefeature vector. Finally, an artificial neural network (ANN)-based multilayer perceptron (MLP) is usedfor recognizing hand movements. Experimental results show that the proposed feature extractionbased on the S-transform analysis method can improve the class separability and hand movementrecognition accuracy compared with wavelet transform and power spectral density methods.

scholarly journals Study on a Fault Identification Method of the Hydraulic Pump Based on a Combination of Voiceprint Characteristics and Extreme Learning Machine

Processes ◽  
2019 ◽  
Vol 7 (12) ◽  
pp. 894 ◽  
Author(s):  
Wanlu Jiang ◽  
Zhenbao Li ◽  
Jingjing Li ◽  
Yong Zhu ◽  
Peiyao Zhang
Keyword(s):  
Fault Diagnosis ◽  
Recognition Accuracy ◽  
Test Sample ◽  
Training Sample ◽  
Accuracy Rate ◽  
Diagnosis Method ◽  
Learning Machine ◽  
Hidden Layer ◽  
Axial Piston ◽  
Sample Set

Aiming at addressing the problem that the faults in axial piston pumps are complex and difficult to effectively diagnose, an axial piston pump fault diagnosis method that is based on the combination of Mel-frequency cepstrum coefficients (MFCC) and the extreme learning machine (ELM) is proposed. Firstly, a sound sensor is used to realize contactless sound signal acquisition of the axial piston pump. The wavelet packet default threshold denoises the original acquired sound signals. Afterwards, windowing and framing are added to the de-noised sound signals. The MFCC voiceprint characteristics of the processed sound signals are extracted. The voiceprint characteristics are divided into a training sample set and test sample set. ELM models with different numbers of neurons in the hidden layers are established for training and testing. The relationship between the number of neurons in the hidden layer and the recognition accuracy rate is obtained. The ELM model with the optimal number of hidden layer neurons is established and trained with the training sample set. The trained ELM model is applied to the test sample set for fault diagnosis. The fault diagnosis results are obtained. The fault diagnosis results of the ELM model are compared with those of the back propagation (BP) neural network and the support vector machine. The results show that the fault diagnosis method that is proposed in this paper has a higher recognition accuracy rate, shorter training and diagnosis times, and better application prospect.

Template-Based Handwritten Numeric Character Recognition

2012 ◽  
Vol 586 ◽  
pp. 384-388
Author(s):  
Ling Hua Li ◽  
Shou Fang Mi ◽  
Heng Bo Zhang
Keyword(s):  
Character Recognition ◽  
Recognition Accuracy ◽  
Experimental Results ◽  
Analysis Method ◽  
Handwriting Analysis ◽  
Better Than

This paper describes a stroke-based handwriting analysis method in classifying handwritten Numeric characters by using a template-based approach. Writing strokes are variable from time to time, even when the writing character is same and comes from the same user. Writing strokes include the properties such as the number of the strokes, the shapes and sizes of them and the writing order and the writing speed. We describe here a template-based system using the properties of writing strokes for the recognition of online handwritten numeric characters. Experimental results show that within the 1500 numeric characters taken from 30 writers, the system got 97.84% recognition accuracy which is better than other systems shown by other literatures.

Back-Analysis of Indoor Test Parameters for Rock-Fill of Shui Bu Ya CFRD

2011 ◽  
Vol 243-249 ◽  
pp. 4581-4586
Author(s):  
Lei Ming He ◽  
Li Hui Du ◽  
Jian Yang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Back Analysis ◽  
Soil Parameters ◽  
Model Parameters ◽  
Analysis Method ◽  
Filling Process ◽  
Rock Fill ◽  
Test Parameters ◽  
Displacement Back Analysis

In the numerical calculation of geotechnical project, it’s difficult to confirm the parameters because of the complexity and the uncertainty of them as the time is changing. However, the back-analysis provides us an effective way. Based on the result of the triaxial test on rock-fill of Shui Bu Ya CFRD, the thesis adopts the direct back-analysis method which combines the BP Neural Network and Genetic Algorithm to calculate the Tsinghua non-linear K-G model parameters of the rock-fill. The back-analysis parameters are used to simulate the filling process of Shui Bu Ya CFRD and predict the displacement of the dam. The thesis provides a technical reference for displacement back-analysis of soil parameters for CFRD.

scholarly journals Error analysis method of intelligent electricity meter based on improved BP neural network

2021 ◽  
Vol 1920 (1) ◽  
pp. 012002
Author(s):  
Xiangyu Yuan ◽  
Penghe Zhang ◽  
Ning Li ◽  
Jiasheng Xu ◽  
Suqin Xiong
Keyword(s):  
Neural Network ◽  
Error Analysis ◽  
Bp Neural Network ◽  
Analysis Method
Sign in / Sign up

Export Citation Format

Share Document