scholarly journals Hand-Drawn Sketch Recognition With Double-Channel CNN

2021 ◽  
Author(s):  
Lei ZHANG
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Feature Fusion ◽  
Recognition Rate ◽  
Contour Extraction ◽  
Sketch Recognition ◽  
Softmax Classifier ◽  
Extraction Algorithm ◽  
Double Channel ◽  
Novel Algorithm

Abstract In the task of hand-drawn sketch recognition, traditional deep learning methods have the insufficient of feature extraction and low recognition rate. To improve the insufficient, a novel algorithm based on double channel convolution neural network is proposed. First of all, the hand-drawn sketch is preprocessed to get a smooth sketch. And the contour extraction algorithm is adopted to get the contour of the sketch. The sketch and its contour are then used as input images of the CNN respectively. Finally, through performing feature fusion at the full connection layer, the classification results are obtained using the softmax classifier. The experimental results show that the proposed method can effectively improve the recognition rate of hand-drawn sketch.

scholarly journals Hand-drawn sketch recognition with a double-channel convolutional neural network

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Lei Zhang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Feature Fusion ◽  
Recognition Rate ◽  
Input Image ◽  
Contour Extraction ◽  
Sketch Recognition ◽  
Softmax Classifier ◽  
Dual Channel ◽  
Extraction Algorithm

AbstractIn hand-drawn sketch recognition, the traditional deep learning method has the problems of insufficient feature extraction and low recognition rate. To solve this problem, a new algorithm based on a dual-channel convolutional neural network is proposed. Firstly, the sketch is preprocessed to get a smooth sketch. The contour of the sketch is obtained by the contour extraction algorithm. Then, the sketch and contour are used as the input image of CNN. Finally, feature fusion is carried out in the full connection layer, and the classification results are obtained by using a softmax classifier. Experimental results show that this method can effectively improve the recognition rate of a hand-drawn sketch.

scholarly journals Quantitative Detection of Financial Fraud Based on Deep Learning with Combination of E-Commerce Big Data

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Jian Liu ◽  
Xin Gu ◽  
Chao Shang
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Deep Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Feature Fusion ◽  
Recognition Rate ◽  
Fraud Detection ◽  
Quantitative Detection ◽  
Financial Fraud

At present, there are more and more frauds in the financial field. The detection and prevention of financial frauds are of great significance for regulating and maintaining a reasonable financial order. Deep learning algorithms are widely used because of their high recognition rate, good robustness, and strong implementation. Therefore, in the context of e-commerce big data, this paper proposes a quantitative detection algorithm for financial fraud based on deep learning. First, the encoders are used to extract the features of the behaviour. At the same time, in order to reduce the computational complexity, the feature extraction is restricted to the space-time volume of the dense trajectory. Second, the neural network model is used to transform features into behavioural visual word representations, and feature fusion is performed using weighted correlation methods to improve feature classification capabilities. Finally, sparse reconstruction errors are used to judge and detect financial fraud. This method builds a deep neural network model with multiple hidden layers, learns the characteristic expression of the data, and fully depicts the rich internal information of the data, thereby improving the accuracy of financial fraud detection. Experimental results show that this method can effectively learn the essential characteristics of the data, and significantly improve the detection rate of fraud detection algorithms.

scholarly journals Multimodal biometrics of fingerprint and signature recognition using multi-level feature fusion and deep learning techniques

2021 ◽  
Vol 22 (1) ◽  
pp. 187
Author(s):  
Arjun Benagatte Channegowda ◽  
H N Prakash
Keyword(s):  
Deep Learning ◽  
Feature Fusion ◽  
Research Work ◽  
Recognition Rate ◽  
Recognition System ◽  
Multimodal Biometrics ◽  
Histograms Of Oriented Gradients ◽  
Multi Level ◽  
Deep Learning Neural Network ◽  
Hidden Neurons

Providing security in biometrics is the major challenging task in the current situation. A lot of research work is going on in this area. Security can be more tightened by using complex security systems, like by using more than one biometric trait for recognition. In this paper multimodal biometric models are developed to improve the recognition rate of a person. The combination of physiological and behavioral biometrics characteristics is used in this work. Fingerprint and signature biometrics characteristics are used to develop a multimodal recognition system. Histograms of oriented gradients (HOG) features are extracted from biometric traits and for these feature fusions are applied at two levels. Features of fingerprint and signatures are fused using concatenation, sum, max, min, and product rule at multilevel stages, these features are used to train deep learning neural network model. In the proposed work, multi-level feature fusion for multimodal biometrics with a deep learning classifier is used and results are analyzed by a varying number of hidden neurons and hidden layers. Experiments are carried out on SDUMLA-HMT, machine learning and data mining lab, Shandong University fingerprint datasets, and MCYT signature biometric recognition group datasets, and encouraging results were obtained.

scholarly journals Handwritten tifinagh character recognition using simple geometric shapes and graphs

2019 ◽  
Vol 13 (2) ◽  
pp. 598
Author(s):  
Youssef Ouadid ◽  
Abderrahmane Elbalaoui ◽  
Mehdi Boutaounte ◽  
Mohamed Fakir ◽  
Brahim Minaoui
Keyword(s):  
Character Recognition ◽  
Graph Matching ◽  
Recognition Rate ◽  
Recognition System ◽  
Features Extraction ◽  
Experimental Results ◽  
Feature Points ◽  
Matching Method ◽  
Extraction Algorithm ◽  
Novel Algorithm

<p>In this paper, a graph based handwritten Tifinagh character recognition system is presented. In preprocessing Zhang Suen algorithm is enhanced. In features extraction, a novel key point extraction algorithm is presented. Images are then represented by adjacency matrices defining graphs where nodes represent feature points extracted by a novel algorithm. These graphs are classified using a graph matching method. Experimental results are obtained using two databases to test the effectiveness. The system shows good results in terms of recognition rate.</p>

scholarly journals Using Artificial Intelligence to Achieve Auxiliary Training of Table Tennis Based on Inertial Perception Data

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6685
Author(s):  
Pu Yanan ◽  
Yan Jilong ◽  
Zhang Heng
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Optical Sensors ◽  
Inertial Sensors ◽  
Feature Fusion ◽  
Recognition Rate ◽  
Table Tennis ◽  
User Privacy ◽  
Tennis Players ◽  
Wearable Inertial Sensors

Compared with optical sensors, wearable inertial sensors have many advantages such as low cost, small size, more comprehensive application range, no space restrictions and occlusion, better protection of user privacy, and more suitable for sports applications. This article aims to solve irregular actions that table tennis enthusiasts do not know in actual situations. We use wearable inertial sensors to obtain human table tennis action data of professional table tennis players and non-professional table tennis players, and extract the features from them. Finally, we propose a new method based on multi-dimensional feature fusion convolutional neural network and fine-grained evaluation of human table tennis actions. Realize ping-pong action recognition and evaluation, and then achieve the purpose of auxiliary training. The experimental results prove that our proposed multi-dimensional feature fusion convolutional neural network has an average recognition rate that is 0.17 and 0.16 higher than that of CNN and Inception-CNN on the nine-axis non-professional test set, which proves that we can better distinguish different human table tennis actions and have a more robust generalization performance. Therefore, on this basis, we have better realized the enthusiast of table tennis the purpose of the action for auxiliary training.

scholarly journals BLNN: Multiscale Feature Fusion-Based Bilinear Fine-Grained Convolutional Neural Network for Image Classification of Wood Knot Defects

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Mingyu Gao ◽  
Fei Wang ◽  
Peng Song ◽  
Junyan Liu ◽  
DaWei Qi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Defect Detection ◽  
Feature Fusion ◽  
Image Features ◽  
Optical Image ◽  
Training Time ◽  
Fine Grained ◽  
Detection Model ◽  
Defect Recognition

Wood defects are quickly identified from an optical image based on deep learning methodology, which effectively improves the wood utilization. The traditional neural network technique is unemployed for the wood defect detection of optical image used, which results from a long training time, low recognition accuracy, and nonautomatic extraction of defect image features. In this paper, a wood knot defect detection model (so-called BLNN) combined deep learning is reported. Two subnetworks composed of convolutional neural networks are trained by Pytorch. By using the feature extraction capabilities of the two subnetworks and combining the bilinear join operation, the fine-grained features of the image are obtained. The experimental results show that the accuracy has reached up 99.20%, and the training time is obviously reduced with the speed of defect detection about 0.0795 s/image. It indicates that BLNN has the ability to improve the accuracy of defect recognition and has a potential application in the detection of wood knot defects.

scholarly journals Atrial Fibrillation Detection Using Feedforward Neural Network

2021 ◽  
Author(s):  
Yunfan Chen ◽  
Chong Zhang ◽  
Chengyu Liu ◽  
Yiming Wang ◽  
Xiangkui Wan
Keyword(s):  
Neural Network ◽  
Atrial Fibrillation ◽  
Deep Learning ◽  
Detection System ◽  
Recognition Rate ◽  
Feedforward Neural Network ◽  
Classification Model ◽  
Detection Sensitivity ◽  
Ecg Signal ◽  
Atrial Fibrillation Detection

Abstract Atrial fibrillation is one of the most common arrhythmias in clinics, which has a great impact on people's physical and mental health. Electrocardiogram (ECG) based arrhythmia detection is widely used in early atrial fibrillation detection. However, ECG needs to be manually checked in clinical practice, which is time-consuming and labor-consuming. It is necessary to develop an automatic atrial fibrillation detection system. Recent research has demonstrated that deep learning technology can help to improve the performance of the automatic classification model of ECG signals. To this end, this work proposes effective deep learning based technology to automatically detect atrial fibrillation. First, novel preprocessing algorithms of wavelet transform and sliding window filtering (SWF) are introduced to reduce the noise of the ECG signal and to filter high-frequency components in the ECG signal, respectively. Then, a robust R-wave detection algorithm is developed, which achieves 99.22% detection sensitivity, 98.55% positive recognition rate, and 2.25% deviance on the MIT-BIH arrhythmia database. In addition, we propose a feedforward neural network (FNN) to detect atrial fibrillation based on ECG records. Experiments verified by a 10-fold cross-validation strategy show that the proposed model achieves competitive detection performance and can be applied to wearable detection devices. The proposed atrial fibrillation detection model achieves an accuracy of 84.00%, the detection sensitivity of 84.26%, the specificity of 93.23%, and the area under the receiver working curve of 89.40% on the mixed dataset composed of Challenge2017 database and MIT-BIH arrhythmia database.

scholarly journals A Deep Learning Model for Fault Diagnosis with a Deep Neural Network and Feature Fusion on Multi-Channel Sensory Signals

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4300 ◽  
Author(s):  
Qing Ye ◽  
Shaohu Liu ◽  
Changhua Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Feature Fusion ◽  
Support Vector ◽  
Diagnostic Model ◽  
Sensory Signals ◽  
Sensory Signal ◽  
Deep Architecture ◽  
Final Drive

Collecting multi-channel sensory signals is a feasible way to enhance performance in the diagnosis of mechanical equipment. In this article, a deep learning method combined with feature fusion on multi-channel sensory signals is proposed. First, a deep neural network (DNN) made up of auto-encoders is adopted to adaptively learn representative features from sensory signal and approximate non-linear relation between symptoms and fault modes. Then, Locality Preserving Projection (LPP) is utilized in the fusion of features extracted from multi-channel sensory signals. Finally, a novel diagnostic model based on multiple DNNs (MDNNs) and softmax is constructed with the input of fused deep features. The proposed method is verified in intelligent failure recognition for automobile final drive to evaluate its performance. A set of contrastive analyses of several intelligent models based on the Back-Propagation Neural Network (BPNN), Support Vector Machine (SVM) and the proposed deep architecture with single sensory signal and multi-channel sensory signals is implemented. The proposed deep architecture of feature extraction and feature fusion on multi-channel sensory signals can effectively recognize the fault patterns of final drive with the best diagnostic accuracy of 95.84%. The results confirm that the proposed method is more robust and effective than other comparative methods in the contrastive experiments.

Flower growth status recognition method based on feature fusion convolutional neural network

2021 ◽  
pp. 1-12
Author(s):  
Haiming Liu ◽  
Shixuan Guan ◽  
Weizhong Lu ◽  
Haiou Li ◽  
Hongjie Wu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Input Data ◽  
Network Performance ◽  
Feature Fusion ◽  
Recognition Rate ◽  
Growth Environment ◽  
Growth Status ◽  
Current Growth ◽  
Flower Growth

The growth state of flowers is affected by many factors such as temperature, humidity, and light. Therefore, the maintenance of flowers often requires more professional knowledge. Ordinary people are often at a loss when face with various flower representations and do not know where the problem is. In response to the above problems, this article proposes the use of deep learning to identify the growth status of flowers to assist people in successfully raising flowers. In this article, we propose that the mainstream convolutional neural network has the limitation of only inputting images. In terms of network input, data of the current growth environment of flowers will also be input to supplement the input data of the network. In view of the lack of information interaction in the network, in terms of network structure, the shallow and deep characteristics of the network are integrated to make the network performance more advantageous. Experiments show that this method can effectively improve the recognition rate of flower growth status, so as to correctly distinguish the current growth status of flowers.

scholarly journals Deep Learning Based Emotion Recognition and Visualization of Figural Representation

2022 ◽  
Vol 12 ◽  
Author(s):  
Xiaofeng Lu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Learning Environment ◽  
Emotion Recognition ◽  
Short Term Memory ◽  
Recognition Rate ◽  
Network Algorithms ◽  
Intelligent Learning Environment ◽  
Graphic Visualization ◽  
Experimental Reference

This exploration aims to study the emotion recognition of speech and graphic visualization of expressions of learners under the intelligent learning environment of the Internet. After comparing the performance of several neural network algorithms related to deep learning, an improved convolution neural network-Bi-directional Long Short-Term Memory (CNN-BiLSTM) algorithm is proposed, and a simulation experiment is conducted to verify the performance of this algorithm. The experimental results indicate that the Accuracy of CNN-BiLSTM algorithm reported here reaches 98.75%, which is at least 3.15% higher than that of other algorithms. Besides, the Recall is at least 7.13% higher than that of other algorithms, and the recognition rate is not less than 90%. Evidently, the improved CNN-BiLSTM algorithm can achieve good recognition results, and provide significant experimental reference for research on learners’ emotion recognition and graphic visualization of expressions in an intelligent learning environment.

Sign in / Sign up

Export Citation Format

Share Document