scholarly journals Imperfect Wheat Grain Recognition Combined with an Attention Mechanism and Residual Network

2021 ◽  
Vol 11 (11) ◽  
pp. 5139
Author(s):  
Weiwei Zhang ◽  
Huimin Ma ◽  
Xiaohong Li ◽  
Xiaoli Liu ◽  
Jun Jiao ◽  
...  
Keyword(s):  
Machine Vision ◽  
Network Model ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Attention Mechanism ◽  
Residual Network ◽  
Wheat Grains ◽  
Key Factor ◽  
Different Depths ◽  
Deep Learning Network

Intelligent detection of imperfect wheat grains based on machine vision is of great significance to correctly and rapidly evaluate wheat quality. There is little difference between the partial characteristics of imperfect and perfect wheat grains, which is a key factor limiting the classification and recognition accuracy of imperfect wheat based on a deep learning network model. In this paper, we propose a method for imperfect wheat grains recognition combined with an attention mechanism and residual network (ResNet), and verify its recognition accuracy by adding an attention mechanism module into different depths of residual network. Five residual networks with different depths (18, 34, 50, 101, and 152) were selected for the experiment, it was found that the recognition accuracy of each network model was improved with the attention mechanism, and the average recognition rate of ResNet-50 with the addition of the attention mechanism reached 96.5%. For ResNet-50 with the attention mechanism, the optimal learning rate was further screened as 0.0003. The average recognition accuracy reached 97.5%, among which the recognition rates of scab wheat grains, insect-damaged wheat grains, sprouted wheat grains, mildew wheat grains, broken wheat grains, and perfect wheat grains reached 97%, 99%, 99%, 95%, 96%, and 99% respectively. This work can provide guidance for the detection and recognition of imperfect wheat grains using machine vision.

scholarly journals Research on Real-Time Face Key Point Detection Algorithm Based on Attention Mechanism

2022 ◽  
Vol 2022 ◽  
pp. 1-11
Author(s):  
Jiangjin Gao ◽  
Tao Yang
Keyword(s):  
Real Time ◽  
Face Detection ◽  
Network Model ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Detection Algorithm ◽  
Attention Mechanism ◽  
Feature Representation ◽  
Point Detection ◽  
Detection Speed

The existing face detection methods were affected by the network model structure used. Most of the face recognition methods had low recognition rate of face key point features due to many parameters and large amount of calculation. In order to improve the recognition accuracy and detection speed of face key points, a real-time face key point detection algorithm based on attention mechanism was proposed in this paper. Due to the multiscale characteristics of face key point features, the deep convolution network model was adopted, the attention module was added to the VGG network structure, the feature enhancement module and feature fusion module were combined to improve the shallow feature representation ability of VGG, and the cascade attention mechanism was used to improve the deep feature representation ability. Experiments showed that the proposed algorithm not only can effectively realize face key point recognition but also has better recognition accuracy and detection speed than other similar methods. This method can provide some theoretical basis and technical support for face detection in complex environment.

scholarly journals Non-Intrusive Load Disaggregation Based on a Multi-Scale Attention Residual Network

2020 ◽  
Vol 10 (24) ◽  
pp. 9132
Author(s):  
Liguo Weng ◽  
Xiaodong Zhang ◽  
Junhao Qian ◽  
Min Xia ◽  
Yiqing Xu ◽  
...  
Keyword(s):  
Smart Grids ◽  
Recognition Rate ◽  
Low Frequency ◽  
Attention Mechanism ◽  
Learning Ability ◽  
Residual Network ◽  
Multi Scale ◽  
Energy Disaggregation ◽  
Benchmark Datasets ◽  
Load Disaggregation

Non-intrusive load disaggregation (NILD) is of great significance to the development of smart grids. Current energy disaggregation methods extract features from sequences, and this process easily leads to a loss of load features and difficulties in detecting, resulting in a low recognition rate of low-use electrical appliances. To solve this problem, a non-intrusive sequential energy disaggregation method based on a multi-scale attention residual network is proposed. Multi-scale convolutions are used to learn features, and the attention mechanism is used to enhance the learning ability of load features. The residual learning further improves the performance of the algorithm, avoids network degradation, and improves the precision of load decomposition. The experimental results on two benchmark datasets show that the proposed algorithm has more advantages than the existing algorithms in terms of load disaggregation accuracy and judgments of the on/off state, and the attention mechanism can further improve the disaggregation accuracy of low-frequency electrical appliances.

Recognition Method of Abnormal Behavior of Marine Fish Swarm Based on In-Depth Learning Network Model

2021 ◽  
Author(s):  
Liyong Chen ◽  
Xiuye Yin
Keyword(s):  
Deep Learning ◽  
False Alarm ◽  
False Alarm Rate ◽  
Network Model ◽  
Marine Fish ◽  
Recognition Accuracy ◽  
Abnormal Behavior ◽  
Fish School ◽  
Learning Network ◽  
Deep Learning Network

In order to solve the problem that individual coordinates are easily ignored in the localization of abnormal behavior of marine fish, resulting in low recognition accuracy, execution efficiency and high false alarm rate, this paper proposes a method of fish abnormal behavior recognition based on deep learning network model. Firstly, the shadow of the fish behavior data is removed, and the background image is subtracted from each frame image to get the gray image of the fish school. Then, the label watershed algorithm is used to identify the fish, and the coordinates of different individuals in the fish swarm are obtained. Combined with the experimental size constraints and the number of fish, and combined with the deep learning network model, the weak link of video tag monitoring of abnormal behavior of marine fish is analyzed. Finally, the multi instance learning method and dual flow network model are used to identify the anomaly of marine fish school. The experimental results show that the method has high recognition accuracy, low false alarm rate and high execution efficiency. This method can provide a practical reference for the related research in this field.

Recognition of students’ behavior states in classroom based on improved MobileNetV2 algorithm

2021 ◽  
pp. 002072092199659
Author(s):  
Dan Cao ◽  
Jianfei Liu ◽  
Luguo Hao ◽  
Wenbin Zeng ◽  
Chen Wang ◽  
...  
Keyword(s):  
Network Model ◽  
Mobile Networks ◽  
Information Exchange ◽  
Classroom Behavior ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Computational Cost ◽  
Teaching Quality ◽  
Positive Role ◽  
Data Set

Analyzing and learning students' behavior states in classroom plays a positive role in understanding and improving the teaching effectiveness. Meanwhile, the application of lightweight network to pattern recognition has become a trend with the development of mobile networks. In order to improve the recognition accuracy of the lightweight network model MobileNetV2 and reduce the computational cost and delay caused by extracting rich features, an improved lightweight network model based on MobileNetV2 is proposed, in which an improved reverse residual module (C-Inverted residual block) is applied to replace the traditional module. In the improved reverse residual module, channel split operation is added to reduce MAC, and channel shuffle operations are used to promote information exchange and channel fusion. Experiments were carried out on Pascal VOC 2007 detection data set to test the general performance of the proposed improved model. Under the operation limits of 140 MFLOPS, 40 MFLOPS and 20 MFLOPS, mean average precision (mAP) of the improved MobileNetV2 algorithm increased by 1.2%, 2.2% and 4.3% compared with MobileNetV2. While the recognition accuracy of the proposed network model on self-made dataset of student classroom behavior states is 4.6% and 3.7% higher than that of MobileNetV1 and MobileNetV2 respectively, and the average recognition rate of students' classroom behavior states can be up to 92.7%. The results of this research combined with mobile networks would be expected to be used to evaluate teaching and learning effects and promote teaching quality improvement.

scholarly journals Dynamic Gesture Contour Feature Extraction Method Using Residual Network Transfer Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xianmin Ma ◽  
Xiaofeng Li
Keyword(s):  
Feature Extraction ◽  
Transfer Learning ◽  
Extraction Method ◽  
Feature Recognition ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Residual Network ◽  
Feature Extraction Method ◽  
Contour Feature ◽  
Dynamic Gestures

The current dynamic gesture contour feature extraction method has the problems that the recognition rate of dynamic gesture contour feature and the recognition accuracy of dynamic gesture type are low, the recognition time is long, and comprehensive is poor. Therefore, we propose a dynamic gesture contour feature extraction method using residual network transfer learning. Sensors are used to integrate dynamic gesture information. The distance between the dynamic gesture and the acquisition device is detected by transfer learning, the dynamic gesture image is segmented, and the characteristic contour image is initialized. The residual network method is used to accurately identify the contour and texture features of dynamic gestures. Fusion processing weights are used to trace the contour features of dynamic gestures frame by frame, and the contour area of dynamic gestures is processed by gray and binarization to realize the extraction of contour features of dynamic gestures. The results show that the dynamic gesture contour feature recognition rate of the proposed method is 91%, the recognition time is 11.6 s, and the dynamic gesture type recognition accuracy rate is 92%. Therefore, this method can effectively improve the recognition rate and type recognition accuracy of dynamic gesture contour features and shorten the time for dynamic gesture contour feature recognition, and the F value is 0.92, with good comprehensive performance.

Overlapped Bubbles Recognition in Two-Phase Flow

2013 ◽  
Vol 373-375 ◽  
pp. 400-403
Author(s):  
Cheng Xuan Wu ◽  
Jun Le Qu ◽  
Zhuo Lei ◽  
Lei Dong ◽  
Jie Liu
Keyword(s):  
Machine Vision ◽  
Background Subtraction ◽  
Two Phase Flow ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Phase Flow ◽  
Two Phase ◽  
Gray Image

We presented an algorithm to recognize overlapped bubbles in two-phase flow. We extracted bubble images from gray image by Background subtraction, and then converted them to binaries. Final images were segmented to compare them with the templates of bubble pattern. Finally, we obtained the recognition accuracy to compare their similarities. The recognition rate is to 93% and it is efficient in the field of the machine vision.

scholarly journals An Unconstrained Face Recognition Method Based on Siamese Networks

2021 ◽  
Author(s):  
Song CunLi ◽  
Shouyong Ji
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Network Model ◽  
High Frequency ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Low Frequency ◽  
Image Features ◽  
Frequency Features ◽  
Frequency Feature

Abstract It is aimed at the low accuracy and low efficiency of face recognition under unlimited conditions.In this paper, a Siamese neural Network model SN-LF (Siamese Network based on LBP and Frequency Feature perception) is designed based on the Local Binary Pattern (LBP) and the Frequency sensing model.Based on Siamese neural networks, the network adopts circular LBP algorithm and frequency feature perception to realize face recognition under unrestricted conditions.The LBP algorithm can eliminate the influence of light on the image and provide directional input to the network model at the same time.Frequency feature sensing divides the image features into low frequency features and high frequency features. The low frequency features are compressed in the Siamese neural network to increase the recognition efficiency of the network. At the same time, information is exchanged with the high frequency features, so that the target noise data can be eliminated while the feature data is retained.In this way, the recognition rate of the network is maintained, and the computing speed of the network is improved.Simulation experiments are carried out on standard face dataset CASIA-Webface and Yale-B, and compared with other network models. The experimental results show that the proposed SN-LF network structure can improve the recognition accuracy of the algorithm, and achieve a good recognition accuracy.

scholarly journals Oestrus Analysis of Sows Based on Bionic Boars and Machine Vision Technology

Animals ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1485
Author(s):  
Kaidong Lei ◽  
Chao Zong ◽  
Xiaodong Du ◽  
Guanghui Teng ◽  
Feiqi Feng
Keyword(s):  
Support Vector Machine ◽  
Machine Vision ◽  
Recognition Accuracy ◽  
Average Duration ◽  
Support Vector ◽  
Contact Duration ◽  
Innovative Design ◽  
Sparse Autoencoder ◽  
Accuracy Rates ◽  
Interactive Behaviour

This study proposes a method and device for the intelligent mobile monitoring of oestrus on a sow farm, applied in the field of sow production. A bionic boar model that imitates the sounds, smells, and touch of real boars was built to detect the oestrus of sows after weaning. Machine vision technology was used to identify the interactive behaviour between empty sows and bionic boars and to establish deep belief network (DBN), sparse autoencoder (SAE), and support vector machine (SVM) models, and the resulting recognition accuracy rates were 96.12%, 98.25%, and 90.00%, respectively. The interaction times and frequencies between the sow and the bionic boar and the static behaviours of both ears during heat were further analysed. The results show that there is a strong correlation between the duration of contact between the oestrus sow and the bionic boar and the static behaviours of both ears. The average contact duration between the sows in oestrus and the bionic boars was 29.7 s/3 min, and the average duration in which the ears of the oestrus sows remained static was 41.3 s/3 min. The interactions between the sow and the bionic boar were used as the basis for judging the sow’s oestrus states. In contrast with the methods of other studies, the proposed innovative design for recyclable bionic boars can be used to check emotions, and machine vision technology can be used to quickly identify oestrus behaviours. This approach can more accurately obtain the oestrus duration of a sow and provide a scientific reference for a sow’s conception time.

Sign in / Sign up

Export Citation Format

Share Document