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.

scholarly journals A Robot Object Recognition Method Based on Scene Text Reading in Home Environments

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1919
Author(s):  
Shuhua Liu ◽  
Huixin Xu ◽  
Qi Li ◽  
Fei Zhang ◽  
Kun Hou
Keyword(s):  
Object Recognition ◽  
Recognition Accuracy ◽  
Multiple Objects ◽  
Recognition Method ◽  
Home Environments ◽  
Complex Scenes ◽  
Scene Text ◽  
Text Reading ◽  
Text Images ◽  
Chinese And English

With the aim to solve issues of robot object recognition in complex scenes, this paper proposes an object recognition method based on scene text reading. The proposed method simulates human-like behavior and accurately identifies objects with texts through careful reading. First, deep learning models with high accuracy are adopted to detect and recognize text in multi-view. Second, datasets including 102,000 Chinese and English scene text images and their inverse are generated. The F-measure of text detection is improved by 0.4% and the recognition accuracy is improved by 1.26% because the model is trained by these two datasets. Finally, a robot object recognition method is proposed based on the scene text reading. The robot detects and recognizes texts in the image and then stores the recognition results in a text file. When the user gives the robot a fetching instruction, the robot searches for corresponding keywords from the text files and achieves the confidence of multiple objects in the scene image. Then, the object with the maximum confidence is selected as the target. The results show that the robot can accurately distinguish objects with arbitrary shape and category, and it can effectively solve the problem of object recognition in home environments.

A Classifier of Shoulder Movements for a Wearable EMG-Based Device

2017 ◽  
Vol 02 (02) ◽  
pp. 1740003
Author(s):  
Giuseppina Gini ◽  
Lisa Mazzon ◽  
Simone Pontiggia ◽  
Paolo Belluco
Keyword(s):  
Real Time ◽  
Computation Time ◽  
Body Part ◽  
Time Constraints ◽  
Pattern Recognition Method ◽  
Noninvasive Method ◽  
Recognition Method ◽  
Two Phase ◽  
The Real ◽  
User Intentions

Prostheses and exoskeletons need a control system able to rapidly understand user intentions; a noninvasive method is to deploy a myoelectric system, and a pattern recognition method to classify the intended movement to input to the controller. Here we focus on the classification phase. Our first aim is to recognize nine movements of the shoulder, a body part seldom considered in the literature and difficult to treat since the muscles involved are deep. We show that our novel sEMG two-phase classifier, working on a signal window of 500[Formula: see text]ms with 62[Formula: see text]ms increment, has a 97.7% accuracy for nine movements and about 100% accuracy on five movements. After developing the classifier using professionally collected sEMG data from eight channels, our second aim is to implement the classifier on a wearable device, composed by the Intel Edison board and a three-channel experimental portable acquisition board. Our final aim is to develop a complete classifier for dynamic situations, considering the transitions between movements and the real-time constraints. The performance of the classifier, using three channels, is about 96.9%, the classification frequency is 62[Formula: see text]Hz, and the computation time is 16[Formula: see text]ms, far less than the real-time constraint of 300[Formula: see text]ms.

scholarly journals Research on Recognition Method of COVID-19 Images Based on Deep Learning

2020 ◽  
Author(s):  
dongshen ji ◽  
yanzhong zhao ◽  
zhujun zhang ◽  
qianchuan zhao
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Feature Fusion ◽  
Recognition Accuracy ◽  
Recognition Performance ◽  
Small Sample ◽  
Experimental Results ◽  
Ct Image ◽  
Recognition Method ◽  
Sample Recognition

In view of the large demand for new coronary pneumonia covid19 image recognition samples,the recognition accuracy is not ideal.In this paper,a new coronary pneumonia positive image recognition method proposed based on small sample recognition. First, the CT image pictures are preprocessed, and the pictures are converted into the picture formats which are required for transfer learning. Secondly, perform small-sample image enhancement and expansion on the converted picture, such as miscut transformation, random rotation and translation, etc.. Then, multiple migration models are used to extract features and then perform feature fusion. Finally,the model is adjusted by fine-tuning.Then train the model to obtain experimental results. The experimental results show that our method has excellent recognition performance in the recognition of new coronary pneumonia images,even with only a small number of CT image samples.

A ROBUST MOVING BODY RECOGNITION METHOD

2012 ◽  
Vol 11 (02) ◽  
pp. 107-114
Author(s):  
SHOUJIA WANG ◽  
WENHUI LI ◽  
BO FU ◽  
HONGYIN NI ◽  
CONG WANG
Keyword(s):  
Computer Vision ◽  
Real Time ◽  
Connected Domain ◽  
Difference Method ◽  
Recognition Accuracy ◽  
Temporal Difference ◽  
Recognition Method ◽  
Moving Body ◽  
Robust Recognition ◽  
Body Recognition

At present, moving body recognition is one of the most active areas of research in the field of computer vision and is used widely in all kinds of videos. But the recognition accuracy of these methods has changed negatively because of the complexity of the background. In this paper, we put forward a robust recognition method. First, we obtain the moving body by tripling the temporal difference method. And then we eliminate noise from these images by mathematical morphology. Finally, we use three-scanning notation method to mark and connect the connected domain. This new method is more accurate and requires less computation in real-time experiments. The experiment result also proves its robustness.

REAL-TIME FACIAL POSE IDENTIFICATION WITH HIERARCHICALLY STRUCTURED ML POSE CLASSIFIER

2004 ◽  
Vol 18 (02) ◽  
pp. 127-142 ◽  
Author(s):  
JAE-WON SUNG ◽  
DAIJIN KIM
Keyword(s):  
Real Time ◽  
High Speed ◽  
Tracking System ◽  
Computation Time ◽  
Feature Space ◽  
Identification Problem ◽  
Pose Tracking ◽  
Time Simulation ◽  
The Face ◽  
Pose Identification

Since pose-varying face images form nonlinear convex manifold in high dimensional image space, it is difficult to model their pose distribution in terms of a simple probabilistic density function. To solve this difficulty, we divide the pose space into many constituent pose classes and treat the continuous pose estimation problem as a discrete pose-class identification problem. We propose to use a hierarchically structured ML (Maximum Likelihood) pose classifiers in the reduced feature space to decrease the computation time for pose identification, where pose space is divided into several pose groups and each group consists of a number of similar neighboring poses. We use the CONDENSATION algorithm to find a newly appearing face and track the face with a variety of poses in real-time. Simulation results show that our proposed pose identification using the hierarchically structured ML pose classifiers can perform a faster pose identification than conventional pose identification using the flat structured ML pose classifiers. A real-time facial pose tracking system is built with high speed hierarchically structured ML pose classifiers.

scholarly journals Multi-Aspect SAR Target Recognition Based on Prototypical Network with a Small Number of Training Samples

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4333
Author(s):  
Pengfei Zhao ◽  
Lijia Huang ◽  
Yu Xin ◽  
Jiayi Guo ◽  
Zongxu Pan
Keyword(s):  
Deep Learning ◽  
Feature Fusion ◽  
Recognition Accuracy ◽  
Target Recognition ◽  
Automatic Target Recognition ◽  
Small Sample ◽  
Recognition Method ◽  
Training Samples ◽  
Model Training ◽  
Sar Target Recognition

At present, synthetic aperture radar (SAR) automatic target recognition (ATR) has been deeply researched and widely used in military and civilian fields. SAR images are very sensitive to the azimuth aspect of the imaging geomety; the same target at different aspects differs greatly. Thus, the multi-aspect SAR image sequence contains more information for classification and recognition, which requires the reliable and robust multi-aspect target recognition method. Nowadays, SAR target recognition methods are mostly based on deep learning. However, the SAR dataset is usually expensive to obtain, especially for a certain target. It is difficult to obtain enough samples for deep learning model training. This paper proposes a multi-aspect SAR target recognition method based on a prototypical network. Furthermore, methods such as multi-task learning and multi-level feature fusion are also introduced to enhance the recognition accuracy under the case of a small number of training samples. The experiments by using the MSTAR dataset have proven that the recognition accuracy of our method can be close to the accruacy level by all samples and our method can be applied to other feather extraction models to deal with small sample learning problems.

scholarly journals Research on Recognition Method of COVID-19 Images Based on Deep Learning

2021 ◽  
Vol 271 ◽  
pp. 01039
Author(s):  
Dongsheng Ji ◽  
Yanzhong Zhao ◽  
Zhujun Zhang ◽  
Qianchuan Zhao
Keyword(s):  
Image Recognition ◽  
Feature Fusion ◽  
Recognition Accuracy ◽  
Recognition Performance ◽  
Small Sample ◽  
Experimental Results ◽  
Fine Tuning ◽  
Ct Image ◽  
Recognition Method ◽  
Sample Recognition

In view of the large demand for new coronary pneumonia covid19 image recognition samples, the recognition accuracy is not ideal. In this paper, a new coronary pneumonia positive image recognition method proposed based on small sample recognition. First, the CT image pictures are preprocessed, and the pictures are converted into the picture formats which are required for transfer learning. Secondly, small-sample image enhancement and extension are performed on the transformed image, such as staggered transformation, random rotation and translation, etc.. Then, multiple migration models are used to extract features and then perform feature fusion. Finally,the model is adjusted by fine-tuning. Then train the model to obtain experimental results. The experimental results show that our method has excellent recognition performance in the recognition of new coronary pneumonia images, even with only a small number of CT image samples.

scholarly journals Pixelwise Phase Unwrapping Based on Ordered Periods Phase Shift

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 377
Author(s):  
Satoshi Tabata ◽  
Michika Maruyama ◽  
Yoshihiro Watanabe ◽  
Masatoshi Ishikawa
Keyword(s):  
High Resolution ◽  
Phase Shift ◽  
Real Time ◽  
High Precision ◽  
High Speed ◽  
Moving Objects ◽  
Global Illumination ◽  
Accurate Method ◽  
Phase Unwrapping ◽  
Order Structure

The existing phase-shift methods are effective in achieving high-speed, high-precision, high-resolution, real-time shape measurement of moving objects; however, a phase-unwrapping method that can handle the motion of target objects in a real environment and is robust against global illumination as well is yet to be established. Accordingly, a robust and highly accurate method for determining the absolute phase, using a minimum of three steps, is proposed in this study. In this proposed method, an order structure that rearranges the projection pattern for each period of the sine wave is introduced, so that solving the phase unwrapping problem comes down to calculating the pattern order. Using simulation experiments, it has been confirmed that the proposed method can be used in high-speed, high-precision, high-resolution, three-dimensional shape measurements even in situations with high-speed moving objects and presence of global illumination. In this study, an experimental measurement system was configured with a high-speed camera and projector, and real-time measurements were performed with a processing time of 1.05 ms and a throughput of 500 fps.

scholarly journals Visual–tactile object recognition of a soft gripper based on faster Region-based Convolutional Neural Network and machining learning algorithm

2020 ◽  
Vol 17 (5) ◽  
pp. 172988142094872
Author(s):  
Chenlei Jiao ◽  
Binbin Lian ◽  
Zhe Wang ◽  
Yimin Song ◽  
Tao Sun
Keyword(s):  
Object Recognition ◽  
Visual Information ◽  
Visual Recognition ◽  
Recognition Accuracy ◽  
Learning Algorithm ◽  
Pressure Sensors ◽  
Tactile Sensors ◽  
Recognition Method ◽  
Tactile Information ◽  
Unknown Object

Object recognition is a prerequisite to control a soft gripper successfully grasping an unknown object. Visual and tactile recognitions are two commonly used methods in a grasping system. Visual recognition is limited if the size and weight of the objects are involved, whereas the efficiency of tactile recognition is a problem. A visual–tactile recognition method is proposed to overcome the disadvantages of both methods in this article. The design and fabrication of the soft gripper considering the visual and tactile sensors are implemented, where the Kinect v2 is adopted for visual information, bending and pressure sensors are embedded to the soft fingers for tactile information. The proposed method is divided into three steps: initial recognition by vision, detail recognition by touch, and a data fusion decision making. Experiments show that the visual–tactile recognition has the best results. The average recognition accuracy of the daily objects by the proposed method is also the highest. The feasibility of the visual–tactile recognition is verified.

Sign in / Sign up

Export Citation Format

Share Document