A Multi-Feature Convolution Neural Network for Automatic Flower Recognition

2021 ◽  
pp. 2150281
Author(s):  
Juan Ran ◽  
Yu Shi ◽  
Jinhao Yu ◽  
Delong Li
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Local Binary Pattern ◽  
Recognition Accuracy ◽  
Texture Features ◽  
Activation Function ◽  
Multiple Features ◽  
Color Features ◽  
Definition Of ◽  
Texture Extraction

This paper discusses how to efficiently recognize flowers based on a convolutional neural network (CNN) using multiple features. Our proposed work consists of three phases including segmentation by Otsu thresholding with particle swarm optimization algorithms, feature extraction of color, shape, texture and recognition with the LeNet-5 neural network. In the feature extraction, an improved H component with the definition of WGB value is applied to extract the color feature, and a new algorithm based on local binary pattern (LBP) is proposed to enhance the accuracy of texture extraction. Besides this, we replace ReLU with Mish as activation function in the network design, and therefore increase the accuracy by 8% accuracy according to our comparison. The Oxford-102 and Oxford-17 datasets are adopted for benchmarking. The experimental results show that the combination of color features and texture features generates the highest recognition accuracy as 92.56% on Oxford-102 and 93% on Oxford-17.

scholarly journals An Advanced Relevance Feedback Method to Improve Performance of CBIR using Convolutional Neural Network and Comprehensive Values

2019 ◽  
Vol 9 (2) ◽  
pp. 5427-5438
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Image Retrieval ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Activation Function ◽  
Image Feature ◽  
Similarity Measurement ◽  
Query Image ◽  
Image Production

Content-Based Image Retrieval (CBIR) is extensively used technique for image retrieval from large image databases. However, users are not satisfied with the conventional image retrieval techniques. In addition, the advent of web development and transmission networks, the number of images available to users continues to increase. Therefore, a permanent and considerable digital image production in many areas takes place. Quick access to the similar images of a given query image from this extensive collection of images pose great challenges and require proficient techniques. From query by image to retrieval of relevant images, CBIR has key phases such as feature extraction, similarity measurement, and retrieval of relevant images. However, extracting the features of the images is one of the important steps. Recently Convolutional Neural Network (CNN) shows good results in the field of computer vision due to the ability of feature extraction from the images. Alex Net is a classical Deep CNN for image feature extraction. We have modified the Alex Net Architecture with a few changes and proposed a novel framework to improve its ability for feature extraction and for similarity measurement. The proposal approach optimizes Alex Net in the aspect of pooling layer. In particular, average pooling is replaced by max-avg pooling and the non-linear activation function Maxout is used after every Convolution layer for better feature extraction. This paper introduces CNN for features extraction from images in CBIR system and also presents Euclidean distance along with the Comprehensive Values for better results. The proposed framework goes beyond image retrieval, including the large-scale database. The performance of the proposed work is evaluated using precision. The proposed work show better results than existing works.

Human body activity recognition using wearable inertial sensors integrated with a feature extraction–based machine-learning classification algorithm

2020 ◽  
pp. 095440542093789
Author(s):  
Chih-Ta Yen ◽  
Jia-De Lin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Discriminant Analysis ◽  
Activity Recognition ◽  
Inertial Sensors ◽  
Recognition Accuracy ◽  
Daily Activities ◽  
Linear Discriminant ◽  
Wearable Inertial Sensors

This study employed wearable inertial sensors integrated with an activity-recognition algorithm to recognize six types of daily activities performed by humans, namely walking, ascending stairs, descending stairs, sitting, standing, and lying. The sensor system consisted of a microcontroller, a three-axis accelerometer, and a three-axis gyro; the algorithm involved collecting and normalizing the activity signals. To simplify the calculation process and to maximize the recognition accuracy, the data were preprocessed through linear discriminant analysis; this reduced their dimensionality and captured their features, thereby reducing the feature space of the accelerometer and gyro signals; they were then verified through the use of six classification algorithms. The new contribution is that after feature extraction, data classification results indicated that an artificial neural network was the most stable and effective of the six algorithms. In the experiment, 20 participants equipped the wearable sensors on their waists to record the aforementioned six types of daily activities and to verify the effectiveness of the sensors. According to the cross-validation results, the combination of linear discriminant analysis and an artificial neural network was the most stable classification algorithm for data generalization; its activity-recognition accuracy was 87.37% on the training data and 80.96% on the test data.

Wear Particles Recognition Based on Improved LBP

2013 ◽  
Vol 427-429 ◽  
pp. 1874-1878
Author(s):  
Guo De Wang ◽  
Zhi Sheng Jing ◽  
Guo Wei Qin ◽  
Shan Chao Tu
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Local Binary Pattern ◽  
Recognition Accuracy ◽  
Binary Sequence ◽  
Texture Feature ◽  
Experimental Results ◽  
Wear Particles ◽  
Texture Feature Extraction ◽  
Feature Extraction Method

Wear particles recognition is a key link in the process of Ferrography analysis. Different kinds of wear particles vary greatly in texture, texture feature is one of the most important feature in wear particles recognition. Local Binary Pattern (LBP) is an efficient operator for texture description. The binary sequence of traditional LBP operator is obtained by the comparison between the gray value of the neighborhood and the gray value of the center pixel of the neighborhood, the comparison is too simple to cause the loss of the texture. In this paper, an improved LBP operator is presented for texture feature extraction and it is applied to the recognition of severe sliding particles, fatigue spall particles and laminar particles. The experimental results show that our method is an effective feature extraction method and obtains better recognition accuracy compared with other methods.

scholarly journals A Method for Recognizing Fatigue Driving Based on Dempster-Shafer Theory and Fuzzy Neural Network

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
WenBo Zhu ◽  
Huicheng Yang ◽  
Yi Jin ◽  
Bingyou Liu
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Multiple Features ◽  
Dempster Shafer Theory ◽  
Recognition Result ◽  
Fuzzy Neural ◽  
Basic Probability ◽  
Definition Of ◽  
Shafer Theory ◽  
Fatigue Driving

This study proposes a method based on Dempster-Shafer theory (DST) and fuzzy neural network (FNN) to improve the reliability of recognizing fatigue driving. This method measures driving states using multifeature fusion. First, FNN is introduced to obtain the basic probability assignment (BPA) of each piece of evidence given the lack of a general solution to the definition of BPA function. Second, a modified algorithm that revises conflict evidence is proposed to reduce unreasonable fusion results when unreliable information exists. Finally, the recognition result is given according to the combination of revised evidence based on Dempster’s rule. Experiment results demonstrate that the recognition method proposed in this paper can obtain reasonable results with the combination of information given by multiple features. The proposed method can also effectively and accurately describe driving states.

scholarly journals Texture Feature On Determining Quantity of Soil Organic Matter For Patchouli Plant Using Backpropagation Neural Network

2019 ◽  
Vol 4 (1) ◽  
pp. 1
Author(s):  
Candra Dewi ◽  
Suci Sundari ◽  
Mardji Mardji
Keyword(s):  
Neural Network ◽  
Organic Matter ◽  
Soil Organic Matter ◽  
Texture Feature ◽  
Texture Features ◽  
Training Data ◽  
Backpropagation Neural Network ◽  
Color Features ◽  
Accuracy Result ◽  
Occurrence Matrix

Patchouli (Pogostemon Cablin Bent) has higher PA (Patchouli Alcohol) and oil production if grown in soil containing 75% organic matter. One way that can be used to detect the content of organic matter is to use soil images. The problem in the use of soil images is the color of the soil that is almost similar, namely the gradation between dark brown to black. Therefore, color features are not enough to be used as input in the recognition process. For this purposes, texture features are added in this study in addition to color features. The color features are extracted using color moment and the texture features are extracted using Gray Level Co-occurrence Matrix (GLCM). These feature was then chosen to get the best combination as input in the identification process using the Backpropagation Neural Network (BPNN). The system identifies the quantity of soil organic matter into five classes, namely very low, low, medium, high, and very high. The highest accuracy result obtained was 73% and MSE value 0.5122 by using five GLCM features (Angular Second Moment, contrast, correlation, Inverse Difference Moment, and entropy). This result was obtained by using the BPNN parameter, namely learning rate values 0.5, maximum iteration values of 1000, number training data 210, and total test data 12.

scholarly journals Memristor Based Binary Convolutional Neural Network Architecture With Configurable Neurons

2021 ◽  
Vol 15 ◽  
Author(s):  
Lixing Huang ◽  
Jietao Diao ◽  
Hongshan Nie ◽  
Wei Wang ◽  
Zhiwei Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Precision ◽  
Network Architecture ◽  
Large Scale ◽  
Network Performance ◽  
Recognition Accuracy ◽  
Activation Function ◽  
Data Set ◽  
Neuron Activation

The memristor-based convolutional neural network (CNN) gives full play to the advantages of memristive devices, such as low power consumption, high integration density, and strong network recognition capability. Consequently, it is very suitable for building a wearable embedded application system and has broad application prospects in image classification, speech recognition, and other fields. However, limited by the manufacturing process of memristive devices, high-precision weight devices are currently difficult to be applied in large-scale. In the same time, high-precision neuron activation function also further increases the complexity of network hardware implementation. In response to this, this paper proposes a configurable full-binary convolutional neural network (CFB-CNN) architecture, whose inputs, weights, and neurons are all binary values. The neurons are proportionally configured to two modes for different non-ideal situations. The architecture performance is verified based on the MNIST data set, and the influence of device yield and resistance fluctuations under different neuron configurations on network performance is also analyzed. The results show that the recognition accuracy of the 2-layer network is about 98.2%. When the yield rate is about 64% and the hidden neuron mode is configured as −1 and +1, namely ±1 MD, the CFB-CNN architecture achieves about 91.28% recognition accuracy. Whereas the resistance variation is about 26% and the hidden neuron mode configuration is 0 and 1, namely 01 MD, the CFB-CNN architecture gains about 93.43% recognition accuracy. Furthermore, memristors have been demonstrated as one of the most promising devices in neuromorphic computing for its synaptic plasticity. Therefore, the CFB-CNN architecture based on memristor is SNN-compatible, which is verified using the number of pulses to encode pixel values in this paper.

scholarly journals A Lightweight Convolutional Neural Network Based on Visual Attention for SAR Image Target Classification

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 3039 ◽  
Author(s):  
Jiaqi Shao ◽  
Changwen Qu ◽  
Jianwei Li ◽  
Shujuan Peng
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Visual Attention ◽  
Convolutional Neural Network ◽  
Recognition Accuracy ◽  
Target Recognition ◽  
Sar Image ◽  
Extraction Ability ◽  
Data Imbalance ◽  
Recognition Efficiency

With the continuous development of the convolutional neural network (CNN) concept and other deep learning technologies, target recognition in Synthetic Aperture Radar (SAR) images has entered a new stage. At present, shallow CNNs with simple structure are mostly applied in SAR image target recognition, even though their feature extraction ability is limited to a large extent. What’s more, research on improving SAR image target recognition efficiency and imbalanced data processing is relatively scarce. Thus, a lightweight CNN model for target recognition in SAR image is designed in this paper. First, based on visual attention mechanism, the channel attention by-pass and spatial attention by-pass are introduced to the network to enhance the feature extraction ability. Then, the depthwise separable convolution is used to replace the standard convolution to reduce the computation cost and heighten the recognition efficiency. Finally, a new weighted distance measure loss function is introduced to weaken the adverse effect of data imbalance on the recognition accuracy of minority class. A series of recognition experiments based on two open data sets of MSTAR and OpenSARShip are implemented. Experimental results show that compared with four advanced networks recently proposed, our network can greatly diminish the model size and iteration time while guaranteeing the recognition accuracy, and it can effectively alleviate the adverse effects of data imbalance on recognition results.

Methods and means for real-time object recognition accuracy increase in video images on ios mobile platform

2021 ◽  
Vol 3 (1) ◽  
pp. 80-88
Author(s):  
D Kushnir ◽  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Recognition Accuracy ◽  
Activation Function ◽  
Frame Rate ◽  
Mobile Platform ◽  
Additional Layer ◽  
The Neural Network ◽  
Analytical Review ◽  
Accuracy Increase

As a result of the analytical review, it was established that the family of Yolo models is a promising area of search and recognition of objects. However, existing implementations do not support the ability to run the model on the iOS platform. To achieve these goals, a comprehensive scalable conversion system has been developed to improve the recognition accuracy of arbitrary models based on the Docker system. The method of improvement is to add a layer with the Mish activation function to the original model. The method of conversion is to quickly convert any Yolo model to CoreML format. As part of the study of these techniques, a model of the neural network Yolov4_TCAR was created. Additionally, a method of accelerating the load on the CPU using an additional layer of neural network with the function of activating Mish in Swift for the iOS mobile platform was added. As a result, the effectiveness of the Mish activation function, the CPU load of the mobile device, the amount of RAM used, and the frame rate when using the improved original Yolov4-TCAR model were studied. The results of the research confirmed the functioning of the algorithm for conversion and accuracy increase of the neural network model in real-time.

Classification of clothing images based on a parallel convolutional neural network and random vector functional link optimized by the grasshopper optimization algorithm

2021 ◽  
pp. 004051752110592
Author(s):  
Zhiyu Zhou ◽  
Wenxiong Deng ◽  
Yaming Wang ◽  
Zefei Zhu
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Random Vector ◽  
Optimization Algorithm ◽  
Activation Function ◽  
Support Vector ◽  
Functional Link ◽  
Grasshopper Optimization Algorithm ◽  
Grasshopper Optimization

To improve accuracy in clothing image recognition, this paper proposes a clothing classification method based on a parallel convolutional neural network (PCNN) combined with an optimized random vector functional link (RVFL). The method uses the PCNN model to extract features of clothing images. Then, the structure-intensive and dual-channel convolutional neural network (i.e., the PCNN) is used to solve the problems of traditional convolutional neural networks (e.g., limited data and prone to overfitting). Each convolutional layer is followed by a batch normalization layer, and the leaky rectified linear unit activation function and max-pooling layers are used to improve the performance of the feature extraction. Then, dropout layers and fully connected layers are used to reduce the amount of calculation. The last layer uses the RVFL as optimized by the grasshopper optimization algorithm to replace the SoftMax layer and classify the features, further improving the stability and accuracy of classification. In this study, two aspects of the classification (feature extraction and feature classification) are improved, effectively improving the accuracy. The experimental results show that on the Fashion-Mnist dataset, the accuracy of the algorithm in this study reaches 92.93%. This value is 1.36%, 2.05%, 0.65%, and 3.76% higher than that of the local binary pattern (LBP)-support vector machine (SVM), histogram of oriented gradients (HOG)-SVM, LBP-HOG-SVM, and AlexNet-sparse representation-based classifier algorithms, respectively, effectively demonstrating the classification performance of the algorithm.

scholarly journals Robust Iris Classification Based on Deep Neural Network (DNN) and Stationary Wavelet Transform (SWT)

2019 ◽  
pp. 198-204
Author(s):  
Priyanka S ◽  
Pavithra V ◽  
Pavithra M ◽  
S. Bhuvana
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Wavelet Transform ◽  
Major Part ◽  
Deep Neural Network ◽  
Local Binary Pattern ◽  
Vital Role ◽  
Stationary Wavelet Transform ◽  
Huge Amount

The eye is a vital part of our body. It consists of several layers like sclera, retina, tunica, and iris. Among these several layers, Iris plays a vital role in human visionary. There are various infections which affect the Iris functioning. The sign, symptoms, and diagnosis of this is still a challenge for doctors. To overcome this many techniques and technologies have been introduced. But still, the existing system has several drawbacks in recognition like a huge amount of dataset, classification, extraction, etc. To overcome this we propose a system where Deep Neural Network plays a major part. It classifies the iris disease in our eyes in a more clear and precise manner. In additional to Deep Neural Network several other algorithms have been used like Stationary Wavelet Transform, for image selection and recognition, Local Binary Pattern, for Feature extraction and at a final stage Deep Neural Network for classification of Iris images.

Sign in / Sign up

Export Citation Format

Share Document