scholarly journals Multi-Fusion Approach for Wood Microscopic Images Identification Based on Deep Transfer Learning

2021 ◽  
Vol 11 (16) ◽  
pp. 7639
Author(s):  
Meng Zhu ◽  
Jincong Wang ◽  
Achuan Wang ◽  
Honge Ren ◽  
Mahmoud Emam
Keyword(s):  
Feature Fusion ◽  
Field Enhancement ◽  
Microscopic Image ◽  
Fusion Model ◽  
Microscopic Images ◽  
Detection Model ◽  
Depth Study ◽  
Computer Based ◽  
Wood Science ◽  
Forestry Resources

With the wide increase in global forestry resources trade, the demand for wood is increasing day by day, especially rare wood. Finding a computer-based method that can identify wood species has strong practical value and very important significance for regulating the wood trade market and protecting the interests of all parties, which is one of the important problems to be solved by the wood industry. This article firstly studies the establishment of wood microscopic images dataset through a combination of traditional image amplification technology and Mix-up technology expansion strategy. Then with the traditional Faster Region-based Convolutional Neural Networks (Faster RCNN) model, the receptive field enhancement Spatial Pyramid Pooling (SPP) module and the multi-scale feature fusion of Feature Pyramid Networks (FPN) module are introduced to construct a microscopic image identification model based on the migration learning fusion model and analyzes the three factors (Mix-up, Enhanced SPP and FPN modules) affecting the wood microscopic image detection model. The experimental results show that the proposed approach can identify 10 kinds of wood microscopic images, and the accuracy rate has increased from 77.8% to 83.8%, which provides convenient conditions for further in-depth study of the microscopic characteristics of wood cells and is of great significance to the field of wood science.

Multi-Feature Fusion and Machine Learning

2021 ◽  
pp. 95-118
Author(s):  
Hadeer Elziaat ◽  
Nashwa El-Bendary ◽  
Ramadan Moawad
Keyword(s):  
Machine Learning ◽  
Early Detection ◽  
Feature Fusion ◽  
Freezing Of Gait ◽  
Feature Learning ◽  
Feature Engineering ◽  
Common Symptom ◽  
Fusion Model ◽  
Feature Sets ◽  
Detection Model

Freezing of gait (FoG) is a common symptom of Parkinson's disease (PD) that causes intermittent absence of forward progression of patient's feet while walking. Accordingly, FoG momentary episodes are always accompanied with falls. This chapter presents a novel multi-feature fusion model for early detection of FoG episodes in patients with PD. In this chapter, two feature engineering schemes are investigated, namely time-domain hand-crafted feature engineering and convolutional neural network (CNN)-based spectrogram feature learning. Data of tri-axial accelerometer sensors for patients with PD is utilized to characterize the performance of the proposed model through several experiments with various machine learning (ML) algorithms. Obtained experimental results showed that the multi-feature fusion approach has outperformed typical single feature sets. Conclusively, the significance of this chapter is to highlight the impact of using feature fusion of multi-feature sets through investigating the performance of a FoG episodes early detection model.

scholarly journals Microscopic Image Segmentation Based on Swarm Intelligence Optimization Algorithms

2019 ◽  
pp. 124-130
Author(s):  
Selen Ayas ◽  
Hulya Dogan ◽  
Eyup Gedikli ◽  
Murat Ekinci
Keyword(s):  
Swarm Intelligence ◽  
Diagnostic Technique ◽  
World Health ◽  
Flower Pollination Algorithm ◽  
Background Concentration ◽  
Sputum Smear ◽  
Microscopic Image ◽  
Visual Examination ◽  
Microscopic Images ◽  
The World

The World Health Organization suggests the visual examination of stained sputum smear samples as a preliminary and basic diagnostic technique for diagnosing tuberculosis which is the most common infectious disease in the world. Due to the fact that the visual examination of slide samples performed by expert laboratory technicians requires much time and the process is prone to mistake, an accurate diagnosis of disease is provided with computer aided automatic diagnosis methods. In this study, the usage of swarm intelligence algorithms based on entropy information are proposed for detecting the tuberculosis bacilli as an ovelap approach in segmentation of microscopic images. The microscopic images used in the study are taken from smear samples in which the background concentration is low and bacilli concentration is low and high. An optimum threshold value in gray-level microscopic image is determined using the bi-level entropy based Particle Swarm Optimization, Firefly Algorithm, Cuckoo Search Optimization and Flower Pollination Algorithm. The acquired visual results show that the proposed swarm intelligence algorithms are quite successful in segmentation of microscopic images.

An Efficient Adaptive Algorithm for Electron Microscopic Image Enhancement and Feature Extraction

2019 ◽  
Vol 9 (1) ◽  
pp. 1-16
Author(s):  
Vivek Arya ◽  
Vipul Sharma ◽  
Garima Arya
Keyword(s):  
Feature Extraction ◽  
Contrast Enhancement ◽  
Block Size ◽  
Sigmoid Function ◽  
Microscopic Image ◽  
Electron Microscopic ◽  
Microscopic Images ◽  
Electron Microscopic Image ◽  
Block Based

In this article, a block-based adaptive contrast enhancement algorithm has been proposed, which uses a modified sigmoid function for the enhancement and features extraction of electron microscopic images. The algorithm is based on a modified sigmoid function that adapts according to the input microscopic image statistics. For feature extraction, the contrast of the image is very important and authentic property by which this article enhances the visual quality of the image. In this work, for better contrast enhancement of image, a block based on input value, combined with a modified sigmoid function that is used as contrast enhancer provides better EMF values for a smaller block size. It provides localized contrast enhancement effects adaptively which is not possible using other existing techniques. Simulation and experimental results demonstrate that the proposed technique gives better results compared to other existing techniques when applied to electron microscopic images. After the enhancement of microscopic images of actinomycetes, various important features are shown, like coil or spiral, long filament, spore and rod shape structures. The proposed algorithm works efficiently for different dark and bright microscopic images.

Photoplethysmogram-based Cognitive Load Assessment Using Multi-Feature Fusion Model

2019 ◽  
Vol 16 (4) ◽  
pp. 1-17
Author(s):  
Xiao Zhang ◽  
Yongqiang Lyu ◽  
Tong Qu ◽  
Pengfei Qiu ◽  
Xiaomin Luo ◽  
...  
Keyword(s):  
Cognitive Load ◽  
Feature Fusion ◽  
Fusion Model

An Enhanced Facial Expression Recognition Model Using Local Feature Fusion of Gabor Wavelets and Local Directionality Patterns

2020 ◽  
Vol 11 (1) ◽  
pp. 48-70 ◽  
Author(s):  
Sivaiah Bellamkonda ◽  
Gopalan N.P
Keyword(s):  
Facial Expression ◽  
Feature Fusion ◽  
Support Vector ◽  
Svm Classifier ◽  
Source Image ◽  
Expression Recognition ◽  
Fusion Model ◽  
Average Accuracy ◽  
Benchmark Datasets ◽  
Operator Fatigue

Facial expression analysis and recognition has gained popularity in the last few years for its challenging nature and broad area of applications like HCI, pain detection, operator fatigue detection, surveillance, etc. The key of real-time FER system is exploiting its variety of features extracted from the source image. In this article, three different features viz. local binary pattern, Gabor, and local directionality pattern were exploited to perform feature fusion and two classification algorithms viz. support vector machines and artificial neural networks were used to validate the proposed model on benchmark datasets. The classification accuracy has been improved in the proposed feature fusion of Gabor and LDP features with SVM classifier, recorded an average accuracy of 93.83% on JAFFE, 95.83% on CK and 96.50% on MMI. The recognition rates were compared with the existing studies in the literature and found that the proposed feature fusion model has improved the performance.

scholarly journals Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion Model

2020 ◽  
Vol 2020 ◽  
pp. 1-22
Author(s):  
Xiaoran Feng ◽  
Liyang Xiao ◽  
Wei Li ◽  
Lili Pei ◽  
Zhaoyun Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Geometric Parameter ◽  
Crack Detection ◽  
Crack Identification ◽  
Single Shot ◽  
Road Maintenance ◽  
Fusion Model ◽  
Detection Model ◽  
Crack Classification

Pavement damage is the main factor affecting road performance. Pavement cracking, a common type of road damage, is a key challenge in road maintenance. In order to achieve an accurate crack classification, segmentation, and geometric parameter calculation, this paper proposes a method based on a deep convolutional neural network fusion model for pavement crack identification, which combines the advantages of the multitarget single-shot multibox detector (SSD) convolutional neural network model and the U-Net model. First, the crack classification and detection model is applied to classify the cracks and obtain the detection confidence. Next, the crack segmentation network is applied to accurately segment the pavement cracks. By improving the feature extraction structure and optimizing the hyperparameters of the model, pavement crack classification and segmentation accuracy were improved. Finally, the length and width (for linear cracks) and the area (for alligator cracks) are calculated according to the segmentation results. Test results show that the recognition accuracy of the pavement crack identification method for transverse, longitudinal, and alligator cracks is 86.8%, 87.6%, and 85.5%, respectively. It is demonstrated that the proposed method can provide the category information for pavement cracks as well as the accurate positioning and geometric parameter information, which can be used directly for evaluating the pavement condition.

scholarly journals Application of Two-Level Joint Information Fusion Model in Intelligent Vehicle

2016 ◽  
Vol 12 (03) ◽  
pp. 77
Author(s):  
Yan Ting Lan ◽  
Jiinying Huang ◽  
Xiaodong Chen
Keyword(s):  
Information Fusion ◽  
Feature Fusion ◽  
Target Identification ◽  
Information Source ◽  
Evidence Theory ◽  
Intelligent Vehicles ◽  
Fusion Model ◽  
Multiple Features ◽  
Model Combining ◽  
Real Vehicle

This paper proposes a two-level joint information fusion model combining BP neural network and D-S evidence theory. The model of great practical value reduces target identification error probability by multiple features of the target information, shows good scalability with its two steps of information fusion model, and conveniently increases/reduces feature fusion information source according to different situations and different objects. The method used for intelligent vehicles has good flexibility and robustness in tracking and avoiding obstacle. The simulation and real vehicle tests have verified effectiveness of the method.

Sign in / Sign up

Export Citation Format

Share Document