Residual Self-Calibration and Self-Attention Aggregation Network for Crop Disease Recognition

The correct diagnosis and recognition of crop diseases play an important role in ensuring crop yields and preventing food safety. The existing methods for crop disease recognition mainly focus on accuracy while ignoring the algorithm’s robustness. In practice, the acquired images are often accompanied by various noises. These noises lead to a huge challenge for improving the robustness and accuracy of the recognition algorithm. In order to solve this problem, this paper proposes a residual self-calibration and self-attention aggregation network (RCAA-Net) for crop disease recognition in actual scenarios. The proposed RCAA-Net is composed of three main modules: (1) multi-scale residual module, (2) feedback self-calibration module, and (3) self-attention aggregation module. Specifically, the multi-scale residual module is designed to learn multi-scale features and provide both global and local information for the appearance of the disease to improve the performance of the model. The feedback self-calibration is proposed to improve the robustness of the model by suppressing the background noise in the original deep features. The self-attention aggregation module is introduced to further improve the robustness and accuracy of the model by capturing multi-scale information in different semantic spaces. The experimental results on the challenging 2018ai_challenger crop disease recognition dataset show that the proposed RCAA-Net achieves state-of-the-art performance on robustness and accuracy for crop disease recognition in actual scenarios.

Download Full-text

Pavement Crack Recognition Algorithm Based on Multi-Scale Shape Feature and BP Neural Network

CICTP 2020 ◽

10.1061/9780784483053.068 ◽

2020 ◽

Author(s):

Yunchao Li ◽

Zhigang Xu ◽

Zijun Jiang

Keyword(s):

Neural Network ◽

Bp Neural Network ◽

Recognition Algorithm ◽

Shape Feature ◽

Multi Scale ◽

Crack Recognition

Download Full-text

Single image super resolution based on multi-scale structure and non-local smoothing

EURASIP Journal on Image and Video Processing ◽

10.1186/s13640-021-00552-8 ◽

2021 ◽

Vol 2021 (1) ◽

Author(s):

Wenyi Wang ◽

Jun Hu ◽

Xiaohong Liu ◽

Jiying Zhao ◽

Jianwen Chen

Keyword(s):

Super Resolution ◽

Principal Component ◽

Feature Mapping ◽

Multi Scale ◽

Non Local ◽

Image Super Resolution ◽

Gaussian Blur ◽

Single Image Super Resolution ◽

Global And Local ◽

Bicubic Interpolation

AbstractIn this paper, we propose a hybrid super-resolution method by combining global and local dictionary training in the sparse domain. In order to present and differentiate the feature mapping in different scales, a global dictionary set is trained in multiple structure scales, and a non-linear function is used to choose the appropriate dictionary to initially reconstruct the HR image. In addition, we introduce the Gaussian blur to the LR images to eliminate a widely used but inappropriate assumption that the low resolution (LR) images are generated by bicubic interpolation from high-resolution (HR) images. In order to deal with Gaussian blur, a local dictionary is generated and iteratively updated by K-means principal component analysis (K-PCA) and gradient decent (GD) to model the blur effect during the down-sampling. Compared with the state-of-the-art SR algorithms, the experimental results reveal that the proposed method can produce sharper boundaries and suppress undesired artifacts with the present of Gaussian blur. It implies that our method could be more effect in real applications and that the HR-LR mapping relation is more complicated than bicubic interpolation.

Download Full-text

Iris Recognition Method Based on Feature Discrimination and Category Correlation

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.602-605.1610 ◽

2014 ◽

Vol 602-605 ◽

pp. 1610-1613

Author(s):

Ming Hai Yao ◽

Na Wang ◽

Jin Song Li

Keyword(s):

Iris Recognition ◽

Predictive Accuracy ◽

Gabor Filter ◽

Recognition Algorithm ◽

Recognition Method ◽

Texture Characteristic ◽

Multi Scale ◽

Laplacian Score ◽

Circular Gabor Filter ◽

Academy Of Sciences

With the increasing number of internet user, the authentication technology is more and more important. Iris recognition as an important method for identification, which has been attention by researchers. In order to improve the predictive accuracy of iris recognition algorithm, the iris recognition method is proposed based feature discrimination and category correlation. The feature discrimination and category correlation are calculated by laplacian score and mutual information. The formula about feature discrimination and category correlation are built. Aiming at texture characteristic of iris image, the multi-scale circular Gabor filter is used to feature extraction. The computational efficiency of algorithm is improved. In order to verify the validity of the algorithm, the CASIA iris database of Chinese Academy of Sciences is used to do the experiment. The experimental results show that our method has high predictive accuracy.

Download Full-text

Multi-scale Method for the Crack Problem in Microstructural Materials

Computational Methods in Applied Mathematics ◽

10.2478/cmam-2010-0003 ◽

2010 ◽

Vol 10 (1) ◽

pp. 69-86 ◽

Cited By ~ 2

Author(s):

R. H. W. Hoppe ◽

S.I. Petrova

Keyword(s):

Finite Element ◽

Crack Problem ◽

Material Model ◽

Superposition Method ◽

The Finite Element Method ◽

Multi Scale ◽

Microscopic Models ◽

Modeling Strategy ◽

Porous Microstructures ◽

Global And Local

AbstractThe paper deals with the numerical computation of a crack problem posed on microstructural heterogeneous materials containing multiple phases in the microstructure. The failure of such materials is a natural multi-scale effect since cracks typically nucleate in regions of defects on the microscopic scale. The modeling strategy for solving the crack problem concerns simultaneously the macroscopic and microscopic models. Our approach is based on an efficient combination of the homogenization technique and the mesh superposition method (s-version of the finite element method). The homogenized model relies on a double-scale asymptotic expansion of the displacement field. The mesh superposition method uses two independent (global and local) finite element meshes and the concept of superposing the local mesh arbitrarily on the global continuous mesh. The crack is treated by the local mesh and the homogenized material model is considered on the global mesh. Numerical experiments for problems on biomorphic microcellular ceramic templates with porous microstructures of different materials constituents are presented.

Download Full-text

THE EFFECT OF DIFFERENT OCCUPATIONAL BACKGROUND NOISES ON VOICE RECOGNITION ACCURACY

Journal of Computing and Information Science in Engineering ◽

10.1115/1.4053521 ◽

2022 ◽

pp. 1-30

Author(s):

Song Li ◽

Mustafa Ozkan Yerebakan ◽

Yue Luo ◽

Ben Amaba ◽

William Swope ◽

...

Keyword(s):

Background Noise ◽

Recognition Accuracy ◽

Voice Recognition ◽

Recognition Algorithm ◽

Control Mechanisms ◽

Recognition Algorithms ◽

Significant Performance ◽

Industrial Productivity ◽

Overall Performance ◽

Occupational Background

Abstract Voice recognition has become an integral part of our lives, commonly used in call centers and as part of virtual assistants. However, voice recognition is increasingly applied to more industrial uses. Each of these use cases has unique characteristics that may impact the effectiveness of voice recognition, which could impact industrial productivity, performance, or even safety. One of the most prominent among them is the unique background noises that are dominant in each industry. The existence of different machinery and different work layouts are primary contributors to this. Another important characteristic is the type of communication that is present in these settings. Daily communication often involves longer sentences uttered under relatively silent conditions, whereas communication in industrial settings is often short and conducted in loud conditions. In this study, we demonstrated the importance of taking these two elements into account by comparing the performances of two voice recognition algorithms under several background noise conditions: a regular Convolutional Neural Network (CNN) based voice recognition algorithm to an Auto Speech Recognition (ASR) based model with a denoising module. Our results indicate that there is a significant performance drop between the typical background noise use (white noise) and the rest of the background noises. Also, our custom ASR model with the denoising module outperformed the CNN based model with an overall performance increase between 14-35% across all background noises. . Both results give proof that specialized voice recognition algorithms need to be developed for these environments to reliably deploy them as control mechanisms.

Download Full-text

SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6733 ◽

2020 ◽

Vol 34 (07) ◽

pp. 10989-10996

Author(s):

Qintao Hu ◽

Lijun Zhou ◽

Xiaoxiao Wang ◽

Yao Mao ◽

Jianlin Zhang ◽

...

Keyword(s):

Online Learning ◽

Object Tracking ◽

Background Noise ◽

State Of The Art ◽

Response Suppression ◽

Learning Approach ◽

Response Distribution ◽

Peak Response ◽

Multi Scale ◽

Tracking Response

Modern visual trackers usually construct online learning models under the assumption that the feature response has a Gaussian distribution with target-centered peak response. Nevertheless, such an assumption is implausible when there is progressive interference from other targets and/or background noise, which produce sub-peaks on the tracking response map and cause model drift. In this paper, we propose a rectified online learning approach for sub-peak response suppression and peak response enforcement and target at handling progressive interference in a systematic way. Our approach, referred to as SPSTracker, applies simple-yet-efficient Peak Response Pooling (PRP) to aggregate and align discriminative features, as well as leveraging a Boundary Response Truncation (BRT) to reduce the variance of feature response. By fusing with multi-scale features, SPSTracker aggregates the response distribution of multiple sub-peaks to a single maximum peak, which enforces the discriminative capability of features for robust object tracking. Experiments on the OTB, NFS and VOT2018 benchmarks demonstrate that SPSTrack outperforms the state-of-the-art real-time trackers with significant margins1

Download Full-text

Virtual scene dynamic interactive image segmentation technology based on OpenGL module

International Journal of Electrical Engineering Education ◽

10.1177/0020720919891080 ◽

2019 ◽

pp. 002072091989108

Author(s):

Li Jing-Hui ◽

Gan Sheng-Jiang

Keyword(s):

Image Segmentation ◽

Expectation Maximization Algorithm ◽

Gaussian Mixture ◽

Recognition Algorithm ◽

Experimental Simulation ◽

Virtual Scene ◽

Interactive Image Segmentation ◽

Multi Scale ◽

Gauss Mixture ◽

Drawing Method

A virtual scene dynamic interactive image segmentation technology based on OpenGL sky module is proposed to improve the performance of image dynamic interactive recognition algorithm and the recognition effect of image segmentation. First, an automatic dynamic interactive image segmentation algorithm is proposed, a probability segmentation model of Gauss mixture fracture based on multi-scale crack enhancement filter is established, and expectation maximization algorithm is used to determine the parameters of GMM (Gaussian Mixture Model) and the underlying segmentation; second, the drawing function of OpenGL is used to draw the graph, and the drawing method needs to be calculated. That is to say, a mathematical model is established, which converts the graph into the calculation of vertex coordinates for drawing. It uses an extended cost function to guide dynamic interactive image segmentation using a set of cracks from the population to be segmented. Finally, the validity of the algorithm is verified by experimental simulation.

Download Full-text