Multi-Scale Cross-Modal Spatial Attention Fusion for Multi-label Image Recognition

2020 ◽  
pp. 736-747
Author(s):  
Junbing Li ◽  
Changqing Zhang ◽  
Xueman Wang ◽  
Ling Du
Keyword(s):  
Spatial Attention ◽  
Image Recognition ◽  
Multi Scale

RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Image Recognition

2021 ◽  
Author(s):  
Yunqing Hu ◽  
Xuan Jin ◽  
Yin Zhang ◽  
Haiwen Hong ◽  
Jingfeng Zhang ◽  
...  
Keyword(s):  
Image Recognition ◽  
Fine Grained ◽  
Multi Scale

Research on the Edge Detection Algorithm of Smokescreen Based on Mathematical Morphology

2014 ◽  
Vol 610 ◽  
pp. 429-436
Author(s):  
Xun Sun ◽  
Xuan Yu Wang ◽  
Zhi Rong Luo ◽  
Han Xiao
Keyword(s):  
Edge Detection ◽  
Real Time ◽  
Mathematical Morphology ◽  
Image Recognition ◽  
Operation Time ◽  
Detection Algorithm ◽  
Edge Detection Algorithm ◽  
Multi Scale ◽  
Practical Complexity

To solve the harmony problem of accuration, real-time with anti-noise capability on edge detection of smokescreen, the edge detection algorithm of smokescreen based on multi-scale mathematical morphological is designed, and the algorithm can effectively reduce the noise of the smokescreen image. Compared with the results of classical edge detection operator: Sobel, Roberts, Prowitt and Canny etc, it is concluded that the algorithm designed has obvious advantages in continuity, smoothness, image recognition, practical complexity, operation time and other related parameters.

SAR Image Recognition via Local Gradient Ratio Pattern

2014 ◽  
Vol 624 ◽  
pp. 344-347
Author(s):  
Xiao Yuan ◽  
Tao Tang ◽  
De Liang Xiang ◽  
Yi Su
Keyword(s):  
Dimensionality Reduction ◽  
Image Recognition ◽  
Speckle Noise ◽  
Synthetic Aperture ◽  
Sar Image ◽  
Multi Scale ◽  
Gradient Ratio ◽  
Local Gradient ◽  
Gradient Variation ◽  
Pattern Histogram

Synthetic Aperture Radar recognition is a non-trivial problem. New features of SAR image are proposed. Based on the gradient ratio pattern for each pixel, the Local Gradient Ratio Pattern Histogram is then computed. Next, multi-scale LGRPH is constructed for dimensionality reduction. Finally, the similarity is obtained by utilizing K-L discrepancy to measure the distance of MLGRPH. The proposed method is theoretically proved to be insensitive to speckle noise, and the adaptability to local gradient variation is also discussed. Experimental results show that the proposed approach performs well.

Multi-scale traffic sign detection model with attention

2020 ◽  
pp. 095440702095005
Author(s):  
Bei Bei Fan ◽  
He Yang
Keyword(s):  
Spatial Attention ◽  
Detection Algorithm ◽  
Attention Mechanism ◽  
Background Information ◽  
Traffic Sign ◽  
Data Set ◽  
Multi Scale ◽  
Sign Detection ◽  
Object Area ◽  
Traffic Sign Detection

The current traffic sign detection technology is disturbed by factors such as illumination changes, weather, and camera angle, which makes it unsatisfactory for traffic sign detection. The traffic sign data set usually contains a large number of small objects, and the scale variance of the object is a huge challenge for traffic indication detection. In response to the above problems, a multi-scale traffic sign detection algorithm based on attention mechanism is proposed. The attention mechanism is composed of channel attention mechanism and spatial attention mechanism. By filtering the background information on redundant contradictions with channel attention mechanism in the network, the information on the network is more accurate, and the performance of the network to recognize the traffic signs is improved. Using spatial attention mechanism, the proposed method pays more attention to the object area in traffic recognition image and suppresses the non-object area or background areas. The model in this paper is validated on the Tsinghua-Tencent 100K data set, and the accuracy of the experiment reached a higher level compared to state-of-the-art approaches in traffic sign detection.

scholarly journals Maize Disease Recognition Based On Image Enhancement And OSCRNet

2021 ◽  
Author(s):  
Hongji Zhang ◽  
Zhou Guoxiong ◽  
Aibin Chen ◽  
Jiayong Li ◽  
Mingxuan Li ◽  
...  
Keyword(s):  
Image Enhancement ◽  
Network Model ◽  
Image Recognition ◽  
Spatial Information ◽  
Incident Light ◽  
Learning Disorders ◽  
Identification Accuracy ◽  
Data Set ◽  
Maize Leaf ◽  
Multi Scale

Abstract Background: Under natural light irradiation, there are significant challenges in the identification of maize leaf diseases because of the difficulties in extracting lesion features from constantly changing environments, uneven illumination reflection of the incident light source and many other factors.Results: In the present paper, a novel maize image recognition method was proposed. Firstly, an image enhancement framework of the maize leaf was designed, and a multi-scale image enhancement algorithm with color restoration was established to enhance the characteristics of the maize leaf in a complex environment and to solve the problems of high noise and blur of maize images. Subsequently, an OSCRNet maize leaf recognition network model based on the traditional ResNet backbone architecture was designed. In the OSCRNet maize leaf recognition network model, an octave convolution with characteristics to accelerate network training was adopted, reducing unnecessary redundant spatial information in the maize leaf images. Additionally, a self-calibrated convolution with multi-scale features was employed to realize the interactions of different feature information in the maize leaf images, enhance feature extraction, and solve the problems of similarity of maize disease features and easy learning disorders. Concurrently, batch normalization was employed to prevent network overfitting and enhance the robustness of the model. The experiment was conducted on the maize leaf image data set. The highest identification accuracy of rust, grey leaf disease, northern fusarium wilt, and healthy maize was 94.67%, 92.34%, 89.31% and 96.63%, respectively. Conclusions: The aforementioned methods were beneficial in solving the problems of slow efficiency, low accuracy and image recognition training, and also outperformed other comparison models. The present method demonstrates strong robustness for maize disease images collected in the natural environment, providing a reference for the intelligent diagnosis of other plant leaf diseases.

Lung tumor image recognition algorithm with densenet fusion multi-scale images

2021 ◽  
Vol 29 (7) ◽  
pp. 1695-1708
Author(s):  
Tao ZHOU ◽  
◽  
Bing-qiang HUO ◽  
Hui-ling LU ◽  
Zong-jun MA ◽  
...  
Keyword(s):  
Image Recognition ◽  
Lung Tumor ◽  
Recognition Algorithm ◽  
Multi Scale
Sign in / Sign up

Export Citation Format

Share Document