Advanced Color Edge Detection Using Clifford Algebra in Satellite Images

Bhatti, Uzair Aslam; Zhou, Mingquan; Huo, Qingsong; Ali, Sajid; Hussain, Akhtar; Yan, Yuhuan; Yu, Zhaoyuan; Yuan, Linwang; Nawaz, Saqib Ali

doi:10.1109/jphot.2021.3059703

Cited by 36 publications

(14 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, image processing is a widely and universally utilized approach that assists in the detection by using images [16][17][18][19]. The method of image processing, i.e., segmentation, was used for the detection of this illness in the early phase [20][21][22][23]. The images of the liver were carried out, and various algorithms such as k-means were applied for the detection of the disease [24,25].…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Logic-Based System for Liver Fibrosis Disease

Alkhalifah¹,

Singla²,

Alurise³

2023

CSSE

View full text Add to dashboard Cite

The diagnosis of liver fibrosis (LF) is crucial as it is a deadly and life-threatening disease. Artificial intelligence techniques aid doctors by using the previous data on health and making a diagnostic system, which helps to take decisions about patients' health as experts can. The historical data of a patient's health can have vagueness, inaccurate, and can also have missing values. The fuzzy logic theory can deal with these issues in the dataset. In this paper, a multilayer fuzzy expert system is developed to diagnose LF. The model is created by using multiple layers of the fuzzy logic approach. This system aids in classifying the health of patients into different classes. The proposed method has two layers, i.e., layer 1 and layer 2. The input variables used in layer 1 for diagnosing liver fibrosis are Appetite, Jaundice, Ascites, Age, and Fatigue. Similarly, in layer 2, the input variables are Platelet count, White blood cell count, spleen, SGPT ALT (Serum Glutamic Pyruvic Transaminase Alanine Aminotransferase), SGOT ALT (Serum Glutamicoxalacetic Transaminase Alanine Aminotransferase), Serum bilirubin, and Serum albumin. The output variables for this developed system are no damage, minimal damage, significant damage, severe damage, and cirrhosis. This research work also presents the examination of results based on performance parameters. The proposed system achieves a classification accuracy of 95%. Moreover, other performance parameters such as sensitivity, specificity, and precision are calculated as 97.14%, 92%, and 94.44%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Fuzzy Logic-Based System for Liver Fibrosis Disease

Alkhalifah¹,

Singla²,

Alurise³

2023

CSSE

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

“…The structure of SE block is shown in Figure 3, where U is a feature map with the size of W×H×C, ⨂ and refers to channel-wise multiplication, so X and U have the same size. Moreover, edge-guided attention mechanisms which can produce visually appealing images also attract the attention of many researchers (Bhatti et al, 2021). Zhao et al (Zhao et al, 2019a) propose an edge guidance network (EGNet) which solves the problems of rough boundary in object detection through the complementarity of the object and salient edge information.…”

Section: Attention Mechanism In Deep Learningmentioning

confidence: 99%

RADFNet: An infrared and visible image fusion framework based on distributed network

Feng

Wu²,

Lin³

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionThe fusion of infrared and visible images can improve image quality and eliminate the impact of changes in the agricultural working environment on the information perception of intelligent agricultural systems.MethodsIn this paper, a distributed fusion architecture for infrared and visible image fusion is proposed, termed RADFNet, based on residual CNN (RDCNN), edge attention, and multiscale channel attention. The RDCNN-based network realizes image fusion through three channels. It employs a distributed fusion framework to make the most of the fusion output of the previous step. Two channels utilize residual modules with multiscale channel attention to extract the features from infrared and visible images, which are used for fusion in the other channel. Afterward, the extracted features and the fusion results from the previous step are fed to the fusion channel, which can reduce the loss in the target information from the infrared image and the texture information from the visible image. To improve the feature learning effect of the module and information quality in the fused image, we design two loss functions, namely, pixel strength with texture loss and structure similarity with texture loss.Results and discussionExtensive experimental results on public datasets demonstrate that our model has superior performance in improving the fusion quality and has achieved comparable results over the state-of-the-art image fusion algorithms in terms of visual effect and quantitative metrics.

show abstract

“…A CNN can automatically extract image features, greatly reducing the workload, while providing a good research direction for plant disease classification. Meanwhile, K-nearest Neighbor (KNN) classifier ( Bazai et al., 2017 ) and other algorithms are also studied in deep learning in data analysis scenarios, Bhatti ( Bhatti et al., 2021a ) proposed a method for edge detection of color images by using Clifford algebra and its subalgebra quaternion in image processing, which improved object detection and classification as well as extraction of other features. Bhatti ( Bhatti et al., 2021b ) also proposed a spatial spectrum HIS classification algorithm – local similarity Projection Gabor Filtering (LSPGF), which uses the reduced-dimension Convolutional Neural Network based on local similarity projection (LSP) and two-dimensional Gabor filtering algorithm.…”

Section: Introductionmentioning

confidence: 99%

Research on cassava disease classification using the multi-scale fusion model based on EfficientNet and attention mechanism

2022

View full text Add to dashboard Cite

Cassava disease is one of the leading causes to the serious decline of cassava yield. Because it is difficult to identify the characteristics of cassava disease, if not professional cassava growers, it will be prone to misjudgment. In order to strengthen the judgment of cassava diseases, the identification characteristics of cassava diseases such as different color of cassava leaf disease spots, abnormal leaf shape and disease spot area were studied. In this paper, deep convolutional neural network was used to classify cassava leaf diseases, and image classification technology was used to recognize and classify cassava leaf diseases. A lightweight module Multi-scale fusion model (MSFM) based on attention mechanism was proposed to extract disease features of cassava leaves to enhance the classification of disease features. The resulting feature map contained key disease identification information. The study used 22,000 cassava disease leaf images as a data set, including four different cassava leaf disease categories and healthy cassava leaves. The experimental results show that the cassava leaf disease classification model based on multi-scale fusion Convolutional Neural Network (CNN) improves EfficientNet compared with the original model, with the average recognition rate increased by nearly 4% and the average recognition rate up to 88.1%. It provides theoretical support and practical tools for the recognition and early diagnosis of plant disease leaves.

show abstract

Advanced Color Edge Detection Using Clifford Algebra in Satellite Images

Cited by 36 publications

References 48 publications

Fuzzy Logic-Based System for Liver Fibrosis Disease

Fuzzy Logic-Based System for Liver Fibrosis Disease

RADFNet: An infrared and visible image fusion framework based on distributed network

Research on cassava disease classification using the multi-scale fusion model based on EfficientNet and attention mechanism

Contact Info

Product

Resources

About