Visual and textual information fusion using Kernel method for content based image retrieval

Unar, Salahuddin; Wang, Xingyuan; Zhang, Chuan

doi:10.1016/j.inffus.2018.03.006

Cited by 37 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Here, the table displays the comparison of fallouts for three image extraction techniques. Figure 15 represents the evaluation of the proposed EDBC method with existing methods [25]. Figure 15 illustrates the experimental outcomes regarding accuracy for image 1, image 2 and image 3.…”

Section: Resultsmentioning

confidence: 99%

Content based Retrieval Management Systems in Web Engineering

2019

IJRTE

View full text Add to dashboard Cite

The tremendous upsurge and abundant availability of graphic documents on the internet directed to the high concern in research on Content-Based Image Retrieval (CBIR). It has cemented the attitude for a massive sum of innovative procedures and schemes, and growing curiosity in respective fields to preserve such research. Existing technologies were discussed about various CBIR techniques such as k-means, content-based image, and hybrid clustering, etc. in combination with the feature vector of information images and texture features. In similar cases, it is constricted in stating the user’s semantic knowledge to permit information distribution and reuse. Hence models ought to be managed within repositories, where they might be retrieved upon users’ queries. Due to the lack of adequate tools on incisive/handling for visual content, this research work proposes an Efficient Density-based Clustering Algorithm (EDBC) for CBIR technique that will enhance scalability, reduce the user search time, and lower the maintenance cost. Using the existing CBIR, the color, texture, and shape features of an image is identified by integrating with the proposed EDBC algorithm and thereby, it improves the scalability and user search time. When comparing the feature between the color histograms of RGB and CMYK, it shows better color characteristics in CMYK by using the proposed technique. Also, the grouping of color, shape and texture features based image retrieval improves the accuracy when compared with existing methods

show abstract

Section: Resultsmentioning

confidence: 99%

Content based Retrieval Management Systems in Web Engineering

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…Support vector machine (SVM) is a supervised machine learning approach that is based on the kernel method, which is often used for classification and regression missions [56][57][58][59]. As we aimed to predict whether an earthquake event was about to occur or not, we used the SVM to classify ionospheric TEC enhancements prior to earthquake events during low and high solar cycle activities, where we introduced the pre-earthquake TEC time series sample as a positive instance of an earthquake event, and its corresponding quiet day time series as a negative instance (i.e., an earthquake would not occur).…”

Section: Bayesian Hyperparameter Optimization For Svmmentioning

confidence: 99%

Using Support Vector Machine (SVM) with GPS Ionospheric TEC Estimations to Potentially Predict Earthquake Events

et al. 2022

View full text Add to dashboard Cite

There are significant controversies surrounding the detection of precursors that may precede earthquakes. Natural hazard signatures associated with strong earthquakes can appear in the lithosphere, troposphere, and ionosphere, where current remote sensing technologies have become valuable tools for detecting and measuring early warning signals of stress build-up deep in the Earth’s crust (presumably associated with earthquake events). Here, we propose implementing a machine learning support vector machine (SVM) technique, applied with GPS ionospheric total electron content (TEC) pre-processed time series estimations, to evaluate potential precursors caused by earthquakes and manifested as disturbances in the TEC data. After filtering and screening our data for solar or geomagnetic influences at different time scales, our results indicate that for large earthquakes (> Mw 6), true negative predictions can be achieved with 85.7% accuracy, and true positive predictions with an accuracy of 80%. We tested our method with different skill scores, such as accuracy (0.83), precision (0.85), recall (0.8), the Heidke skill score (0.66), and true skill statistics (0.66).

show abstract

“…Traditional image processing methods usually extract crack objects by the threshold, edge, and region [6][7][8] or manually set features [9,10]. The method of detecting targets is to extract the morphological features of the shallow layer or middle layer by hand.…”

Section: Related Workmentioning

confidence: 99%

A deep learning‐based method for pixel‐level crack detection on concrete bridges

Zhang

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Crack detection of the concrete bridge is an essential index for the safety assessment of bridge structure. It is more important to check the whole structure than to check the accuracy in the damage assessment. However, the traditional deep learning model method cannot completely detect the crack structure, which challenges image-based crack detection. For this reason, we propose deep bridge crack classification (DBCC)-Net as a classification-based deep learning network. By pruning the Yolox, the regression problem of the target detection is converted to the binary classification problem to avoid the network performance degradation caused by the translation invariance of the convolutional neural network (CNN). In addition, the network post-processing and a two-stage crack detection strategy are proposed to enable the network to detect cracks and extract crack morphology in high-resolution images quickly. In the first stage, DBCC-Net realizes the coarse extraction of crack position based on image slice classification. In the second stage, the complete crack morphology is extracted from the location suggested by the semantic segmentation network. Experimental results show that the proposed two-stage method has 19 frames per second (FPS) and 0.79 Miou (mean intersection over union) at the actual bridge images with 2560×2560 pixels. Although FPS is reduced, the Miou value is 7.8% higher than other methods, proving this paper's practical value.

show abstract

Visual and textual information fusion using Kernel method for content based image retrieval

Cited by 37 publications

References 30 publications

Content based Retrieval Management Systems in Web Engineering

Content based Retrieval Management Systems in Web Engineering

Using Support Vector Machine (SVM) with GPS Ionospheric TEC Estimations to Potentially Predict Earthquake Events

A deep learning‐based method for pixel‐level crack detection on concrete bridges

Contact Info

Product

Resources

About