Swarm intelligence based image fusion for noisy images using consecutive pixel intensity

Paramanandham, Nirmala; Rajendiran, Kishore

doi:10.1007/s11042-018-6233-9

Cited by 8 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To examine the efficiency of the implemented technique under several noise conditions, images were generated with different noises with Gaussian, salt and pepper, and speckle with various mean and variance levels. The Gaussian noise model [ 37 ] is expressed in Equation (1).

where σ denotes the standard deviation, g indicates the gray value and µ represents the mean value.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…The binary noise is also called impulse noise and salt and pepper, as its value is either 0 or 255. Speckle noise is also termed as multiplicative noise [ 37 ]. It occurs in the same way in an image as Gaussian noise.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Miguel Carrasco et al [ 32 ] discussed a methodology for measuring the width of cracks using smoothing, filtering, segmentation and estimation. The authors of [ 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 ] proposed several techniques based on CNN, pyramidal residual network for concrete crack detection, binocular vision system for pipe crack and deformation detection and also analyzed the performance of the techniques. From the literature, it can be identified that the existing techniques for detecting cracks can be classified into two broad domains.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pixel Intensity Resemblance Measurement and Deep Learning Based Computer Vision Model for Crack Detection and Analysis

Paramanandham

Rajendiran²,

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

This research article is aimed at improving the efficiency of a computer vision system that uses image processing for detecting cracks. Images are prone to noise when captured using drones or under various lighting conditions. To analyze this, the images were gathered under various conditions. To address the noise issue and to classify the cracks based on the severity level, a novel technique is proposed using a pixel-intensity resemblance measurement (PIRM) rule. Using PIRM, the noisy images and noiseless images were classified. Then, the noise was filtered using a median filter. The cracks were detected using VGG-16, ResNet-50 and InceptionResNet-V2 models. Once the crack was detected, the images were then segregated using a crack risk-analysis algorithm. Based on the severity level of the crack, an alert can be given to the authorized person to take the necessary action to avoid major accidents. The proposed technique achieved a 6% improvement without PIRM and a 10% improvement with the PIRM rule for the VGG-16 model. Similarly, it showed 3 and 10% for ResNet-50, 2 and 3% for Inception ResNet and a 9 and 10% increment for the Xception model. When the images were corrupted from a single noise alone, 95.6% accuracy was achieved using the ResNet-50 model for Gaussian noise, 99.65% accuracy was achieved through Inception ResNet-v2 for Poisson noise, and 99.95% accuracy was achieved by the Xception model for speckle noise.

show abstract

where σ denotes the standard deviation, g indicates the gray value and µ represents the mean value.…”

Section: Proposed Methodsmentioning

confidence: 99%

Section: Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pixel Intensity Resemblance Measurement and Deep Learning Based Computer Vision Model for Crack Detection and Analysis

Paramanandham

Rajendiran²,

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the context of IR intensity measurement, features can include shapes, patterns, or temperature gradients. [30] Contribution: Extracted features provide quantitative information about spatial variations, contributing to more precise intensity measurements and aiding in the identification of specific thermal patterns.…”

Section: Feature Extractionmentioning

confidence: 99%

Application of Image Processing Methods for IR Intensity Measurement in Spatial and Temporal Domains: A Comprehensive Review

2024

IRJMETS

View full text Add to dashboard Cite

The research presented in this study focuses on the application of image processing methods for infrared (IR) intensity measurement in both spatial and temporal domains. The primary goal is to calculate the intensity at any given point in space over time, leveraging thermal imaging technology. The experimental setup involves the use of a thermal camera to capture the burning flare, which provides radiometric output. Additionally, a spectroradiometer is employed to measure intensity. The methodology integrates Plank's quantization law and employs image processing techniques using MATLAB to develop a specialized application.The application developed in this study aims to compute IR intensity, considering both spatial and temporal dimensions. Plank's quantization law serves as a foundational principle for the calculation process, and MATLAB-based image processing algorithms enhance the accuracy and efficiency of the intensity measurements. The intended application of this developed tool is within the defence sector, specifically for enhancing the security of aircraft. By providing a reliable and accurate means of assessing IR intensity over both space and time, the developed application can contribute to advanced surveillance and monitoring capabilities, ensuring the safety and security of aircraft in defence applications.

show abstract

Artificial Neural Network Based Image Fusion for Surveillance Application

Paramanandham

Sasithradevi

Poovathy

et al. 2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Swarm intelligence based image fusion for noisy images using consecutive pixel intensity

Cited by 8 publications

References 22 publications

Pixel Intensity Resemblance Measurement and Deep Learning Based Computer Vision Model for Crack Detection and Analysis

Pixel Intensity Resemblance Measurement and Deep Learning Based Computer Vision Model for Crack Detection and Analysis

Application of Image Processing Methods for IR Intensity Measurement in Spatial and Temporal Domains: A Comprehensive Review

Artificial Neural Network Based Image Fusion for Surveillance Application

Contact Info

Product

Resources

About