Histograms of oriented gradients for automatic detection of defective regions in thermograms

Erazo-Aux, Jorge; Correa, Humberto Loaiza; Girón, Andrés David Restrepo

doi:10.1364/ao.58.003620

Cited by 16 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grayscale transformation is an image enhancement method that can be increased, which can increase the dynamic range of the image, expand the contrast of the image, and make the image clearer and more obvious. Grayscale transformation is also known as image contrast enhancement [22]. Grayscale transformation's contrast enhancement method is very effective.…”

Section: Grayscale Transformation Methodmentioning

confidence: 99%

Image Contrast Enhancement Method Based on Nonlinear Space and Space Constraints

Zhao¹,

Xia²

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Remote sensing, environmental monitoring, pattern recognition, and other fields all use this critical and indispensable basic technology. The article proposes an image contrast enhancement detection algorithm based on a linear model to address the problem that the current global contrast enhancement detection algorithm does not have high classification accuracy under the low-intensity JPEG compression quality factor. To decompose the original image, use the biorthogonal wavelet transform. The improved fuzzy set enhancement algorithm is used for the low-frequency subband coefficient. The results obtained after simulating this algorithm show that it is very effective in improving contrast, enhancing image details, and suppressing noise. It has the ability to greatly improve the image’s visual effect, as well as the advantages of parameter adaptation and high algorithm efficiency.

show abstract

Section: Grayscale Transformation Methodmentioning

confidence: 99%

Image Contrast Enhancement Method Based on Nonlinear Space and Space Constraints

Zhao¹,

Xia²

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…In this paper, we present a Deep-CNN method for feature extraction of three kinds of breast cancer masses. Multiple properties of the gray level co-occurrence matrix (GLCM) and the histogram of oriented gradient (HOG) [34,35] are examined to emphasize the texture features of the region of interest (ROI). Texture scoring features analogous to each breast mammogram are pooled into multi-features.…”

Section: Introductionmentioning

confidence: 99%

Breast Cancer Classification Using Deep Convolution Neural Network with Transfer Learning

Mahmoud¹,

Alharbi²,

Khafga³

2021

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

In this paper, we aim to apply deep learning convolution neural network (Deep-CNN) technology to classify breast masses in mammograms. We develop a Deep-CNN combined with multi-feature extraction and transfer learning to detect breast cancer. The Deep-CNN is utilized to extract features from mammograms. A support vector machine (SVM) is then trained on the Deep-CNN features to classify normal, benign, and cancer cases. The scoring features from the Deep-CNN are coupled with texture features and used as inputs to the final classifier. Two texture features are included: texture features of spatial dependency and gradient-based histograms. Both are employed to locate breast masses in mammograms. Next we apply transfer learning to the classifier of the SVM. Four techniques are devised for the experimental evaluation of the proposed system. The fourth technique combines the Deep-CNN with texture features and local features extracted by the scale-invariant feature transform (SIFT) algorithm. Experiments are designed to measure the performance of the various techniques. The results demonstrate that the proposed CNN coupled with the texture features and the SIFT outperforms the other models and performs best with transfer learning embedded. The accuracy of this model is 97.8%, with a true positive rate of 98.45% and a true negative rate of 96%.

show abstract

“…However, flash thermography is inherently limited by the highly diffusive and strongly damped nature of the induced thermal waves, making the accurate detection of small and deep defects very challenging. Several image processing techniques, which only use the input of one single thermogram, have been developed to enhance the defect detectability by reducing noise and background non-uniformities [6][7][8]. Also many data post-processing techniques, which use the complete recorded thermographic sequence, have been implemented to further enhance the defect detectability [1,[9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Adaptive spectral band integration in flash thermography: Enhanced defect detectability and quantification in composites

Poelman

Hedayatrasa

Segers

et al. 2020

Composites Part B: Engineering

View full text Add to dashboard Cite

Histograms of oriented gradients for automatic detection of defective regions in thermograms

Cited by 16 publications

References 17 publications

Image Contrast Enhancement Method Based on Nonlinear Space and Space Constraints

Image Contrast Enhancement Method Based on Nonlinear Space and Space Constraints

Breast Cancer Classification Using Deep Convolution Neural Network with Transfer Learning

Adaptive spectral band integration in flash thermography: Enhanced defect detectability and quantification in composites

Contact Info

Product

Resources

About