Edge detection in noisy images with different edge types

Ruslau, Maria F. V.; Pratama, Rian Ade; Nurhayati, .; Asmal, Sapta

doi:10.1088/1755-1315/343/1/012198

Cited by 4 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperparameter optimization identifies a pair of hyperparameters that minimize a loss function on independent data. The traditional methods are grid search, Random search, Gradient-based, Evolutionary, population-based, and early stopping-based [ 98 , 100 , 101 , 102 ].…”

Section: Resultsmentioning

confidence: 99%

“…All images will be changed to function in RGB space. After analyzing the potential image restoration procedures, the median filter was implemented using Gaussian noise to smooth the images [ 98 , 99 , 100 , 101 , 102 ].…”

Section: Methodsmentioning

confidence: 99%

“…Since the pictures for the model training came from different online dermatology sites and could be different sizes and color spaces, image scaling and color space transformation were used to make al images the same size and color space. All images will be changed to function in RGB space After analyzing the potential image restoration procedures, the median filter was implemented using Gaussian noise to smooth the images [98][99][100][101][102].…”

Section: Image Preprocessing Techniquesmentioning

confidence: 99%

See 2 more Smart Citations

Skin Lesion Synthesis and Classification Using an Improved DCGAN Classifier

2023

View full text Add to dashboard Cite

The prognosis for patients with skin cancer improves with regular screening and checkups. Unfortunately, many people with skin cancer do not receive a diagnosis until the disease has advanced beyond the point of effective therapy. Early detection is critical, and automated diagnostic technologies like dermoscopy, an imaging device that detects skin lesions early in the disease, are a driving factor. The lack of annotated data and class-imbalance datasets makes using automated diagnostic methods challenging for skin lesion classification. In recent years, deep learning models have performed well in medical diagnosis. Unfortunately, such models require a substantial amount of annotated data for training. Applying a data augmentation method based on generative adversarial networks (GANs) to classify skin lesions is a plausible solution by generating synthetic images to address the problem. This article proposes a skin lesion synthesis and classification model based on an Improved Deep Convolutional Generative Adversarial Network (DCGAN). The proposed system generates realistic images using several convolutional neural networks, making training easier. Scaling, normalization, sharpening, color transformation, and median filters enhance image details during training. The proposed model uses generator and discriminator networks, global average pooling with 2 × 2 fractional-stride, backpropagation with a constant learning rate of 0.01 instead of 0.0002, and the most effective hyperparameters for optimization to efficiently generate high-quality synthetic skin lesion images. As for the classification, the final layer of the Discriminator is labeled as a classifier for predicting the target class. This study deals with a binary classification predicting two classes—benign and malignant—in the ISIC2017 dataset: accuracy, recall, precision, and F1-score model classification performance. BAS measures classifier accuracy on imbalanced datasets. The DCGAN Classifier model demonstrated superior performance with a notable accuracy of 99.38% and 99% for recall, precision, F1 score, and BAS, outperforming the state-of-the-art deep learning models. These results show that the DCGAN Classifier can generate high-quality skin lesion images and accurately classify them, making it a promising tool for deep learning-based medical image analysis.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Image Preprocessing Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Skin Lesion Synthesis and Classification Using an Improved DCGAN Classifier

2023

View full text Add to dashboard Cite

show abstract

“…which is chosen manually, m is the sequence number of the image in different angles and i is the number of the pixel in each image. [23] We focus on the nearest range besides the central part as shown in Fig. 4(b).…”

Section: Data Analysis 31 Image Processingmentioning

confidence: 99%

New measuring method of fiber alignment in precision torsion pendulum experiments*

et al. 2020

View full text Add to dashboard Cite

Testing the extreme weak gravitational forces between torsion pendulum and surrounding objects will indicate new physics which attracts many interests. In these measurements, the fiber alignment plays a crucial role in fulfilling high precision placement measurement, especially in measuring the deviation between the fiber and source mass or other objects. The traditional way of the fiber alignment requires to measure the component of the pendulum body and then transfer to the torsion fiber by some complicated calculations. A new method is reported here by using a CCD camera to get the projection image of the torsion fiber, which is a direct and no-contact measurement. Furthermore, the relative position change of the torsion fiber can also be monitored during the experiment. In our experiment, the alignment between the fiber and the center of the turntable has been operated as an example. Our result reaches the accuracy of several micrometers which is higher than the previous method.

show abstract

Comparative Analysis of Edge Detectors Applying on the Noisy Image Using Edge-Preserving Filter

Kumar

Bardhan

2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

Edge detection in noisy images with different edge types

Cited by 4 publications

References 1 publication

Skin Lesion Synthesis and Classification Using an Improved DCGAN Classifier

Skin Lesion Synthesis and Classification Using an Improved DCGAN Classifier

New measuring method of fiber alignment in precision torsion pendulum experiments*

Comparative Analysis of Edge Detectors Applying on the Noisy Image Using Edge-Preserving Filter

Contact Info

Product

Resources

About