Automated Optic Disc removal in fundus images using iterative heuristics and morphological operations

Hassan, H.; Tahir, N. M.; Yassin, Ihsan Mohd; Zabidi, Azlee; Shafie, Suraiya M.

doi:10.1109/spc.2013.6735137

Cited by 4 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Digital images are processed depending on their forms using a variety of image processing techniques known as morphological operations [47]. Each image pixel in a morphological procedure corresponds to the number of other pixels in the region.…”

Section: Morphological Operationmentioning

confidence: 99%

Dcariesnet: Dental Caries Segmentation With Three-Fold Features and Optimized U-Net

Shajahan,

Usman,

Mohd Aris

et al. 2023

INDJCSE

View full text Add to dashboard Cite

Early detection of dental caries is essential for effective treatment. The refore, deep learning methods have achieved extraordinary radiological diagnostic efficiency. This research seeks to effectively employ the DCariesNet based deep learning approach for dental caries segmentation. The DCariesNet is utilized for identifyng dental caries-affected regions in X-ray images. The three main steps of the newly proposed DCariesNet are "(a) Pre-processing, (b) Feature Extraction, and (c) Dental caries Segmentation." The acquired dental X-ray images are first pre-processed using Partition Supported Median, Interpolation, and Discrete Wavelet Transform (NRPMID), morphological operations (dilation, erosion, opening, and closure), and histogram equalization. The three-fold features, like Local Binary Pattern (LBP), Local Discriminative Pattern (LDP), and Local Optimal-Oriented Pattern (LOOP) are extracted from the preprocessed images. To train the segmentation framework, these retrieved characteristics are combined. A novel, improved U-NET-based CNN architecture is used to mimic the dental caries segmentation phase. A novel Aquila Explored Crow search Optimizer (CrAqOA) is used to optimize the weight function of U-NET. The standard Aquila Optimizer (AO) and standard Crow Search Optimization (CSA) concepts are blended to create the CrAqOA model. The segmented result (i.e. caries affected area) is the end outcome of the optimized U-NET. The proposed model assists in the early diagnosis of dental cavities with enhanced accuracy. Finally, to confirm the effectiveness of the anticipated model, a comparison evaluation is conducted.

show abstract

Section: Morphological Operationmentioning

confidence: 99%

Dcariesnet: Dental Caries Segmentation With Three-Fold Features and Optimized U-Net

Shajahan,

Usman,

Mohd Aris

et al. 2023

INDJCSE

View full text Add to dashboard Cite

show abstract

“…Median filter, fill up the blood vessels inside the optic disc which made easy to remove the optic disc by using thresholding. H. A. Hassan et al [11] proposed automatic optic disc removal in fundus image using iterative morphological operations. The morphological operation such as erosion and dilation enhance the image.…”

Section: Elimination Of Non-haemorrhage Featuresmentioning

confidence: 99%

Haemorrhage Detection and Classification: A Review

Jaware¹

2017

IJERA

View full text Add to dashboard Cite

In Indian population, the count of diabetic peoples gets increasing day by day. Due to improper balance of insulin in the human body causes Diabetic. The most common symptom of the person with diabetes is diabetic retinopathy, which leads to blindness. The effect due to DR can reduce by early detection of Haemorrhages and treated at an early stage. In recent year, there is an increased interest in the field of medical image processing. Many researchers have developed advanced algorithms for Haemorrhage detection using fundus images. In proposed paper, we discuss various methods for Haemorrhage detection and classification.

show abstract

Severity Analysis Automation for Detection of Non-Proliferative Diabetic Retinopathy

Neelapala,

Satapathi,

Mosa

2024

Innovations in Sustainable Technologies and Computing

View full text Add to dashboard Cite

Automated Optic Disc removal in fundus images using iterative heuristics and morphological operations

Cited by 4 publications

References 7 publications

Dcariesnet: Dental Caries Segmentation With Three-Fold Features and Optimized U-Net

Dcariesnet: Dental Caries Segmentation With Three-Fold Features and Optimized U-Net

Haemorrhage Detection and Classification: A Review

Severity Analysis Automation for Detection of Non-Proliferative Diabetic Retinopathy

Contact Info

Product

Resources

About