Image Segmentation Using Hybrid Optimization Algorithms: Review

Hemeida, Ashraf Mohamed; Yahya, Heba; Al-Sanary, Hamida

doi:10.21608/aujst.2023.183546.1012

Cited by 3 publications

(3 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A histogram analysis may provide insight into an image's pixel value distribution. Original images typically exhibit distinct patterns and biases in their histograms, reflecting features like dominant colors, shapes, and textures [33][34][35][36]. Secure encryption techniques aim to disrupt these patterns and create a more uniform distribution of pixel values in the encrypted image's histogram.…”

Section: Analytical Histogrammentioning

confidence: 99%

Scrambled Encryption Approach for Color Images Based on 9-D Chaotic Systems with 3-D Substitution Bit Levels

Abdel Hameed

2024

Aswan University Journal of Sciences and Technology

View full text Add to dashboard Cite

Over the past few decades, the need for robust and secure communication has grown exponentially, particularly in image transmission over networks. This is due to the increasing reliance on digital technologies. This work demonstrates a novel "Scrambled Encryption Approach" that leverages the inherent unpredictability. To this end, nine-dimensional chaotic systems are combined with the innovative technique of 3-D substitution bit levels to verify strengths such as the confidentiality and integrity of visual data while maintaining fast encryption and decryption processes. This has the drawback of being vulnerable to known plaintext attacks and performing more sophisticated calculations than simpler encryption approaches. So, the proposed technique first separates the color input image into 24 bits to be categorized into 8 bits for each color channel (red, green, and blue). Then, 3-bit levels are used with position sequences for substitutions taken from the 9-D Lorenz chaotic system. After that, a multilayer differentiation technique produces three key matrices, which are then used to diffuse the scrambled components and produce the color cipher image. The simulation results show that our method has a high visual quality of decrypted images as well as high protection against brute force attacks because we have a large key space used for encryption data. Moreover, our proposed technique achieves more security against statistical attacks, including histogram analysis, information entropy, and correlation coefficients between pixels. Finally, the proposed encryption technique achieves a more secure transmission than state-of-the-art encryption approaches to guarantee integrity, privacy, and efficiency through global networks.

show abstract

Section: Analytical Histogrammentioning

confidence: 99%

Scrambled Encryption Approach for Color Images Based on 9-D Chaotic Systems with 3-D Substitution Bit Levels

Abdel Hameed

2024

Aswan University Journal of Sciences and Technology

View full text Add to dashboard Cite

show abstract

“…One distinctive feature of the proposed model is its integration of deep learning techniques for glaucoma detection with ensemble semantic segmentation for the optic disc and optic cup. While previous studies have looked at deep learning models for structure segmentation alone [29], the suggested approach introduces a novel ensemble framework that combines the predictions of multiple models. The accuracy and robustness of the glaucoma detection system can be enhanced by learning from a bigger pool of information through the combination of different models.…”

Section: The Modelmentioning

confidence: 99%

Improving Glaucoma Detection: Harnessing the Power of Ensemble Semantic Segmentation for Optic Disc and Optic Cup with Deep Learning

dahab

2024

Aswan University Journal of Sciences and Technology

View full text Add to dashboard Cite

Globally, glaucoma is a leading cause of irreversible visual loss. Due to the lack of symptoms in the early stages of the disease, glaucoma is typically not diagnosed until severe vision loss has occurred. One of the most common ways to diagnose glaucoma is with a comprehensive eye exam. However, a substantial commitment of time, money, and specialist equipment and personnel is necessary to carry out such investigations. Using deep learning optic cup and disc segmentation based on retinal fundus images, this work aims to develop and evaluate the effectiveness of a novel, affordable glaucoma screening tool. The research made use of ensemble learning technique to enhance semantic segmentation models. A number of recognized deep learning architectures, including Unet 3Plus, Deep Lab V3P, PSPNET and UW-Net, are combined in the proposed semantic ensemble segmentation model. Ensemble combination involves merging predictions from several models using a weighted averaging technique that considers the accuracy and dependability of each individual model. Metrics such as accuracy, specificity, sensitivity, area under the curve, intersection over union, dice coefficient, and f1-score are used to evaluate the performance in the study. The proposed model was validated on three publicly available datasets, namely ORIGA, REFUGE and RIM-ONE DL. The experimental results show that the suggested method can estimate the Cup to Disc Ratio CDR for thorough glaucoma screening, and it is on par with the state-of-the-art architecture utilized for optic disc and cup segmentation.

show abstract

“…The ability to recognize and categories sick areas in plant images make image segmentation a valuable tool for studying plant diseases. A well-liked unsupervised machine learning approach called K-means clustering separates a picture into groups or segments depending on how similar the pixel intensity values are [2]. However, there is a possible production failure due to various diseases because of the high area under tomato cultivation and low efficiency (20 tonnes per hectare).…”

mentioning

confidence: 99%

Image segmentation in Diagnosing the Ground Bud Necrosis Virus in Tomatoes using K-Means Clustering

Kadam,

Dhumale,

Dhumale

et al. 2023

IJEER

View full text Add to dashboard Cite

Early-stage fruit disease detection will ensure the natural product quality for the organic agriculture business. The potential of using K-Means segmentation for diagnosing tomatoes fruit disease was intended to be explored by this proposed method. The main goal of paper is to increase classification accuracy by locating tomatoes with Ground Bud Necrosis Virus in Tomatoes disease using an image segmentation approach. The K-means clustering algorithm is intended to boost segmentation effectiveness. In the end product, the images are divided into three classes: Grade 0—00-15%; Grade 1—16-35%; Grade 2—36-65%; Grade 3—66-85%; and Class 4—86-100%. Moreover, the tested results of the proposed approach explore a variety of unhealthy images and disease Tomatoes and demonstrate that, when compared to existing methods, the proposed method has the highest accuracy.

show abstract

Image Segmentation Using Hybrid Optimization Algorithms: Review

Cited by 3 publications

References 88 publications

Scrambled Encryption Approach for Color Images Based on 9-D Chaotic Systems with 3-D Substitution Bit Levels

Scrambled Encryption Approach for Color Images Based on 9-D Chaotic Systems with 3-D Substitution Bit Levels

Improving Glaucoma Detection: Harnessing the Power of Ensemble Semantic Segmentation for Optic Disc and Optic Cup with Deep Learning

Image segmentation in Diagnosing the Ground Bud Necrosis Virus in Tomatoes using K-Means Clustering

Contact Info

Product

Resources

About