Image Classification Using an Ensemble-Based Deep CNN

Aloysius, Neena; Geetha, M. Kalaiselvi

doi:10.1007/978-981-10-8633-5_44

Cited by 24 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent times ensembling is a popular concept to improve the results for discriminative CNNs, particularly for image classification (Neena & Geetha, 2018), object detection (X. Wang & Gupta, 2015), or medical image segmentation tasks (Altaf et al, 2021; Kavur, Gezer, et al, 2020; Kavur, Kuncheva, et al, 2020; Menze et al, 2014). Ensembling of GANs has also been experimented with for imbalanced image classification (Ermaliuc et al, 2021; Huang et al, 2020).…”

Section: Methodsmentioning

confidence: 99%

Long future frame prediction using optical flow‐informed deep neural networks for enhancement of robotic teleoperation in high latency environments

Moniruzzaman

Rassau

Chai

et al. 2022

Journal of Field Robotics

View full text Add to dashboard Cite

High latency in teleoperation has a significant negative impact on operator performance. While deep learning has revolutionized many domains recently, it has not previously been applied to teleoperation enhancement. We propose a novel approach to predict video frames deep into the future using neural networks informed by synthetically generated optical flow information. This can be employed in teleoperated robotic systems that rely on video feeds for operator situational awareness. We have used the image-to-image translation technique as a basis for the prediction of future frames. The Pix2Pix conditional generative adversarial network (cGAN) has been selected as a base network. Optical flow components reflecting real-time control inputs are added to the standard RGB channels of the input image. We have experimented with three data sets of 20,000 input images each that were generated using our custom-designed teleoperation simulator with a 500-ms delay added between the input and target frames. Structural Similarity Index Measures (SSIMs) of 0.60 and Multi-SSIMs of 0.68 were achieved when training the cGAN with three-channel RGB image data. With the five-channel input data (incorporating optical flow) these values improved to 0.67 and 0.74, respectively. Applying Fleiss' κ gave a score of 0.40 for three-channel RGB data, and 0.55 for fivechannel optical flow-added data. We are confident the predicted synthetic frames are of sufficient quality and reliability to be presented to teleoperators as a video feed that will enhance teleoperation. To the best of our knowledge, we are the first to attempt to reduce the impacts of latency through future frame prediction using deep neural networks.

show abstract

Section: Methodsmentioning

confidence: 99%

Long future frame prediction using optical flow‐informed deep neural networks for enhancement of robotic teleoperation in high latency environments

Moniruzzaman

Rassau

Chai

et al. 2022

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…The Matlab 3 coding has been implemented to retrieve the properties of the images like mean, standard deviation, contrast, entropy, and kurtosis, which frame the rules to classify figures. Convolutional Neural Networks (CNN) have advanced and improved architecture to model and classifies images by hierarchically training the data [17]. The images have been classified into four categories depending on a set of rules implemented in python, as shown below: the rules are classified into good, average, bad, and contradictory pictures.…”

Section: Image Classificationmentioning

confidence: 99%

Abstract and Image Analysis of High-Temperature Materials from Scientific Journals Using Deep Learning and Rule-Based Machine Learning Approaches

Jayaram

Prakash

Vishakantaiah

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

In this digital world, many research papers have been getting added to the scientific journals in PDF format. It has become essential to the process and needs digitalization due to the exponential growth of newly published research papers. Survey of Abstract, Figures, and Captions convey the necessary information and extracted from scientific research journals. The section algorithm is used for extracting "Abstract" and "Result and Discussion" sections from the published research papers about high-temperature materials (HTM) by converting PDF to word documents. HTM got complete applications in aerospace engineering and electronic. After exposure to high-temperature test facilities, various characterization techniques are used to produce numerous high-resolution images. Abstract summarization, SEM figures, and caption extraction from HTM documents are performed using Deep learning, PDFFigure, and Machine learning (ML) techniques. MatLab is used for feature extraction and to classify SEM images by rule-based ML techniques. This summarization helps new researchers understand existing research datasets and proceed with new approaches to solve more complex problems. This research paper presents automatic extraction and summary of abstract, high-resolution figures, and captions from scientific journals on HTM; all these documents will be analyzed to categorize with a different tailor-made approach using deep learning and machine learning techniques.

show abstract

“…Ensemble learning involve the combination of multiple models to make a final prediction, with the goal of improving the performance of the individual models [16]. Ensemble learning has been shown to be effective in a variety of machine learning tasks, including image classification [17]. In the context of skin cancer detection, ensemble learning can potentially improve the accuracy and robustness of deep learning models by incorporating the predictions of multiple models trained on subsets of a dataset or with different architectures [18], [19].…”

Section: Introductionmentioning

confidence: 99%

Deep learning model enhanced skin cancer detection

Kolachina

Agada²,

Li³

et al. 2023

Biophotonics and Immune Responses XVIII

View full text Add to dashboard Cite

According to the American Academy of Dermatology Association, identifying the types of skin cancer depends on the origin of a cell mutation resulting in the rapid growth of these abnormal cells in the epidermis. These mutations lead the skin cells to multiply rapidly and form malignant tumors. Skin cancer is ranked as the 17th most common form of cancer worldwide according to the World Cancer Research Fund. Skin cancer treatments cost the United States more than $8 billion (about $25 per person in the US) each year, making skin cancer the fifth most costly cancer for Medicare. Furthermore, skin cancer is an under recognized problem for diverse populations, including young women and minorities. Researchers have been exploring different technologies to detect skin care at its early stage to avoid high mortality rate and expensive medical treatment. This paper presents a novel ensembled deep learning model for the early detection of skin cancer. Our research is based on The HAM10000 dataset, a diverse collection of multi-sourced dermatoscopic images of common pigmented skin lesions which consists of 10015 dermatoscopic images. We have compared several deep learning neural network architectures and classifiers such as DNN, RNN, SVM and KNN in terms of accuracy rate and computation complexity and presented an ensembled deep learning model for early skin cancer detection. The main contribution of this paper is the productions of a comparative study of several skin cancer detection techniques using powerful computer vision techniques and deep learning models and a novel ensembled deep learning model for skin cancer detection.

show abstract

Image Classification Using an Ensemble-Based Deep CNN

Cited by 24 publications

References 8 publications

Long future frame prediction using optical flow‐informed deep neural networks for enhancement of robotic teleoperation in high latency environments

Long future frame prediction using optical flow‐informed deep neural networks for enhancement of robotic teleoperation in high latency environments

Abstract and Image Analysis of High-Temperature Materials from Scientific Journals Using Deep Learning and Rule-Based Machine Learning Approaches

Deep learning model enhanced skin cancer detection

Contact Info

Product

Resources

About