99,216 Hits in 7.1 sec

Satellite and Scene Image Classification Based on Transfer Learning and Fine Tuning of ResNet50

Amsa Shabbir, Nouman Ali, Jameel Ahmed, Bushra Zafar, Aqsa Rasheed, Muhammad Sajid, Afzal Ahmed, Saadat Hanif Dar, Muazzam Maqsood
2021 Mathematical Problems in Engineering  
Recent trends for remote sensing and scene classification are focused on the use of Convolutional Neural Network (CNN).  ...  Earlier approaches for remote sensing images and scene analysis are based on low-level feature representations such as color- and texture-based features.  ...  Table 9 demonstrates the classwise performance for Corel-1K image benchmark in terms of precision, recall, and F-score. e average precision, recall, and F-score values for Name of algorithm/model Classification  ... 
doi:10.1155/2021/5843816 fatcat:sk6arf2jkfa2xfthw7rxcs2ey4

Multi-Phase Feature Representation Learning for Neurodegenerative Disease Diagnosis [chapter]

Siqi Liu, Sidong Liu, Weidong Cai, Sonia Pujol, Ron Kikinis, David Dagan Feng
2015 Lecture Notes in Computer Science  
The proposed approach outperformed the original neural network in both binary and ternary Alzheimer's disease classification tasks.  ...  , because they could be simple and effective for the clinicians to assess the disorder's progression and severity.  ...  The feature representation network is optimised to estimate the low-dimensional biomarkers before it is finally used for classification.  ... 
doi:10.1007/978-3-319-14803-8_27 fatcat:6r46rorxnfhbjdq4by4uz2xgga

Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths [article]

Ximeng Sun, Rameswar Panda, Chun-Fu Chen, Naigang Wang, Bowen Pan, Kailash Gopalakrishnan, Aude Oliva, Rogerio Feris, Kate Saenko
2021 arXiv   pre-print
Extensive experiments on multiple image classification datasets including video classification benchmarks for the first time, well demonstrate the efficacy of our approach over state-of-the-art methods  ...  First, we propose a collaborative strategy to choose a high-precision teacher for transferring knowledge to the low-precision student while jointly optimizing the model with all bit-widths.  ...  Despite recent progress in network quantization for improving efficiency of deep networks, most of the existing methods repeat the quantization process and retrain the low-precision network from scratch  ... 
arXiv:2103.01435v3 fatcat:qukv5qgpxjfxnixlor6blwfbi4

Using deep transfer learning to detect scoliosis and spondylolisthesis from x-ray images

Mohammad Fraiwan, Ziad Audat, Luay Fraiwan, Tarek Manasreh, Thippa Reddy Gadekallu
2022 PLoS ONE  
In this paper, we utilize advances in deep transfer learning to diagnose spondylolisthesis and scoliosis from X-ray images without the need for any measurements.  ...  Regarding pair-wise binary classification, high accuracy values were achieved for most of the models (i.e., > 98%).  ...  The mean overall F1 score, precision, and recall parameters for the 14 deep learning models performing three-class classification. 2 Model F1 Score Precision Recall Specificity SqueezeNet 89.98% 94.10%  ... 
doi:10.1371/journal.pone.0267851 fatcat:p5la33yjrzgl3g5lhaichudzaa

Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing

Anant R. Bhatt, Amit Ganatra, Ketan Kotecha
2021 PeerJ Computer Science  
We achieved singular multiclass classification scores for WSI images of the SIPaKMed dataset, that is, accuracy (99.70%), precision (99.70%), recall (99.72%), F-Beta (99.63%), and Kappa scores (99.31%)  ...  However, they suffer from inherent challenges for minute feature extraction and precise classification.  ...  Ragini Thapa, a Graded Pathologist, for valuable medical inputs and extending help in manual validation of the Pap smear image samples.  ... 
doi:10.7717/peerj-cs.348 pmid:33816998 pmcid:PMC7959623 fatcat:qcfdzjottvbxzeibelna3hbqgy

A Comparative Analysis of Feature Sets for Image Classification Using Back Propagation Neural Network

Syed Husain
2015 International Journal of Information and Electronics Engineering  
The goal of this research is to evaluate some common features sets used for classification of images and identify the best features depending upon the user requirement.  ...  The results have been evaluated on the basis of precision and recall and it can be concluded that for natural images none of the feature sets perform well universally on all classes and the selection of  ...  Therefore, recall is diminished at the expense of improving precision. (2) Aria et al. [7] have explored Back Propagation Neural Network (BPNN) for classification of remote sensing images.  ... 
doi:10.7763/ijiee.2015.v5.490 fatcat:mekfjlolmjc4nhyuwvd24nravm

COVID-19 Pulmonary Consolidations Detection in Chest X-Ray using Progressive Resizing and Transfer Learning Techniques

Anant Bhatt, Amit Ganatra, Ketan Kotecha
2021 Heliyon  
The Progressive Resizing technique reuses old computations while learning new ones in Convolution Neural Networks (CNN), enabling it to incorporate prior knowledge of the feature hierarchy.  ...  Existing Deep Learning techniques demonstrate promising results in analyzing X-ray images when employed with Transfer Learning.  ...  We used Transfer Learning with Progressive resizing on the EfficientNet-B3 model by progressively giving the images in 128x128, 256x256, and 512x512 sizes, and obtained an ideal score of 100% for these  ... 
doi:10.1016/j.heliyon.2021.e07211 pmid:34109279 pmcid:PMC8178060 fatcat:jdnoydltprea7eds5z7ge62vme

Deep Inside Feature Learning for Image Classification Using Transfer Learning Approach [chapter]

Ranjini Surendran, J. Anitha, D. Jude Hemanth
2022 Frontiers in Artificial Intelligence and Applications  
We have used the concept of deep learning networks which is a sub class of machine learning to develop a model that can detect the vehicles which got drowned in flood.  ...  This approach has shown an overall success rate of 91% in classification.  ...  Lower layers of the network learns more low level features which bear the minuscule details of the image and decides the feature learning effectiveness of the network.  ... 
doi:10.3233/faia220051 fatcat:eeucozfg5vgatkzoiraz7lkf64

A Lightweight Model of VGG-16 for Remote Sensing Image Classification

Ye Mu
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
fine classification, very low pixel, less image classification.  ...  that our model still has a high accuracy rate of 95% for the remote sensing image with ultra-low pixels and less feature points.Therefore, the model has a good application prospect in remote sensing image  ...  In this way, the remote sensing images with low pixel and low feature points can be extracted more precisely; for highprecision and low-precision remote sensing images, we will use the more precise feature  ... 
doi:10.1109/jstars.2021.3090085 fatcat:m5hmzjc4jvch5h5uillvlihyqm

Low-Parameter Small Convolutional Neural Network Applied to Functional Medical Imaging of Tc-99m Trodat-1 Brain Single-Photon Emission Computed Tomography for Parkinson's Disease

Yu-Chieh Chang, Te-Chun Hsieh, Jui-Cheng Chen, Kuan-Pin Wang, Zong-Kai Hsu, Pak-Ki Chan, Chia-Hung Kao
2021 Journal of Personalized Medicine  
We developed a set of functional imaging multiclassification deep learning algorithms suitable for TRODAT SPECT on the basis of the annotations of medical experts.  ...  Tc-99m Trodat-1 brain (TRODAT) single-photon emission computed tomography (SPECT) aids the functional imaging of dopamine transporters and is used for dopaminergic neuron enumeration.  ...  Conflicts of Interest: All authors report no conflict of interest.  ... 
doi:10.3390/jpm12010001 pmid:35055316 pmcid:PMC8780265 fatcat:o5jo5j4wfvbqbnrt7vwd2dhtfy

Groundnuts Leaf Disease Recognition using Neural Network with Progressive Resizing

Rajnish M. Rakholia, Jinal H. Tailor, Jatinderkumar R. Saini, Jasleen Kaur, Hardik Pahuja
2022 International Journal of Advanced Computer Science and Applications  
In this paper, a deep learning based model with progressive resizing is proposed for groundnut leaf disease recognition and classification tasks.  ...  The proposed model achieved state-of-the-art accuracy of 96.12%. The model with progressive resizing performed better than the traditional core neural network-based model built on cross-entropy loss.  ...  Almost all the existing CNN-based architectures designed for leaf disease recognition and classification perform well at some level in terms of precision, recall, f1-score, and accuracy.  ... 
doi:10.14569/ijacsa.2022.0130611 fatcat:ewfgactcnzhbvhncdjia2vleoy

Feature Learning to Automatically Assess Radiographic Knee Osteoarthritis Severity [article]

Joseph Antony, Kevin McGuinness, Kieran Moran, Noel E O' Connor
2019 arXiv   pre-print
OA image classification.  ...  In summary, this work primarily contributes to the field of automated methods for localization (automatic detection) and quantification (image classification) of radiographic knee OA.  ...  ) funded by the National Institutes of Health, a branch of the Department of Health and Human Services, and conducted by MOST study investigators.  ... 
arXiv:1908.08840v1 fatcat:j7i6fwsnkrc5vguemlpv3d5tra

Progressive Cascaded Convolutional Neural Networks for Single Tree Detection with Google Earth Imagery

Tianyang Dong, Yuqi Shen, Jian Zhang, Yang Ye, Jing Fan
2019 Remote Sensing  
To solve these problems, this paper presents progressive cascaded convolutional neural networks for single tree detection with Google Earth imagery and adopts three progressive classification branches  ...  However, the existing single tree detection methods have many errors of commission and omission in complex scenes, close values on the digital data of the image for background and trees, unclear canopy  ...  [14] used a method of scale-invariant feature transform (SIFT) to extract the key points of palm trees and put them into the extreme learning machine (ELM) for learning classification, thereby realising  ... 
doi:10.3390/rs11151786 fatcat:23wzgeo75jhjzocq4c7zxm5qvi

Brain MRI Classification using Deep Learning Algorithm

2020 International Journal of Engineering and Advanced Technology  
The AlexNet transfer learning network of CNN is used because of the limitation of the brain MRI dataset.  ...  The classification layer of Alexnet is replaced by the softmax layer with benign and malignant training images and trained using small weights.  ...  Training using Deep Learning Algorithm DL is extensively used for classification in recent years. Among the DL algorithm, CNN is the most trendy algorithm for the classification of medical images.  ... 
doi:10.35940/ijeat.c5350.029320 fatcat:yiscwytdsbf3deovg4iriekhdq

The Artificial Intelligence-Enabled Medical Imaging Today and Its Future

2019 Chinese Medical Sciences Journal  
Medical imaging is now being reshaped by artificial intelligence (AI) and progressing rapidly toward future. In this article, we review the recent progress of AI-enabled medical imaging.  ...  Then, we discuss the recent successes of AI in different medical imaging tasks, especially in image segmentation, registration, detection and recognition.  ...  The initial version of CNN is well known for its classification capability. However, the architecture of CNN might not be a proper choice to image segmentation.  ... 
doi:10.24920/003615 pmid:31315746 fatcat:65avq2fcgzfgxosc42z44tyjfa
« Previous Showing results 1 — 15 out of 99,216 results