Analysis of various image feature extraction methods against noisy image: SIFT, SURF and HOG

Routray, Sidheswar; Ray, Arun Kumar; Mishra, Chandrabhanu

doi:10.1109/icecct.2017.8117846

Cited by 36 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Others (𝐿 𝑥𝑦 , 𝐿 𝑦𝑥 , 𝐿 𝑦𝑦 ) are calculated similarly. Since key point calculations will be made for each pixel, the SURF method is affected by noise in the image and faulty or missing features can be extracted [49][50][51]. Because SURF features are calculated for each pixel.…”

Section: Feature Extractionmentioning

confidence: 99%

Comparative Analysis of CNN Models and Bayesian Optimization-Based Machine Learning Algorithms in Leaf Type Classification

Aslan

2023

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

In this study, the leaves are classified by various Machine Learning (ML) and Deep Learning (DL) based Convolutional Neural Networks (CNN) methods. In the proposed method, first, image pre-processing is performed to increase the accuracy of the posterior process. The obtained image is a grayscale image without noise as a result of the pre-processing. These preprocessed images are used in classification with ML and DL. The Speeded Up Robust Features (SURF) are extracted from the grayscale image for ML-based learning. The features are restructured as visual words using the Bag of Visual Words (BoVW) method. Then, histograms are generated for each image according to the frequency of the visual word. Those histograms represent the new feature data. The histogram features are classified by four different ML methods, Decision Tree (DT), k-Nearest Neighbor (KNN), Naive Bayes (NB) and Support Vector Machine (SVM). Before using the ML methods, Bayesian Optimization (BO) method, which is one of the Hyperparameter Optimization (HO) algorithms, is applied to determine hyperparameters. In the classification process performed with four different ML algorithms, the best accuracy is achieved with the KNN algorithm as 98.09%. Resnet18, ResNet50, MobileNet, GoogLeNet, DenseNet, which are state-of-the-art CNN architectures, are used for DL-based learning. CNN models have higher accuracy than ML algorithms.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Comparative Analysis of CNN Models and Bayesian Optimization-Based Machine Learning Algorithms in Leaf Type Classification

Aslan

2023

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…There are several feature extraction methods such as Histogram of Oriented Gradients (HOG), Scale Invariant Feature Transformation (SIFT), Speeded-Up Robust Features (SURF), and Features from Accelerated Segment Test (FAST). 28,29 In this study, for feature extraction, we used one of the most popular machine learning methods called transfer learning. [30][31][32] Transfer learning is especially popular in medical image analysis for deep learning where the data are not sufficient for training.…”

Section: Feature Extraction For the Clustering Using Transfer Learnin...mentioning

confidence: 99%

CluSA: Clustering-based Spatial Analysis framework through Graph Neural Network for Chronic Kidney Disease Prediction using Histopathology Images

Lee

Warner

Shaikhouni

et al. 2022

Preprint

View full text Add to dashboard Cite

Machine learning applied to digital pathology has been increasingly used to assess kidney function and diagnose the underlying cause of chronic kidney disease (CKD). We developed a novel computational framework, Clustering-based Spatial Analysis (CluSA), that leverages unsupervised learning to learn spatial relationships between local visual patterns in kidney tissue. This framework minimizes the need for time-consuming and impractical expert annotations. To incorporate spatial information over the clustered image patterns on the biopsy sample, we spatially encoded clustered patterns with colors and performed spatial analysis through graph neural network. A random forest classifier with various groups of features were used to predict CKD. For predicting high/low eGFR at the biopsy, we achieved a sensitivity of 0.97, specificity of 0.90, and accuracy of 0.95. AUC was 0.96. For predicting eGFR changes in one-year, we achieved a sensitivity of 0.83, specificity of 0.85, and accuracy of 0.84. AUC was 0.85. This study presents the first spatial analysis based on unsupervised machine learning algorithms. Without expert annotation, CluSA framework can not only accurately classify and predict the degree of kidney function at the biopsy and in one year, but also identify novel predictors of kidney function and renal prognosis.

show abstract

“…Dalal et al [12] have generated Histograms of Oriented Gradients (HOG) features by inheriting them from Scale Invariant Feature Transform (SIFT) [13] features. Sidheswar Routray et al [14] have analysed SIFT, HOG and Speeded-Up Robust Features (SURF) [15] image feature extraction techniques. Their experimental results observation reveals that SIFT performance is good on noisy images.…”

Section: Related Workmentioning

confidence: 99%

Eigen and HOG Features based Algorithm for Human Face Tracking in Different Background Challenging Video Sequences

Ranganatha¹,

Gowramma²

2022

IJIGSP

View full text Add to dashboard Cite

We are proposing a unique novel algorithm for tracking human face(s) in different background video sequences. In the beginning, Eigen features and corner points are extracted from the detected face(s). HOG (Histograms of Oriented Gradients) features are isolated from corner points. Eigen and HOG features are combined together. Using these combined features, point tracker keeps track of the face(s) in the frames of the video sequence. Proposed algorithm is being tested on challenging datasets video sequences with technical challenges such as partial occlusion (e.g. moustache, beard, spectacles, helmet, headscarf etc.), changes in expression, variations in illumination and pose; and measured for performance using standard metrics such as accuracy, precision, recall and specificity. Experimental results clearly indicate the robustness of the proposed algorithm on all different background challenging video sequences.

show abstract

Analysis of various image feature extraction methods against noisy image: SIFT, SURF and HOG

Cited by 36 publications

References 13 publications

Comparative Analysis of CNN Models and Bayesian Optimization-Based Machine Learning Algorithms in Leaf Type Classification

Comparative Analysis of CNN Models and Bayesian Optimization-Based Machine Learning Algorithms in Leaf Type Classification

CluSA: Clustering-based Spatial Analysis framework through Graph Neural Network for Chronic Kidney Disease Prediction using Histopathology Images

Eigen and HOG Features based Algorithm for Human Face Tracking in Different Background Challenging Video Sequences

Contact Info

Product

Resources

About