scholarly journals The Influence of Region of Interest Heterogeneity on Classification Accuracy in Wetland Systems

2019 ◽  
Vol 11 (5) ◽  
pp. 551 ◽  
Author(s):  
Tedros M. Berhane ◽  
Hugo Costa ◽  
Charles R. Lane ◽  
Oleg A. Anenkhonov ◽  
Victor V. Chepinoga ◽  
...  
Keyword(s):  
Image Classification ◽  
Classification Accuracy ◽  
Region Of Interest ◽  
Complex Environments ◽  
Sampling Frame ◽  
Single Class ◽  
Natural Systems ◽  
Data Points ◽  
Large Heterogeneity ◽  
Supervised Image Classification

Classifying and mapping natural systems such as wetlands using remote sensing frequently relies on data derived from regions of interest (ROIs), often acquired during field campaigns. ROIs tend to be heterogeneous in complex systems with a variety of land cover classes. However, traditional supervised image classification is predicated on pure single-class observations to train a classifier. This ultimately encourages end-users to create single-class ROIs, nudging ROIs away from field-based points or gerrymandering the ROI, which may produce ROIs unrepresentative of the landscape and potentially insert error into the classification. In this study, we explored WorldView-2 images and 228 field-based data points to define ROIs of varying heterogeneity levels in terms of class membership to classify and map 22 discrete classes in a large and complex wetland system. The goal was to include rather than avoid ROI heterogeneity and assess its impact on classification accuracy. Parametric and nonparametric classifiers were tested with ROI heterogeneity that varied from 7% to 100%. Heterogeneity was governed by ROI area, which we increased from the field-sampling frame of ~100 m2 nearly 19-fold to ~2124 m2. In general, overall accuracy (OA) tended downwards with increasing heterogeneity but stayed relatively high until extreme heterogeneity levels were reached. Moreover, the differences in OA were not statistically significant across several small-to-large heterogeneity levels. Per-class user’s and producer’s accuracies behaved similarly. Our findings suggest that ROI heterogeneity did not harm classification accuracy unless heterogeneity became extreme, and thus there are substantial practical advantages to accommodating heterogeneous ROIs in image classification. Rather than attempting to avoid ROI heterogeneity by gerrymandering, classification in wetland environments, as well as analyses of other complex environments, should embrace ROI heterogeneity.

Assessment of residual slash coverage using UAVs and implications for aspen regeneration

2020 ◽  
Vol 8 (1) ◽  
pp. 19-29
Author(s):  
Landon L. Sealey ◽  
Ken C.J. Van Rees
Keyword(s):  
Maximum Likelihood ◽  
High Resolution ◽  
Image Classification ◽  
Populus Tremuloides ◽  
Classification Accuracy ◽  
Forest Floor ◽  
Aerial Imagery ◽  
Detailed Method ◽  
Slash Distribution ◽  
Supervised Image Classification

Proper redistribution of residual slash following harvesting is crucial for ensuring successful regeneration and continued health in trembling aspen (Populus tremuloides) forests. As traditional methods of measuring residual slash are a strenuous and tedious process, the objective of this study was to develop a new, faster, and more detailed method to assess residual slash distribution for entire harvested blocks. This study also aimed to assess the influence residual slash coverage had on the success of aspen regeneration 1 year after winter harvesting. Using high-resolution UAV imagery and maximum likelihood supervised image classification, residual slash was differentiated from the underlying forest floor. Overall, classification accuracy ranged between 85% and 96% with the highest accuracy occurring when aerial imagery was collected at the beginning of the second spring following winter harvesting. Slash distribution was quite consistent across harvested blocks, with 92% of harvested blocks experiencing <33% coverage. There was no relationship between the level of aspen regeneration following 1 year of growth and percentage slash coverage up to 60%. No vegetation plots occurred in areas with >60% slash coverage; therefore, it is unknown whether aspen regeneration will be affected in areas with higher slash coverage.

scholarly journals Deep Semi-Supervised Image Classification Algorithms: a Survey

2021 ◽  
Vol 27 (12) ◽  
pp. 1390-1407
Author(s):  
Ani Vanyan ◽  
Hrant Khachatrian
Keyword(s):  
Machine Learning ◽  
Image Classification ◽  
Supervised Learning ◽  
Classification Accuracy ◽  
Classification Algorithms ◽  
The Past ◽  
Supervised Learning Algorithms ◽  
Supervised Image Classification ◽  
Learning Focused ◽  
Remarkable Progress

Semi-supervised learning is a branch of machine learning focused on improving the performance of models when the labeled data is scarce, but there is access to large number of unlabeled examples. Over the past five years there has been a remarkable progress in designing algorithms which are able to get reasonable image classification accuracy having access to the labels for only 0.1% of the samples. In this survey, we describe most of the recently proposed deep semi-supervised learning algorithms for image classification and identify the main trends of research in the field. Next, we compare several components of the algorithms, discuss the challenges of reproducing the results in this area, and highlight recently proposed applications of the methods originally developed for semi-supervised learning.

scholarly journals An Imbalanced Image Classification Method for the Cell Cycle Phase

Information ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 249
Author(s):  
Xin Jin ◽  
Yuanwen Zou ◽  
Zhongbing Huang
Keyword(s):  
Cell Cycle ◽  
Deep Learning ◽  
Image Classification ◽  
Classification Accuracy ◽  
Data Augmentation ◽  
Cycle Phase ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Cellular Life

The cell cycle is an important process in cellular life. In recent years, some image processing methods have been developed to determine the cell cycle stages of individual cells. However, in most of these methods, cells have to be segmented, and their features need to be extracted. During feature extraction, some important information may be lost, resulting in lower classification accuracy. Thus, we used a deep learning method to retain all cell features. In order to solve the problems surrounding insufficient numbers of original images and the imbalanced distribution of original images, we used the Wasserstein generative adversarial network-gradient penalty (WGAN-GP) for data augmentation. At the same time, a residual network (ResNet) was used for image classification. ResNet is one of the most used deep learning classification networks. The classification accuracy of cell cycle images was achieved more effectively with our method, reaching 83.88%. Compared with an accuracy of 79.40% in previous experiments, our accuracy increased by 4.48%. Another dataset was used to verify the effect of our model and, compared with the accuracy from previous results, our accuracy increased by 12.52%. The results showed that our new cell cycle image classification system based on WGAN-GP and ResNet is useful for the classification of imbalanced images. Moreover, our method could potentially solve the low classification accuracy in biomedical images caused by insufficient numbers of original images and the imbalanced distribution of original images.

scholarly journals Hyperspectral Image Classification Based on Multi-Scale Residual Network with Attention Mechanism

2021 ◽  
Vol 13 (3) ◽  
pp. 335
Author(s):  
Yuhao Qing ◽  
Wenyi Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Principal Component ◽  
Hyperspectral Image Classification ◽  
Deep Network ◽  
Multi Scale

In recent years, image classification on hyperspectral imagery utilizing deep learning algorithms has attained good results. Thus, spurred by that finding and to further improve the deep learning classification accuracy, we propose a multi-scale residual convolutional neural network model fused with an efficient channel attention network (MRA-NET) that is appropriate for hyperspectral image classification. The suggested technique comprises a multi-staged architecture, where initially the spectral information of the hyperspectral image is reduced into a two-dimensional tensor, utilizing a principal component analysis (PCA) scheme. Then, the constructed low-dimensional image is input to our proposed ECA-NET deep network, which exploits the advantages of its core components, i.e., multi-scale residual structure and attention mechanisms. We evaluate the performance of the proposed MRA-NET on three public available hyperspectral datasets and demonstrate that, overall, the classification accuracy of our method is 99.82 %, 99.81%, and 99.37, respectively, which is higher compared to the corresponding accuracy of current networks such as 3D convolutional neural network (CNN), three-dimensional residual convolution structure (RES-3D-CNN), and space–spectrum joint deep network (SSRN).

scholarly journals Generating Natural Counterfactual Visual Explanations

2020 ◽  
Author(s):  
Wenqi Zhao ◽  
Satoshi Oyama ◽  
Masahito Kurihara
Keyword(s):  
Image Classification ◽  
Classification Accuracy ◽  
Classification Task ◽  
Learning Models ◽  
Generative Adversarial Network ◽  
Fine Grained ◽  
Class A ◽  
Adversarial Network ◽  
Class B ◽  
Machine Learning Models

Counterfactual explanations help users to understand the behaviors of machine learning models by changing the inputs for the existing outputs. For an image classification task, an example counterfactual visual explanation explains: "for an example that belongs to class A, what changes do we need to make to the input so that the output is more inclined to class B." Our research considers changing the attribute description text of class A on the basis of the attributes of class B and generating counterfactual images on the basis of the modified text. We can use the prediction results of the model on counterfactual images to find the attributes that have the greatest effect when the model is predicting classes A and B. We applied our method to a fine-grained image classification dataset and used the generative adversarial network to generate natural counterfactual visual explanations. To evaluate these explanations, we used them to assist crowdsourcing workers in an image classification task. We found that, within a specific range, they improved classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document