- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium - Yokohama, Japan (2019.7.28-2019.8.2)] IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium - Extraction of a Specific Land-Cover Class from Very High Spatial Resolution Imagery Using Positive and Unlabeled Learning with Convolutional Neural Networks
摘要： In remote sensing, supervised multiclass classifiers show a very promising performance in terms of classification accuracy. However, they require that all classes, in the study area, are labeled. In many applications, users may only be interested in specific land classes. When considering only one class, this referred to as One-Class classification (OC) problem. In this paper, we investigated the possibility of using Convolutional Neural Networks (CNN) within the Positive and Unlabeled Learning (PUL) framework for estimating the urban tree canopy coverage from very high spatial resolution aerial imagery. We also compared the proposed approach to the Binary CNN classification and to ensemble classifications based on various color-texture based features. The obtained classification accuracies show that PUL strategies provide competitive extraction results, especially the proposed CNN based one, due to the fact that PUL is a positive-unlabeled method in which large amounts of available unlabeled samples is incorporated into the training phase, allowing the classifier to model effectively the tree class.
关键词： convolutional neural networks,texture analysis,One-class classification,positive and unlabeled learning,ensemble classification
更新于2025-09-16 10:30:52
-
The automated detection of proliferative diabetic retinopathy using dual ensemble classification
摘要： Objective: Diabetic retinopathy (DR) is a retinal vascular disease that is caused by complications of diabetes. Proliferative diabetic retinopathy (PDR) is the advanced stage of the disease which carries a high risk of severe visual impairment. This stage is characterized by the growth of abnormal new vessels. We aim to develop a method for the automated detection of new vessels from retinal images. Methods: This method is based on a dual classification approach. Two vessel segmentation approaches are applied to create two separate binary vessel maps which each hold vital information. Local morphology, gradient and intensity features are measured using each binary vessel map to produce two separate 21-D feature vectors. Independent classification is performed for each feature vector using an ensemble system of bagged decision trees. These two independent outcomes are then combined to a produce a final decision. Results: Sensitivity and specificity results using a dataset of 60 images are 1.0000 and 0.9500 on a per image basis. Conclusions: The described automated system is capable of detecting the presence of new vessels.
关键词： Retinal images,Ensemble classification,Dual classification,New vessels,Proliferative diabetic retinopathy
更新于2025-09-04 15:30:14