Semi-Supervised Novelty Detection Using SVM Entire Solution Path

Morsier, Frank de; Tuia, Devis; Borgeaud, M.; Gass, Volker; Thiran, Jean-Philippe

doi:10.1109/tgrs.2012.2236683

Cited by 36 publications

(17 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In medical applications, ND has been used to detect any unusual record and raise a flag of potential health problems [38]. Remote sensing is another domain where ND can be employed, more specifically in change detections [40]. Usually, the change characteristics such as new buildings, new desertification areas, and forest fires are often unknown and only the characteristics of unchanged areas are available.…”

Section: Novelty Detectionmentioning

confidence: 99%

Feature-Ensemble-Based Novelty Detection for Analyzing Plant Hyperspectral Datasets

Grieve

AlSuwaidi

2018

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Abstract-Recently, there has been a significant increase in the use of proximal or remote hyperspectral imaging systems to study plant properties, types, and conditions. Numerous financial and environmental benefits of using such systems have been the driving force behind this growth. This paper is concerned with the analysis of hyperspectral data for detecting plant diseases and stress conditions and classifying crop types by means of advanced machine learning techniques. Main contribution of the work lies in the use of an innovative classification framework for the analysis, in which adaptive feature selection, novelty detection, and ensemble learning are integrated. Three hyperspectral datasets and a nonimaging hyperspectral dataset were used in the evaluation of the proposed framework. Experimental results show significant improvements achieved by the proposed method compared to the use of empirical spectral indices and existing classification methods.Index Terms-Ensemble learning, feature selection, hyperspectral imaging (HSI), novelty detection (ND), plant monitoring, remote sensing, support vector machine (SVM).

show abstract

Section: Novelty Detectionmentioning

confidence: 99%

Feature-Ensemble-Based Novelty Detection for Analyzing Plant Hyperspectral Datasets

Grieve

AlSuwaidi

2018

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Among the change feature learning methods, physically-meaningful features and learned change features both lead to a good performance and have been applied in various domains. As physically-meaningful features, vegetation indices, forest canopy variables and water indices are often extracted to identify changes in specific ground-object types [12,13]. For learned features and transformations, various features or transformed feature spaces are learned to highlight the change information to detect a changed region more easily than when using the original spectral information of multi-temporal images, such as in Principal Component Analysis (PCA) [14], Multivariate Alteration Detection (MAD) [15], subspace learning [16,17], sparse learning [18] and slow features [19].…”

Section: Introductionmentioning

confidence: 99%

Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection

2016

View full text Add to dashboard Cite

When exploited in remote sensing analysis, a reliable change rule with transfer ability can detect changes accurately and be applied widely. However, in practice, the complexity of land cover changes makes it difficult to use only one change rule or change feature learned from a given multi-temporal dataset to detect any other new target images without applying other learning processes. In this study, we consider the design of an efficient change rule having transferability to detect both binary and multi-class changes. The proposed method relies on an improved Long Short-Term Memory (LSTM) model to acquire and record the change information of long-term sequence remote sensing data. In particular, a core memory cell is utilized to learn the change rule from the information concerning binary changes or multi-class changes. Three gates are utilized to control the input, output and update of the LSTM model for optimization. In addition, the learned rule can be applied to detect changes and transfer the change rule from one learned image to another new target multi-temporal image. In this study, binary experiments, transfer experiments and multi-class change experiments are exploited to demonstrate the superiority of our method. Three contributions of this work can be summarized as follows: (1) the proposed method can learn an effective change rule to provide reliable change information for multi-temporal images; (2) the learned change rule has good transferability for detecting changes in new target images without any extra learning process, and the new target images should have a multi-spectral distribution similar to that of the training images; and (3) to the authors' best knowledge, this is the first time that deep learning in recurrent neural networks is exploited for change detection. In addition, under the framework of the proposed method, changes can be detected under both binary detection and multi-class change detection.

show abstract

“…The second forces the solution to be coherent via the solution path, hereby offer classification boundaries which are nested (included in each other). Authors also present a low density criterion for selecting the optimal classification boundaries, hereby avoiding the recourse to cross-validation that generally requires in-formation about the "change" class [6].…”

Section: Literature Surveymentioning

confidence: 99%

“…The size and efficiency of hyper plane decide the efficiency of detection. In detection process Linear discriminate analysis suffered two types of problem in region detection one is core point problem and another is outlier of feature point, in single class detection [6].A motion based descriptors are combined with histogram of oriented gradient appearance descriptors. The resulting descriptor is tested on several databases [4] In the process of video detection the lower content of visual feature such as color texture and dimensions.…”

Section: Introductionmentioning

confidence: 99%

Improving the Performance of Human Detection Technique using Cascaded Support Vector Machine

Tomar¹,

Vishwakarma²,

Pippal³

2015

IJCA

View full text Add to dashboard Cite

Human detection plays an important role in security surveillance and computer vision. The process of human detection is very complex due to variant feature of human such as color, texture and shape and size. The process of feature extraction imparts a major role in human detection technique. Now a days used classification technique to define the feature of human. The classification process define the pattern of feature for the process of detection, the process of features generates a bag of feature for the process of classification technique. In this paper improved the support vector machine classification technique for the classification of human detection. The improved support vector machine is called cascaded support vector machine. The cascading of support vector machine improved the process of human detection. Our proposed algorithm implemented in MATLAB 7.8.0 software and used human video of different location. Our empirical evaluation of experimental result shows that the proposed methods give a better result in compression of support vector machine classifier.

show abstract

Semi-Supervised Novelty Detection Using SVM Entire Solution Path

Cited by 36 publications

References 49 publications

Feature-Ensemble-Based Novelty Detection for Analyzing Plant Hyperspectral Datasets

Feature-Ensemble-Based Novelty Detection for Analyzing Plant Hyperspectral Datasets

Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection

Improving the Performance of Human Detection Technique using Cascaded Support Vector Machine

Contact Info

Product

Resources

About