Singular Value Decomposition based Features for Vehicle Classification under Cluttered Background and Mild Occlusion

Nagarajan, B.; Devendran, V.

doi:10.1016/j.proeng.2012.01.894

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The diagonal elements of matrix S are called the singular values of X which are used to create the feature vectors [ 16 ]. If the input image size is 256 × 256, the singular value size will be 1 × 256.…”

Section: Texture Featuresmentioning

confidence: 99%

Singular Value Decomposition Based Features for Automatic Tumor Detection in Wireless Capsule Endoscopy Images

Dinevari

Khosroshahi

Lighvan

2016

Applied Bionics and Biomechanics

View full text Add to dashboard Cite

Wireless capsule endoscopy (WCE) is a new noninvasive instrument which allows direct observation of the gastrointestinal tract to diagnose its relative diseases. Because of the large number of images obtained from the capsule endoscopy per patient, doctors need too much time to investigate all of them. So, it would be worthwhile to design a system for detecting diseases automatically. In this paper, a new method is presented for automatic detection of tumors in the WCE images. This method will utilize the advantages of the discrete wavelet transform (DWT) and singular value decomposition (SVD) algorithms to extract features from different color channels of the WCE images. Therefore, the extracted features are invariant to rotation and can describe multiresolution characteristics of the WCE images. In order to classify the WCE images, the support vector machine (SVM) method is applied to a data set which includes 400 normal and 400 tumor WCE images. The experimental results show proper performance of the proposed algorithm for detection and isolation of the tumor images which, in the best way, shows 94%, 93%, and 93.5% of sensitivity, specificity, and accuracy in the RGB color space, respectively.

show abstract

Section: Texture Featuresmentioning

confidence: 99%

Singular Value Decomposition Based Features for Automatic Tumor Detection in Wireless Capsule Endoscopy Images

Dinevari

Khosroshahi

Lighvan

2016

Applied Bionics and Biomechanics

View full text Add to dashboard Cite

show abstract

“…Vehicle identification and classification are necessary components in an artificially intelligent traffic monitoring system. Vehicle identification plays a major role in applications such as vehicle security system, traffic monitoring system, etc [1][2][3]. It is expected that these artificially intelligent traffic monitoring system venture onto the street of the world, thus requiring identification and classification of car objects commonly found on the road side.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Features based on Zernike Moments and Single Value Decomposition (SVD) for Vehicle Classification System

Jayadurga¹,

Gunasundari²

2016

IJERT

View full text Add to dashboard Cite

Vehicle identification and classification in a traffic environment containing mixed background is an important application of machine vision. The goal of this paper is to build a classifier for vehicle identification using hybrid features. The proposed work is to identify a "car" from a "non-car" amidst the mixed background taken from University of Illinois at Urbana-Champaign (UIUC) standard database. UIUC image database contains mixer of car and non-car image database. Every image is divided into equal sized small sub-block images. The Zernike features and Singular Value Decomposition (SVD) features are extracted from each sub-block of the image. The features of the vehicle objects are fed to the artificial neural classifier after normalization. The performance of the classifier is compared with various literature methods of similar work. Quantitative evaluation shows improved results of 95.6% compared with the literature papers. A critical evaluation of this approach under the proposed standards is presented.

show abstract

“…In the present study, singular value decomposition is utilized to convert the input image of size 200×200 pixels into a spatial domain feature vector composed of singular values of size 1×200. In it, the singular values are ranked in a descending order, whereas the first entries of the singular value matrix contain the most substantial information while the last entries at the vector contain the least significant information(Nagarajan and Devendran, 2012;Jha et al, 2014). With respect to the frequency domain features, DWT-based feature extraction exhibits three levels of decomposition, whereas N levels of decomposition result in (3 × N) + 1 sub-…”

mentioning

confidence: 99%

Entropy-Based Automated Method for Detection and Assessment of Spalling Severities in Reinforced Concrete Bridges

Abdelkader

Moselhi

Marzouk

et al. 2021

J. Perform. Constr. Facil.

View full text Add to dashboard Cite

Existing bridges are aging and deteriorating rapidly; elevating concerns for public safety and preservation of these valuable assets. Large numbers of bridges exist in transportation networks and the current budget limitations worsen the situation. This necessitates the development of automated condition assessment and rating methods. Spalling is a common problem that majorly influences the health, safety and structural integrity of bridges. The present study introduces a self-adaptive three-tier method for the automated detection and assessment of spalling using computer vision technologies. The first model introduces a newly-developed segmentation model that adopts multi-objective invasive weed optimization and information theory-based formalism of images for spalled concrete detection. In the second model, an integration of singular value decomposition and discrete wavelet transform are integrated for the efficient feature extraction of information in images. Additionally, Elman neural network is coupled with invasive weed optimization algorithm to enhance the accuracy of evaluation of spalling severities by amplifying exploration-exploitation trade-off mechanism of Elman neural network. The third model is developed for the purpose of structuring a rating system of spalling severity based on its area and depth. A computerized platform is developed using C#.net language to facilitate the implementation of the developed method by the users. Results demonstrated that the developed multi-objective spalling segmentation model is capable of improving detection accuracy of spalling by 12.29% with respect to the Region growing algorithm. It was inferred also the developed quantification model outperformed other prediction models such that it achieved mean absolute percentage error, root mean-squared error and root mean squared percentage error of 4.07%, 76.061 and 0.065, respectively based on the original dataset. In this regard, it is expected that the developed computer vision-based method can aid in establishing cost-effective bridge condition assessment models by transportation agencies.

show abstract

Singular Value Decomposition based Features for Vehicle Classification under Cluttered Background and Mild Occlusion

Cited by 3 publications

References 10 publications

Singular Value Decomposition Based Features for Automatic Tumor Detection in Wireless Capsule Endoscopy Images

Singular Value Decomposition Based Features for Automatic Tumor Detection in Wireless Capsule Endoscopy Images

Hybrid Features based on Zernike Moments and Single Value Decomposition (SVD) for Vehicle Classification System

Entropy-Based Automated Method for Detection and Assessment of Spalling Severities in Reinforced Concrete Bridges

Contact Info

Product

Resources

About