Using Bag of Visual Words and Spatial Pyramid Matching for Object Classification Along with Applications for RIS

Vyas, Kushal; Vora, Yash; Vastani, Raj

doi:10.1016/j.procs.2016.06.102

Cited by 12 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Advantages of Bag of Words include its ease of use and low computational cost. The main steps required to implement Bag of Words for image classification include (Anwar et al, 2013;MathWorks , 2019;Vyas et al, 2016): extracting features from a set of training images; establishing a visual vocabulary, or Bag of Words, with a quantisation scheme; training a multi-class classifier with visual vocabularies as feature vectors; evaluating the quality of the classifier by testing the classifier with a test set of images; and applying the trained classifier to predict labels in images.…”

Section: Image-based Methods and Automatic Recognitionmentioning

confidence: 99%

“…Bag of Words method was selected to conduct image classification because of its simplicity, maturity and practical performance (Nowak et al, 2006) in various applications. In addition, classifying different objects is one of the main objectives of this system, and recent studies have proven that Bag of Words is an effective and robust approach to object classification (Ali et al, 2016;Hannat et al, 2016;Vyas et al, 2016;Ergene and Durdu, 2017;Nguyen-Hoang et al, 2017;Unlu et al, 2017).…”

Section: Image Classification With Bag Of Wordsmentioning

confidence: 99%

See 1 more Smart Citation

Improvement of the inspection-repair process with building information modelling and image classification

Zhan

Huang

et al. 2019

View full text Add to dashboard Cite

Purpose-Automated technologies have been applied to facility management (FM) practices to address labour demands of, and time consumed by, inputting and processing manual data. Less attention has been focused on automation of visual information, such as images, when improving timely maintenance decisions. This study aimed to develop image classification algorithms to improve information flow in the inspection-repair process through building information modelling (BIM). Design/methodology/approach-To improve and automate the inspection-repair process, image classification algorithms were employed to connect images with a corresponding image database in a BIM knowledge repository. QR code decoding and Bag of Words were chosen to classify images in the system. Graphical user interfaces (GUIs) were developed to facilitate activity collaboration and communication. A pilot case study in an inspection-repair process was applied to demonstrate the applications of this system. Findings-The system developed in this study associates the inspection-repair process with a digital three dimensional (3D) model, GUIs, a BIM knowledge repository and image classification algorithms. By implementing the proposed application in a case study, the authors found that improvement of the inspection-repair process and automated image classification with a BIM knowledge repository (such as the one developed in this study) can enhance FM practices by increasing productivity and reducing time and costs associated with decision-making. Originality/value-This study introduces an innovative approach that applies image classification and leverages a BIM knowledge repository to enhance the inspection-repair process in facility management practice. The system designed provides automated image-classifying data from a smart phone, eliminates time required to input image data manually, and improves communication and collaboration between FM personnel for maintenance in the decision-making process.

show abstract

Section: Image-based Methods and Automatic Recognitionmentioning

confidence: 99%

Section: Image Classification With Bag Of Wordsmentioning

confidence: 99%

Improvement of the inspection-repair process with building information modelling and image classification

Zhan

Huang

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Influential posts seem to contain objects and entities that attract the attention of other users, so we aim to find influential posts by employing local features to detect significant objects in an image. The best local feature extraction methods in image classification systems are bag-of-features (BOW) [29], [30] and spatial pyramid matching (SPM) [30]. The BOW method represents an image as a histogram of its local features.…”

Section: Local Featuresmentioning

confidence: 99%

Identifying Influential Users on Instagram Through Visual Content Analysis

2020

View full text Add to dashboard Cite

In recent years, social networks have attracted many users' interests. People express their daily experiences and emotions through social networks and become aware of others interests and thoughts. In these networks, influential users play an important role in broadcasting information to their communities. As a result, discovering such users in social networks has become very important, in particular, for marketing purposes. Various solutions already exist for identifying influential users, most of which are structure-based, in that they investigate the influence of a user according to his location in the network graph. This paper proposes a novel approach for identifying influential users on Instagram, by examining User Generated Contents (UGC). More specifically, the proposed method combines various types of features extracted from the images posted on Instagram to determine whether or not a user is influential, without requiring any information about the structure of the network. An extensive set of experiments are performed to validate the effectiveness of the proposed method in identifying influential users.

show abstract

“…Other improvements for the refinement of the code book [13] resulting 32% faster than the traditional method, the use of another algorithm of grouping k-means GMM has seemed [14] obtaining less memory use. The Early fusion model [15] introducing the color descriptor together with the shape descriptor, another method that is related to the SPM spatial image [16], finally, one of the methods in which the use of the CNN convolutional neural networks for image recognition [17], is Soft Assignment / Hard Assignment [18] focusing on the representation of the image.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Classification in Bag of Visual Words Model

Zurita¹,

Luna²,

Hernández³

et al. 2018

CCS Archive

View full text Add to dashboard Cite

Classification of images by means of the BOVW method is well known and applied in different recognition projects, this method rely on three phases: detection and extraction of characteristics, representation of the image and finally the classification. SIFT, Kmeans and SVM is the most accepted combination. This article aims to demonstrate that this combination is not always the best choice for all types of datasets, different training sets of images were created from scratch and will be used for the bag of visual words model: the first phase of detection and extraction, SIFT will be used, later in the second phase a dictionary of words will be created through a clustering process using K-means, EM, K-means in combination with EM, finally, for classification it will be compared the algorithms of SVM, Gaussian NB, KNN, Decision Tree, Random Forest, Neural Network and AdaBoost in order to determine the performance and accuracy of every method.

show abstract

Using Bag of Visual Words and Spatial Pyramid Matching for Object Classification Along with Applications for RIS

Cited by 12 publications

References 8 publications

Improvement of the inspection-repair process with building information modelling and image classification

Improvement of the inspection-repair process with building information modelling and image classification

Identifying Influential Users on Instagram Through Visual Content Analysis

Hybrid Classification in Bag of Visual Words Model

Contact Info

Product

Resources

About