Bag-of-Visual-Words codebook generation using deep features for effective classification of imbalanced multi-class image datasets

Saini, Manisha; Susan, Seba

doi:10.1007/s11042-021-10612-w

Cited by 14 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Especially, there are many coding methods proposed in the era of BoVW model [5], e.g., hard voting, soft voting, sparse coding, LLC, local coordinate coding, super vector coding, fisher coding, grouping saliency coding, etc. Given the high similarity between BoVW model and BoDVW model in terms of workflow, some of them have been applied in the existing BoDVW methods such as hard voting [12] [13], sparse coding [4], and LLC [10].…”

Section: Related Workmentioning

confidence: 99%

“…In [11], the author adopted the layer "conv5" of AlexNet, the layer "inception 4(e)" of GoogleNet, and the layer "conv5-3" of VGGNet-16 to extract features, leading to 169 256dimensional features, 196 832-dimensional features, and 196 512-dimensional features for each image, respectively. In [12], the last convolutional layer of ResNet-50 is used to generate 49 2048-dimensional features for each image.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Improving Bag-of-Deep-Visual-Words Model via Combining Deep Features With Feature Difference Vectors

Wang

2022

IEEE Access

View full text Add to dashboard Cite

Bag-of-Deep-Visual-Words (BoDVW) model has shown its advantage to Convolutional Neural Network (CNN) model in image classification tasks with a small number of training samples. An essential step in BoDVW model is to extract deep features by using an off-the-shelf CNN model as a feature extractor. Two deep feature extraction methods have been raised in recent years. The first method densely samples multi-scale image patches and then converts them into deep features via a deep-level fullyconnected layer.The second method uses the output of a deep-level convolutional layer or pooling layer as the source of deep features. By contrast, the second method is much more efficient. However, it performs worse than the first method in classification accuracy. The reason is that deep features extracted by the second method are yielded in receptive fields of a single size. To make BoDVW model have high feature extraction efficiency and high classification accuracy, we propose enhancing deep features extracted by the second method at low added computation costs by supplementing the information obtained from receptive fields of different sizes. Concretely, we raise a novel feature named "feature difference (FD) vector" in this article. It can roughly preserve the information of multiple deep features extracted by the convolutional layers of different receptive field sizes. Each deep feature is enhanced by combining an FD vector to form a combined feature. The image representation vector of an image is generated using the combined features extracted from it. Our experimental results on three public datasets (15-Scenes, TF-Flowers, and NWPU-RESISC45) show that our method can avoid the high computation costs of the first method and achieve comparable results to the first method, which exhibits the effectiveness of our method.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Improving Bag-of-Deep-Visual-Words Model via Combining Deep Features With Feature Difference Vectors

Wang

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Their approach enhanced the accuracy by approximately 15% and 3% compared to [ 29 , 30 ] respectively, which were sophisticatedly designed convolutional neural networks (CNNs) introduced in 2020. Saini et al [ 12 ] utilized the BoDVW model to address the imbalance issue encountered when processing multi-class image datasets. In the realm of remote sensing classification tasks, the BoDVW model’s classification accuracy surpasses CNN-based methods by about 6% [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

Can using a pre-trained deep learning model as the feature extractor in the bag-of-deep-visual-words model always improve image classification accuracy?

Xu,

Zhang,

Huang

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

This article investigates whether higher classification accuracy can always be achieved by utilizing a pre-trained deep learning model as the feature extractor in the Bag-of-Deep-Visual-Words (BoDVW) classification model, as opposed to directly using the new classification layer of the pre-trained model for classification. Considering the multiple factors related to the feature extractor -such as model architecture, fine-tuning strategy, number of training samples, feature extraction method, and feature encoding method—we investigate these factors through experiments and then provide detailed answers to the question. In our experiments, we use five feature encoding methods: hard-voting, soft-voting, locally constrained linear coding, super vector coding, and fisher vector (FV). We also employ two popular feature extraction methods: one (denoted as Ext-DFs(CP)) uses a convolutional or non-global pooling layer, and another (denoted as Ext-DFs(FC)) uses a fully-connected or global pooling layer. Three pre-trained models—VGGNet-16, ResNext-50(32×4d), and Swin-B—are utilized as feature extractors. Experimental results on six datasets (15-Scenes, TF-Flowers, MIT Indoor-67, COVID-19 CXR, NWPU-RESISC45, and Caltech-101) reveal that compared to using the pre-trained model with only the new classification layer re-trained for classification, employing it as the feature extractor in the BoDVW model improves the accuracy in 35 out of 36 experiments when using FV. With Ext-DFs(CP), the accuracy increases by 0.13% to 8.43% (averaged at 3.11%), and with Ext-DFs(FC), it increases by 1.06% to 14.63% (averaged at 5.66%). Furthermore, when all layers of the pre-trained model are fine-tuned and used as the feature extractor, the results vary depending on the methods used. If FV and Ext-DFs(FC) are used, the accuracy increases by 0.21% to 5.65% (averaged at 1.58%) in 14 out of 18 experiments. Our results suggest that while using a pre-trained deep learning model as the feature extractor does not always improve classification accuracy, it holds great potential as an accuracy improvement technique.

show abstract

“…Over the past few years, detecting focal zones in images has generated sustained interest among the engineering design and computer vision community. Many vision-based methods have been proposed using features [40], models [41][42][43][44], and general image processing framework. The applied experimental approaches in engineering areas still remains a specialized task due to the certain specifics of each task.…”

Section: Introductionmentioning

confidence: 99%

New indicators and standards for measuring of the end mill's helical groove by image processing

Pivkin,

Ershov,

Grechishnikov

et al. 2023

Optical Metrology and Inspection for Industrial Applications X

View full text Add to dashboard Cite

The studies will be carried out using optical metrology methods on a Walter Helicheck inspection machine in reflected light and a number of images were stored to form a statistical sample. Established new indicators and criteria for grinding efficiency based on image processing of the helical groove of the end mill. As a result, recommendations for the selection of optical control techniques were made for the first time at the intermediate stage of technological preparation for production, in real time, and after processing. In this work, for the first time, we prove the possibility of determining the camera displacement pith distance during continuous scanning of the profile of a helical surface in a radial section, the measurement accuracy and recreating a three-dimensional model of the object. As a result of the work of the new algorithm using the Haar-wavelet with new indicators, it was established that the actual one is located inside the focal zone, which proves the possibility of applied application of the method of monitoring the shape of helical flute of end mills using computer vision. The measurement accuracy of the helical flute increased from 4 to 12% along its profile.

show abstract

Bag-of-Visual-Words codebook generation using deep features for effective classification of imbalanced multi-class image datasets

Cited by 14 publications

References 34 publications

Improving Bag-of-Deep-Visual-Words Model via Combining Deep Features With Feature Difference Vectors

Improving Bag-of-Deep-Visual-Words Model via Combining Deep Features With Feature Difference Vectors

Can using a pre-trained deep learning model as the feature extractor in the bag-of-deep-visual-words model always improve image classification accuracy?

New indicators and standards for measuring of the end mill's helical groove by image processing

Contact Info

Product

Resources

About