A New Bag of Words LBP (BoWL) Descriptor for Scene Image Classification

Banerji, Sugata; Sinha, Atreyee; Liu, Chengjun

doi:10.1007/978-3-642-40261-6_59

Cited by 22 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are lots of low-level features, e.g. HSV (Hue, Saturation, Value) (Wang, Li, Wang, Liu, & Li, 2013), GIST (Oliva & Torralba, 2001;Oliva & Torralba, 2006), SIFT (Scale-Invariant Feature Transform) (Lowe, 2004), HOG (Histogram of Oriented Gradient) (Navneet & Bill, 2005), SPM (Spatial Pyramid Matching) (Lazebnik, Schmid, & Ponce, 2006), BOW (Bag of Words) (Banerji, Sinha, & Liu, 2013) etc. HSV describes colours from the perspective of hue, saturation, and value in human visual system.…”

Section: Related Workmentioning

confidence: 99%

A scene recognition algorithm based on deep residual network

Mao

Wang

et al. 2019

Systems Science & Control Engineering

View full text Add to dashboard Cite

Scene recognition is quite important in the field of robotics and computer vision. Aiming at providing high performance and universality of feature extraction, a convolutional neural network-based scene recognition model entitled Scene-RecNet is proposed. To reduce parameter space and improve the feature quality, deep residual network is introduced as the feature extractor. A feature adjustment layer composed of a convolutional layer and a fully connected layer is added after the feature extractor to further synthesize and compress the extracted features. Migration learning-based 'pre-training and fine-tuning' mode is used to train Scene-RecNet. The feature extractor is pre-trained by Ima-geNet, and the overall network performance is fine-tuned on specific data sets. Experiments show that comparing with other algorithms, the features obtained by Scene-RecNet have high generality and robustness, and Scene-RecNet can provide better scene classification accuracy rate.

show abstract

Section: Related Workmentioning

confidence: 99%

A scene recognition algorithm based on deep residual network

Mao

Wang

et al. 2019

Systems Science & Control Engineering

View full text Add to dashboard Cite

show abstract

“…The process of extracting sift features points is slow, and the dimension of each features point is 128. Because the number of features points in each graph is different, the eigenvector dimension of each graph is inconsistent, so we first extract the sift features, combine it with the bag of words model (BOW) (Banerji, Sinha, & Liu, 2013) and the spatial pyramid matching (SPM) algorithm (Lazebnik, Schmid, & Ponce, 2006), or combine it with the fisher vector coding (FV) (Perronnin & Dance, 2007) to represent the eigenvector.…”

Section: Sift / Surf Features and Bow Fv Spmmentioning

confidence: 99%

“…It pioneers the use of Inception architecture, using 1 × 1 convolution kernel to reduce the dimension of the features image to deepen the network. Inception v1 has 22 convolution layers, not including the fully (Banerji et al, 2013) 1000 31.7 ScSPM(500)+PCA (Chatfield et al 2014) 1024 36.9 HOG+PCA (Zhang et al, 2016) 128 35.1 GIST 960 41.8…”

Section: Features Performance Simulationmentioning

confidence: 99%

An image authentication technology based on depth residual network

Mao

Zhong

et al. 2018

Systems Science & Control Engineering

View full text Add to dashboard Cite

The traditional image authentication technique generally determines the image attribution by extracting specific features and combining the similarity calculation algorithm. Because of the selected features dimensions, characterization and other factors, the accuracy and speed of image authentication have been restricted. In this paper, Recog-Net, an end-to-end image authentication model based on convolution neural network has been proposed. Deep residual network is chosen as the features extractor. Mahalanobis distance and threshold method are used to complete the image authentication. Experiments show that the performance of the extractor's features, compared with the traditional features and the features of other convolution neural network architectures, is more excellent, with a high degree of generality, recognition rate and robustness, still having these advantages even after a substantial compression. The Recog-Net for image authentication is able to accurately authenticate the images tampered with certain range.

show abstract

“…Furthermore, BOW is also widely used in target monitoring and [19] and feature descriptor [20]. In these methods, feature dictionaries play a very important role.…”

Section: Related Workmentioning

confidence: 99%

Low-Rank Optimization Dictionary Training for Image Classification

Liu

2018

MATEC Web Conf.

View full text Add to dashboard Cite

Abstract. Bag-of-words model has been extremely popular in image categorization. The method of constructing the dictionary is important. In this paper a category constrained low-rank optimization dictionary training approach is proposed for the dictionary construction. Through the low-rank optimization, the rank of the coefficient matrix constructed by same category images is minimized. Experimental results show that the proposed method can obtain better performance on two standard image databases (Caltech-101 and Caltech-256) than not employing the category constrained low-rank optimization.

show abstract

A New Bag of Words LBP (BoWL) Descriptor for Scene Image Classification

Cited by 22 publications

References 16 publications

A scene recognition algorithm based on deep residual network

A scene recognition algorithm based on deep residual network

An image authentication technology based on depth residual network

Low-Rank Optimization Dictionary Training for Image Classification

Contact Info

Product

Resources

About