Bark texture classification using improved local ternary patterns and multilayer neural network

Fekri-Ershad, Shervan

doi:10.1016/j.eswa.2020.113509

Cited by 65 publications

(37 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…I think the discriminative power would be further enhanced if we consider an additional constraint on the intra-class compactness alone. So in the future research, we plan to explore new types of loss functions to improve the performance of deep embedding learning, and validate the methods on other related vision tasks, such as face recognition [8], texture classification [45], and so on.…”

Section: Discussionmentioning

confidence: 99%

A Novel Soft Margin Loss Function for Deep Discriminative Embedding Learning

Zhao

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Deep embedding learning aims to learn discriminative feature representations through a deep convolutional neural network model. Commonly, such a model contains a network architecture and a loss function. The architecture is responsible for hierarchical feature extraction, while the loss function supervises the training procedure with the purpose of maximizing inter-class separability and intra-class compactness. By considering that loss function is crucial for the feature performance, in this paper we propose a new loss function called soft margin loss (SML) based on a classification framework for deep embedding learning. Specifically, we first normalize the learned features and the classification weights to map them into the hypersphere. After that, we construct our loss with the difference between the maximum intra-class distance and minimum inter-class distance. By constraining the distance difference with a soft margin that is inherent in the proposed loss, both the inter-class discrepancy and intra-class compactness of learned features can be effectively improved. Finally, under the joint training with an improved softmax loss, the model can learn features with strong discriminability. Toy experiments on MNIST dataset are conducted to show the effectiveness of the proposed method. Additionally, experiments on re-identification tasks are also provided to demonstrate the superior performance of embedding learning. Specifically, 65.48% / 62.68% mAP on CUHK03 labeled / detected dataset (person re-id) and 74.36% mAP on VeRi-776 dataset (vehicle re-id) are achieved respectively. INDEX TERMS Soft margin loss, deep embedding learning, feature representation, person re-identification, vehicle re-identification. JIEHAO LIU received a Bachelor's degree in Electronics and Information Engineering from Guangzhou University in 2019. He is currently a master degree candidate in the School of Electronics and Communication Engineering, Guangzhou University. His research interests include face recognition and person reidentification. LI WANG received a Bachelor's degree in Electronic Engineering from Southeast University, China, in 2009 and received a Ph. D. degree in Physical Electronics from Southeast University, China, in 2015. He is now working in the School of Electronics and Communication Engineering, Guangzhou University. His research interests include brain-computer interfaces, biomedical signal processing, pattern recognition, etc. SAI ZHAO received the Ph. D degree in communication and information system from Sun Yat-Sen University (SYSU), Guangzhou, China, in 2015, and the Master and Bachelor degrees in Communication Engineering from Central South University, Changsha, China, in 2006 and 2003, respectively. She is currently a lecture in the School of Electronics and Communication Engineering, Guangzhou University. Her current research interests include machine learning in wireless communication, convex optimization, physical layer security and non-orthogonal multiple access.

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Soft Margin Loss Function for Deep Discriminative Embedding Learning

Zhao

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the end, the two upper and lower local binary patterns histograms are generated individually and connected together to produce a single histogram. LTP provide more discriminative features than LBP and some other version of LBP-based on reported results in recent papers [14][15][16].…”

Section: Iiii Local Ternary Patternsmentioning

confidence: 96%

Image classification using concatenated of co-occurrence matrix features and local ternary patterns

Kiani

2021

Preprint

View full text Add to dashboard Cite

Texture, color, and shape are the three main components that the human visual brain uses to identify or identify environments and objects. Therefore, tissue classification has been considered by many scientific researchers in the last decade. The texture features can be used in many different vision and machine learning problems. As of now, various methods have been proposed for classifying tissues. In all methods, the accuracy of the classification is a major challenge that needs to be improved. This article presents a new method based on a combination of two efficient tissue descriptors, the co-occurrence matrix and local ternary patterns (LTP). First, the local binary pattern and LTP are performed to extract information from the local tissue. In the next step, a subset of statistical properties is extracted from the gray surface concurrency matrices. Finally, the interconnected features are used to teach classification. Performance is evaluated for accuracy on the Brodatz reference data set. The experimental results show that the proposed method offers a higher degree of classification compared to some advanced methods.

show abstract

“…Bilinear interpolation can obtain the coordinates of adjacent pixels that do not completely fall at the center of adjacent pixels. Next, the difference between the center and its neighborhood is used to extract the LBP value of each neighborhood [31]. The histogram of each field was calculated, and then the histogram was normalized.…”

Section: Figure 8 Superpixel Generation and Feature Extractionmentioning

confidence: 99%

Superpixel Image Segmentation-Based Particle Size Distribution Analysis of Fragmented Rock

et al. 2021

View full text Add to dashboard Cite

Research on the particle size of blast piles has always been an essential issue in mining engineering. Reasonable blasting parameters can reduce mining costs and reduce the workload of secondary crushing, which can significantly improve mining efficiency. The usual particle size analysis methods include the sieving method, the large particle size statistical method and other manual measurement methods. Nevertheless, these methods have the disadvantages of a high labor intensity, low efficiency and low precision. This paper analyzes UAV image information based on the single-picture photogrammetry method of computer image processing technology. A two-dimensional empirical wavelet transform (EWT) is used for image noise reduction. The nonlocal multiscale fractional differential (NMFD) enhances the texture of dark images and uses superpixel image segmentation technology so that the processed image can meet the granularity statistical study requirements of blast piles. The research results show that the accuracy of the ore particle size distribution by the method proposed in this paper is more than 90%.

show abstract

Bark texture classification using improved local ternary patterns and multilayer neural network

Cited by 65 publications

References 21 publications

A Novel Soft Margin Loss Function for Deep Discriminative Embedding Learning

A Novel Soft Margin Loss Function for Deep Discriminative Embedding Learning

Image classification using concatenated of co-occurrence matrix features and local ternary patterns

Superpixel Image Segmentation-Based Particle Size Distribution Analysis of Fragmented Rock

Contact Info

Product

Resources

About