4.7 Article

Multi-Scale Boosting Feature Encoding Network for Texture Recognition

Journal

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3051003

Keywords

Feature extraction; Encoding; Interference; Image coding; Boosting; Image recognition; Task analysis; Texture recognition; feature encoding; boosting; multi-scale; convolutional neural network

Funding

  1. National Natural Science Foundation of China [51875228]
  2. National Key Research and Development Program of China [2020YFA0405700]
  3. National Defense Science and Technology Innovation Special Zone Project [193-A14-202-01-23]
  4. Program for Guangdong Introducing Innovative and Enterpreneurial Teams [2017ZT07G331]

Ask authors/readers for more resources

The study proposes a novel multi-scale boosting feature encoding network (MSBFEN) for accurate texture recognition by extracting multi-scale features using texture priors and then encoding them, along with a multi-scale boosting learning (MSBL) method to enhance recognition accuracy. Results show state-of-the-art performance on challenging texture recognition datasets.
Texture recognition remains a challenging visual task due to the complex appearance variations caused by scale changes in the real world. In most existing texture recognition methods, textures are represented at a single scale; thus, multi-scale texture information is not fully utilized, resulting in insufficient representation and inaccurate recognition. In this study, with the goal of addressing the challenge of scale changes, we propose a novel multi-scale boosting feature encoding network (MSBFEN) for accurate texture recognition. MSBFEN first extracts multi-scale features with multi-scale texture structure information under the guidance of texture priors using a novel prior-guided feature extraction (PFE) method. Then, a multi-scale texture encoding (MSTE) method is devised to capture discriminative multi-scale texture representations by encoding the extracted features. Finally, to fully utilize the multi-scale texture representations for accurate texture recognition, a novel multi-scale boosting learning (MSBL) method is proposed. In MSBL, the learning procedure for multi-scale texture recognition is boosted in a hierarchical, progressively reinforced manner, significantly addressing the challenge of scale changes and greatly enhancing the recognition accuracy. In addition, a novel outlier-aware texture encoding (OTE) method is proposed for robust texture encoding at each scale of MSTE. OTE can resist the influence of background interference and can further enhance the robustness of MSBFEN. In extensive experiments conducted on six challenging texture recognition datasets, namely, KTH-TIPS2b, FMD, DTD, MINC, GTOS and GTOS-mobile, MSBFEN achieves accuracies of 86.2%, 86.4%, 77.8%, 85.3%, 86.4% and 87.57%, respectively, representing state-of-the-art texture recognition performance.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available