Ms. Lanfang Dong Profile

Lanfang Dong

at Univ of Science and Technology of China

SPIE Involvement:

Author

Publications (5)

Proceedings Article | 11 October 2023 Paper

ATB-Net: attention-based network for facial expression recognition

Lanfang Dong, Yingchao Tang, Puzhao Hu, Meng Mao, Guoming Li, Linxiang Tan

Proceedings Volume 12918, 129181W (2023) https://doi.org/10.1117/12.3009441

KEYWORDS: Facial recognition systems, Convolution, Machine learning, Data modeling, Matrices, Emotion, Performance modeling, Education and training, Convolutional neural networks, Feature extraction

Read Abstract +

Proceedings Article | 11 October 2023 Paper

Robot intent recognition method based on state grid business office

Lanfang Dong, Yanyan Zhan, Yingchao Tang

Proceedings Volume 12918, 129181R (2023) https://doi.org/10.1117/12.3009440

KEYWORDS: Data modeling, Machine learning, Education and training, Performance modeling, Transformers, Industry, Semantics, Deep learning, Systems modeling, Human computer interaction

Read Abstract +

Proceedings Article | 9 October 2023 Paper

An effective and efficient real-time facial expression recognition method in the wild

Yuhang Zhang, Lanfang Dong, Xuesong Liu, Meng Mao, Guoming Li

Proceedings Volume 12791, 127911Q (2023) https://doi.org/10.1117/12.3004653

KEYWORDS: Robots, Neural networks, Facial recognition systems, Emotion, Education and training, Network architectures, Feature extraction, Convolutional neural networks, Data modeling, Convolution

Read Abstract +

Proceedings Article | 16 February 2022 Paper

Image recognition of sandstone slice based on a lightweight network

Hao Gui, Xiaolu Yu, Tao Ma, Lanfang Dong

Proceedings Volume 12083, 120832F (2022) https://doi.org/10.1117/12.2623242

KEYWORDS: Data modeling, Convolution, Image enhancement, Image processing, Statistical modeling, Particles, Convolutional neural networks, Performance modeling, Image resolution, Image fusion

Read Abstract +

Identifying the property of sandstone slice has important directive to exploration of oil and gas resources. The traditional sandstone slice identification method based on manual observation, which is time-consuming and laborintensive. In recent years, the Convolutional Neural Networks (CNNs) have achieved excellent results in the field of image recognition and a CNN-supported recognition algorithm has practical value in various application. However, there are multiple challenges for using the classic CNN for the sandstone slice image recognition: the industrialized recognition needs efficiency, which means the sandstone slice image recognition should be finished accurately and quickly; the sandstone image recognition requires expert annotations, resulting in lack of data; some mineral particles in sandstone are uncommon, which caused the sandstone image dataset has unbalanced data distribution problem. We invited several geologists to annotate sandstone slice image and start experiments. For sandstone slice image recognition, in order to ensure recognition speed and accuracy of sandstone slice, we built the Res2DwNet model. The model is optimized for the characteristics of the sandstone slice image. In this model, we proposed the Res2Dw module, which combines deep separable convolution, dense connection and residual learning ideas. Combining geology expertise, the sandstone slice image in our model is divided into two types of single-polarized and cross-polarized images for processing, which helps the recognition accuracy improves significantly. To solve the problem of small amount of data, a unique data enhancement method is designed on the basis of the experience of sandstone slice identification. To handle the uneven data distribution problem, the class-balanced softmax loss function is used during training. Compared with other classic Convolutional Neural Network models, the Res2DwNet model has a deeper network structure, which can achieve higher recognition accuracy than models of the same magnitude while maintaining lightweight parameters, and is suitable for sandstone slice image recognition tasks.

Proceedings Article | 16 February 2022 Paper

A weakly supervised object detection method based on attention mechanism

Hanchao Liu, Diancheng Zhou, Yang Zhao, Lanfang Dong

Proceedings Volume 12083, 120832K (2022) https://doi.org/10.1117/12.2623134

KEYWORDS: Data modeling, Edge detection, Machine learning, Target detection, Performance modeling, Visual process modeling, Process modeling, Detection and tracking algorithms, Neural networks, Machine vision

Read Abstract +

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years