Tao Huang

Tao Huang

Auto-generated profile, based on publicly available information

Tao Huang

School of Intelligent Manufacturing

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 September 2021 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
Bin ZhengBin Zheng
Bin Zheng
THTao Huang
Tao Huang
In order to achieve the accuracy of mango grading, a mango grading system was designed by using the deep learning method. The system mainly includes CCD camera image acquisition, image preprocessing, model training, and model evaluation. Aiming at the traditional deep learning, neural network training needs a large number of sample data sets; a convolutional neural network is proposed to realize the efficient grading of mangoes through the continuous adjustment and optimization of super-parameters and batch size. The ultra-lightweight SqueezeNet related algorithm is introduced. Compared with AlexNet and other related algorithms with the same accuracy level, it has the advantages of small model scale and fast operation speed. The experimental results show that the convolutional neural network model after super-parameters optimization and adjustment has excellent effect on deep learning image processing of small sample data set. Two hundred thirty-four Jinhuang mangoes of Panzhihua were picked in the natural environment and tested. The analysis results can meet the requirements of the agricultural industry standard of the People’s Republic of China—mango and mango grade specification. At the same time, the average accuracy rate was 97.37%, the average error rate was 2.63%, and the average loss value of the model was 0.44. The processing time of an original image with a resolution of 500 374 was only 2.57 milliseconds. This method has important theoretical and application value and can provide a powerful means for mango automatic grading.

1 October 2009
Verified
Conference Paper
Closed access
THTao Huang
Tao Huang
LQLele Qin
Lele Qin
In many application occasions, symmetry or antisymmetry of wavelet is fairly important to signal processing. In mid 1990s, Sweldens advanced the lifting wavelet transform. Compared with the first-generation wavelet, the lifting scheme could complete the wavelet transform currently without allocating additional memory, so it is easy to achieve with chips; the algorithm is simple and suitable for parallel processing, which makes the computation more fast; it could realize integral wavelet transform, which has wide potential applications. The paper analyzes the wavelet lifting algorithm and its poly-phase decomposition mechanism and approaches the image processing algorithm based on lifting wavelet transform. Since the structure of lifting wavelet is independent of Fourier transform, conducting image fusion by using the lifting wavelet could improve the processing speed and save memory.

1 January 2023 in Journal of Measurement Science and Instrumentation
Verified
Journal Article
Closed access
CBChenshuai Bai
Chenshuai Bai
WKWu Kaijun
Wu Kaijun
DWDicong Wang
Dicong Wang
HTHuang Tao
Huang Tao
TXTao Xiaomiao
Tao Xiaomiao