Han Li

Bio: Han Li is an academic researcher from Xiamen University. The author has contributed to research in topics: Computer science & Artificial intelligence. The author has an hindex of 7, co-authored 7 publications receiving 145 citations.

A Small-Sized Object Detection Oriented Multi-Scale Feature Fusion Approach With Application to Defect Detection

Abstract: Object detection is a well-known task in the field of computer vision, especially the small target detection problem that has aroused great academic attention. In order to improve the detection performance of small objects, in this article, a novel enhanced multiscale feature fusion method is proposed, namely, the atrous spatial pyramid pooling-balanced-feature pyramid network (ABFPN). In particular, the atrous convolution operators with different dilation rates are employed to make full use of context information, where the skip connection is applied to achieve sufficient feature fusions. In addition, there is a balanced module to integrate and enhance features at different levels. The performance of the proposed ABFPN is evaluated on three public benchmark datasets, and experimental results demonstrate that it is a reliable and efficient feature fusion method. Furthermore, in order to validate the applicational potential in small objects, the developed ABFPN is utilized to detect surface tiny defects of the printed circuit board (PCB), which acts as the neck part of an improved PCB defect detection (IPDD) framework. While designing the IPDD, several powerful strategies are also employed to further improve the overall performance, which is evaluated via extensive ablation studies. Experiments on a public PCB defect detection database have demonstrated the superiority of the designed IPDD framework against the other seven state-of-the-art methods, which further validates the practicality of the proposed ABFPN.

A new deep belief network-based multi-task learning for diagnosis of Alzheimer’s disease

Abstract: Accurate classification of Alzheimer’s disease (AD) and mild cognitive impairment (MCI), especially distinguishing the progressive MCI (pMCI) from stable MCI (sMCI), will be helpful in both reducing the risk of converting into AD and also releasing the burden on the family and even the society. In this study, a novel deep belief network (DBN) based multi-task learning algorithm is developed for the classification issue. In particular, the dropout technology and zero-masking strategy are exploited for getting over the overfitting problem and also enhancing the generalization ability and robustness of the model. Then, a new framework based on the DBN-based multi-task learning is established for accurate diagnosis of AD. After MRI preprocessing, not only the principal component analysis is utilized to reduce the feature dimension, but also multi-task feature selection approach is introduced to select the feature set related to all tasks as a result of taking the internal relevancy among multiple related tasks into consideration. Using data from the ADNI dataset, our method achieves satisfactory results in six tasks of health control (HC) vs. AD, HC vs. pMCI, HC vs. sMCI, pMCI vs. AD, sMCI vs. AD and sMCI vs. pMCI with the accuracies are 98.62%, 96.67%, 92.31%, 91.89%, 99.62% and 87.78%, respectively. Experimental results demonstrate that the DBN-based MTL algorithm developed in this study is an effective, superior and practical method of AD diagnosis.

Cov-Net: A computer-aided diagnosis method for recognizing COVID-19 from chest X-ray images via machine vision

Abstract: In the context of global pandemic Coronavirus disease 2019 (COVID-19) that threatens life of all human beings, it is of vital importance to achieve early detection of COVID-19 among symptomatic patients. In this paper, a computer aided diagnosis (CAD) model Cov-Net is proposed for accurate recognition of COVID-19 from chest X-ray images via machine vision techniques, which mainly concentrates on powerful and robust feature learning ability. In particular, a modified residual network with asymmetric convolution and attention mechanism embedded is selected as the backbone of feature extractor, after which skip-connected dilated convolution with varying dilation rates is applied to achieve sufficient feature fusion among high-level semantic and low-level detailed information. Experimental results on two public COVID-19 radiography databases have demonstrated the practicality of proposed Cov-Net in accurate COVID-19 recognition with accuracy of 0.9966 and 0.9901, respectively. Furthermore, within same experimental conditions, proposed Cov-Net outperforms other six state-of-the-art computer vision algorithms, which validates the superiority and competitiveness of Cov-Net in building highly discriminative features from the perspective of methodology. Hence, it is deemed that proposed Cov-Net has a good generalization ability so that it can be applied to other CAD scenarios. Consequently, one can conclude that this work has both practical value in providing reliable reference to the radiologist and theoretical significance in developing methods to build robust features with strong presentation ability.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Elastic-net regularization in learning theory

Abstract: Within the framework of statistical learning theory we analyze in detail the so-called elastic-net regularization scheme proposed by Zou and Hastie [H. Zou, T. Hastie, Regularization and variable selection via the elastic net, J. R. Stat. Soc. Ser. B, 67(2) (2005) 301-320] for the selection of groups of correlated variables. To investigate the statistical properties of this scheme and in particular its consistency properties, we set up a suitable mathematical framework. Our setting is random-design regression where we allow the response variable to be vector-valued and we consider prediction functions which are linear combinations of elements (features) in an infinite-dimensional dictionary. Under the assumption that the regression function admits a sparse representation on the dictionary, we prove that there exists a particular ''elastic-net representation'' of the regression function such that, if the number of data increases, the elastic-net estimator is consistent not only for prediction but also for variable/feature selection. Our results include finite-sample bounds and an adaptive scheme to select the regularization parameter. Moreover, using convex analysis tools, we derive an iterative thresholding algorithm for computing the elastic-net solution which is different from the optimization procedure originally proposed in the above-cited work.

Rapid Detection of Rice Disease Based on FCM-KM and Faster R-CNN Fusion

Abstract: In this paper, a method for detecting rapid rice disease based on FCM-KM and Faster R-CNN fusion is proposed to address various problems with the rice disease images, such as noise, blurred image edge, large background interference and low detection accuracy. Firstly, the method uses a two-dimensional filtering mask combined with a weighted multilevel median filter (2DFM-AMMF) for noise reduction, and uses a faster two-dimensional Otsu threshold segmentation algorithm (Faster 2D-Otsu) to reduce the interference of complex background with the detection of target blade in the image. Then the dynamic population firefly algorithm based on the chaos theory as well as the maximum and minimum distance algorithm is applied for optimization of the K-Means clustering algorithm (FCM-KM) to determine the optimal clustering class k value while addressing the tendency of the algorithm to fall into the local optimum problem. Combined with the R-CNN algorithm for the identification of rice diseases, FCM-KM analysis is conducted to determine the different sizes of the Faster R-CNN target frame. As revealed by the application results of 3010 images, the accuracy and time required for detection of rice blast, bacterial blight and blight were 96.71%/0.65s, 97.53%/0.82s and 98.26%/0.53s, respectively, indicating clearly that the method is more capable of detecting rice diseases and improving the identification accuracy of Faster R-CNN algorithm, while reducing the time required for identification.