22 February 2019 in Granular Computing
Handwritten digits recognition has been treated as a multi-class classification problem in the machine learning context, where each of the ten digits (0–9) is viewed as a class and the machine learning task is essentially to train a classifier that can effectively discriminate the ten classes. In practice, it is very usual that the performance of a single classifier trained using a standard learning algorithm is varied on different datasets, which indicates that the same learning algorithm may train strong classifiers on some datasets but weak classifiers may be trained on other datasets. It is also possible that the same classifier shows different performance on different test sets, especially when considering the case that image instances can be highly diverse due to the different handwriting styles of different people on the same digits. To address the above issue, development of ensemble learning approaches have been very necessary to improve the overall performance and make the performance more stable on different datasets. In this paper, we propose a framework that involves CNN-based feature extraction from the MINST dataset and algebraic fusion of multiple classifiers trained on different feature sets, which are prepared through feature selection applied to the original feature set extracted using CNN. The experimental results show that the classifiers fusion can achieve the classification accuracy of ≥ 98%.
31 July 2019 in The Visual Computer
13 June 2019 in IEEE Access
This paper presents a new image synthesis method for image style transfer. For some common methods, the textures and colors in the style image are sometimes applied inappropriately to the content image, which generates artifacts. In order to improve the results, we propose a novel method based on a new strategy that combines both local and global style losses. On the one hand, a style loss function based on a local approach is used to keep the style details. On the other hand, another style loss function based on global measures is used to capture the more global structural information. Results on various images show that the proposed method reduces artifacts while faithfully transferring the style image’s characteristics and preserving the structure and color of the content image.
29 March 2024 in IEEE Transactions on Intelligent Transportation Systems
To improve reconstruction performance in imagery compressive sensing, the present paper changes solving a block image compressive sensing reconstruction into a convex optimization problem. First, a Total-Variation norm minimization constraints model that includes both L1 and L2 norm functions is established. The split Bregman iterative method solves the model with convex optimization. Then, a robust adaptive image block compressive sensing algorithm is studied based on an analysis of the image features. The image is divided into blocks, and an overlap image block compressive reconstruction method is proposed. Finally, to solve the block effect caused by block compressive sensing reconstruction, a novel image overlap block compressive sensing reconstruction based on the Poisson function is suggested to avoid the block effect in the reconstruction process. The experimental results show that compared with other traditional compressive sensing reconstruction algorithms, the proposed method can generate a better image reconstruction result. According to the PSNR evaluation, when the sampling rate is 0.3, the proposed method is improved by more than 20.98% compared to the conventional techniques, and according to the SSIM evaluation, it has improved by more than 11.92% from the traditional methods. We can also find that the proposed method has better construction effect for traffic sign image recognition compared with ordinary natural image reconstruction. When the sampling rate is only 0.1, the PSNR value reaches 44.28dB, and the SSIM reconstruction accuracy reaches 98.14%. After reconstructing different types and characteristic images, it is supported that the proposed algorithm has good robustness and anti-noise performance.
17 February 2025 in IEEE Transactions on Multimedia
Image hazing refers to adding haze to a clear image, which is important for improving the data amount and diversity of synthetic hazy images that are required to train deep image dehazing models. However, existing image hazing works generate hazy images from a given clear image with a single transmission map. This violates the fact that hazy images are diverse for a natural scene at different times. The domain shift issue between synthetic and real-world hazy images constrains the robustness of deep dehazing models when dealing with real-world hazy images. In this work, we propose an unsupervised haze generation work to synthesize multiple hazy images with diverse haze distributions from a clear image, which requires only an atmospheric scattering model without extra labeling information. Instead of estimating a transmission map from a clear image, we propose to customize the transmission maps by redefining the transmission function. In such a controllable way, hazy images with diverse haze distributions are generated, which avoids the labor-intensive collection of paired data and alleviates the common domain-shift issue of deep image dehazing. Incorporating the unsupervised hazy images generator, we also construct a generalizable self-supervised image dehazing (SSID) framework, where deep image dehazing models can be trained without any human annotations. Extensive experiments on real-world hazy images show that the proposed approach is superior to state-of-the-art unsupervised dehazing works, and achieves competitive performance with the supervised works. Moreover, the proposed SSID framework can be easily generalized to the existing deep dehazing models, greatly improving dehazing robustness on real-world hazy images. The source code is released at https://github.com/CVhnu/SSID.
1 September 2013 in International Journal of Systems Science
In this article, by using the fractional order PIλ controller, we propose a simple and effective method to compute the robust stability region for the fractional order linear time-invariant plant with interval type uncertainties in both fractional orders and relevant coefficients. The presented method is based on decomposing the fractional order interval plant into several vertex plants using the lower and upper bounds of the fractional orders and relevant coefficients and then constructing the characteristic quasi-polynomial of each vertex plant, in which the value set of vertex characteristic quasi-polynomial in the complex plane is a polygon. The D-decomposition method is used to characterise the stability boundaries of each vertex characteristic quasi-polynomial in the space of controller parameters, which can obtain the stability region by varying λ orders in the range (0, 2). These regions of each vertex plant are computed by using three stability boundaries: real root boundary (RRB), complex root boundary (CRB) and infinite root boundary (IRB). The method gives the explicit formulae corresponding to these boundaries in terms of fractional order PIλ controller parameters. Thus, the robust stability region for fractional order interval plant can be obtained by intersecting stability region of each vertex plant. The robustness of stability region is tested by the value set approach and zero exclusion principle. Our presented technique does not require sweeping over the parameters and also does not need linear programming to solve a set of inequalities. It also offers several advantages over existing results obtained in this direction. The method in this article is useful for analysing and designing the fractional order PIλ controller for the fractional order interval plant. An example is given to illustrate this method.