Nian Cai

Blind inpainting using the fully convolutional neural network

Most of existing inpainting techniques require to know beforehandwhere those damaged pixels are, i.e., non-blind inpainting methods. However, in many applications, such information may not be readily available. In this paper, we propose a novel blind inpainting method based on a fully convolutional neural network. We term this method as blind inpainting convolutional neural network (BICNN). It purely cascades three convolutional layers to directly learn an end-to-end mapping between a pre-acquired dataset of corrupted/ground truth subimage pairs. Stochastic gradient descent with standard backpropagation is used to train the BICNN. Once the BICNN is learned, it can automatically identify and remove the corrupting patterns from a corrupted image without knowing the specific regions. The learned BICNN takes a corrupted image of any size as input and directly produces a clean output by only one pass of forward propagation. Experimental results indicate that the proposed method can achieve a better inpainting performance than the existing inpainting methods for various corrupting patterns.

Difference angle quantization index modulation scheme for image watermarking

In this paper, we propose a new angle quantization index modulation (AQIM) method, called the difference AQIM (DAQIM) method. The proposed method aims to improve the watermarking performance against gain attacks. Unlike the original AQIM method (Ourique et al., Angle QIM: a novel watermark embedding scheme robust against amplitude scaling distortions, in: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, 2005, pp. 797-800), the DAQIM method quantizes the difference of the two angles instead of the angles themselves. The main advantage of the DAQIM method is to disperse the interference to the watermark signal from one angle to more angles. Thus, the watermark has a higher ability to resist attacks. We perform a theoretical analysis of the document-to-watermark ratio (DWR) based on our proposed method. We show that our proposed method can obtain a lower embedding distortion compared to the AQIM and the gradient direction watermarking (GDWM) (Nezhadarya et al., IEEE Trans. Inf. Forensics Secur., 6(4), 2011, 1200-1213), methods under the same robustness and payload conditions. The experimental results demonstrate that our proposed method outperforms common existing methods in terms of the robustness against various attacks such as the JPEG quantization noise, additive white Gaussian noise (AWGN), cropping effect and mean filtering. Difference angle quantization index modulation method is proposed for watermarking.Quantize the difference of the two angles instead of the angle themselves.The method is for against the gain attacks.The method is to disperse interference to watermark from one angle to more angles.

Image denoising via patch-based adaptive Gaussian mixture prior method

Although the expected patch log likelihood (EPLL) achieves good performance for denoising, an inherent nonadaptive problem exists. To solve this problem, an adaptive learning is introduced into the EPLL in this paper. Inspired from the structured sparse dictionary, an adaptive Gaussian mixture model (GMM) is proposed based on patch priors. The maximum a posteriori estimation is employed to cluster and update the image patches. Also, the new image patches are used to update the GMM. We perform these two steps alternately until the desired denoised results are achieved. Experimental results show that the proposed denoising method outperforms the existing image denoising algorithms.

A New IC Solder Joint Inspection Method for an Automatic Optical Inspection System Based on an Improved Visual Background Extraction Algorithm

In the field of automatic optical inspection (AOI), defect recognition for an integrated circuit (IC) solder joint is a long-standing task. Inspired by a visual background extraction (ViBe) algorithm, an object detection method in computer vision, we propose a new inspection method for IC solder joints with an improved ViBe algorithm. To the best of our knowledge, we are the first to consider the defect inspection problem as an object detection problem. We build a solder joint model using the ViBe model updating scheme. Then, we compare the solder joint image with the well-trained model to detect potential defects. Finally, we introduce a frequency map method and define a metric named defect degree to evaluate the qualities of the solder joints. Experimental results show that our method is universal, accurate, and easily debugged compared with the other existing methods.

Optimal discrete fractional fourier transform descriptors for image retrieval

This paper proposes to extend the conventional discrete Fourier transform (DFT) descriptor to discrete fractional Fourier transform (DFrFT) descriptors for representing edges in images. The DFrFT descriptors of training images are employed for constructing a dictionary. However, it is required to determine the optimal rotational angles. This problem is formulated as an optimization problem such that the Fisher discriminant is minimized. Nevertheless, this optimization problem is nonconvex. Also, both the intraclass and interclass separations of the DFrFT descriptors are independent of the rotational angles if these separations are defined using the 2-norm operator. To tackle these difficulties, the 1-norm operator is employed instead. However, this reformulated optimization problem is nonsmooth. To solve this problem, the nondifferentiable points of the objective function are found. Then, the stationary points between any two consecutive nondifferentiable points are identified. After that, the objective functional values are evaluated at these nondifferentiable points and stationary points. The smallest L objective functional values are picked up and the corresponding rotational angles are chosen for constructing the dictionary. Here, L is the total number of the rotational angles for constructing the dictionary. Finally, a 1-NN classification rule is applied for performing the image retrieval. Computer numerical simulation results show that our proposed method outperforms the conventional DFT descriptor approach.

Image denoising method based on a deep convolution neural network

Image denoising is still a challenging problem in image processing. The authors propose a novel image denoising method based on a deep convolution neural network (DCNN). Different from other learning-based methods, the authors design a DCNN to achieve the noise image. Thus, the latent clear image can be achieved by separating the noise image from the contaminated image. At the training stage, the gradient clipping scheme is employed to prevent gradient explosions and enables the network to converge quickly. Experimental results demonstrate that the proposed denoising method can achieve a better performance compared with the state-of-the-art denoising methods. Also, the results indicate that the denoising method has the ability of suppressing different noises with different noise levels by means of one single denoising model.

IC solder joint inspection based on the Gaussian mixture model

Purpose This paper aims to inspect solder joint defects of integrated circuit (IC) components on printed circuit boards. Here, an IC solder joint inspection algorithm is developed based on a Gaussian mixture model (GMM). Design/methodology/approach First, the authors train a GMM using numerous qualified IC solder joints. Then, the authors compare the IC solder joint images with the trained model to inspect the potential defects. Finally, the authors introduce a frequency map and define a metric termed as normalized defect degree to evaluate qualities of the tested IC solder joints. Findings Experimental results indicate that the proposed method is superior to the state-of-the-art methods on IC solder joint inspection. Originality/value The approach is a promising method for IC solder joint inspection, which is quite different from the traditional classifier-based methods.

Object Tracking Using Mean Shift for Adaptive Weighted-Sum Histograms

An object tracking method is proposed that uses mean shift for adaptive weighted-sum histograms and makes an attempt to incorporate contourlet histograms and spatial histograms. The tracking results of the contourlet-based method and the spatial-histogram-based method have been incorporated with adaptive weights. We employ the Bhattacharyya distance to evaluate the values of the weights. The experimental results indicate that the proposed method is robust for small targets, occlusion, rotation, scale transformation, or complex backgrounds, and is superior to three methods based on mean shift and a tracking method based on particle filters.

RETRACTED ARTICLE: Robust high dynamic range image watermarking using nonlinear hybrid spread spectrum approach

This paper has been withdrawn at the request of the Authors. They acknowledge that text from background sources was used without proper reference to the original source. This paper has been withdrawn at the request of the Authors. They acknowledge that text from background sources was used without proper reference to the original source.

Mixed

The sparsity adaptive matching pursuit (SAMP) algorithm has an advantage of reconstructing signals without the prior information of the sparsity level. However, the required computational power is high and the reconstruction performance is not satisfied for perturbed systems. This is because this algorithm is based on the expectation maximization algorithm. Also, a pseudo-inverse operation of the matrix is employed to select the element candidates of the sensing matrix in each iteration. In this paper, a mixed