Deep convolution neural networks have proven their powerful ability in comparing many tasks of computer vision due to their strong data learning capacity. In this paper, we propose a novel end-to-end denoising network, termed Fourier embedded U-shaped network (FEUSNet). By analyzing the amplitude spectrum and phase spectrum of Fourier coefficients, we find that low-frequency features of an image are in the former while noise features are in the latter. To make full use of this characteristic, Fourier features are learned and are concatenated as a prior module that is embedded into a U-shaped network to reduce noise while preserving multi-scale fine details. In the experiments, we first present ablation studies on the Fourier coefficients’ learning networks and loss function. Then, we compare the proposed FEUSNet with the state-of-the-art denoising methods in quantization and qualification. The experimental results show that our FEUSNet performs well in noise suppression and preserves multi-scale enjoyable structures, even outperforming advanced denoising approaches.

Mixed (random and stripe) noise will cause serious degradation of optical remotely sensed image quality, making it hard to analyze their contents. In order to remove such noise, various inverse problems are usually constructed with different priors, which can be solved by either model-based optimization methods or discriminative learning methods. However, they have their own drawbacks, such as the former methods are flexible but are time-consuming for the pursuit of good performance; while the later methods are fast but are limited for extensive applications due to their specialized tasks. To fast obtain pleasing results with combination of their merits, in this paper, we propose a novel denoising strategy, namely, Dual Denoiser Driven Convolutional Neural Networks (D³CNNs), to remove both random and stripe noise. The D³CNNs includes the following two key parts: one is that two auxiliary variables respective for the denoised image and the stripe noise are introduced to reformulate the inverse problem as a constrained optimization problem, which can be iteratively solved by employing the alternating direction method of multipliers (ADMM). The other is that the U-shape network is used for the denoised auxiliary variable while the residual CNN (RCNN) for the stripe auxiliary variable. The subjectively and objectively comparable results of experiments on both synthetic and real-world remotely sensed images verify that the proposed method is effective and is even better than the state-of-the-arts.

Print matter authentication based on anti-counterfeiting techniques has received continuously increasing concern from academia and industry. However, the existing printing anti-counterfeiting solutions often have the defects of poor identification experience, high cost, or weak anti-counterfeiting ability, and cannot achieve pre-sale anti-counterfeiting. Therefore, a novel steganography-based pattern for print matter anti-counterfeiting by smartphone cameras is proposed in this study. Firstly, every pixel in the original binary message image (such as QR code) is replaced by a square pixel block with the same binary gray value of 0 or 255 (the first-level expansion). Secondly, the obtained image is encrypted based on the logistic chaotic sequence, and then scrambled by Arnold transform. Lastly, once again every pixel in the generated image is replaced with a square pixel block (the second-level expansion), the size and gray value of which can be set to control the semi-fragile ability to distinguish an originally printed pattern from its illegitimate copy. If the message extracted from the printed pattern through the inverse procedure is complete enough to decode and read, the pattern is assumed to be an original print. Experimental results verify the advancement and effectiveness of the proposed scheme in distinguishing the copied pattern.

At present, anti-counterfeiting schemes based on the combination of anti-counterfeiting patterns and two-dimensional codes is a research hotspot in digital anti-counterfeiting technology. However, many existing identification schemes rely on special equipment such as scanners and microscopes; there are few methods for authentication that use smartphones. In particular, the ability to classify blurry pattern images is weak, leading to a low recognition rate when using mobile terminals. In addition, the existing methods need a sufficient number of counterfeit patterns for model training, which is difficult to acquire in practical scenarios. Therefore, an authentication scheme for an anti-counterfeiting pattern captured by smartphones is proposed in this paper, featuring a single classifier consisting of two modules. A feature extraction module based on U-Net extracts the features of the input images; then, the extracted feature is input to a one-class classification module. The second stage features a boundary-optimized OCSVM classification method. The classifier only needs to learn positive samples to achieve effective identification. The experimental results show that the proposed approach has a better ability to distinguish the genuine and counterfeit anti-counterfeiting pattern images. The precision and recall rate of the approach reach 100%, and the recognition rate for the blurry images of the genuine anti-counterfeiting patterns is significantly improved.

In this article, we propose an effective grasp detection network based on an improved deformable convolution and spatial feature center mechanism (DCSFC-Grasp) to precisely grasp unidentified objects. DCSFC-Grasp includes three key procedures as follows. First, improved deformable convolution is introduced to adaptively adjust receptive fields for multiscale feature information extraction. Then, an efficient spatial feature center (SFC) layer is explored to capture the global remote dependencies through a lightweight multilayer perceptron (MLP) architecture. Furthermore, a learnable feature center (LFC) mechanism is reported to gather local regional features and preserve the local corner region. Finally, a lightweight CARAFE operator is developed to upsample the features. Experimental results show that DCSFC-Grasp achieves a high accuracy (99.3% and 96.1% for the Cornell and Jacquard grasp datasets, respectively) and even outperforms the existing state-of-the-art grasp detection models. The results of real-world experiments on the six-DoF Realman RM65 robotic arm further demonstrate that our DCSFC-Grasp is effective and robust for the grasping of unknown targets.

Facial expression plays an important role in human–computer interaction and affective computing. However, existing expression recognition methods cannot effectively capture multi-scale structural details contained in facial expressions, leading to a decline in recognition accuracy. Inspired by the multi-scale processing mechanism of the biological visual system, this paper proposes a wavelet-guided global–local feature aggregation network (WGGLFA) for facial expression recognition (FER). Our WGGLFA network consists of three main modules: the scale-aware expansion (SAE) module, which combines dilated convolution and wavelet transform to capture multi-scale contextual features; the structured local feature aggregation (SLFA) module based on facial keypoints to extract structured local features; and the expression-guided region refinement (ExGR) module, which enhances features from high-response expression areas to improve the collaborative modeling between local details and key expression regions. All three modules utilize the spatial frequency locality of the wavelet transform to achieve high-/low-frequency feature separation, thereby enhancing fine-grained expression representation under frequency domain guidance. Experimental results show that our WGGLFA achieves accuracies of 90.32%, 91.24%, and 71.90% on the RAF-DB, FERPlus, and FED-RO datasets, respectively, demonstrating that our WGGLFA is effective and has more capability of robustness and generalization than state-of-the-art (SOTA) expression recognition methods.