Concerning the problem that wafer surface defects are easily confused with the background and are difficult to detect, a new detection method for wafer surface defects based on background subtraction and Faster R-CNN is proposed. First, an improved spectral analysis method is proposed to measure the period of the image, and the substructure image can then be obtained on the basis of the period. Then, a local template matching method is adopted to position the substructure image, thereby reconstructing the background image. Then, the interference of the background can be eliminated by an image difference operation. Finally, the difference image is input into an improved Faster R-CNN network for detection. The proposed method has been validated on a self-developed wafer dataset and compared with other detectors. The experimental results show that compared with the original Faster R-CNN, the proposed method increases the mAP effectively by 5.2%, which can meet the requirements of intelligent manufacturing and high detection accuracy.

Image steganalysis aims to detect whether secret information is hidden in images and is a means to solve the communication security. Recently, a series of convolutional neural network-based steganalysis models has been proposed and has achieved remarkable performance. Given that the steganalysis task is different from other computer vision tasks, the series of models is inevitably restricted by manual factors, and some other useful residual information will be missed in the process of feature extraction. To solve this problem, this paper proposes a network model based on non-local operations and multi-channel convolution as part of the basic block of feature extraction for spatial grayscale image steganalysis. The preprocessing layer is improved to compress the image content, further using the introduced non-local operations and multi-channel convolution modules to enhance the residual information in high-frequency regions and extract diverse steganographic features effectively. Extensive ablation study shows that the introduced extraction module can improve the steganographic detection accuracy effectively. Our method is generally better than other methods in terms of detection accuracy, especially in low payload detection.

For wafer surface defect detection, a new method based on improved Faster RCNN is proposed here to solve the problems of missing detection due to small objects and multiple boxes detection due to discontinuous objects. First, focusing on the problem of small objects missing detection, a feature enhancement module (FEM) based on dynamic convolution is proposed to extract high-frequency image features, enrich the semantic information of shallow feature maps, and improve detection performance for small-scale defects. Second, for the multiple boxes detection caused by discontinuous objects, a predicted box aggregation method is proposed to aggregate redundant predicted boxes and fine-tune real predicted boxes to further improve positioning accuracy. Experimental results show that the mean average precision of the proposed method, when validated on a self-developed dataset, reached 87.5%, and the detection speed was 0.26 s per image. The proposed method has a certain engineering application value.

Image steganalysis is a technique for detecting the presence of hidden information in images, which has profound significance for maintaining cyberspace security. In recent years, various deep steganalysis networks have been proposed in academia, and have achieved good detection performance. Although convolutional neural networks (CNNs) can effectively extract the features describing the image content, the difficulty lies in extracting the subtle features that describe the existence of hidden information. Considering this concern, this paper introduces separable convolution and adversarial mechanism, and proposes a new network structure that effectively solves the problem. The separable convolution maximizes the residual information by utilizing its channel correlation. The adversarial mechanism makes the generator extract more content features to mislead the discriminator, thus separating more steganographic features. We conducted experiments on BOSSBase1.01 and BOWS2 to detect various adaptive steganography algorithms. The experimental results demonstrate that our method extracts the steganographic features effectively. The separable convolution increases the signal-to-noise ratio, maximizes the channel correlation of residuals, and improves efficiency. The adversarial mechanism can separate more steganographic features, effectively improving the performance. Compared with the traditional steganalysis methods based on deep learning, our method shows obvious improvements in both detection performance and training efficiency.

Unsupervised industrial anomaly detection uses normal training images to identify and localize defects. The challenge addressed here is localizing small defects amid normal appearance variation without requiring different feature layers to share one normal reference. We propose dual-layer DINOv3 anomaly-score fusion (DT-FS), which allows the two layers to retrieve different normal references before their anomaly maps are combined. Separate memory banks are constructed from the fourth-to-last and last transformer blocks. The two distance maps are normalized and combined with fixed equal weights, without fine-tuning the backbone or training a fusion module. Under a matched five-seed protocol, DT-FS improves pixel-level average precision over feature concatenation by 2.678 and 3.920 percentage points on MVTec AD and VisA, and by 6.470 points on supplementary MPDD. An eight-configuration ablation supports the selected layer pair, while a DINOv2 comparison shows positive fusion gains on all three datasets. A PaDiM baseline, normalization analysis and runtime measurements further assess the method. The results support independent retrieval followed by score fusion for pixel-level defect localization, while showing that image-wise normalization can weaken image-level detection and that separate retrieval increases inference time.