Checkerboard corners are routinely used during tasks such as camera calibration, and accurate detection of them is essential. Traditional methods such as those based on the Harris corner detector are usually affected by image artefacts such as noise and blur. The more recently proposed deep network approach also suffers from the lack of accurate training data. In this article, we make the following contributions: First, we propose a synthetic training data generation method that simulates the real imaging process, with the most notable being that the exact sub‐pixel corner positions in the image become readily available. Second, we design a relatively simple deep network and train it using the synthetic data generated by the proposed method. Finally, because the exact sub‐pixel corner positions can be obtained in the proposed method, this article paves a way for objectively comparing different checkerboard corner detectors in terms of metrics such as the mean Euclidean location error. Experimental results using both synthetic and real data show that the proposed detector significantly outperforms typical methods, including the commonly used Matlab camera calibration toolbox, the OpenCV checkerboard corner detectors, and the more recently proposed deep learning‐based methods.

The state of the art impulse noise removal methods make use of the noise variance, or equivalently the noise mixing probability p, and are iterative procedures (e.g., , ). However, so far there has been a lack of effective estimator for p. As a result, true values of p are often used during simulation, which may not be practical. Furthermore, the optimal stopping criteria for the iterative algorithms have been elusive until recently. In a computationally heavy method is proposed for determining the optimal number of iterations. In this letter we make two contributions. We first develop a robust estimator for p by using the empirical observation that a natural image usually doesn't cover all pixel value range, then we design an efficient linear transformation to replace complicated computation of order statistics. Based on this estimated p value, we further derive the formula for estimating the true image histogram, and use it to formulate a new efficient optimal stopping criterion during the iterative denoising process. This formulation has a simple interpretation of its optimality and yields improved denoising performance.

Attention mechanisms are critical tools for enhancing the performance of convolutional neural networks (CNNs), focusing on spatial and channel dimensions of feature maps, known as spatial attention and channel attention, respectively. While many advanced attention methods combine these dimensions to improve performance, particularly in downstream computer vision tasks, such methods often introduce significant computational overhead or fail to effectively capture long-range spatial dependencies alongside channel attention. To address these challenges, this paper proposes the sequential fusion attention (SFA) method, which introduces a complementary fusion strategy to integrate spatial and channel attention. Spatial attention leverages strip pooling to model long-range dependencies, while channel attention employs dynamic encoding to refine features. By utilizing a grouped processing approach, the SFA module achieves an optimal balance between computational efficiency and representation power. Extensive experiments on benchmark datasets demonstrate that SFA consistently outperforms state-of-the-art attention mechanisms, delivering competitive accuracy in image classification, object detection, and semantic segmentation tasks while maintaining reduced model complexity. This work underscores the potential of lightweight attention mechanisms in modern computer vision and paves the way for further innovations in resource-efficient neural network design. Our code is publicly available at the following URL: https://github.com/Xuwei86/SFA

Color image binarization plays a pivotal role in image preprocessing work and significantly impacts subsequent tasks, particularly for text recognition. This paper concentrates on document image binarization (DIB), which aims to separate an image into a foreground (text) and background (non-text content). We thoroughly analyze conventional and deep-learning-based approaches and conclude that prevailing DIB methods leverage deep learning technology. Furthermore, we explore the receptive fields of pre- and post-network training to underscore the Transformer model’s advantages. Subsequently, we introduce a lightweight model based on the U-Net structure and enhanced with the MobileViT module to capture global information features in document images better. Given its adeptness at learning both local and global features, our proposed model demonstrates competitive performance on two standard datasets (DIBCO2012 and DIBCO2017) and good robustness on the DIBCO2019 dataset. Notably, our proposed method presents a straightforward end-to-end model devoid of additional image preprocessing or post-processing, eschewing the use of ensemble models. Moreover, its parameter count is less than one-eighth of the model, which achieves the best results on most DIBCO datasets. Finally, two sets of ablation experiments are conducted to verify the effectiveness of the proposed binarization model.