Fracture detection plays a critical role in medical imaging analysis, traditional fracture diagnosis relies on visual assessment by experienced physicians, however the speed and accuracy of this approach are constrained by the expertise. With the rapid advancements in artificial intelligence, deep learning models based on the YOLO framework have been widely employed for fracture detection, demonstrating significant potential in improving diagnostic efficiency and accuracy. This study proposes an improved YOLO-based model, termed Fracture-YOLO, which integrates novel Critical-Region-Selector Attention (CRSelector) and Scale-Aware (ScA) heads to further enhance detection performance. Specifically, the CRSelector module utilizes global texture information to focus on critical features of fracture regions. Meanwhile, the ScA module dynamically adjusts the weights of features at different scales, enhancing the model’s capacity to identify fracture targets at multiple scales. Experimental results demonstrate that, compared to the baseline model, Fracture-YOLO achieves a significant improvement in detection precision, with mAP50and mAP50−95increasing by 4 and 3, surpassing the baseline model and achieving state-of-the-art (SOTA) performance.

This article presents a generalized collaborative representation-based classification (GCRC) framework, which includes many existing representation-based classification (RC) methods, such as collaborative RC (CRC) and sparse RC (SRC) as special cases. This article also advances the GCRC theory by exploring theoretical conditions on the general regularization matrix. A key drawback of CRC and SRC is that they fail to use the label information of training data and are essentially unsupervised in computing the representation vector. This largely compromises the discriminative ability of the learned representation vector and impedes the classification performance. Guided by the GCRC theory, we propose a novel RC method referred to as discriminative RC (DRC). The proposed DRC method has the following three desirable properties: 1) discriminability: DRC can leverage the label information of training data and is supervised in both representation and classification, thus improving the discriminative ability of the representation vector; 2) efficiency: it has a closed-form solution and is efficient in computing the representation vector and performing classification; and 3) theory: it also has theoretical guarantees for classification. Experimental results on benchmark databases demonstrate both the efficacy and efficiency of DRC for multiclass classification.

Sparse representation has achieved great success across various fields including signal processing, machine learning and computer vision. However, most existing sparse representation methods are confined to the real valued data. This largely limit their applicability to the quaternion valued data, which has been widely used in numerous applications such as color image processing. Another critical issue is that their performance may be severely hampered due to the data noise or outliers in practice. To tackle the problems above, in this work we propose a robust quaternion valued sparse representation (RQVSR) method in a fully quaternion valued setting. To handle the quaternion noises, we first define a new robust estimator referred as quaternion Welsch estimator to measure the quaternion residual error. Compared to the conventional quaternion mean square error, it can largely suppress the impact of large data corruption and outliers. To implement RQVSR, we have overcome the difficulties raised by the noncommutativity of quaternion multiplication and developed an effective algorithm by leveraging the half-quadratic theory and the alternating direction method of multipliers framework. The experimental results show the effectiveness and robustness of the proposed method for quaternion sparse signal recovery and color image reconstruction.

Various greedy algorithms have been developed for sparse signal recovery in recent years. However, most of them utilize the l2 norm based loss function and sensitive to non-Gaussian noises and outliers. This paper proposes a Cauchy matching pursuit (CauchyMP) algorithm for robust sparse representation and classification. By leveraging a Cauchy estimator based loss function, the proposed approach can robustly learn the sparse representation of noisy data corrupted by various severe noises. As a greedy algorithm, CauchyMP is also computationally efficient. We also develop a CauchyMP based classifier for robust classification with application to face recognition. The experiments on the datasets with gross corruptions demonstrate the efficacy and robustness of CauchyMP for learning robust sparse representation.

Owing to its simplicity and efficacy, orthogonal matching pursuit (OMP) has been a popular sparse representation method for compressed sensing and pattern classification. As a recent extension of OMP, generalized OMP (GOMP) improves the efficiency of OMP by identifying multiple atoms each iteration. Nonetheless, GOMP utilizes the mean square error (MSE) criterion as the loss function, which has been proven to rely on the Gaussianity assumption of the noise distribution and sensitive to non-Gaussian noise. In this paper, we propose a robust sparse representation method, called information-theoretic generalized OMP (ITGOMP), to reduce the limitation of GOMP. The key idea is to minimize the correntropy based information-theoretic loss function, which is independent of the noise distribution. We also devise a half-quadratic based algorithm to tackle the optimization problem. Finally, an ITGOMP based classifier is developed for robust pattern classification. The experiments on public real-world databases verify the effectiveness and robustness of the proposed method for classification.

Collaborative representation-based classification (CRC) and sparse RC (SRC) have recently achieved great success in face recognition (FR). Previous CRC and SRC are originally designed in the real setting for grayscale image-based FR. They separately represent the color channels of a query color image and ignore the structural correlation information among the color channels. To remedy this limitation, in this paper, we propose two novel RC methods for color FR, namely, quaternion CRC (QCRC) and quaternion SRC (QSRC) using quaternion ℓ1minimization. By modeling each color image as a quaternionic signal, they naturally preserve the color structures of both query and gallery color images while uniformly coding the query channel images in a holistic manner. Despite the empirical success of CRC and SRC on FR, a few theoretical results are developed to guarantee their effectiveness. Another purpose of this paper is to establish the theoretical guarantee for QCRC and QSRC under mild conditions. Comparisons with competing methods on benchmark real-world databases consistently show the superiority of the proposed methods for both color FR and reconstruction.