Search

Although plant disease recognition has witnessed a significant improvement with deep learning in recent years, a common observation is that current deep learning methods with decent performance tend to suffer in real-world applications. We argue that this illusion essentially comes from the fact that current plant disease recognition datasets cater to deep learning methods and are far from real scenarios. Mitigating this illusion fundamentally requires an interdisciplinary perspective from both plant disease and deep learning, and a core question arises. What are the characteristics of a desired dataset? This paper aims to provide a perspective on this question. First, we present a taxonomy to describe potential plant disease datasets, which provides a bridge between the two research fields. We then give several directions for making future datasets, such as creating challenge-oriented datasets. We believe that our paper will contribute to creating datasets that can help achieve the ultimate objective of deploying deep learning in real-world plant disease recognition applications. To facilitate the community, our project is publicly available at https://github.com/xml94/PPDRD with the information of relevant public datasets.

Cow behavior carries important health information. The timely and accurate detection of standing, grazing, lying, estrus, licking, fighting, and other behaviors is crucial for individual cow monitoring and understanding of their health status. In this study, a model called CAMLLA-YOLOv8n is proposed for Holstein cow behavior recognition. We use a hybrid data augmentation method to provide the model with rich Holstein cow behavior features and improve the YOLOV8n model to optimize the Holstein cow behavior detection results under challenging conditions. Specifically, we integrate the Coordinate Attention mechanism into the C2f module to form the C2f-CA module, which strengthens the expression of inter-channel feature information, enabling the model to more accurately identify and understand the spatial relationship between different Holstein cows’ positions, thereby improving the sensitivity to key areas and the ability to filter background interference. Secondly, the MLLAttention mechanism is introduced in the P3, P4, and P5 layers of the Neck part of the model to better cope with the challenges of Holstein cow behavior recognition caused by large-scale changes. In addition, we also innovatively improve the SPPF module to form the SPPF-GPE module, which optimizes small target recognition by combining global average pooling and global maximum pooling processing and enhances the model’s ability to capture the key parts of Holstein cow behavior in the environment. Given the limitations of traditional IoU loss in cow behavior detection, we replace CIoU loss with Shape–IoU loss, focusing on the shape and scale features of the Bounding Box, thereby improving the matching degree between the Prediction Box and the Ground Truth Box. In order to verify the effectiveness of the proposed CAMLLA-YOLOv8n algorithm, we conducted experiments on a self-constructed dataset containing 23,073 Holstein cow behavior instances. The experimental results show that, compared with models such as YOLOv3-tiny, YOLOv5n, YOLOv5s, YOLOv7-tiny, YOLOv8n, and YOLOv8s, the improved CAMLLA-YOLOv8n model achieved increases in Precision of 8.79%, 7.16%, 6.06%, 2.86%, 2.18%, and 2.69%, respectively, when detecting the states of Holstein cows grazing, standing, lying, licking, estrus, fighting, and empty bedding. Finally, although the Params and FLOPs of the CAMLLA-YOLOv8n model increased slightly compared with the YOLOv8n model, it achieved significant improvements of 2.18%, 1.62%, 1.84%, and 1.77% in the four key performance indicators of Precision, Recall, mAP@0.5, and mAP@0.5:0.95, respectively. This model, named CAMLLA-YOLOv8n, effectively meets the need for the accurate and rapid identification of Holstein cow behavior in actual agricultural environments. This research is significant for improving the economic benefits of farms and promoting the transformation of animal husbandry towards digitalization and intelligence.

Recent advancements in deep learning have brought significant improvements to plant disease recognition. However, achieving satisfactory performance often requires high-quality training datasets, which are challenging and expensive to collect. Consequently, the practical application of current deep learning–based methods in real-world scenarios is hindered by the scarcity of high-quality datasets. In this paper, we argue that embracing poor datasets is viable and aims to explicitly define the challenges associated with using these datasets. To delve into this topic, we analyze the characteristics of high-quality datasets, namely, large-scale images and desired annotation, and contrast them with the limited and imperfect nature of poor datasets. Challenges arise when the training datasets deviate from these characteristics. To provide a comprehensive understanding, we propose a novel and informative taxonomy that categorizes these challenges. Furthermore, we offer a brief overview of existing studies and approaches that address these challenges. We point out that our paper sheds light on the importance of embracing poor datasets, enhances the understanding of the associated challenges, and contributes to the ambitious objective of deploying deep learning in real-world applications. To facilitate the progress, we finally describe several outstanding questions and point out potential future directions. Although our primary focus is on plant disease recognition, we emphasize that the principles of embracing and analyzing poor datasets are applicable to a wider range of domains, including agriculture. Our project is public available at https://github.com/xml94/EmbracingLimitedImperfectTrainingDatasets.

Abstract In recent years, vehicle re‐identification has attracted more and more attention. How to learn the discriminative information from multi‐view vehicle images becomes one of the challenging problems in vehicle re‐identification field. For example, when the viewpoint of the image changes, the features extracted from one image may be lost in another image. A two‐branch network with pyramid‐based local and spatial attention global feature learning (PSA) is proposed for vehicle re‐identification to solve this issue. Specifically, one branch learns local features at different scales by building pyramid from coarse to fine and the other branch learns attentive global features by using spatial attention module. Subsequently, pooling operation by using global maximum pooling (GMP) for local features and global average pooling (GAP) for global feature is performed. Finally, local feature vectors and global feature vector extracted from the last pooling layer, respectively, are employed for identity re‐identification. The experimental results demonstrate that the proposed method achieves state‐of‐the‐art results on the VeRi‐776 dataset and VehicleID dataset.

Instance-level image translation aims to only translate instance of interest and can be operated more finely and flexibly than object-level and holistic-level image translation. However, current algorithms are not suitable to do it since they employ a holistic or object level’s discriminator that tends to change the whole image or all instances. To address the issue, we propose a simple yet effective local discriminator, in which the input image is split into two parts, region of interest (ROI) and background. Instance mask is employed to align the ROI and the background is design to be random in a prior distribution to mitigate a divergence between the ROI and the background. In this way, we obtain translated instance with decent margins without artifacts as current algorithms get. Moreover we propose a new architecture to simultaneously realize versatile instance-level image translation. Experimental results prove that our proposed algorithm outperforms the state-of-the-art in position accuracy and background retainment by a clear margin.

Deep learning shows its advantages and potentials in plant disease recognition and has witnessed a profound development in recent years. To obtain a competing performance with a deep learning algorithm, enough amount of annotated data is requested but in the natural world, scarce or imbalanced data are common, and annotated data is expensive or hard to collect. Data augmentation, aiming to create variations for training data, has shown its power for this issue. But there are still two challenges: creating more desirable variations for scarce and imbalanced data, and designing a data augmentation to ease object detection and instance segmentation. First, current algorithms made variations only inside one specific class, but more desirable variations can further promote performance. To address this issue, we propose a novel data augmentation paradigm that can adapt variations from one class to another. In the novel paradigm, an image in the source domain is translated into the target domain, while the variations unrelated to the domain are maintained. For example, an image with a healthy tomato leaf is translated into a powdery mildew image but the variations of the healthy leaf are maintained and transferred into the powdery mildew class, such as types of tomato leaf, sizes, and viewpoints. Second, current data augmentation is suitable to promote the image classification model but may not be appropriate to alleviate object detection and instance segmentation model, mainly because the necessary annotations can not be obtained. In this study, we leverage a prior mask as input to tell the area we are interested in and reuse the original annotations. In this way, our proposed algorithm can be utilized to do the three tasks simultaneously. Further, We collect 1,258 images of tomato leaves with 1,429 instance segmentation annotations as there is more than one instance in one single image, including five diseases and healthy leaves. Extensive experimental results on the collected images validate that our new data augmentation algorithm makes useful variations and contributes to improving performance for diverse deep learning-based methods.

Finger vein recognition has been considered one of the most promising biometrics for personal authentication. However, the capacities and percentages of finger tissues (e.g., bone, muscle, ligament, water, fat, etc.) vary person by person. This usually causes poor quality of finger vein images, therefore degrading the performance of finger vein recognition systems (FVRSs). In this paper, the intrinsic factors of finger tissue causing poor quality of finger vein images are analyzed, and an intensity variation (IV) normalization method using guided filter based single scale retinex (GFSSR) is proposed for finger vein image enhancement. The experimental results on two public datasets demonstrate the effectiveness of the proposed method in enhancing the image quality and finger vein recognition accuracy.

Computer 3D character animation essentially is a product, which is combined with computer graphics and robotics, physics, mathematics, and the arts. It is based on computer hardware and graphics algorithms and related sciences rapidly developed new technologies. At present, the mainstream character animation technology is based on the artificial production of key technologies and capture frames based on the motion capture device technology. 3D character animation is widely used not only in the production of film, animation, and other commercial areas but also in virtual reality, computer-aided education, flight simulation, engineering simulation, military simulation, and other fields. In this paper, we try to study physics based character animation to solve these problems such as poor real-time interaction that appears in the character, low utilization rate, and complex production. The paper deeply studied the kinematics, dynamics technology, and production technology based on the motion data. At the same time, it analyzed ODE, PhysX, Bullet, and other variety of mainstream physics engines and studied OBB hierarchy bounding box tree, AABB hierarchical tree, and other collision detection algorithms. Finally, character animation based on ODE is implemented, which is simulation of the motion and collision process of a tricycle.

In the field of Facial Expression Recognition (FER), traditional local texture coding methods have a low computational complexity, while providing a robust solution with respect to occlusion, illumination, and other factors. However, there is still need for improving the accuracy of these methods while maintaining their real-time nature and low computational complexity. In this paper, we propose a feature-based FER system with a novel local texture coding operator, named central symmetric local gradient coding (CS-LGC), to enhance the performance of real-time systems. It uses four different directional gradients on 5 × 5 grids, and the gradient is computed in the center-symmetric way. The averages of the gradients are used to reduce the sensitivity to noise. These characteristics lead to symmetric of features by the CS-LGC operator, thus providing a better generalization capability in comparison to existing local gradient coding (LGC) variants. The proposed system further transforms the extracted features into an eigen-space using a principal component analysis (PCA) for better representation and less computation; it estimates the intended classes by training an extreme learning machine. The recognition rate for the JAFFE database is 95.24%, whereas that for the CK+ database is 98.33%. The results show that the system has advantages over the existing local texture coding methods.

Finger veins have been proved to be an effective biometric for personal identification in the recent years. However, finger vein images are easily affected by influences such as image translation, orientation, scale, scattering, finger structure, complicated background, uneven illumination, and collection posture. All these factors may contribute to inaccurate region of interest (ROI) definition, and so degrade the performance of finger vein identification system. To improve this problem, in this paper, we propose a finger vein ROI localization method that has high effectiveness and robustness against the above factors. The proposed method consists of a set of steps to localize ROIs accurately, namely segmentation, orientation correction, and ROI detection. Accurate finger region segmentation and correct calculated orientation can support each other to produce higher accuracy in localizing ROIs. Extensive experiments have been performed on the finger vein image database, MMCBNU_6000, to verify the robustness of the proposed method. The proposed method shows the segmentation accuracy of 100%. Furthermore, the average processing time of the proposed method is 22 ms for an acquired image, which satisfies the criterion of a real-time finger vein identification system.

Multimodal biometrics combine a variety of biological features to have a significant impact on identification performance, which is a newly developed trend in biometrics identification technology. This study proposes a novel multimodal biometrics recognition model based on the stacked extreme learning machines (ELMs) and canonical correlation analysis (CCA) methods. The model, which has a symmetric structure, is found to have high potential for multimodal biometrics. The model works as follows. First, it learns the hidden-layer representation of biological images using extreme learning machines layer by layer. Second, the canonical correlation analysis method is applied to map the representation to a feature space, which is used to reconstruct the multimodal image feature representation. Third, the reconstructed features are used as the input of a classifier for supervised training and output. To verify the validity and efficiency of the method, we adopt it for new hybrid datasets obtained from typical face image datasets and finger-vein image datasets. Our experimental results demonstrate that our model performs better than traditional methods.

Due to the vulnerable environment, limited recourse and open communication channel, wireless sensor networks (WSNs) are necessary to be protected from various attacks. The key management is an important way to protect the communication in WSNs. In this paper, we present a hierarchical key management scheme (HKMS) which can efficiently enhance the security and survivability for the clustered WSNs. Different from previous works, the HKMS distributes keys based on hop counts and one-way function by the clustered architecture, which not only localizes the key things but also has no overhead. The HKMS provides the session keys among sensors and the cluster key between the cluster head and member nodes. The HKMS dynamically generates different keys based on different hops in different periods which can protect the network from the compromised nodes and reduce the high probability of the common keys without any special sensors (such as the anchor nodes). The security analysis and simulation show the HKMS can prevent several attacks effectively and reduce the energy consumption.