Precision agriculture has recently gained significant importance in computer vision technologies. Various processes as a part of agricultural production cycle from planting to harvesting can be carried out automatical...
详细信息
The deep learning field is converging towards the use of general foundation models that can be easily adapted for diverse tasks. While this paradigm shift has become common practice within the field of natural languag...
详细信息
ISBN:
(纸本)9798350318920;9798350318937
The deep learning field is converging towards the use of general foundation models that can be easily adapted for diverse tasks. While this paradigm shift has become common practice within the field of natural language processing, progress has been slower in computer vision. In this paper we attempt to address this issue by investigating the transferability of various state-of-the-art foundation models to medical image classification tasks. Specifically, we evaluate the performance of five foundation models, namely SAM, SEEM, DINOv2, BLIP, and OPENCLIP across four well-established medical imaging datasets. We explore different training settings to fully harness the potential of these models. Our study shows mixed results. DINOv2 consistently outperforms the standard practice of imageNET pretraining. However, other foundation models failed to consistently beat this established baseline indicating limitations in their transferability to medical image classification tasks.
As the basis work of imageprocessing, rain removal from a single image has always been an important and challenging problem. Due to the lack of real rain images and corresponding clean images, most rain removal netwo...
详细信息
As the basis work of imageprocessing, rain removal from a single image has always been an important and challenging problem. Due to the lack of real rain images and corresponding clean images, most rain removal networks are trained by synthetic datasets, which makes the output images unsatisfactory in practical applications. In this work, we propose a new feature decoupling network for unsupervised image rain removal. Its purpose is to decompose the rain image into two distinguishable layers: clean image layer and rain layer. In order to fully decouple the features of different attributes, we use contrastive learning to constrain this process. Specifically, the image patch with similarity is pulled together as a positive sample, while the rain layer patch is pushed away as a negative sample. We not only make use of the inherent self-similarity within the sample, but also make use of the mutual exclusion between the two layers, so as to better distinguish the rain layer from the clean image. We implicitly constrain the embedding of different samples in the depth feature space to better promote rainline removal and image restoration. Our method achieves a PSNR of 25.80 on Test100, surpassing other unsupervised methods.
The fields of imageprocessing and computer vision have witnessed significant growth due to the proliferation of digital images across diverse domains. image Segmentation is the fundamental task in digital image proce...
详细信息
The fields of imageprocessing and computer vision have witnessed significant growth due to the proliferation of digital images across diverse domains. image Segmentation is the fundamental task in digital imageprocessing, finding applications in pivotal areas such as medical imaging, covert communication, autonomous driving, satellite imaging, among others. One particularly intriguing application of image segmentation lies in Reversible Data Hiding (RDH), where the delineation of the main Region of Interest (ROI) and Non-Region of Interest (NROI) using segmentation plays a crucial role for effective data encryption in the images. Over the last two decades, various studies focussed on developing an efficient data hiding approach, which can embed secret data within ROI and NROI part of image while ensuring its quality. A comprehensive survey has been conducted that meticulously examines different segmentation techniques, along with its usage in reversible data hiding. The main objective of this survey is to compare the performance metrics of reversible data hiding after applying different image segmentation techniques. The image segmentation techniques have been categorized systematically into three main classes: i) Traditional segmentation techniques, encompassing a spectrum of approaches like thresholding, region-based and edge detection based techniques, ii) machine Learning (ML) based approach consisting of Clustering, Support Vector machine (SVM) and iii) Deep Learning (DL) based technique, propelled by Convolutional Neural Networks (CNNs) that have emerged as a transformative paradigm, revolutionizing segmentation tasks with their ability to learn complex images. The survey finds out that PSNR value of data embedded images is high after applying deep learning based segmentation technique.
Ensuring the reliability and safety of electrical equipment is essential for industrial and residential applications. Traditional fault diagnosis methods involving physical inspections are time-consuming and ineffecti...
详细信息
Ensuring the reliability and safety of electrical equipment is essential for industrial and residential applications. Traditional fault diagnosis methods involving physical inspections are time-consuming and ineffective for early fault detection. Infrared (IR) thermography offers a non-invasive and efficient solution by identifying anomalies in temperature profiles. This review explores thermal vision-based fault diagnosis techniques, including region of interest (ROI) segmentation, image pre-processing, and fault diagnosis algorithms, with a focus on deep learning approaches. The study highlights the effectiveness of machine learning models in enhancing fault detection accuracy while identifying challenges such as environmental variations, data inconsistencies, and system integration issues. The review discusses the role of real-time applications, wireless technologies, and AI-based automation in improving fault detection. Research gaps are identified, and future directions are proposed to enhance efficiency, reliability, and industrial adoption.
This research delves into quantum machine learning (QML) in the context of computer vision analysis by exploring the progress made in quantum computing and its impact on machine learning applications such as managing ...
详细信息
作者：
Li, DaoliangDu, LingChina Agr Univ
Natl Innovat Ctr Digital Fishery Beijing Peoples R China China Agr Univ
Beijing Engn & Technol Res Ctr Internet Things Ag Beijing 100083 Peoples R China China Agr Univ
China EU Ctr Informat & Commun Technol Agr Beijing 100083 Peoples R China China Agr Univ
Key Lab Agr Informat Acquisit Technol Minist Agr Beijing 100083 Peoples R China China Agr Univ
Coll Informat & Elect Engn Beijing 100083 Peoples R China
Monitoring the growth conditions and behavior of fish will enable scientific management, reduce the threat of losses caused by disease and stress. Traditional monitoring methods are time-consuming, laborious, and unti...
详细信息
Monitoring the growth conditions and behavior of fish will enable scientific management, reduce the threat of losses caused by disease and stress. Traditional monitoring methods are time-consuming, laborious, and untimely monitoring readily leads to aquaculture accidents. As a non-invasive, objective, and repeatable tool, machinevision systems have been widely used in various aspects of aquaculture monitoring. Nevertheless, the complex underwater environment makes it difficult to obtain ideal data processing results only using traditional imageprocessing methods. Due to their powerful feature extraction capabilities, deep learning (DL) algorithms have been widely used in underwater imageprocessing. Hence, the combination of DL algorithms and machinevision for the automated monitoring of aquaculture is of great importance. As evidence for the multidisciplinary aspects of DL applications, attention is focused on the latest DL methods applied to five fields of research: classification, detection, counting, behavior recognition, and biomass estimation. Meanwhile, due to the low training efficiency of DL models caused by insufficient dataset, transfer learning and GAN have also put into spotlight of this filed to pursue high performance of DL models. We also present the challenges and benchmarks in terms of the advantages and disadvantages of the selected method in each field. In addition, we review the sources of image acquisition and pre-processing methods in aquaculture. Finally, the challenges and prospects of DL in aquaculture machinevision systems are discussed. The literature review shows that the deep neural networks such as AlexNet, LSTM, VGG, and GoogLeNet, have been used for aquaculture machinevision systems.
Computer vision research uses self-driving systems, robot surveillance, and science interpretation. A plethora of applications, including robotics, self-driving systems, video surveillance, and scene interpretation, h...
详细信息
In the process of image acquisition, transmission, and storage, the image quality is often degraded due to a variety of unfavorable factors, resulting in information loss, which poses certain difficulties for subseque...
详细信息
In the process of image acquisition, transmission, and storage, the image quality is often degraded due to a variety of unfavorable factors, resulting in information loss, which poses certain difficulties for subsequent imageprocessing and analysis. How to enhance the visibility of image details and maintain the naturalness of the image is one of the important challenges in imageprocessing. In response to this challenge, an image enhancement algorithm is proposed based on the advantages of histogram equalization and bilateral filtering. This algorithm organically integrates histogram equalization and bilateral filtering, aiming to improve image quality while reducing noise in the image. Specifically, the study first utilizes an improved histogram equalization strategy to preprocess the image and then applies a bilateral filter for further optimization. The experimental results showed that the optimized histogram equalization could effectively improve the global contrast of the image and avoid excessive enhancement and gray phenomenon of the image. Moreover, its peak signal-to-noise ratio could reach 0.71. However, bilateral filters showed significant advantages in processing complex data sets, and the peak signal-to-noise ratio could reach 0.95. It illustrated that the optimal research method has obvious advantages in improving image quality and reducing noise. The new enhancement strategy not only significantly improves the global contrast of the image but also preserves the naturalness of the image, providing important technical support for image analysis, machinevision, and artificial intelligence applications.
Automatically understanding the content of medical images and delivering accurate descriptions is an emerging field of artificial intelligence that combines skills in both computer vision and natural language processi...
详细信息
Automatically understanding the content of medical images and delivering accurate descriptions is an emerging field of artificial intelligence that combines skills in both computer vision and natural language processing fields. Medical image captioning is involved in various applications related to diagnosis, treatment, report generation and computer-aided diagnosis to facilitate the decision making and clinical workflows. Unlike generic image captioning, medical image captioning highlights the relationships between image objects and clinical findings, which makes it a very challenging task. Although few review papers have already been published in this field, their coverage is still quite limited and only particular problems are addressed. This motivates the current paper where a rapid review protocol was adopted to review the latest achievements in automatic medical image captioning from the medical domain perspective. We aim through this review to provide the reader with an up-to-date literature in this field by summarizing the key findings and approaches in this field, including the related datasets, applications and limitations as well as highlighting the main competitions, challenges and future directions.
暂无评论