Explore the vast range of titles available.

In recent decades, the development of multimedia and computer vision has sparked significant interest among researchers in the field of automatic image annotation. However, much of the research has primarily focused on using a single graph for annotating images in semi-supervised learning. Conversely, numerous approaches have explored the integration of multi-view or image segmentation techniques to create multiple graph structures. Yet, relying solely on a single graph proves to be challenging, as it struggles to capture the complete manifold of structural information. Furthermore, the computational complexity of building multiple graph structures based on multi-view or image segmentation is substantial and time-consuming. To address these issues, we propose a novel method called \"Central Attention with Multi-graphs for Image Annotation.\" Our approach emphasizes the critical role of the central image region in the annotation process. Remarkably, we demonstrate that impressive performance can be achieved by leveraging just two graph structures, composed of central and overall features, in semi-supervised learning. To validate the effectiveness of our proposed method, we conducted a series of experiments on benchmark datasets, including Corel5K, ESPGame, and IAPRTC12. These experiments provide empirical evidence of our method’s capabilities.

Large-scale collection and annotation of sensitive facial data in real-world traffic scenarios face significant hurdles regarding privacy protection, temporal consistency, and high costs. To address these issues, this work proposes an integrated method specifically designed for sensitive information anonymization and semi-automatic image annotation (AIA). Specifically, the Nullface anonymization model is applied to remove identity information from facial data while preserving non-identity attributes including pose, expression, and background that are relevant to downstream vision tasks. Secondly, the Qwen3-VL multimodal foundation model is combined with the Grounding DINO detection model to build an end-to-end annotation platform using the Dify workflow, covering data cleaning and automated labeling. A traffic-sensitive information dataset with diverse and complex backgrounds is then constructed. Subsequently, the systematic experiments on the WIDER FACE subset show that Nullface significantly outperforms baseline methods including FAMS and Ciagan in head pose preservation and image quality. Finally, evaluation on object detection further confirms the effectiveness of the proposed approach. The accuracy achieved by the proposed method reaches 91.05%, outperforming AWS, and is almost identical to the accuracy of manual annotation. This demonstrates that the anonymization process maintains critical semantic details required for effective object detection.

Purpose The growing usage of medical imaging for diagnosis and clinical processes provides an increasing amount of materials that can be reused for secondary use. However, this valuable resource often remains underutilized due to non-standardized formatting and annotation. Our study aims to devise a validated annotation model for standardizing and facilitating the reuse of medical images based on real clinical data. Methods We extract a dataset with 20k DICOM X-ray images, routinely captured as standard clinical care and stored in the PACS system. A radiologist iteratively annotates and validates 1) examined body parts (single-label pathological classification) and 2) visible body parts (multi-label classification) using 36 relevant SNOMED CT codes. Results The proposed model shows an accuracy of 0.889 for classifying examined body parts and 0.853 for classifying visible body parts on the curated dataset. The approach demonstrated advantages in simplicity of use, universal availability, and the ability to enhance data quality. Reducing body parts from 116 distinct DICOM header entries to 36 SNOMED CT codes promises improved retrieval and more concise communication in future applications. In addition, the intersection of Deep Learning models and initial DICOM headers achieved the best result, with a recall of 98.7% in our simulated use case. Conclusion Deep learning techniques show potential to address data standardization and quality issues, offering a technically feasible and cost-effective solution for annotating and reusing diverse medical images. Future work should enhance accuracy via multi-radiologist validation and explore methods such as unsupervised or online learning.

Purpose The training of deep medical image segmentation networks usually requires a large amount of human-annotated data. To alleviate the burden of human labor, many semi- or non-supervised methods have been developed. However, due to the complexity of clinical scenario, insufficient training labels still causes inaccurate segmentation in some difficult local areas such as heterogeneous tumors and fuzzy boundaries. Methods We propose an annotation-efficient training approach, which only requires scribble guidance in the difficult areas. A segmentation network is initially trained with a small amount of fully annotated data and then used to produce pseudo labels for more training data. Human supervisors draw scribbles in the areas of incorrect pseudo labels (i.e., difficult areas), and the scribbles are converted into pseudo label maps using a probability-modulated geodesic transform. To reduce the influence of the potential errors in the pseudo labels, a confidence map of the pseudo labels is generated by jointly considering the pixel-to-scribble geodesic distance and the network output probability. The pseudo labels and confidence maps are iteratively optimized with the update of the network, and the network training is promoted by the pseudo labels and the confidence maps in turn. Results Cross-validation based on two data sets (brain tumor MRI and liver tumor CT) showed that our method significantly reduces the annotation time while maintains the segmentation accuracy of difficult areas (e.g., tumors). Using 90 scribble-annotated training images (annotated time: ~ 9 h), our method achieved the same performance as using 45 fully annotated images (annotation time: > 100 h) but required much shorter annotation time. Conclusion Compared to the conventional full annotation approaches, the proposed method significantly saves the annotation efforts by focusing the human supervisions on the most difficult regions. It provides an annotation-efficient way for training medical image segmentation networks in complex clinical scenario.

Image annotation is the task of assigning keywords to images with the goal of facilitating their organization and accessibility options (e.g., searching by keywords). Traditional annotation methods are based on supervised learning. Although being very effective, these methods require of large amounts of manually labeled images, and are limited in the sense that images can only be labeled with concepts seen during the training phase. Unsupervised automatic image annotation (UAIA) methods, on the other hand, neglect strongly-labeled images and instead rely on huge collections of unstructured text containing images for the annotation. In addition to not requiring labeled images, unsupervised techniques are advantageous because they can assign (virtually) any concept to an image. Despite these benefits, unsupervised methods have not been widely studied in image annotation, a reason for this is the lack of a reference framework for UAIA. In this line, this paper introduces two effective methods for UAIA in the context of a common framework inspired in the way a query is expanded throughout Automatic Query Expansion (AQE) in information retrieval. On the one hand, we describe a local method that processes text information associated to images retrieved when using the image to annotate as query, several methods from the state of the art can be described under this formulation. On the other hand, we propose a global method that pre-process offline the reference collection to identify visual-textual associations that are later used for annotation. Both methods are extensively evaluated in benchmarks for large-scale UAIA. Experimental results show the competitiveness of both strategies when compared to the state of the art. We foresee the AQE-based framework will pave the way for the development of alternative and effective methods for UAIA.

What are the main findings? * Four spectral indices were identified as important for the quantification of seagrass within and adjacent to the MSC-certified Western Australia Enhanced Greenlip Abalone Fishery. The Normalised Difference Aquatic Vegetation Index (NDAVI) and Depth Invariant Index of the blue and green bands were the most important indices. * Similar seagrass cover and distribution were observed inside and outside of the fishery area of operation. Four spectral indices were identified as important for the quantification of seagrass within and adjacent to the MSC-certified Western Australia Enhanced Greenlip Abalone Fishery. The Normalised Difference Aquatic Vegetation Index (NDAVI) and Depth Invariant Index of the blue and green bands were the most important indices. Similar seagrass cover and distribution were observed inside and outside of the fishery area of operation. What are the implication of the main finding? * The use of indices from free satellite products via Google Earth Engine workflows and automatic image annotation provides a rapidly repeatable method to support ecosystem-based fisheries management for this fishery. * These findings may have broader applications for ecosystem monitoring across moderately deep (<20 m) fisheries and marine management areas. The use of indices from free satellite products via Google Earth Engine workflows and automatic image annotation provides a rapidly repeatable method to support ecosystem-based fisheries management for this fishery. These findings may have broader applications for ecosystem monitoring across moderately deep (<20 m) fisheries and marine management areas. Understanding and monitoring benthic habitat distribution is essential for implementing ecosystem-based fisheries management (EBFM). Satellite remote sensing offers a rapid and cost-effective approach to marine habitat assessments; however, its application requires context-specific adjustment to account for environmental variability and differing study aims. As such, predictor variables must be tailored to the specific site and target habitat. This study uses Sentinel-2 Level 2A surface reflectance satellite imagery and stability selection via Random Forest Recursive Feature Elimination to assess the importance of remote sensing indices for mapping moderately deep (<20 m) seagrass habitats in relation to the Marine Stewardship Council-certified Western Australia Enhanced Greenlip Abalone Fishery (WAEGAF). Of the seven indices tested, the Normalised Difference Aquatic Vegetation Index (NDAVI) and Depth Invariant Index for the blue and green bands were selected in the optimal model on every run. The kernelised NDAVI and Water-Adjusted Vegetation Index also scored highly (both 0.92) and were included in the final classification and regression models. Both models performed well and predicted a similar cover and distribution of seagrass within the fishery compared to the surrounding area, providing a baseline and supporting EBFM of the WAEGAF within the surrounding marine protected area. Importantly, the use of indices from freely accessible ready-to-use satellite products via Google Earth Engine workflows and expedited ground truth image annotation using highly accurate (0.96) automatic image annotation provides a rapidly repeatable method for delivering ecosystem information for this fishery.

The number of digital images uploaded in the virtual world is rapidly growing every day. Therefore, an automatic image annotation system that can retrieve information from these images seems to be in high demand. One of the challenges in this field is the imbalanced data sets and the difficulty of successfully learning tags from them. Even if a nearly balanced data set exists for image annotation, it is unlikely to find a single learner, which could learn all tags with the same accuracy. In this paper, we suggest a novel integration system that selects an elite group of models from all existing annotation models and then combines them to take the best advantage of each model’s learning technique. The proposed system studies the data sets of selected models without the need for direct access to those data sets. As this algorithm is independent of the annotation models or data sets, it could be used to combine the currently available annotation models and those developed in future, along with their data sets and learning models. We believe the proposed approach has the potential of becoming an integrated ground for automatic image annotation models.

The present-day business online web indexes have embraced electronic picture search to further develop precision in picture information recovery. However Re-positioning is expectedly considered as a successful cycle for deciding the situation with electronic picture web search tools, yet it experiences a lack of a couple of. Consequently, some grouping methods, particularly (Novel Image Re-positioning System) NIRS have to be proposed to carry out inquiry picture re-positioning with semantic marks in electronic picture information recovery, which naturally recovers results in view of visual semantic highlights for various question or catchphrase extensions. To get to productive picture with the annotation is an aggressive concept in present. So that in the present paper, we are going to propose the Unsupervised Multi Labeled Image Annotate Learning Approach (UMLIALA) to decrease complexity in indexing of image with mining of web related convex optimization and classify required image data from large image data sets. And also use group based approximation calculation to improve accuracy in retrieval of images from different image data sources. Experiments of proposed approach give better and efficient results when compare to traditional approaches in terms of different image exploration parameters studies on different large image data sets.

Refining image annotation has become one of the core research topics in computer vision and pattern recognition due to its great potentials in image retrieval. However, it is still in its infancy and is not sophisticated enough to extract perfect semantic concepts just according to the image low-level features. In this paper, we propose a two-stage hybrid probabilistic topic model to improve the quality of automatic image annotation. To start with, a probabilistic latent semantic analysis model with asymmetric modalities is learned to estimate the posterior probabilities of each annotation keyword, during which the image-to-word relation can be well established. Next, a label similarity graph is constructed by a weighted linear combination of label similarity and visual similarity of images associated with the corresponding labels. By this way, the information from image low-level visual features and high-level semantic concepts can be seamlessly integrated by fully taking into account the word-to-word and image-to-image relations. Finally, the rank-two relaxation heuristics is exploited to further mine the correlation of the candidate annotations so as to capture the refining results, which plays a critical role in semantic based image retrieval. Extensive experiments show that the proposed model achieves not only superior annotation accuracy but also better retrieval performance.

Thanks to the evolution of technology, we find a very large number of internet users who use social networks to react and share things with each other. These networks are exploited in the study of several domains. In fact, an Internet user can easily share his images with a simple click on his/her Smartphone. However, we get a large amount of published images on the Internet. Such an amount requires specific access techniques to be used by the search engines to provide searchers with the desired results. An effective way to access the target images is their keywords (or tags). Nevertheless, tags, which people manually attach to images, are of low quality and negatively affect the search engines. Consequently, automatic annotation of images by tags has become an active topic of research in recent years. In this paper, we introduce an automatic annotation method in social networks named MDL-STag (Multimodal features Deep Learning approach for Social image Tagging). This method provides high-quality features using the visual content of the image as well as the textual content of the annotation tag history to personalize the annotation, and that’s with the help of some deep learning models. Then, it merges these features and makes multimodal features for the images of the annotator’s contacts who share the same interests to provide more useful tags through the propagation of images tags that are similar to the target image. In fact, we find that tests give good results on real social networks as the well known Instagram and Flickr.