Explore the vast range of titles available.

In recent years we have witnessed an increasing interest in food processing and eating behaviors. This is probably due to several reasons. The biological relevance of food choices, the complexity of the food-rich environment in which we presently live (making food-intake regulation difficult), and the increasing health care cost due to illness associated with food (food hazards, food contamination, and aberrant food-intake). Despite the importance of the issues and the relevance of this research, comprehensive and validated databases of stimuli are rather limited, outdated, or not available for non-commercial purposes to independent researchers who aim at developing their own research program. The FoodCast Research Image Database (FRIDa) we present here includes 877 images belonging to eight different categories: natural-food (e.g., strawberry), transformed-food (e.g., french fries), rotten-food (e.g., moldy banana), natural-non-food items (e.g., pinecone), artificial food-related objects (e.g., teacup), artificial objects (e.g., guitar), animals (e.g., camel), and scenes (e.g., airport). FRIDa has been validated on a sample of healthy participants (N = 73) on standard variables (e.g., valence, familiarity, etc.) as well as on other variables specifically related to food items (e.g., perceived calorie content); it also includes data on the visual features of the stimuli (e.g., brightness, high frequency power, etc.). FRIDa is a well-controlled, flexible, validated, and freely available (http://foodcast.sissa.it/neuroscience/) tool for researchers in a wide range of academic fields and industry.

This paper describes a newly-created image database termed as the NITS-IQA database for image quality assessment (IQA). In spite of recently developed IQA databases, which contain a collection of a huge number of images and type of distortions, there is still a lack of new distortion and use of real natural images taken by the camera. The NITS-IQA database contains total 414 images, including 405 distorted images (nine types of distortion with five levels in each of the distortion type) and nine original images. In this paper, a detailed step by step description of the database development along with the procedure of the subjective test experiment is explained. The subjective test experiment is carried out in order to obtain the individual opinion score of the quality of the images presented before them. The mean opinion score (MOS) is obtained from the individual opinion score. In this paper, the Pearson, Spearman and Kendall rank correlation between a state-of-the-art IQA technique and the MOS are analyzed and presented.

In the domain of image and multimedia processing, image quality is a critical factor, as it directly influences the performance of subsequent tasks such as compression, transmission, and content analysis. Reliable assessment of image quality is therefore essential not only for benchmarking algorithms but also for ensuring user satisfaction in real-world multimedia applications. The most advanced Blind image quality assessment (BIQA) methods are typically built upon deep learning models and rely on complex architectures that, while effective, require substantial computational resources and large-scale training datasets. This complexity can limit their scalability and practical deployment, particularly in resource-constrained environments. In this paper, we revisit a model inspired by one of the early applications of convolutional neural networks (CNNs) in BIQA and demonstrate that by leveraging recent advancements in machine learning—such as Bayesian hyperparameter optimization and widely used stochastic optimization methods (e.g., Adam)—it is possible to achieve competitive performance using a simpler, more scalable, and lightweight architecture. To evaluate the proposed approach, we conducted extensive experiments on widely used benchmark datasets, including TID2013 and KADID-10k. The results show that the proposed model achieves competitive performance while maintaining a substantially more efficient design. These findings suggest that lightweight CNN-based models, when combined with modern optimization strategies, can serve as a viable alternative to more elaborate frameworks, offering an improved balance between accuracy, efficiency, and scalability.

The primary motivation of computer vision in the robotics field is to obtain a perception level that is as close as possible to human visual system. To achieve this, the inclusion of large datasets is necessary, sometimes involving less-frequent and seemingly irrelevant data to increase the system robustness. To minimize the effort and time in forming such extensive datasets from real world, the preferred method is to utilize simulation environments, replicating real-world conditions as much as possible. Following this solution path, the machine vision problems in robotics (i.e., object detection, recognition, and manipulation) often employ synthetic images in datasets and, however, do not mix them with real-world images. When the systems are trained only using the synthetic images and tested within the simulated world, the tasks requiring object recognition in robotics can be accomplished. However, the systems trained using this procedure cannot be directly used in the real-world experiments or end-user products due to the inconsistencies between real and simulation environments. Therefore, we propose a hybrid image dataset including annotated desktop objects from real and synthetic worlds (ADORESet). This hybrid dataset provides purposeful object categories with a sufficient number of real and synthetic images. ADORESet is composed of colored images with the dimension of 300×300 pixels within 30 categories. Each class has 2500 real-world images acquired from the wild web and 750 synthetic images that are generated within Gazebo simulation environment. This hybrid dataset enables researchers to implement their own algorithms for both real-world and simulation environment conditions. ADORESet is composed of fully annotated object images. The limits of objects are manually specified, and the bounding box coordinates are provided. The successor objects are also labeled to give statistical information and the likelihood about the relations of the objects within the dataset. To further demonstrate the benefits of this dataset, it is tested in object recognition tasks by fine-tuning the state-of-the-art deep convolutional neural networks such as VGGNet, InceptionV3, ResNet, and Xception. The possible combinations regarding the data types for these models are compared in terms of time, accuracy, and loss values. As a result of the conducted object recognition experiments, training with all-real images yields approximately 49% validation accuracy for simulation images. When the training is performed with all-synthetic images and validated using all-real images, the accuracy becomes lower than 10%. If the complete ADORESet is employed for training and validation, the hybrid dataset validation accuracy reaches approximately to 95%. This result proves further that including the real and synthetic images together in the training and validation sessions increases the overall system accuracy and reliability.

Lung cancer is the leading cause of death from cancer worldwide. Finding pulmonary nodules is a critical step in the diagnosis of early-stage lung cancer. It has the potential to become a tumour. Computed tomography (CT) scans for lung disease analysis offer useful data. Finding malignant pulmonary nodules and determining whether lung cancer is benign or malignant are the main goals. Before further image preparation, image denoising is an important process for removing noise from images (feature extraction, segmentation, surface detection, and so on) maximising the preservation of edges and other intact features. This study employs a novel evolutionary method dubbed the binary grasshopper optimisation algorithm in order to address some of the shortcomings of feature selection and provide an efficient feature selection algorithm, the artificial bee colony (BGOA-ABC) algorithm enhance categorisation. Then, to categorise the chosen features, we employ a hybrid classifier known as a double deep neural network (DDNN) algorithm. A technique used by MATLAB that segments impacted areas utilising improved IPCT (Profuse) aggregation technology employing datasets from the cancer image archive (CIA), the image database resource initiative (IDRI), and the lung imaging database consortium. Various performance metrics are evaluated and associated with different cutting-edge techniques, classifiers that are already in use.

Content-based image retrieval (CBIR) is essential for managing and searching massive image repositories across a wide variety of applications. Nevertheless, some traditional CBIR systems exhibit low retrieval accuracy because they use predetermined feature weights, lack semantic gaps, and poorly exploit heterogeneous visual features. To overcome such difficulties, the present study will introduce a multi-feature adaptive CBIR framework that combines deep and handcrafted features using an information entropy-based fusion and a trust-based weighting system. Deep convolutional models, combined with complementary low-level descriptors, are used to extract discriminative features in the proposed approach. A PageRank-based similarity propagation strategy is also used to narrow image ranking by leveraging similarity relationships across the globe. Evaluation is performed using standard retrieval measures, such as Mean Average Precision (mAP), Precision at K, Recall at K, and NDCG. The experimental results show that the proposed approach consistently improves performance across benchmark datasets. The framework boosts mAP by up to 8.6% over traditional fixed-weight fusion methods, while Precision@10 and NDCG@10 increase by 6.2% and 7.4%, respectively. The statistical analysis shows that these improvements are significant at the 95% confidence level, indicating that retrieval behavior is robust and reliable. These findings confirm the efficiency of entropy-driven adaptive fusion and ranking refinement in overcoming the major drawbacks of current CBIR systems, and the suggested framework is appropriate for large-scale image search in practice.

Forecasting geological cross-section ahead of tunnel face is an essential ingredient for tunnel design and construction. Geological analysis and drilling have been the most traditional approach for predicting tunnel ahead geological conditions. However, this practice is often subjective, and geological information retrieved from previous tunnel excavation in the same project has not been used quantitatively. In this study, a data-driven framework is proposed to sequentially develop geological cross-sections along planned tunnel trajectory conditioning on site-specific data and prior geological knowledge. The proposed framework dynamically and continuously incorporates geological information revealed from tunnel excavation as additional site-specific data, which provide first-hand direct geological information from the immediate past tunnel sections and can actually serve as the most relevant prior geological knowledge for forward prediction. All the prior geological knowledge is compiled as a site-specific training image database. When the actual geological cross-sections are revealed from tunnel excavation, the training image database is also updated for the next loop of tunnel ahead geological prediction. The proposed method is illustrated using data obtained from a real tunnelling project in Australia. Results indicate that the proposed method continuously provides accurate prediction of geological cross-sections along planned tunnel trajectory with quantified stratigraphic uncertainty.

Accurate optic disc (OD) segmentation is an important step in obtaining cup-to-disc ratio-based glaucoma screening using fundus imaging. It is a challenging task because of the subtle OD boundary, blood vessel occlusion and intensity inhomogeneity. In this Letter, the authors propose an improved version of the random walk algorithm for OD segmentation to tackle such challenges. The algorithm incorporates the mean curvature and Gabor texture energy features to define the new composite weight function to compute the edge weights. Unlike the deformable model-based OD segmentation techniques, the proposed algorithm remains unaffected by curve initialisation and local energy minima problem. The effectiveness of the proposed method is verified with DRIVE, DIARETDB1, DRISHTI-GS and MESSIDOR database images using the performance measures such as mean absolute distance, overlapping ratio, dice coefficient, sensitivity, specificity and precision. The obtained OD segmentation results and quantitative performance measures show robustness and superiority of the proposed algorithm in handling the complex challenges in OD segmentation.

New imaging technologies to identify food can reduce the reporting burden of participants but heavily rely on the quality of the food image databases to which they are linked to accurately identify food images. The objective of this study was to develop methods to create a food image database based on the most commonly consumed U.S. foods and those contributing the most to energy. The objective included using a systematic classification structure for foods based on the standardized United States Department of Agriculture (USDA) What We Eat in America (WWEIA) food classification system that can ultimately be used to link food images to a nutrition composition database, the USDA Food and Nutrient Database for Dietary Studies (FNDDS). The food image database was built using images mined from the web that were fitted with bounding boxes, identified, annotated, and then organized according to classifications aligning with USDA WWEIA. The images were classified by food category and subcategory and then assigned a corresponding USDA food code within the USDA’s FNDDS in order to systematically organize the food images and facilitate a linkage to nutrient composition. The resulting food image database can be used in food identification and dietary assessment.

Designing an automatic vehicle detection (AVD) system from still images or videos would be a useful tool to cater to the requirements of the traffic management system. Over the past few years, numerous databases have been developed for the use of researchers in this field of AVD. However, most of them are not acceptable in the Indian scenarios due to certain practical constraints like the road infrastructure, nature of congestion, and vehicle types commonly found in India. The aim of this research is to develop a still image database, named as JUVDsi v1 , which includes nine different types of vehicle classes collected through mobile phone cameras in various ways for designing an automated traffic management system. Identifying and analyzing the shortcomings of existing databases, the developed database presents an improvement to address such bottle-necks. Furthermore, the efficiency of this database is evaluated using an ensemble of three state-of-the-art deep learning architectures. At first, each vehicle in the scene images is localized and categorized. Five base object detection models, namely, YOLOv3, Faster-RCNN, RFCN, SSDv1 and SSDLitev2 are used. Finally, the Weighted Boxes Fusion technique is used as the ensemble method (ensemble of best three out of the five base learners), thereby enhancing the performance obtained by the individual object detection models. The database can be found at: https://github.com/JUVDsi/JUVD-Still-Image-database.git .