Search

Abstract Automatic brain abnormality detection is a major challenge in medical image processing. Manual lesion delineation techniques are susceptible to subjective errors, and therefore, computer aided preliminary screening of a lesion is necessary. This study introduces an efficient and automated algorithm based on the symmetry of the brain structures in the two hemispheres for brain tumour segmentation using multimodal brain magnetic resonoce imaging. Symmetry is a vital clue for determining intensity‐based lesion difference in the two hemispheres of brain. A reliable method is proposed for extracting the cancerous region in order to improve the speed and accuracy of brain tumour segmentation. First, a symmetry plane is detected and then through features extracted from both sides of the brain, a similarity measure for comparing the hemisphere is defined. The cancerous region is extracted using similarity measurement, and the accuracy is improved using postprocessing operation. This algorithm is evaluated against the BRATS datasets including high‐ and low‐grade glioma brain tumours. The performance indices are calculated and comparative analysis is implemented as well. Experimental results demonstrate accuracy close to manual lesion demarcation with performance indices.

Abstract One of the main issues in colour image processing is changing objects' colour due to colour of illumination source. Colour constancy methods tend to modify overall image colour as if it was captured under natural light illumination. Without colour constancy, the colour would be an unreliable cue to object identity. Till now, many methods in colour constancy domain are presented. They are in two categories; statistical methods and learning‐based methods. This paper presents a new statistical weighted algorithm for illuminant estimation. Weights are adjusted to highlight two key factors in the image for illuminant estimation, that is contrast and brightness. The focus was on the convex part of the contrast stretching function to create the weights. Moreover, a novel partitioning mechanism in the colour domain that leads to improvement in efficiency is proposed. The proposed algorithm is evaluated on two benchmark linear image databases according to two evaluation metrics. The experimental results showed that it is competitive to the statistical state of the art methods. In addition to its low computational cost, it has the advantage of improving the efficiency of statistics‐based algorithms for dark images and images with low brightness contrast. Moreover, it is robust to camera change types.

In our digital age, data are generated constantly from public and private sources, social media platforms, and the Internet of Things. A significant portion of this information comes in the form of unstructured images and videos, such as the 95 million daily photos and videos shared on Instagram and the 136 billion images available on Google Images. Despite advances in image processing and analytics, the current state of the art lacks effective methods for discovering, linking, and comprehending image data. Consider, for instance, the images from a crime scene that hold critical information for a police investigation. Currently, no system can interactively generate a comprehensive narrative of events from the incident to the conclusion of the investigation. To address this gap in research, we have conducted a thorough systematic literature review of existing methods, from labeling and captioning to extraction, enrichment, and transforming image data into contextualized information and knowledge. Our review has led us to propose the vision of storytelling with image data, an innovative framework designed to address fundamental challenges in image data comprehension. In particular, we focus on the research problem of understanding image data in general and, specifically, curating, summarizing, linking, and presenting large amounts of image data in a digestible manner to users. In this context, storytelling serves as an appropriate metaphor, as it can capture and depict the narratives and insights locked within the relationships among data stored across different islands. Additionally, a story can be subjective and told from various perspectives, ranging from a highly abstract narrative to a highly detailed one.

Automatic image annotation (AIA) is an image retrieval mechanism to extract relative semantic tags from visual content. So far, the improvement of accuracy in newly developed such methods have been about 1 or 2% in the F1‐score and the architectures seem to have room for improvement. Therefore, the authors designed a more detailed architecture for AIA and suggested new algorithms for its main parts. The proposed architecture has three main parts: feature extraction, learning, and annotation. They designed a novel learning method using machine learning and probability bases. In the annotation part, they suggest a novel method that gains the maximum benefit from the learning part. The combination of the proposed architecture, algorithms, and novel ideas resulted in new accuracy milestones in F1‐score on most commonly used datasets. In their architecture, N+ measure which shows the number of tags with non‐zero recalls showed that they could recall all tags for IAPRTC‐12 and ESP‐Games datasets.

Abstract Real-world image classification, which aims to determine the semantic class of un-labeled images, is a challenging task. In this paper, we focus on two challenges of image classification and propose a method to address both of them simultaneously. The first challenge is that representing images by heterogeneous features, such as color, shape and texture, helps to provide better classification accuracy. The second challenge comes from dissimilarities in the visual appearance of images from the same class (intra class variance) and similarities between images from different classes (inter class relationship). In addition to these two challenges, we should note that the feature space of real-world images is highly complex so they cannot be linearly classified. The kernel trick is efficacious to classify them. This paper proposes a feature fusion based multiple kernel learning (MKL) model for image classification. By using multiple kernels extracted from multiple features, we address the first challenge. To provide a solution for the second challenge, we use the idea of a localized MKL by assigning separate local weights to each kernel. We employed spatial pyramid match (SPM) representation of images and computed kernel weights based on Χ 2kernel. Experimental results demonstrate that our proposed model has achieved promising results.

Nowadays, the number of digital images has increased so that the management of this volume of data needs an efficient system for browsing, categorising and searching. Automatic image annotation is designed for assigning tags to images for more accurate retrieval. Non‐negative matrix factorisation (NMF) is a traditional machine learning technique for decomposing a matrix into a set of basis and coefficients under the non‐negative constraints. In this study, the authors propose a two‐step algorithm for designing an automatic image annotation system that employs the NMF framework for its first step and a variant of K‐nearest neighbourhood as its second step. In the first step, a new multimodal NMF algorithm is proposed to extract the latent factors which reflect the content of images. This is done by jointly factorising the visual and textual data feature matrices so that they have close representation, although not necessarily the same. In the second step, after mapping images to the latent factors space a few tags are predicted for the new images based on a weighted average of similar data. They evaluated the performance of the proposed method and compared it to the state‐of‐the‐art literature. Comparison results demonstrate the effectiveness and potential of the proposed method in image annotation applications.