Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
Portfolio item number 3
Short description of portfolio item number 3
publications
Deep-based quality assessment of medical images through domain adaptation
Published in 2022 IEEE International Conference on Image Processing (ICIP), 2022
Predicting the quality of multimedia content is often needed in different fields. In some applications, quality met rics are crucial with a high impact, and can affect decision making such as diagnosis from medical multimedia. In thispaper, we focus on such applications by proposing an efficient and shallow model for predicting the quality of medical images without reference from a small amount of annotated data. Our model is based on convolution self-attention that aims to model complex representation from relevant local characteristics of images, which itself slide over the image to interpolate the global quality score. We also apply domain adaptation learning in unsupervised and semi-supervised manner. The proposed model is evaluated through a dataset composed of several images and their corresponding subjective scores. The obtained results showed the efficiency of the proposed method, but also, the relevance of the applying domain adaptation to generalize over different multimedia domains regarding the downstream task of perceptual quality prediction.
Download here
Automatic diagnosis of knee osteoarthritis severity using Swin transformer
Published in 20th International Conference on Content-based Multimedia Indexing (CBMI), 2023
Knee osteoarthritis (KOA) is a widespread condition that can cause chronic pain and stiffness in the knee joint. Early detection and diagnosis are crucial for successful clinical intervention and man agement to prevent severe complications, such as loss of mobility. In this paper, we propose an automated approach that employs the Swin Transformer to predict the severity of KOA. Our model uses publicly available radiographic datasets with Kellgren and Lawrence scores to enable early detection and severity assessment. Toimprovetheaccuracyofourmodel,weemployamulti-prediction head architecture that utilizes multi-layer perceptron classifiers. Additionally, we introduce a novel training approach that reduces the data drift between multiple datasets to ensure the generalization ability of the model. The results of our experiments demonstrate the effectiveness and feasibility of our approach in predicting KOA severity accurately.
Download here
Do digital images tell the truth?
Published in Digital Image Security, 2024
Since the advent of digital cameras, many image editing tools have spread and allowed everyday users to modify picture content. Image filtering and retouching are broadly used to enhance color, contrast, and brightness to improve pictures’ aesthetics. Going deeper into image editing, Copy Move is considered one of the most popular alterations in the pixel domain. It consists of copying and pasting a portion of pixels onto another area in the same digital image. Having counterfeited pictures travel all over the Internet is pretty usual nowadays. However, spotting Copy Move is not straightforward to human eyes, as editing tools have achieved such high accuracy and detail. That is often used for two reasons: fun or criminal purposes. The former represents a way to hide or add multiple copies of an object, a face, or whatever lets users have fun. In that case, the latter undermines the trustworthiness of digital images as proof of something taken from a visual scene. This chapter surveys this field’s SOTA (state-of-the-art) methods by accounting for image features, approaches, and datasets used for experimental campaigns. In particular, low-level image processing, machine learning, and deep learning methods have been analyzed and compared against some publicly available datasets, including different tampering transformations, such as translation, rotation, and scaling. Finally, some considerations are discussed on the pros and cons of SOTA methods.
Download here
Shifting Focus: From Global Semantics to Local Prominent Features in Swin-Transformer for Knee Osteoarthritis Severity Assessment
Published in 32nd European Signal Processing Conference EUSIPCO 2024, 2024
Conventional imaging diagnostics frequently encounter bottlenecks due to manual inspection, which can lead to delays and inconsistencies. Although deep learning offers a pathway to au tomation and enhanced accuracy, foundational models in com puter vision often emphasize global context at the expense of lo cal details, which are vital for medical imaging diagnostics. To address this, we harness the Swin Transformer’s capacity to dis cern extended spatial dependencies within images through the hierarchical framework. Our novel contribution lies in refining local feature representations, orienting them specifically toward the final distribution of the classifier. This method ensures that local features are not only preserved but are also enriched with task-specific information, enhancing their relevance and detail at every hierarchical level. By implementing this strategy, our model demonstrates significant robustness and precision, as ev idenced by extensive validation of two established benchmarks for Knee OsteoArthritis (KOA) grade classification. Thesere sults highlight our approach’s effectiveness and its promising implications for the future of medical imaging diagnostics.
Download here
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.