David Dueñas, Mostafa Kamal, & Petia Radeva. (2023). Efficient Deep Learning Ensemble for Skin Lesion Classification. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (pp. 303–314).
Abstract: Vision Transformers (ViTs) are deep learning techniques that have been gaining in popularity in recent years.
In this work, we study the performance of ViTs and Convolutional Neural Networks (CNNs) on skin lesions classification tasks, specifically melanoma diagnosis. We show that regardless of the performance of both architectures, an ensemble of them can improve their generalization. We also present an adaptation to the Gram-OOD* method (detecting Out-of-distribution (OOD) using Gram matrices) for skin lesion images. Moreover, the integration of super-convergence was critical to success in building models with strict computing and training time constraints. We evaluated our ensemble of ViTs and CNNs, demonstrating that generalization is enhanced by placing first in the 2019 and third in the 2020 ISIC Challenge Live Leaderboards
(available at https://challenge.isic-archive.com/leaderboards/live/).
|
Reuben Dorent, Aaron Kujawa, Marina Ivory, Spyridon Bakas, Nikola Rieke, Samuel Joutard, et al. (2023). CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation. MIA - Medical Image Analysis, 83, 102628.
Abstract: Domain Adaptation (DA) has recently raised strong interests in the medical imaging community. While a large variety of DA techniques has been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality DA. The challenge's goal is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are performed using contrast-enhanced T1 (ceT1) MRI. However, there is growing interest in using non-contrast sequences such as high-resolution T2 (hrT2) MRI. Therefore, we created an unsupervised cross-modality segmentation benchmark. The training set provides annotated ceT1 (N=105) and unpaired non-annotated hrT2 (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137). A total of 16 teams submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice – VS:88.4%; Cochleas:85.7%) and close to full supervision (median Dice – VS:92.5%; Cochleas:87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image.
Keywords: Domain Adaptation; Segmen tation; Vestibular Schwnannoma
|
M. Danelljan, Fahad Shahbaz Khan, Michael Felsberg, & Joost Van de Weijer. (2014). Adaptive color attributes for real-time visual tracking. In 27th IEEE Conference on Computer Vision and Pattern Recognition (pp. 1090–1097).
Abstract: Visual tracking is a challenging problem in computer vision. Most state-of-the-art visual trackers either rely on luminance information or use simple color representations for image description. Contrary to visual tracking, for object
recognition and detection, sophisticated color features when combined with luminance have shown to provide excellent performance. Due to the complexity of the tracking problem, the desired color feature should be computationally
efficient, and possess a certain amount of photometric invariance while maintaining high discriminative power.
This paper investigates the contribution of color in a tracking-by-detection framework. Our results suggest that color attributes provides superior performance for visual tracking. We further propose an adaptive low-dimensional
variant of color attributes. Both quantitative and attributebased evaluations are performed on 41 challenging benchmark color sequences. The proposed approach improves the baseline intensity-based tracker by 24% in median distance precision. Furthermore, we show that our approach outperforms
state-of-the-art tracking methods while running at more than 100 frames per second.
|
Mariella Dimiccoli, Jean-Pascal Jacob, & Lionel Moisan. (2016). Particle detection and tracking in fluorescence time-lapse imaging: a contrario approach. MVAP - Journal of Machine Vision and Applications, 27, 511–527.
Abstract: In this work, we propose a probabilistic approach for the detection and the
tracking of particles on biological images. In presence of very noised and poor
quality data, particles and trajectories can be characterized by an a-contrario
model, that estimates the probability of observing the structures of interest
in random data. This approach, first introduced in the modeling of human visual
perception and then successfully applied in many image processing tasks, leads
to algorithms that do not require a previous learning stage, nor a tedious
parameter tuning and are very robust to noise. Comparative evaluations against
a well established baseline show that the proposed approach outperforms the
state of the art.
Keywords: particle detection; particle tracking; a-contrario approach; time-lapse fluorescence imaging
|
|
Ferran Diego. (2007). Alignment of Videos Recorded from Moving Vehicles.
|
Mariella Dimiccoli. (2016). Figure-ground segregation: A fully nonlocal approach. VR - Vision Research, 126, 308–317.
Abstract: We present a computational model that computes and integrates in a nonlocal fashion several configural cues for automatic figure-ground segregation. Our working hypothesis is that the figural status of each pixel is a nonlocal function of several geometric shape properties and it can be estimated without explicitly relying on object boundaries. The methodology is grounded on two elements: multi-directional linear voting and nonlinear diffusion. A first estimation of the figural status of each pixel is obtained as a result of a voting process, in which several differently oriented line-shaped neighborhoods vote to express their belief about the figural status of the pixel. A nonlinear diffusion process is then applied to enforce the coherence of figural status estimates among perceptually homogeneous regions. Computer simulations fit human perception and match the experimental evidence that several cues cooperate in defining figure-ground segregation. The results of this work suggest that figure-ground segregation involves feedback from cells with larger receptive fields in higher visual cortical areas.
Keywords: Figure-ground segregation; Nonlocal approach; Directional linear voting; Nonlinear diffusion
|
Katerine Diaz, & Francesc J. Ferri. (2013). Extensiones del método de vectores comunes discriminantes Aplicadas a la clasificación de imágenes.
Abstract: Los métodos basados en subespacios son una herramienta muy utilizada en aplicaciones de visión por computador. Aquí se presentan y validan algunos algoritmos que hemos propuesto en este campo de investigación. El primer algoritmo está relacionado con una extensión del método de vectores comunes discriminantes con kernel, que reinterpreta el espacio nulo de la matriz de dispersión intra-clase del conjunto de entrenamiento para obtener las características discriminantes. Dentro de los métodos basados en subespacios existen diferentes tipos de entrenamiento. Uno de los más populares, pero no por ello uno de los más eficientes, es el aprendizaje por lotes. En este tipo de aprendizaje, todas las muestras del conjunto de entrenamiento tienen que estar disponibles desde el inicio. De este modo, cuando nuevas muestras se ponen a disposición del algoritmo, el sistema tiene que ser reentrenado de nuevo desde cero. Una alternativa a este tipo de entrenamiento es el aprendizaje incremental. Aquí se proponen diferentes algoritmos incrementales del método de vectores comunes discriminantes.
|
Ferran Diego. (2011). Probabilistic Alignment of Video Sequences Recorded by Moving Cameras (Joan Serrat, Ed.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Video alignment consists of integrating multiple video sequences recorded independently into a single video sequence. This means to register both in time (synchronize
frames) and space (image registration) so that the two videos sequences can be fused
or compared pixel–wise. In spite of being relatively unknown, many applications today may benefit from the availability of robust and efficient video alignment methods.
For instance, video surveillance requires to integrate video sequences that are recorded
of the same scene at different times in order to detect changes. The problem of aligning videos has been addressed before, but in the relatively simple cases of fixed or rigidly attached cameras and simultaneous acquisition. In addition, most works rely
on restrictive assumptions which reduce its difficulty such as linear time correspondence or the knowledge of the complete trajectories of corresponding scene points on the images; to some extent, these assumptions limit the practical applicability of the solutions developed until now. In this thesis, we focus on the challenging problem of aligning sequences recorded at different times from independent moving cameras following similar but not coincident trajectories. More precisely, this thesis covers four studies that advance the state-of-the-art in video alignment. First, we focus on analyzing and developing a probabilistic framework for video alignment, that is, a principled way to integrate multiple observations and prior information. In this way, two different approaches are presented to exploit the combination of several purely visual features (image–intensities, visual words and dense motion field descriptor), and
global positioning system (GPS) information. Second, we focus on reformulating the
problem into a single alignment framework since previous works on video alignment
adopt a divide–and–conquer strategy, i.e., first solve the synchronization, and then
register corresponding frames. This also generalizes the ’classic’ case of fixed geometric transform and linear time mapping. Third, we focus on exploiting directly the
time domain of the video sequences in order to avoid exhaustive cross–frame search.
This provides relevant information used for learning the temporal mapping between
pairs of video sequences. Finally, we focus on adapting these methods to the on–line
setting for road detection and vehicle geolocation. The qualitative and quantitative
results presented in this thesis on a variety of real–world pairs of video sequences show that the proposed method is: robust to varying imaging conditions, different image
content (e.g., incoming and outgoing vehicles), variations on camera velocity, and
different scenarios (indoor and outdoor) going beyond the state–of–the–art. Moreover, the on–line video alignment has been successfully applied for road detection and
vehicle geolocation achieving promising results.
|
Katerine Diaz, Aura Hernandez-Sabate, & Antonio Lopez. (2016). A reduced feature set for driver head pose estimation. ASOC - Applied Soft Computing, 45, 98–107.
Abstract: Evaluation of driving performance is of utmost importance in order to reduce road accident rate. Since driving ability includes visual-spatial and operational attention, among others, head pose estimation of the driver is a crucial indicator of driving performance. This paper proposes a new automatic method for coarse and fine head's yaw angle estimation of the driver. We rely on a set of geometric features computed from just three representative facial keypoints, namely the center of the eyes and the nose tip. With these geometric features, our method combines two manifold embedding methods and a linear regression one. In addition, the method has a confidence mechanism to decide if the classification of a sample is not reliable. The approach has been tested using the CMU-PIE dataset and our own driver dataset. Despite the very few facial keypoints required, the results are comparable to the state-of-the-art techniques. The low computational cost of the method and its robustness makes feasible to integrate it in massive consume devices as a real time application.
Keywords: Head pose estimation; driving performance evaluation; subspace based methods; linear regression
|
Hamdi Dibeklioglu, M.O. Hortas, I. Kosunen, P. Zuzánek, Albert Ali Salah, & Theo Gevers. (2011). Design and implementation of an affect-responsive interactive photo frame. JMUI - Journal on Multimodal User Interfaces, 81–95.
Abstract: This paper describes an affect-responsive interactive photo-frame application that offers its user a different experience with every use. It relies on visual analysis of activity levels and facial expressions of its users to select responses from a database of short video segments. This ever-growing database is automatically prepared by an offline analysis of user-uploaded videos. The resulting system matches its user’s affect along dimensions of valence and arousal, and gradually adapts its response to each specific user. In an extended mode, two such systems are coupled and feed each other with visual content. The strengths and weaknesses of the system are assessed through a usability study, where a Wizard-of-Oz response logic is contrasted with the fully automatic system that uses affective and activity-based features, either alone, or in tandem.
|
Arka Ujjal Dey, Suman Ghosh, Ernest Valveny, & Gaurav Harit. (2021). Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding. PRL - Pattern Recognition Letters, 149, 164–171.
Abstract: Images with visual and scene text content are ubiquitous in everyday life. However, current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper, we propose to jointly use scene text and visual channels for robust semantic interpretation of images. We do not only extract and encode visual and scene text cues, but also model their interplay to generate a contextual joint embedding with richer semantics. The contextual embedding thus generated is applied to retrieval and classification tasks on multimedia images, with scene text content, to demonstrate its effectiveness. In the retrieval framework, we augment our learned text-visual semantic representation with scene text cues, to mitigate vocabulary misses that may have occurred during the semantic embedding. To deal with irrelevant or erroneous recognition of scene text, we also apply query-based attention to our text channel. We show how the multi-channel approach, involving visual semantics and scene text, improves upon state of the art.
|
Arka Ujjal Dey, Suman Ghosh, & Ernest Valveny. (2018). Don't only Feel Read: Using Scene text to understand advertisements. In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.
Abstract: We propose a framework for automated classification of Advertisement Images, using not just Visual features but also Textual cues extracted from embedded text. Our approach takes inspiration from the assumption that Ad images contain meaningful textual content, that can provide discriminative semantic interpretetion, and can thus aid in classifcation tasks. To this end, we develop a framework using off-the-shelf components, and demonstrate the effectiveness of Textual cues in semantic Classfication tasks.
|
Marta Diez-Ferrer, Debora Gil, Cristian Tebe, & Carles Sanchez. (2018). Positive Airway Pressure to Enhance Computed Tomography Imaging for Airway Segmentation for Virtual Bronchoscopic Navigation. RES - Respiration, 96(6), 525–534.
Abstract: Abstract
RATIONALE:
Virtual bronchoscopic navigation (VBN) guidance to peripheral pulmonary lesions is often limited by insufficient segmentation of the peripheral airways.
OBJECTIVES:
To test the effect of applying positive airway pressure (PAP) during CT acquisition to improve segmentation, particularly at end-expiration.
METHODS:
CT acquisitions in inspiration and expiration with 4 PAP protocols were recorded prospectively and compared to baseline inspiratory acquisitions in 20 patients. The 4 protocols explored differences between devices (flow vs. turbine), exposures (within seconds vs. 15-min) and pressure levels (10 vs. 14 cmH2O). Segmentation quality was evaluated with the number of airways and number of endpoints reached. A generalized mixed-effects model explored the estimated effect of each protocol.
MEASUREMENTS AND MAIN RESULTS:
Patient characteristics and lung function did not significantly differ between protocols. Compared to baseline inspiratory acquisitions, expiratory acquisitions after 15 min of 14 cmH2O PAP segmented 1.63-fold more airways (95% CI 1.07-2.48; p = 0.018) and reached 1.34-fold more endpoints (95% CI 1.08-1.66; p = 0.004). Inspiratory acquisitions performed immediately under 10 cmH2O PAP reached 1.20-fold (95% CI 1.09-1.33; p < 0.001) more endpoints; after 15 min the increase was 1.14-fold (95% CI 1.05-1.24; p < 0.001).
CONCLUSIONS:
CT acquisitions with PAP segment more airways and reach more endpoints than baseline inspiratory acquisitions. The improvement is particularly evident at end-expiration after 15 min of 14 cmH2O PAP. Further studies must confirm that the improvement increases diagnostic yield when using VBN to evaluate peripheral pulmonary lesions.
Keywords: Multidetector computed tomography; Bronchoscopy; Continuous positive airway pressure; Image enhancement; Virtual bronchoscopic navigation
|
Hamdi Dibeklioglu, Theo Gevers, & Albert Ali Salah. (2012). Are You Really Smiling at Me? Spontaneous versus Posed Enjoyment Smiles. In 12th European Conference on Computer Vision (Vol. 7574, pp. 525–538). LNCS. Springer Berlin Heidelberg.
Abstract: Smiling is an indispensable element of nonverbal social interaction. Besides, automatic distinction between spontaneous and posed expressions is important for visual analysis of social signals. Therefore, in this paper, we propose a method to distinguish between spontaneous and posed enjoyment smiles by using the dynamics of eyelid, cheek, and lip corner movements. The discriminative power of these movements, and the effect of different fusion levels are investigated on multiple databases. Our results improve the state-of-the-art. We also introduce the largest spontaneous/posed enjoyment smile database collected to date, and report new empirical and conceptual findings on smile dynamics. The collected database consists of 1240 samples of 400 subjects. Moreover, it has the unique property of having an age range from 8 to 76 years. Large scale experiments on the new database indicate that eyelid dynamics are highly relevant for smile classification, and there are age-related differences in smile dynamics.
|
Manisha Das, Deep Gupta, Petia Radeva, & Ashwini M. Bakde. (2021). Optimized CT-MR neurological image fusion framework using biologically inspired spiking neural model in hybrid ℓ1 - ℓ0 layer decomposition domain. BSPC - Biomedical Signal Processing and Control, 68, 102535.
Abstract: Medical image fusion plays an important role in the clinical diagnosis of several critical neurological diseases by merging complementary information available in multimodal images. In this paper, a novel CT-MR neurological image fusion framework is proposed using an optimized biologically inspired feedforward neural model in two-scale hybrid ℓ1 − ℓ0 decomposition domain using gray wolf optimization to preserve the structural as well as texture information present in source CT and MR images. Initially, the source images are subjected to two-scale ℓ1 − ℓ0 decomposition with optimized parameters, giving a scale-1 detail layer, a scale-2 detail layer and a scale-2 base layer. Two detail layers at scale-1 and 2 are fused using an optimized biologically inspired neural model and weighted average scheme based on local energy and modified spatial frequency to maximize the preservation of edges and local textures, respectively, while the scale-2 base layer gets fused using choose max rule to preserve the background information. To optimize the hyper-parameters of hybrid ℓ1 − ℓ0 decomposition and biologically inspired neural model, a fitness function is evaluated based on spatial frequency and edge index of the resultant fused image obtained by adding all the fused components. The fusion performance is analyzed by conducting extensive experiments on different CT-MR neurological images. Experimental results indicate that the proposed method provides better-fused images and outperforms the other state-of-the-art fusion methods in both visual and quantitative assessments.
|
