Belfast, United Kingdom
Belfast, United Kingdom

Time filter

Source Type

Jemec J.,University of Ljubljana | Pernus F.,University of Ljubljana | Pernus F.,Sensum Inc. | Likar B.,University of Ljubljana | And 2 more authors.
Optics Express | Year: 2014

In this paper, we propose a novel method for spectral and spatial calibration and resolution enhancement of hyperspectral images by a two-step procedure. The spectral and spatial variability of the hyperspectral imaging system response function is characterized by a global parametric model, which is derived from a pair of calibration images corresponding to an exactly defined calibration target and a set of gas-discharge lamps. A 2D Richardson-Lucy deconvolution-based algorithm is used to remove the distortions and enhance the resolution of subsequently acquired hyperspectral images. The results of the characterization and deconvolution process obtained by the proposed method are thoroughly evaluated by an independent set of exactly defined calibration and spectral targets, and compared to the existing state-of-the-art characterization method. The proposed method significantly improves the spectral and spatial coregistration and provides more than five-fold resolution enhancement in the spatial and two-fold resolution enhancement in the spectral domain. © 2014 Optical Society of America


Katrasnik J.,University of Ljubljana | Pernus F.,University of Ljubljana | Pernus F.,Sensum Inc. | Likar B.,University of Ljubljana | Likar B.,Sensum Inc.
Optics Express | Year: 2013

Near-infrared hyperspectral imaging is becoming a popular tool in various fields. In all imaging systems, proper illumination is crucial for attaining optimal image quality that is needed for the best performance of image analysis algorithms. In hyperspectral imaging, the acquired spectral signature has to be representative in all parts of the imaged object. Therefore, the whole object must be equally well illuminated-without shadows or specular reflections. As there are no restrictions imposed on the material and geometry of the object, the desired illumination of the object can only be achieved with completely diffuse illumination. In order to minimize shadows and specular reflections, the light illuminating the object must be spatially, angularly and spectrally uniform. The quality of illumination systems for hyperspectral imaging can therefore be assessed using spatial-intensity, spatial-spectral, angular-intensity and angular-spectral non-uniformity measures that are presented in this paper. Emphasis is given to the angular-intensity and angular-spectral non-uniformity measures, which are the most important contributions of this paper. The measures were defined on images of two reference targets-a flat, white diffuse reflectance target and a sphere grid target-acquired with an acousto-optic tunable filter (AOTF) based hyperspectral imaging system. The proposed measures were tested on a ring light and on a diffuse dome illumination system. © 2013 Optical Society of America.


Kosec M.,Sensum Inc. | Burmen M.,University of Ljubljana | Tomazevic D.,Sensum Inc. | Tomazevic D.,University of Ljubljana | And 4 more authors.
Optics Express | Year: 2013

A significant part of the uniformity degradation in the acquired hyperspectral images can be attributed to the coregistration distortions and spectrally and spatially dependent resolution arising from the misalignments and the operation principle of the spectrograph based hyperspectral imaging system. The aim of this study was the development and validation of a practical method for characterization of the geometric coregistration distortions and position dependent resolution. The proposed method is based on modeling the imaging system response to several affordable reference objects. The results of the characterization can be used for calibration of the acquired images or as a tool for assessment of the expected errors in various hyperspectral imaging systems. © 2013 Optical Society of America.


Burmen M.,University of Ljubljana | Pernus F.,University of Ljubljana | Pernus F.,Sensum Inc. | Likar B.,University of Ljubljana | Likar B.,Sensum Inc.
Applied Spectroscopy | Year: 2011

In this study, we propose and evaluate a method for spectral characterization of acousto-optic tunable filter (AOTF) hyperspectral imaging systems in the near-infrared (NIR) spectral region from 900 nm to 1700 nm. The proposed spectral characterization method is based on the SRM-2035 standard reference material, exhibiting distinct spectral features, which enables robust non-rigid matching of the acquired and reference spectra. The matching is performed by simultaneously optimizing the parameters of the AOTF tuning curve, spectral resolution, baseline, and multiplicative effects. In this way, the tuning curve (frequency-wavelength characteristics) and the corresponding spectral resolution of the AOTF hyperspectral imaging system can be characterized simultaneously. Also, the method enables simple spectral characterization of the entire imaging plane of hyperspectral imaging systems. The results indicate that the method is accurate and efficient and can easily be integrated with systems operating in diffuse reflection or transmission modes. Therefore, the proposed method is suitable for characterization, calibration, or validation of AOTF hyperspectral imaging systems. © 2011 Society for Applied Spectroscopy.


Spiclin Z.,University of Ljubljana | Spiclin Z.,Sensum Inc.
Elektrotehniski Vestnik/Electrotechnical Review | Year: 2015

Technology for spatial co-registration of pre-operative and intra-operative images is a crucial part of surgical image guidance systems. The pre-operative images are usually 3D, i.e. computed tomography, and used for diagnosis and planning, whereas the intra-operative imaging needs to be fast and unobtrusive, which renders the 2D X-ray fluoroscopy as the only suitable technique. The most important properties required for implementation of 3D-2D image registration into image-guidance systems are its computational time and robustness, while the accuracy of spatial alignment should be in the order of the image sampling step. These properties are mainly determined by a similarity measure (SM) between the 3D and 2D images. In this paper, we evaluate a 3D-2D registration method based on matching structural tensors with nine different SMs. The majority of evaluated SMs enable sufficiently accurate 3D-2D registration, while the most robust SMs were Bhattacharrya, Jensen-Bregman divergence, affine invariant and log-Euclidean distance. These four SMs achieved a registration success rate of 85% and capture range from 9 to 10 mm with respect to optimal 3D-2D registration. The first two of the four SMs enabled the fastest registration times around 0.4 seconds. Registration of 3D and 2D images based on these two SMs is accurate, robust and fast and, thus, feasible for implementation into surgical image-guidance systems.


Markelj P.,University of Ljubljana | Likar B.,University of Ljubljana | Likar B.,Sensum Inc. | Pernus F.,University of Ljubljana
Medical Physics | Year: 2010

Purpose: A new image database with a reference-based standardized evaluation methodology for objective evaluation and comparison of three-dimensional/two-dimensional (3D/2D) registration methods has been introduced. Methods: Computed tomography (CT) images of a male and female from the Visible Human Project were used and 16 subvolumes, each containing one of vertebrae T3-T12 and L1-L5 and the pelvis, were defined from the CTs. Six pairs of 2D fluoroscopic x-ray images from different views, showing the thoracic, lumbar, and pelvic regions, were rendered from the CT data using a ray-casting algorithm with an energy conversion function. Furthermore, a single 13-gauge needle was analytically simulated and projected onto the 2D images. By the novel standardized evaluation methodology, a 3D/2D registration method is evaluated by four evaluation criteria: Accuracy, reliability, robustness, and algorithm complexity. Results: To demonstrate the usefulness of the proposed data set and the standardized evaluation methodology, a part of the data set was used in an evaluation study of two gradient-based 3D/2D registration methods. It was shown that the use of a failure criterion to calculate the registration accuracy and reliability is not required, since all the information about a registration method can be determined from the estimated distribution of registration errors. Conclusions: The proposed simulated image data set with quite realistic synthetic 2D images, depicting soft tissues and outliers, is especially suitable for preliminary testing of 3D/2D registration algorithms. Since the aim of this article is to provide objective comparison and unbiased evaluation of 3D/2D registration methods, the standardized evaluation methodology is available upon request from the authors. © 2010 American Association of Physicists in Medicine.


Markelj P.,University of Ljubljana | Tomazevic D.,University of Ljubljana | Tomazevic D.,Sensum Inc. | Likar B.,University of Ljubljana | And 2 more authors.
Medical Image Analysis | Year: 2012

Registration of pre- and intra-interventional data is one of the key technologies for image-guided radiation therapy, radiosurgery, minimally invasive surgery, endoscopy, and interventional radiology. In this paper, we survey those 3D/2D data registration methods that utilize 3D computer tomography or magnetic resonance images as the pre-interventional data and 2D X-ray projection images as the intra-interventional data. The 3D/2D registration methods are reviewed with respect to image modality, image dimensionality, registration basis, geometric transformation, user interaction, optimization procedure, subject, and object of registration. © 2010 Elsevier B.V.


Grant
Agency: GTR | Branch: Innovate UK | Program: | Phase: Smart - Development of Prototype | Award Amount: 107.90K | Year: 2013

Sensum’s audience insight system provides ad agencies, market research firms, and broadcast media with an innovative way to accurately measure customer response to media. Current market research relies on focus groups’ verbal or written responses to questions before and after viewing media. This qualitative approach relies on cognitive processes where post-facto responses are consciously formulated. These responses are prone to self-editing and test biases that skew or distort the data, including moderator bias where the presence of a moderator or the test environment itself influences responses. Recent research in neuroscience has suggested that up to 95 percent of our purchase decision making actually takes place in the subconscious mind. Strong brands, e.g., excite parts of the brain associated with pleasure and reward and trigger physiological reactions. As physiological responses are involuntary, instantaneous, and may be measured quantitatively, they provide a better measure of the level of engagement and emotional response to stimuli while avoiding conscious cognition test biases. To date, no existing cost-effective solution is available to market researchers to measure subconscious emotional response. Sensum’s neuromarketing platform addresses this need by providing an affordable, portable system that simultaneously measures subconscious and conscious cognitive responses. Realtime physiological response is measured via a low-cost, non-intrusive, wearable wireless sensor. Sensor data is captured, processed, and displayed on a mobile platform, such as a tablet, that incorporates an integrated e-survey tool that poses questions during the test. Both subconscious and conscious cognitive responses can be recorded, mapped, and compared, providing deep insight into how audiences truly respond to the media. This allows development of media that is both more engaging and cost effective, resulting in higher return on investment for advertisers


Sensum, the emotions-based software solutions company, today launches the next-generation of its Sensum Insights neuromarketing solution which now includes facial-recognition, eye-tracking & implicit testing technology to help brands build a 360 degree view of audience's emotional responses to content, experiences and products. Sensum Insights is the first self-service product available on the market to include all of these capabilities. Brands and agencies have instinctively known for some time that appealing to a person's emotions enables them to better sell a product, create great experiences and shape brand loyalty. But now science and technology such as Sensum Insights is helping to prove and make more of this. Instead of relying exclusively on traditional market research methods based on conscious questioning and surveys, which only provide a singular point of view, new research tools that weave in biometric responses allow brands to build a 360-degree real-time view of the consumer's emotional journey. Sensum Insights is the world's first web-based and mobile enabled self- service platform that allows organisations to combine data from traditional market research methods with non-conscious data from wearable devices & biometric sensors to help organisations understand and engage their  audiences in deeper, more personal, emotive and exciting ways. Shane Keats, Director of Industry Marketing, Media and Entertainment at leading content delivery network and cloud services provider Akamai Technologies, wanted to understand the relationship between video quality of experience (QoE) and viewer satisfaction. "Our customers are in the business of telling great stories that generate great feeling.  We asked Sensum to investigate how differing video quality made consumers feel rationally and emotionally, explicitly and implicitly. By using Sensum Insights we were able to see the emotional impact of low and high quality video content delivery, and the associated impacts on various business models." Sensum Insights is web-based so can be accessed by anyone with a connected device anywhere in the world. The interface is user-friendly and intuitive so simple for both those running research projects and participants taking part to use. Gawain Morrison, CEO & Co-Founder, Sensum adds: "The ability to build a truly personalised relationship with consumers is what enables brands to not just survive, but thrive.  We've specifically developed Sensum Insights to help marketers, creative agencies & researchers be able to do this in the most efficient, cost-effective and in-depth way possible. The platform brings together insights from multiple sources to build the clearest 360-degree picture of an audience's emotional response in real-time…which in today's cut-throat world is invaluable." For more information on Sensum Insights please visit http://www.sensum.co Sensum is a emotions-based software solutions company that helps organisations build the clearest 360-degree picture of an audience's emotional response to content, products or experiences. We bring together the art and science of emotions with our creative expertise and technology. Our online platform Sensum Insights gathers emotional responses from audiences and turns them into actionable insights to help brands hone their products, user experiences, content, retail and immersive experiences. We work with leading brands such as the BBC, Red Bull Media House, Unilever, Jaguar, Cisco and Publicis.

Loading Sensum Inc. collaborators
Loading Sensum Inc. collaborators