InfoSys

Information Systems Group > BI > FSE > RUG * Print * Search

Brain-Inspired Computing with Application to Medical, Forensic, Radio Astronomy, and First-Person Image Analysis

Summary

The focus of this research line is to develop computational models that are inspired by the phenomenon of inhibition in the visual system of the mammalian brain. The sub-topics that we address include:

  • Robustness to perturbations
  • Robustness to adversarial attacks
  • Sparse representation and energy efficiency

The algorithms that we develop are evaluated in various applications:

  • Large-scale medical image analysis
  • Large-scale radio astronomy image analysis
  • Forensic image analysis
  • First-person image analysis with wearable cameras
  • Face analysis

Participants

  • George Azzopardi
  • Jiapan Guo
  • Astone Shi
  • Xueyi Wang
  • Guru Swaroop Bennabhaktula
  • Anusha Aswath
  • Steven Ndung'u

Students

  • Amey Bhole
  • Derrick Timmerman
  • Joey Antonisse
  • Damiano Melotti

Journal Publications

  1. A. Bhole, S. S. Udmale, O. Falzon, G. Azzopardi (2021), CORF3D contour maps with application to Holstein cattle recognition from RGB and thermal images, Expert Systems with Applications, 116354. https://doi.org/10.1016/j.eswa.2021.116354
  2. C. Shi, J. J. Meijer, G. Azzopardi, G. F. H. Diercks, J. Guo, N. Petkov (2021), Use of convolutional neural networks for the detection of u-serrated patterns in direct immunofluorescence images to facilitate the diagnosis of epidermolysis bullosa acquisita, Journal of American Pathology, pp. 1520-1525, vol. 191 (9). https://doi.org/10.1016/j.ajpath.2021.05.024
  3. D. Chaves, E. Fidalgo, E. Alegre, R. Alaiz-Rodriguez, F. Janez-Martin, G. Azzopardi (2020), Assessment and Estimation of Face Detection Performance Based on Deep Learning for Forensic Applications, Sensors, 20(16), 4491. https://doi.org/10.3390/s20164491
  4. D. Melotti, K. Heimbach, A. Rodriguez-Sanchez, N. Strisciuglio, and G. Azzopardi (2020), “A robust contour detection operator with combined push-pull inhibition and surround suppression, Information Sciences, vol. 524, pp.229-240. https://doi.org/10.1016/j.ins.2020.03.026
  5. S. Ramachandran, N. Strisciuglio, A. Vinekar, R. John, and G. Azzopardi (2019), U-COSFIRE filters for vessel tortuosity quantification with application to automated diagnosis of retinopathy of prematurity, Neural Computing and Applications, vol. 32, pp. 12453–12468. https://doi.org/10.1007/s00521-019-04697-6
  6. N. Strisciuglio, G. Azzopardi, N. Petkov (2019), Inhibition-augmented operator for delineation of curvilinear structures, IEEE Transactions on Image Processing, vol. 28 (12). https://doi.org/10.1109/TIP.2019.2922096
  7. J. Guo, G. Azzopardi, C. Shi, N. M. Jansonius, N. Petkov (2019), Automatic determination of vertical cup-to-disc ratio in retinal fundus images for glaucoma screening, IEEE Access, vol. 7, pp. 8527-8541. https://doi.org/10.1109/ACCESS.2018.2890544
  8. C. Shi, D. Zillikens, E. Schmidt, G. Azzopardi, G.F.H. Diercksr, J. Guo, J.M. Meijer, M. Jonkman, N. Petkov (2019), Detection of u-serrated patterns in direct immunofluorescence images of autoimmune bullous diseases by inhibition-augmented COSFIRE filters, International Journal of Medical Informatics, vol. 122, pp. 27-36. https://doi.org/10.1016/j.ijmedinf.2018.11.007
  9. G. Azzopardi, A. Greco, A. Saggese, M. Vento (2018), Fusion of domain-specific and trainable features for gender recognition from face images, IEEE Access, vol. 6(1), pp.24171-24183. https://doi.org/10.1109/ACCESS.2018.2823378

Publications in Conference Proceedings

  1. G. S. Bennabhaktula, J. Antonisse, G. Azzopardi (2021), On Improving Generalization of CNN-Based Image Classification with Delineation Maps Using the CORF Push-Pull Inhibition Operator. In: Tsapatsoulis N., Panayides A., Theocharides T., Lanitis A., Pattichis C., Vento M. (eds) Computer Analysis of Images and Patterns. CAIP 2021. Lecture Notes in Computer Science, vol 13052. Springer, Cham. https://doi.org/10.1007/978-3-030-89128-2_42
  2. J. Velasco-Mata, D. Chaves, V. De Mata, M. W. Al-Nabki, E. Fidalgo, E. Alegre and G. Azzopardi (2021), Development of a Hardware Benchmark for Forensic Face Detection Applications, Cybersecurity Research National Conferences (JNIC), INCIBE, N.º 34: Investigación en Ciberseguridad. Jornadas Nacionales de Investigación en Ciberseguridad ISBN: 978-84-9044-463-4; Editores: Manuel A. Serrano, Eduardo Fernández-Medina, Cristina Alcaraz, Noemí de Castro, Guillermo Calvo.
  3. R. Biswas, D. Chaves, F. Jáñez-Martino, P. Blanco-Medina, E. Fidalgo, C. García-Olalla, G. Azzopardi (2021), Reinforcement of age estimation in forensic tools to detect Child Sexual Exploitation Material, Cybersecurity Research National Conferences (JNIC), INCIBE, N.º 34: Investigación en Ciberseguridad. Jornadas Nacionales de Investigación en Ciberseguridad ISBN: 978-84-9044-463-4; Editores: Manuel A. Serrano, Eduardo Fernández-Medina, Cristina Alcaraz, Noemí de Castro, Guillermo Calvo.
  4. X. Wang, E. Talavera, D. Karastoyanova, G. Azzopardi (2021) Fall Detection and Recognition from Egocentric Visual Data: A Case Study. In: Del Bimbo A. et al. (eds) Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Lecture Notes in Computer Science, vol 12661. Springer, Cham. https://doi.org/10.1007/978-3-030-68763-2_33
  5. D. Timmerman, G. S. Bennabhaktula, E. Alegre, G. Azzopardi (2020), Video Camera Identification from Sensor Pattern Noise with a Constrained ConvNet, In Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2021), pages 417-425.
  6. G. S. Bennabhaktula, E. Alegre, D. Karastoyanova, G. Azzopardi (2020), Matching images with similarity learning by convolutional neural networks that exploit the underlying camera sensor pattern noise, ICPRAM2020, Valletta (Malta). https://doi.org/10.5220/0009155505780584
  7. A. Bhole, O. Falzon, M. Biehl, G. Azzopardi (2019), A Computer Vision Pipeline that Uses Thermal and RGB Images for the Recognition of Holstein Cattle, CAIP2019, Salerno (Italy). https://doi.org/10.1007/978-3-030-29891-3_10
  8. A. Kind, G. Azzopardi (2019), An Explainable AI-Based Computer Aided Detection System for Diabetic Retinopathy Using Retinal Fundus Images, CAIP2019, Salerno (Italy). https://doi.org/10.1007/978-3-030-29888-3_37
  9. F. Simanjuntak, G. Azzopardi (2019), Fusion of CNN- and COSFIRE-Based Features with Application to Gender Recognition from Face Images, Advances in Intelligent Systems and Computing – Proceedings of the 1st International Computer Vision Conference (CVC), Vegas, USA.
  10. W. Tabone, M.H.F. Wilkinson, A.E.J.V. Gaalen, J. Georgiadis, G. Azzopardi (2019), Alpha-Tree Segmentation of Human Anatomical Photographic Imagery, Applications of Intelligent Systems – Proceedings of the 2nd International APPIS Conference, Gran Canaria Spain. https://doi.org/10.1145/3309772.3309776
  11. L. M. Demajo, K. Guillaumier, G. Azzopardi (2019), Age Group Recognition from Face Images using a Fusion of CNN- and COSFIRE-based Features, Applications of Intelligent Systems – Proceedings of the 2nd International APPIS Conference, Gran Canaria Spain.
  12. N. Strisciuglio, G. Azzopardi, N. Petkov (2018), Robust curvilinear detection operator, ECCVW Proceedings.
  13. G. Azzopardi, P. Foggia, A. Greco, A. Saggese, M. Vento (2018), Gender recognition from face images using trainable shape and colour features, ICPR, Beijing. https://doi.org/10.1109/ICPR.2018.8545771
  14. A. Bonnici, D. Bugeja, G, Azzopardi (2018), Vectorisation of sketches with shadows and shading using COSFIRE filters, DocEng, Halifax. https://doi.org/10.1145/3209280.3209525
  15. A. Bonnici, J. Abela, N. Zammit, G. Azzopardi (2018), Localisation, Recognition and Expression of Ornaments in Music Scores, DocEng, Halifax. https://doi.org/10.1145/3209280.3209536
  16. A. Apap, L. Fernández-Robles and G. Azzopardi (2018), Person Identification with Retinal Fundus Biometric Analysis Using COSFIRE Filters”, Applications of Intelligent Systems – Proceedings of the 1st International APPIS Conference 2018, Frontiers in Artificial Intelligence and Applications 310 (2018), 10-18 . IOS Press, Amsterdam.
  17. J. Buhagiar, N. Strisciuglio, N. Petkov and G. Azzopardi (2018), Automatic Segmentation of Indoor and Outdoor Scenes from Visual Lifelogging, Applications of Intelligent Systems – Proceedings of the 1st International APPIS Conference 2018, Frontiers in Artificial Intelligence and Applications 310, 194-202 . IOS Press, Amsterdam.
  18. A. Rodriguez-Sanchez, D. Chea, G. Azzopardi, S. Stabinger (2017), A deep learning approach for detecting and correcting highlights in endoscopic images, International Conference on Image Processing Theory, Tools and Applications (IPTA), Montreal, Canada. https://doi.org/10.1109/IPTA.2017.8310082
  19. N. Strisciuglio, G. Azzopardi, N. Petkov (2017), Curvilinear detection with B-COSFIRE Filters: A case study on crack delineation, Proceedings of the 17th International Conference on Computer Analysis of Images and Patterns (CAIP), in print, Ystad, Sweden. https://doi.org/10.1007/978-3-319-64689-3_9
  20. G. Azzopardi, Antonio Greco, Alessia Saggese, M. Vento (2017), Fast gender recognition in videos using a novel descriptor based on the gradient magnitudes of facial landmarks, 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), in print, Lecce, Italy. https://doi.org/10.1109/AVSS.2017.8078525

Poster presentation in Conferences

  1. A. Aswath, B. Giepmans, D. Karastoyanova, G. Azzopardi (2021), “Detection of mitochondria in large electron microscopy images”, ICTOpen

Data Sets

  1. A. Bhole, S. S. Udmale, O. Falzon, G. Azzopardi (2021), "Recognition of Holstein Cattle with Thermal and RGB images", https://doi.org/10.34894/7M108F
    • This data set was collected from the Dairy Campus in Leeuwarden (The Netherlands) with a FLIR E6 thermal camera over a period of 9 days. It consists of 3694 images of 383, with each cow represented with an average of 9 images. Each snapshot created two images; 1) RGB and ii) Temperature. The image filenames are in the format [cow_id-4 digits]_[day no-1 digit]_[counter-1 digit]. The timestamp.xlsx file indicates the day number (day 1 to day 9) of when an image in the data set was collected. This allows to design and run leave-one day-out cross validation, the same as we did in our paper. Here is the link to the scripts that reproduce the results reported in the paper, and the following is the link to the GitHub repository that contains all the scripts.
  2. J. Guo; G. Azzopardi, C. Shi, N. Jansonius, N. Petkov (2021), "Labelled Dataset of Retinal Images for Glaucoma detection", https://doi.org/10.34894/H2SZSO
  3. X. Wang, E. Talavera, D. Karastoyanova, G. Azzopardi (2020), "Fall detection and recognition from egocentric visual data: A case study", https://doi.org/10.34894/3DV8BF
    • This data set contains egocentric videos from two cameras attached to the waist and chest of one volunteer. The contents of the videos contain indoor and outdoor scenes and do not contain people. The data set was compiled for the evaluation of a novel fall detection system using ego centric visual data.