MRMike Rogers

Mike Rogers

*This is an algorithmically generated author record based on publicly available information.

Mike Rogers has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Survey on Facial Wrinkles Detection and Inpainting: Datasets, Methods, and Challenges

    by Moi Hoon Yap, Nazre Batool, Choon-Ching Ng, Mike Rogers, Kevin Walker

    Automatic facial wrinkles detection and inpainting algorithms have gained attention of researchers in cosmetics, forensics and computer vision. The majority of current inpainting algorithms was implemented on the whole face, despite the fact that only imperfections need inpainting. In general, the definition of an imperfection is sign of ageing, spot, scar and freckles. This paper focuses on wrinkles as it is an obvious sign of ageing. We survey the computer vision techniques in facial wrinkles localisation from detection to inpainting. We present a comprehensive literature review on benchmark datasets, automated wrinkles detection algorithms and facial inpainting algorithms. Due to limited study on wrinkle inpainting, we inpaint the wrinkle regions using three state-of-the-art inpainting algorithms, namely flood-fill, Coherence Sensitivity Hashing and exemplar-based method. To assess the realism of inpainting results, we present the original and inpainted images to 40 participants, where they provide rating on the realism scale and age group of each image. The result shows that flood-fill method preserved the realism but there was no significant difference in age prediction. Finally, we conclude the paper by proposing some future directions to advance this field.


  • Robust and Accurate Registration of 2-D Electrophoresis Gels Using Point-Matching

    by Mike Rogers, Jim Graham

    Point-matching is a widely applied image registration method and many algorithms have been developed. Registration of 2-D electrophoresis gels is an important problem in biological research that presents many of the technical difficulties that beset point-matching: large numbers of points with variable densities, large nonrigid transformations between point sets, paucity of structural information and large numbers of unmatchable points (outliers) in either set. In seeking the most suitable algorithm for gel registration we have evaluated a number of approaches for accuracy and robustness in the face of these difficulties. Using synthetic images we test combinations of three algorithm components: correspondence assignment, distance metrics and image transformation. We show that a version of the iterated closest point (ICP) algorithm using a non-Euclidean distance metric and a robust estimation of transform parameters provides best performance, equalling SoftAssign in the presence of moderate image distortion, and providing superior robustness against large distortions and high outlier proportions. From this evaluation we develop a gel registration algorithm based on robust ICP and a novel distance metric combining Euclidean, shape context and image-related features. We demonstrate the accuracy of gel matching using synthetic distortions of real gels and show that robust estimation of transform parameters using M-estimators can enforce inverse consistency, ensuring that matching results are independent of the order of the images