Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
4 results
Search Results
Item Cell tracking using particle filters and level sets(2013) Vishwanath, B.; Seelamantula, C.S.We propose an algorithm to track moving cells and microbes in a video. A major challenge in tracking living cells is that their movement is often nonlinear which causes problems in case of approaches using the generic particle filter (GPF) framework. In order to overcome this problem, we propose the use of an auxiliary particle filtering (APF) algorithm with dynamic variance adaptation of the posterior distribution to account for nonlinear movements. The object of interest in each frame is segmented using level sets. The proposed tracking algorithm is tested on real data and the tracking performance is compared with that of GPF and APF without dynamic variance adaptation. Experimental results show that the proposed algorithm tracks more accurately compared to GPF and APF without variance adaption, with lesser number of particles, thereby reducing the running time. © 2013 IEEE.Item FRI Modelling of Fourier Descriptors(Institute of Electrical and Electronics Engineers Inc., 2019) Kamath, A.J.; Rudresh, S.; Seelamantula, C.S.Fourier descriptors are used to parametrically represent closed contours. In practice, a finite set of Fourier descriptors can model a large class of smooth contours. In this paper, we propose a method for estimating the Fourier descriptors of a given contour from its partial samples. We take a sampling-theoretic approach to model the x and y coordinate functions of the shape and express them as a sum of weighted complex exponentials, which belong to the class of finite-rate-of-innovation (FRI) signals. The weights represent the Fourier descriptors of the shape. We use the FRI framework to estimate the shape parameters reliably from noisy and partial measurements. We model non-uniformities in sampling using the sampling jitter model and employ a prefiltering process to reduce the effect of measurement noise and jitter. The average sampling interval is estimated by a block annihilating filter, which is then followed by the estimation of Fourier descriptors using least-squares fitting. We demonstrate the robustness of the proposed algorithm to noise and sampling jitter. Monte Carlo performance analysis shows that the variances of the estimators are close to the Cramér-Rao lower bounds. We present results for outlining shapes in synthetic as well as real images. © 2019 IEEE.Item Addressing Diffusion Model Based Counter-Forensic Image Manipulation for Synthetic Image Detection(Association for Computing Machinery, 2024) Herur, A.N.; Santhosh, V.; Shetty, N.; Seelamantula, C.S.With the rapid development of modern generative models, the need for an automated synthetic image detection process has never been greater. Recent works in the field of synthetic image detection focus on improving out-of-distribution (OoD) classification performance and robustness to common image pre-processing techniques. However, in this work, we intend to explore the nature of an intricate counter-forensic attack, i.e., the reconstruction of real images with Diffusion Model autoencoders, which could be used to adversely affect the performance of modern synthetic image detection algorithms. We present a variety of experiments to study the nature of this counter-forensic attack and use the inferences from these experiments to develop multiple algorithms to detect such reconstructed images while attempting to detect real and purely synthetic images accurately. To do so, we make use of trained classifiers that can detect real images, autoencoder-reconstructed images, and purely synthetic images. Furthermore, we combine these techniques to build a novel ensemble algorithm that competes with state-of-the-art (SoTA) algorithms in the ‘Real vs. Fake’ image detection task, while detecting autoencoder reconstructed images accurately, attaining an accuracy of 99.2% in the multiclass setting. © 2024 Copyright held by the owner/author(s).Item Some Intriguing Observations on the Learnt Matrices in Deep Unfolded Networks(Institute of Electrical and Electronics Engineers Inc., 2025) Nareddy, K.K.R.; Perumal, I.; Seelamantula, C.S.Deep-unfolded networks (DUNs) have set new performance benchmarks in fields such as compressed sensing, image restoration, and wireless communications. DUNs are built from conventional iterative algorithms, where an iteration is transformed into a layer/block of a network with learnable parameters. Despite their huge success, the reasons behind their superior performance over their iterative counterparts are not fully understood. This paper focuses on enhancing the explainability of DUNs by investigating potential reasons behind their superior performance over traditional iterative methods. We concentrate on the Learnt Iterative Shrinkage-Thresholding Algorithm (LISTA), a foundational contribution that achieves sparse recovery with significantly fewer layers than its iterative counterpart, ISTA. Our findings reveal that the learnt matrices in LISTA always have Gaussian distributed entries regardless of whether the sensing matrix is random Gaussian, Bernoulli, exponential, or uniform. The findings also show that the singular values of the learnt matrices exceed unity, despite which, the reconstruction scheme is stable. We conjecture that the activation function may have a role to play in ensuring stability. We also present an unbiasing technique that substantially improves the sparse recovery performance by reestimating the amplitudes based on the converged support. ©2025 IEEE.