http://dspace.dtu.ac.in:8080/jspui/handle/123456789/99 2026-04-28T04:03:52Z 2026-04-28T04:03:52Z SINGH, SUMITRA http://dspace.dtu.ac.in:8080/jspui/handle/repository/22163 2025-09-02T06:36:46Z 2025-05-01T00:00:00Z

Title: ENHANCEMENT OF REVERSIBLE IMAGE STEGANOGRAPHY AND OPTIMIZATION OF QUANTUM IMAGE REPRESENTATION USING THE NEQR MODEL Authors: SINGH, SUMITRA Abstract: Reversible steganography allows for exact reconstruction of the cover media after hidden data extraction, making it vital for applications such as content authentication, medical imaging, and military communications. Various reversible steganography techniques include histogram shifting, image interpolation, and difference expansion. Histogram shifting methods apply shifting to pixel-domain histograms or prediction error histograms. Prediction error histogram methods offer higher embedding capacity, but they are more complex, lack a guaranteed lower bound on PSNR, and are more susceptible to histogram-based steganalysis. Pixel-domain histogram shifting techniques, though simpler and more efficient with a theoretical PSNR bound, generally have lower embedding capacity. Under this project, experiments are conducted on pixel-domain histogram shifting- based techniques. The capacity and histogram for varying number of non-overlapping image blocks and histogram blocks are analyzed. Experimental results show that embedding in image blocks does not significantly enhance the capacity compared to embedding in histogram blocks. Analysis of histogram blocks shows that embedding in two blocks yields the optimal results. A method is developed for making histogram shifting adaptive to payload size and a two layer embedding is developed for improved hiding capacity. Compared to previous methods, the two-layer embedding achieves higher capacity, better resistance to steganalysis, and maintains the PSNR acceptable for real-world applications. Quantum computing is an advancing field that offers significant speed advantages for certain computational tasks over classical computing. Notable examples include Shor’s algorithm, which efficiently solves integer factorization and discrete logarithm problems, and Grover’s algorithm, which accelerates the search process in unstructured databases. Quantum computing is based on quantum arithmetic operations where addition forms the core of all operations, as subtraction, multiplication, exponentiation, and division ix can all be reduced to repeated or modified forms of addition. Experiments are conducted for performance analysis of quantum addition on quantum hardware. Development of quantum circuits for addition and comparison, including half adders, full adders, Toffoli-based adders, QFT-based adders (utilizing the Quantum Fourier Transform), and quantum comparators is carried out using IBM Qiskit. The circuits are first validated on ideal simulators to confirm correctness, followed by testing on noisy simulators to emulate real quantum hardware conditions. Final execution is carried out on IBM's Eagle 127-qubit Quantum Processing Unit (QPU). Results show that computation accuracy on actual hardware is limited by physical constraints such as short qubit coherence times and instability. A performance comparison shows that Toffoli-based adders outperform QFT-based adders in terms of accuracy, making them more reliable for precise arithmetic computations. Quantum image representation provides exponential efficiency in image storage and processing. It relies on the fundamental principles of superposition and entanglement. NEQR (Novel Enhanced Quantum Representation) is a lossless encoding method used to represent digital images on a quantum computer. It is widely applicable in domains such as quantum machine learning, image steganography, and quantum image analysis. This work introduces two enhancements to the NEQR framework: (1) Optimizing the decomposition of Multi-Controlled NOT (MCX) gates into Toffoli gates, and (2) Parallelizing the NEQR by parallel bit-plane encoding of the NEQR circuit, where the NEQR circuit is simultaneously constructed for each of the eight bit-planes of an image, thereby reducing overall circuit depth. Experimental results demonstrate that these enhancements lead to reduced circuit depth and faster execution, thereby mitigating decoherence-related errors. Additionally, quantum image processing operations that demonstrate exponential speedup over classical approaches — such as image negation, rotation, and intensity superposition — are also implemented and evaluated as part of this work.

2025-05-01T00:00:00Z SUTTY, SAHIL http://dspace.dtu.ac.in:8080/jspui/handle/repository/21847 2025-07-08T08:48:56Z 2025-06-01T00:00:00Z

Title: A STUDY ON DEEP LEARNING AND TRANSFORMER BASED MODELS FOR HAND GESTURE AND ACTION RECOGNITION Authors: SUTTY, SAHIL Abstract: Fundamental technologies in the evolution of human-computer interaction (HCI), hand gestures and human action recognition enable more natural, intuitive, and accessible interfaces across sectors including assistive technologies, robotics, virtual reality, and surveillance. Using the MSRA Hand Gesture Dataset and the UCF101 Dataset, this paper presents a thorough comparative analysis of state-of- the-art deep learning and transformer-based models for hand gesture recognition and for human action recognition. Comprising 76,500 depth images distributed over 17 gesture classes, the MSRA Hand Gesture Dataset offers a strong basis for spatial feature extraction. ResNet101 obtained the highest F1-score (0.9978) among all architectures; closely followed by DenseNet 169 (0.9919) and DenseNet 201 (0.9901). MobileNetV2 demonstrated a good balance between computational efficiency and accuracy with an F1-score of 0.9847; VGG variants lagged since they lacked sophisticated architectural elements. Human action recognition using the UCF101 dataset—which consists of over 13,000 video clips in 101 action categories—was driven with an eye toward the 50 most frequent classes to guarantee computational feasibility and class balance.With F1-score 0.9997, transformer-based models especially ViT Tiny Patch surpassed even the deepest CNNs. While MobileNetV2 once shown efficiency in settings with limited resources, VGG16bn’s performance revealed the limits of older CNN architectures for demanding tasks. The results underline how architectural innovations including residual connections, dense connectivity, and attention mechanisms help to raise recognition accuracy and computational efficiency. The paper claims that transformer-based models are redefin ing benchmarks even if deep CNNs continue to be strong candidates. More particularly, considering hybrid CNN-transformer designs, explicit temporal modeling, and advanced augmentation techniques helps to increase recognition capacities in pragmatic settings.

2025-06-01T00:00:00Z MEHEVI, AZIZ http://dspace.dtu.ac.in:8080/jspui/handle/repository/21833 2025-07-08T08:47:12Z 2025-05-01T00:00:00Z

Title: FISH SPECIES CLASSIFICATION USING MACHINE LEARNING AND DEEP LEARNING MODELS Authors: MEHEVI, AZIZ Abstract: Fish species classification is fundamental to ecological monitoring, biodiversity con servation, and sustainable fishery management. Conventionally, the identification of fish species is based upon manual observations by domain experts and, hence, incurs heavy expenses with time, labor, and considerable lows in scalability. This study provides broad coverage of the fish species classification problem, with a huge focus on both traditional machine learning (ML) models and architectures of deep learning (DL). A custom dataset of underwater fish images was composed, with images of nine different fish species to cater to various environmental condition-based considerations in the training and testing of several models. The ML models discussed include Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Logistic Regression (LR), and Naive Bayes (NB): all of these were subject to two types of dimension reduction, namely Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). These were com pared against DL models including VGG-19, DenseNet121, EfficientNet B0, Inception V3, ResNet150 V2, and LSTMs, with evaluations conducted for accuracy, precision, re call, and F1-score. The experimental results demonstrated that DL models significantly outclassed conventional ML algorithms in classification accuracy and the ability to han dle variability in images. VGG-19 attained 99.4% overall accuracy; DenseNet121 and EfficientNet B0 followed closely and are considered fit for deployment in real-world fish classification systems. Image preprocessing, normalization, and data augmentation were deemed critical in improving model performance. This study emphasizes the possibility of having deep learning automate fish species recognition with high accuracy under difficult underwater conditions. The present findings open several avenues for real-time marine surveillance, automated ecological data analysis, and smart decision support systems for marine biologists and conservationists.

2025-05-01T00:00:00Z SHUKLA, GAURAV http://dspace.dtu.ac.in:8080/jspui/handle/repository/21830 2025-07-08T08:46:52Z 2025-05-01T00:00:00Z

Title: COMPREHENSIVE STUDY OF DEEP LEARNING-BASED SUPER-RESOLUTION WITH EMPHASIS ON GANS Authors: SHUKLA, GAURAV Abstract: Image super-resolution using Generative Adversarial Networks (GANs) has been ex tensively researched in recent years due to its ability to recover high-perceptual-quality high-resolution images from low-resolution inputs. Various GAN-based methods have been proposed over the years, which employ di!erent architectures and loss functions to increase the fidelity and realism of output images. This work integrates these develop ments and investigates their impact on various categories of images in various application domains. By extensive experimentation, we compare three highly acclaimed GAN-based super-resolution models SRGAN, ESRGAN, and Real-ESRGAN on twelve disparate im age classes. The results confirm that the performance of the model varies significantly depending on the image features and domain, which calls for the need of domain-specific methods that are capable of learning to generalize across varying image content. To address these findings, we add a new component to loss functions with orthogonal reg ularization for, Wide Activation SRGAN (WDSR-GAN), which employs wide activation residual blocks to increase feature representa-tion and training stability. Furthermore, in this work we explore how various loss functions impact super-resolution quality and illustrate how various combinations impact image sharpness and perceptual detail. To quantitatively compare model performance, we use a collection of metrics consisting of PSNR and SSIM, which collectively capture pixel-level accuracy and structural integrity. The findings of this thesis provide valuable insights into the problems and opportuni- con nections of GAN-based image super-resolution. By extensive analysis of di!erent models and loss functions in di!erent domains and metrics, this work lays a strong foundation for the design of more e”cient and flexible super-resolution algorithms. Such e!orts seek to steer future research towards more fidelity, improved perceptual quality, and increased adaptability to real-world imaging applications.

2025-05-01T00:00:00Z