Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shraddha R. Khonde has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Deep Learning Innovations in Ray Tracing: A Survey of Transition to Neural Rendering

    by Pranali Dahiwal, Shraddha Khonde, Kaustubh Warade, Vaishali Sonawane, Suvarna S. Pawar, Shalaka Deore, Shobha Raskar, Tarandeep Singh, Manisha A. Dudhedia, Tanaji A. Dhaigude, et al.

    This work provides a comprehensive analysis of the evolution of rendering techniques in computer graphics, focusing on the transition from rasterization, a method renowned for its efficiency, to physically based rendering techniques such as ray tracing and path tracing, which offer superior visual realism. Despite the unmatched accuracy of ray tracing in simulating complex light interactions, its widespread adoption has historically been limited by its high computational demands and sampling noise. Recent breakthroughs in deep learning have catalyzed a paradigm shift in rendering workflows, offering practical solutions to these challenges. Neural networks, through intelligent denoising, adaptive sampling strategies, and novel acceleration architectures, are now significantly enhancing both the performance and quality of ray tracing. This technological synergy is becoming increasingly critical to meet the escalating demand for high-fidelity, real-time graphics in fields such as gaming, virtual production, and immersive simulations. The report evaluates the transformative impact of deep learning on ray tracing and its implications for the future of interactive digital media.

  • A Review on Iris Recognition Using Machine Learning Techniques

    by Yashwant S. Ingle, Parikshit N. Mahalle, Shraddha R. Khonde, Suvarna Bhagwat, Mandar P. Diwakar

    An iris is round in shape and colored part of a person’s eye. Iris’s characteristics are unique in every person, and therefore, it distinguishes one person from others. Several recognition systems exist in the biometric verification system, like face, voice, Iris, and finger. But Iris has a crucial role in authenticating or recognizing a human being. Generally, the iris recognition arrangement is associated with specific top expensive applications where security is paramount and uses a delicate infrared illumination camera to capture images. Even in the same person, the texture of the left and right eye is not similar. It differs even among the twins’ eyes, making it an extra secure way to automatically identify a person than other recognition systems. In the review paper, we highlight several existing iris datasets on iris recognition. Moreover, image preprocessing processes and segmentation techniques can be practically used to iris datasets and feature extraction methods, which will be used as input for any machine learning technique to identify the individuals efficiently.


  • Open Access

    Detection and Interpretation of Indian Sign Language Using LSTM Networks

    by Piyusha Vyavahare, Sanket Dhawale, Priyanka Takale, Vikrant Koli, Bhavana Kanawade, Shraddha Khonde

    Sign language plays a crucial role in communication for individuals with speech or hearing difficulties. However, the lack of a comprehensive Indian Sign Language (ISL) corpus impedes the development of text-to-ISL conversion systems. This study proposes a specific deep learning-based sign language detection system tailored specifically for Indian Sign Language (ISL). The proposed system utilizes Long Short-Term Memory (LSTM) networks to detect and recognize actions from dynamic ISL gestures captured in videos. Initially, the system employs computer vision algorithms to extract relevant features and representations from the input gestures. Subsequently, an LSTM-based deep learning architecture is employed to capture the temporal dependencies and patterns within the gestures. LSTM models excel in sequential data processing, making them well-suited for analyzing the dynamic nature of sign language gestures. To assess the effectiveness of the proposed system, extensive experimentation and evaluation were conducted. A customized dataset was curated, encompassing a diverse range of ISL sign language actions. This dataset was created by collecting video recordings of native ISL users performing various actions, ensuring comprehensive coverage of gestures and expressions. These videos were meticulously annotated and labelled with corresponding textual representations of the gestures. The dataset was then split into training and testing sets to train the LSTM-based model and evaluate its performance. The proposed system yielded promising results during the validation process, achieving a training accuracy of 96% and a test accuracy of 87% for ISL recognition. These results outperformed previous approaches in the field. The system's ability to effectively detect and recognize actions from dynamic ISL gestures, facilitated by the deep learning-based approach utilizing LSTM networks, demonstrates the potential for more accurate and robust sign language recognition systems. However, it is important to acknowledge the limitations of the system. Currently, the system's primary focus is on recognizing individual words rather than full sentences, indicating the need for further research to enhance sentence-level interpretations. Additionally, variations in lighting conditions, camera angles, and hand orientations can potentially impact the system's accuracy, particularly in the context of ISL.