About
- I am a University assistant and a Ph.D. student in Technical University Vienna (TU Wien), Austria. Guided by Prof. Walter Kropatsch
- In my wonderful journey of masters from Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India, I was lucky to be mentored by Prof. Aditya Tatu.
Professional
- Publications [Download here!]
- - A step towards learning Contraction Kernels for Irregular Pyramids
BibTeX
International Conference on Pattern Recognition Applications and Methods (ICPRAM), 2022@article{batavia2022a,
title={A Step Towards Learning Contraction Kernels for Irregular Pyramids},
author={ Batavia, Darshan and Gonzalez-Diaz, Rocio and Kropatsch, Walter G},
booktitle={In Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods},
pages={60--70},
year={2022},
publisher={ICPRAM}
} - - Characterizing slope regions
BibTeX
Journal of Combinatorial Optimization, 2021@article{gonzalez2021characterizing,
title={Characterizing slope regions},
author={Gonzalez-Diaz, Rocio and Batavia, Darshan and Casablanca, Rocio M and Kropatsch, Walter G},
journal={Journal of Combinatorial Optimization},
pages={1--20},
year={2021},
publisher={Springer}
} - - Image = Structure + Few Colors
BibTeX
Structural, Syntactic, and Statistical Pattern Recognition (S+SSPR), 2020@INPROCEEDINGS{batavia2019congratulations,
title={Image = Structure + Few Colors},
author={Batavia, Darshan and Gonzalez-Diaz, Rocio and Kropatsch, Walter G},
booktitle={Structural, Syntactic, and Statistical Pattern Recognition - Joint {IAPR} International Workshops, {S+SSPR} 2020, Padua, Italy, January 21-22, 2021, Proceedings},
SERIES = {Lecture Notes in Computer Science},
volume = {12644},
pages={365--375},
year={2020},
publisher={Springer}
} - - Partitioning 2D Images into Prototypes of Slope Region
BibTeX
InternationalConference on Computer Analysis of Images and Patterns (CAIP), 2019@INPROCEEDINGS{batavia2019partitioning,
title={Partitioning 2{D} {I}mages into {P}rototypes of {S}lope {R}egion},
author={Batavia, Darshan and Hladůvka Jiří and Kropatsch, Walter G},
booktitle={International Conference on Computer Analysis of Images and Patterns},
SERIES = {Lecture Notes in Computer Science},
pages={363--374},
year={2019},
publisher={Springer}
} - - Congratulations! Dual Graphs Are Now Orientated!
BibTeX
International Workshop on Graph-Based Representations in Pattern Recognition (GbR), 2019@INPROCEEDINGS{batavia2019congratulations,
title={Congratulations! Dual Graphs Are Now Orientated!},
author={Batavia, Darshan and Kropatsch, Walter G and Casablanca, Rocio M and Gonzalez-Diaz, Rocio},
booktitle={International Workshop on Graph-Based Representations in Pattern Recognition},
SERIES = {Lecture Notes in Computer Science},
pages={131--140},
year={2019},
publisher={Springer}
} - - On the space between critical points
BibTeX
Discrete Geometry for Computer Imagery (DGCI), 2019@INPROCEEDINGS{kropatsch2019space,
TITLE={{O}n the Space between Critical Points},
AUTHOR={{K}ropatsch, Walter G. and Casablanca, Rocio M. and Batavia, Darshan and Gonzalez-Diaz, Rocio},
BOOKTITLE={Discrete Geometry for Computer Imagery},
SERIES = {Lecture Notes in Computer Science},
volume={11414},
pages={},
year={2019},
publisher={Springer}
} - - Counting Slope Regions in the Surface Graphs
BibTeX
Computer Vision Winter Workshop (CVWW), 2019@INPROCEEDINGS{batavia2019counting,
title={Counting slope regions in surface graphs},
author={Batavia, Darshan and Kropatsch, Walter G. and Gonzalez-Diaz, Rocio and Casablanca, Rocio M.},
booktitle={Computer Vision Winter Workshop},
EDITOR = {Friedrich Fraundorfer, Peter M. Roth and Fabian Schenk},
ORGANIZATION = {},
PUBLISHER = {TU Graz},
NOTE = {},
YEAR = {2019},
PAGES = {42--50}
} - - Computing and reducing slope complexes
BibTeX
International Workshop on Computational Topology in Image Context (CTIC), 2019@INPROCEEDINGS{kropatsch2019computing,
title={Computing and reducing slope complexes},
author={Kropatsch, Walter G and Casablanca, Rocio M and Batavia, Darshan and Gonzalez-Diaz, Rocio},
booktitle={International Workshop on Computational Topology in Image Context},
SERIES = {Lecture Notes in Computer Science},
pages={12--25},
year={2019},
publisher={Springer}
} - - Estimating graph topology from sparse graph signals with an application to image denoising
BibTeX
International Workshop on Multimedia Signal Processing (MMSP), 2017@INPROCEEDINGS{batavia2017estimating,
author={D. {Batavia} and A. {Tatu}},
booktitle={2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)},
title={Estimating graph topology from sparse graph signals with an application to image denoising},
year={2017},
volume={},
number={},
pages={1-6},
doi={10.1109/MMSP.2017.8122233}
}
- Research
- - Ph.D. (June 2018 - present)
- - Masters (M.Tech. 2015-2017)
- Study trips
- - Jan. 2021 Statistical + Structural and Syntactic Pattern Recognition (S+SSPR) 2020 (virtual)
- - Sep. 2019 Computer Analysis of Images and Patterns (CAIP) in Salerno, Italy
Erasmus - Staff exchange in University of Salerno, Italy - - Jun. 2019 Graph based Representations (GbR) in Tours, France
- - Mar. 2019 Discrete Geometry for Computer Imagery (DGCI) in Marne-la-Vallée (Paris downtown), France
- - Feb. 2019 Computer Vision Winter Workshop (CVWW) in Stift Vorau, Austria
- - Jan. 2019 Computational Topology in Image Context (CTIC) in Malaga, Spain
- - Jul. 2017 Multimedia Signal Prcessing (MMSP, IEEE) in London-Luton, UK
- Teaching Assistance
- - Pattern Recognision (TU Wien - SS 2019, 2020, 2021)
- Lecture for 3rd semester Masters students
- - Scientific Works (TU Wien - WS 2018, 2019)
- Lecture for 5th semester Bachelor students
- - Introduction to Digital Image Processing (TU Wien - WS 2018, 2019, 2020, 2021)
- Lecture for 3rd semester Bachelor students
- - Analog and Digital Communication (DA-IICT - WS 2016)
- Lecture for 6th semester Bachelor students
- - Probability and Statistics (IIIT Vadodara - SS 2016)
- Lecture for 3rd semester Bachelor students
- - Systems and Signals (DA-IICT - SS 2015)
- Lecture for 3rd semester Bachelor students
My research work is in the area of topological image analysis and pattern recognition. Currently, I am developing an algorithm reinforced with theory for irregular image pyramids. The reconstructed image from the image pyramid preserves the topological content and high-frequency texture information of the image. The algorithm and related theory can be used in different image processing applications such as multi-resolution image segmentation, topological image analysis, contour detection, solving stereo correspondence, decomposition of 2D space into cells called slope regions. I am also interested in merging machine learning algorithms with my current research to attain better results and widen the scope of applications to other fields.
Topology plays an important role in processing structured and unstructured data represented as graph signals. My master research focused on estimating (w/o deep learning) the graph topology (graph Laplacian matrix) for the graph signals with the prior assumption that signals have a sparse representation in the frequency domain. The research falls under algebraic graph signal processing. For application purposes, we demonstrated image denoising for all three classes of images - natural, piecewise smooth (depth map), and texture images. It was observed that the algorithm performs better for texture images as compared to the natural and piecewise-smooth images.
Personal
- Triathlon Vienna Triathlon 2021 (Olympic distance)
- - 1.5 km Swim -> 00:37 hours
- - 40 km Bike -> 01:10 hours
- - 10 km Run -> 01:20 hours Total time 03:12 hours
- Bike rides More than 100 hours of planned and recorded bike rides in Vienna. Click here for more details.
Contact
darshan [at] prip [dot] tuwien [dot] ac [dot] at
bataviadarshan755 [at] gmail [dot] com