Milind G. Padalkar

I am a postdoc at PAVIS, Istituto Italiano di Tecnologia (IIT), Genova, Italy, working with Dr. Alessio Del Bue (previously with Prof. Vittorio Murino). My current work is broadly on defect detection in infrastructure elements using computer vision and machine learning. I am also interested in the topics of multi-exposure and multi-illumination fusion. Earlier I have worked on industrial projects focused on defect enhancement and detection mainly for combustion chamber tiles and textile yarn.

Prior to joining IIT, I worked as a senior research engineer at Vehant Technologies (Mar. 2017 - Dec. 2018).

I completed my Ph.D. in 2017 under the supervision of Prof. Manjunath V. Joshi at DA-IICT, Gandhinagar, India. Before that I did my M.Tech. in 2010 under the supervision of Prof. M. A. Zaveri at SVNIT, Surat, India and B.E. in 2008 from FAMT, Ratnagiri (The University of Mumbai).

my_page@IIT  /  LinkedIn  /  Google Scholar  /  Twitter  /  Github  /  CV

profile photo

Postdoc @ PAVIS ,
IIT, Genova, Italy

Publications

Artificial Intelligence tools to predict the level of defectiveness of existing bridges
Agnese Natali, Milind G. Padalkar, Vincenzo Messina, Walter Salvatore, Pietro Morerio, Alessio Del Bue, Carlos Beltran-Gonzalez
19th ANIDIS Conference, 2022
PDF

Various defects in bridges are detected using patch based classifiers.

Preview coming soon
3D Key-points Estimation From Single-view RGB Images
Mohammad Zohaib, Matteo Taiana, Milind G. Padalkar, Alessio Del Bue
ICIAP, 2022 [Oral presentation]
PDF / Sup. Material / Video

Our paper presents an end-to-end approach that leverages single-view RGB images for estimating an ordered list of 3D key-point.

Enhancing Machine Learning Pipelines on Industrial Applications
Carlos Beltran-Gonzalez, Milind G. Padalkar, Alessio Del Bue
Ital-IA, 2022
PDF

Our paper explains how a hybrid image fusion technique can help to enhance the human annotation performance for industrial defect detection.

Multi-illumination Fusion with Crack Enhancement using Cycle-Consistent Losses
Milind G. Padalkar, Carlos Beltran-Gonzalez, Alessio Del Bue
ICIP, 2021
PDF / Sup. Material / Poster / Slides / Video

Crack details are combined from several mutually registered multi-illumination images of ceramic tiles, into a single representative image.

A Versatile Crack Inspection Portable System based on Classifier Ensemble and Controlled Illumination
Milind G. Padalkar, Carlos Beltran-Gonzalez, Matteo Bustreo,
Alessio Del Bue, Vittorio Murino
ICPR, 2020
arXiv / Poster / Video

A novel setup for automatic visual inspection of cracks in ceramic tile as well as studies the effect of various classifiers and height-varying illumination conditions for this task.

Digital Heritage Reconstruction Using Super-resolution and Inpainting
Milind G. Padalkar, Manjunath V. Joshi, Nilay L. Khatri
Book, Dec. 2016 (Synthesis Lectures on Visual Computing)
Springer Nature (origianlly published by Morgan & Claypool Publishers)

Our book presents image super-resolution methods and techniques for automatically detecting and inpainting damaged regions in heritage monuments, in order to provide an enhanced visual experience.

Automatic detection and inpainting of defaced regions and cracks in heritage monuments
Milind G. Padalkar, Manjunath V. Joshi
Chapter in book, 2017 (Digital Hampi: Preserving Indian Cultural Heritage)
Springer, Singapore
PDF (draft)

In this chapter, we discuss techniques for automatically detecting the damaged facial regions and cracks in photographs of monuments. Unlike the usual practice of manually selecting the mask for inpainting, the regions to be inpainted are automatically selected and inpainting is done using the existing algorithm.

Simultaneous Inpainting and Super-resolution Using Self-learning
Milind G. Padalkar, Manjunath V. Joshi, Nilay L. Khatri
BMVC, 2015
PDF / Sup. Material / Poster

We construct dictionaries of image-representative low and high resolution patch pairs from the known regions in the test image and its coarser resolution. Inpainting of the missing pixels is performed using exemplars found by comparing patch details at a finer resolution by making use of the constructed dictionaries.

Auto-inpainting Heritage Scenes: A Complete Framework for Detecting and Infilling Cracks in Images and Videos with Quantitative Assessment
Milind G. Padalkar, Manjunath V. Joshi
Machine Vision and Applications, March 2015
PDF (draft)

A technique for automatically detecting the cracked regions in photographs of monuments, based on comparison of patches using a measure derived from the edit distance. This is extended to perform inpainting of video frames using SIFT and homography, which is quantified with our temporal consistency measure.

Identifying vandalized regions in facial images of statues for inpainting
Milind G. Padalkar, Manali Vora, Manjunath V. Joshi,
Mukesh A. Zaveri, Mehul Raval
MM4CH, 2013 (2nd International Workshop on Multimedia for Cultural Heritage)
[ICIAP-2013 Workshops]
Video

Automates the process of identifying the damage to visually dominant regions viz. eyes, nose and lips in facial image of statues, for the purpose of inpainting.

SVD based automatic detection of target regions for image inpainting
Milind G. Padalkar, Mukesh A. Zaveri, Manjunath V. Joshi
2nd ACCV Workshop on e-Heritage, 2012
[ACCV-2012 Workshops]

We present a Singular Value Decomposition (SVD) based technique for automatic detection of the damaged regions in the photographed object/scene, for digitally restoring the entirety using inpainting.

Exemplar based Inpainting using Autoregressive Parameter Estimation
Milind G. Padalkar, Manjunath V. Joshi, Mukesh A. Zaveri, Chintan M. Parmar
International Conference on Signal, Image and Video Processing (ICSIVP), 2012
PDF

Unlike simply copying pixels from an exemplar into the target or damaged pixels (i.e. pixels to be inpainted), we estimate and use autoregressive parameters along with the best matching exemplar to modify the damaged pixel.

Dissolve Detection Based Shot Identification Using Singular Value Decomposition
Milind G. Padalkar, Mukesh A. Zaveri
4th Asia International Conference on Modelling & Simulation (AMS), 2010

A dual stage divide-and-merge approach to detect video-shots joined by dissolve type transitions.

Thesis and Reports
Novel Techniques for Auto-inpainting in Heritage Reconstruction
Ph.D. Thesis, April 2017
PDF (draft) / Bibtex

Histogram based Efficient Video Shot Detection Algorithms
M.Tech. Thesis, June 2010
PDF (draft) / Bibtex

Misc
My Video Player using OpenCV
Hobby project, 2010
Project doc. / Code

This is an old code that I created sometime in 2010. While working on video shot detection, I needed a tool to perform frame-by-frame visual analysis. However, I wasn't aware of any that existed at that time and created one with Matlab. To sharpen my skills with C and OpenCV, I re-created the same.

TECHRECONN
My blog
- Installing Torch without root privileges, March 4, 2016
- Doxygen: Source code to Documentation..., June 7, 2011
- Inform Synaptic Package Manager about Locally Compiled Packages, June 6, 2011
- Gedit-latex-plugin for TeXLive2010, June 3, 2011
- Restraining software piracy, May 27, 2011
- Startup Applications in Ubuntu Desktop, May 19, 2011
- Drag and drop not working properly in Ubuntu 11.04?, May 13, 2011
- Using Remote Desktop in Ubuntu, May 12, 2011, [Updated, Nov. 22, 2019]
- Back up an entire Linux System to an installable Live CD/DVD, May 9, 2011
- Creating a boot script in Ubuntu, May 9, 2011
- Sharing folders over the network using Samba in Ubuntu, May 8, 2011
- Auto mounting NTFS drive in Ubuntu at boot time, May 5, 2011
- Installing TeXLive using ISO in Ubuntu, May 4, 2011

PhD Thesis Templates for SVNIT students
Hobby project, 2010
- LaTeX template for thesis with page border on initial pages using pdflatex (v16.01.03)
- LaTeX template for thesis without page border on initial pages (v13.11.26)
- LaTeX template for RPS with page border on initial pages.

Interesting links for information related to Travel Grants for Indian students
- A comprehensive piece of information by Arun Karthik
- Anant Kulkarni's handy document
- Microsoft Research India Travel Grants
- ACM India-IARCS travel grants

My Notes
- Computer vision course (IT524), taught by Prof. M. V. Joshi at DA-IICT, 2012


Website built using source code provided by Jon Barron.

Last updated on: