Savita Walia, Ph.D.
I am working as an Assistant Professor in the Department of Computer Science Engineering at Chitkara University, Punjab. I have also worked as a Senior Project Engineer in Advanced Computing and Marketing Solutions (ACMS) Division at the Centre for Development of Advanced Computing (C-DAC), Delhi. Before this, I've worked as a Project Engineer in Applied Artificial Intelligence and Analytics (AAIA) Division at C-DAC, Mohali. Prior to working at CDAC, I had the privilege to serve as an Assistant Professor at UIET, Panjab University for a year. I have completed Masters in Engineering and Ph.D. from UIET, Panjab University. My previous research work is associated with Digital Image Processing in the field of Digital Image Forensics and Machine Learning/Deep Learning. In general, I am interested in exploring the domain of Object Detection, Pattern Recognition, Explainable AI, Computer Vision, and further exploring the possible applications of AI in the Healthcare domain.
Research Publications
Savita Walia, Krishan Kumar, Saurabh Agarwal, Hyunsung Kim, "Using XAI for Deep Learning based Image Manipulation Detection with Shapley Additive Explanation", Symmetry, 2022. (Accepted, SCI Impact Factor: 2.940)
Savita Walia, Krishan Kumar, Munish Kumar, "Unveiling digital image forgeries using Markov based quaternions in frequency domain and fusion of machine learning algorithms", Multimedia Tools and Applications, 2022. DOI:10.1007/s11042-022-13610-8 (SCI Impact Factor: 2.757)
Savita Walia, Krishan Kumar, Munish Kumar, Xiao-Zhi Gao, “Fusion of handcrafted and deep features for forgery detection in digital images”, IEEE Access, Volume 9, pp. 99742-99755, 2021. DOI: 10.1109/ACCESS.2021.3096240. (SCI Impact Factor: 3.476)
Savita Walia, Krishan Kumar, “Digital Image Forgery Detection: A Systematic Scrutiny”, Australian Journal of Forensic Sciences, Volume 51, Issue 5, 2019. DOI:10.1080/00450618.2018.1424241. (SCI Impact Factor: 1.118)
Savita Walia, Krishan Kumar, “Characterization of splicing in digital images using gray scale co-occurrence matrices”, Twelfth International Conference on Contemporary Computing (IC3), August 2019. DOI: 10.1109/IC3.2019.8844881. (Scopus)
Savita Walia, Krishan Kumar, “Pragmatical investigation of Frequency-domain and Spatial-structure based image forgery detection methods”, International Journal of Computational Intelligence & IoT, Vol. 1, No. 2, 2018. Available at SSRN: https://ssrn.com/abstract=3354715.
Savita Walia, Krishan Kumar, “An Eagle-Eye View of Recent Digital Image Forgery Detection Methods”, Smart and Innovative Trends in Next Generation Computing Technologies (NGCT 2017), 2018, CCIS 828, pp. 469-487. DOI: 10.1007/978-981-10-8660-1_36. (Scopus)
Savita Walia, Krishan Kumar, “Calibrating thresholds based on trade-offs between detection accuracy and FPR for copy-move forgery detection”, International Journal of Recent Technology and Engineering, Volume 8, Issue 2, 2019. DOI: 10.35940/ijrte.B2083.078219. (Scopus)
Savita Walia, Mandeep Kaur, “Forgery Detection using Noise estimation and HOG feature extraction”, International Journal of Multimedia and Ubiquitous Engineering (IJMUE), April 2016, Volume 11, Issue 4, pp. 37-48. DOI: 10.14257/ijmue.2016.11.4.05. (Scopus)
Akshita Aggarwal, Ashwani Thakur, Savita Walia, Krishan Kumar, “Localisation of splicing forgery using pixel correlation in digital images”, IEEE-5th International Conference on Signal Processing and Communication (ICSC) 2019. DOI: 10.1109/ICSC45622.2019.8938229. (Scopus)
Deva Prasad, Savita Walia, Krishan Kumar, “Determination of light direction using 3D analysis of known shapes in images”, IEEE - International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), Chennai, India, 2017, pp. 1774-1779. DOI: 10.1109/ICECDS.2017.8389754. (Scopus)
Amanpreet Kaur, Savita Walia, Krishan Kumar, “Comparative analysis of different keypoint based copy-move forgery detection methods”, Eleventh International Conference on Contemporary Computing (IC3), 2018, pp. 172-176. DOI: 10.1109/IC3.2018.8530489. (Scopus and WoS)
Deva Prasad, Savita Walia, Krishan Kumar, “Characterization of forged objects in images using 3D surface analysis”, International Conference on Innovations in Engineering, Technology & Sciences (ICIETS), 2018.
Recent Research Contributions
Savita Walia, Krishan Kumar
The major contributions of this study can be precisely given, as follows:
Identified high-quality studies in the field of digital image forgeries using a systematic survey protocol.
Provided state-of-art taxonomy of digital image forgeries and detection methods.
Presented critical review of approaches and modeling practices followed by various detection methods.
Signified hopeful future research directions through vigilant scrutiny of various limitations and challenges of existing studies.
Savita Walia, Krishan Kumar, Munish Kumar, Xiao-Zhi Gao
The method presented in the paper is novel in four different ways as follows:
This is the first approach for detecting image manipulations utilizing a blend of in-depth, high-level features and manually engineered image features. The detection accuracy has been improved by combining the deep high-level features and manually engineered image features compared to traditional state-of-the-art detection methods on CASIA v1 and CASIA v2 datasets.
Three channels of RGB color space are used in the case of handcrafted feature extraction, and the luma channel of YCbCr color space is used in the case of deep features to detect forgery in images. The complementary information in two different colorspaces has effectively characterized forgeries in digital images
We feed Scale and Orientation invariant local binary pattern maps of the image to the pre-trained ResNet-18 model instead of giving RGB images directly. The rich textural description capability of LBP helps to obtain a more meaningful and low-dimensional representation from the deep neural network.