Ankit Kumar Jaiswal
@thapar.edu
Assistant Professor
Thapar Institute of Engineering and Technology
5
Scopus Publications
Scopus Publications
- Feature Selection and Reduction for Analysis of Histopathology Images
Shiksha Singh, Ankit Kumar Jaiswal, and Rajesh Kumar
Springer Nature Singapore - Fake region identification in an image using deep learning segmentation model
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC - FSD: A novel forged document dataset and baseline
Ankit Kumar Jaiswal, Shiksha Singh, and Santosh Kumar Tripathy
IEEE
Forgery detection in multimedia is an emerging research area in the field of digital content security. The current research focuses on finding several solutions to digital image forgery detection but a small number of works have been reported for scanned document forgery detection. The reason would be the unavailability of a forged scanned document (FSD) dataset. A scanned document can be manipulated in different ways: deleting a region, copy paste a region of the document either in the same document or in another document. Detection of these manipulations becomes arduous when a post-processing operation is performed on the manipulated region. To advance research in this field, we created a large dataset for the FSD. To generate such a dataset, we collected scanned documents from the FUNSD dataset (Publicly Available). The resolution of each sample of the dataset is of size 755x1000. The samples of the dataset are forged using different post-processing operations. The dataset comprises 6656 instances of manipulated scanned documents with their ground truth masks. To build the baseline for forged scanned document detection, we evaluated state-of-the-art object segmentation algorithms on the FSD dataset. Experiments demonstrate that the FSD well represents forged scanned documents and is quite challenging. - Multi-Layer Feature Fusion-based Deep Multi-layer Depth Separable Convolution Neural Network for Alzheimer's Disease Detection
Santosh Kumar Tripathy, Divya Singh, and Ankit Jaiswal
IEEE
Alzheimer's disease (AD) is a severe degenerative neurological disorder that can cause heart and respiratory dysfunction. Thus, early detection of such disease is highly required. Using MRI images, a number of deep models have been created to predict AD as artificial intelligence (AI) has advanced. However, these models suffer from limited representation in extracting fine-grained features from MRI images thereby performance is declined. The proposed model overcomes such limitation and presents a methodology for AD detection by proposing a novel multi-layer feature fusion-based deep multi-layer depth-wise separable convolution neural network (CNN). The proposed model enhances the quality of features by fusing multi-layer features. These features range from representations of low-level features to features at the object level. The fused multiscale features are used for predicting AD disease. Publicly available dataset is used to validate the model's performance. With an accuracy of 95.16 percent, the suggested model performs better than the current state of the art. - Some Methods for Digital Image Forgery Detection and Localization
Ankit Kumar Jaiswal, Shiksha Singh, Santosh Kr. Tripathy, Nirbhay Kr. Tagore, and Arya Shahi
Springer Nature Singapore - Occlusion Reconstruction for Person Re-identification
Nirbhay Kumar Tagore, Ramakant Kumar, Naina Yadav, and Ankit Kumar Jaiswal
Springer Nature Singapore - Source Camera Identification Using Hybrid Feature Set and Machine Learning Classifiers
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer International Publishing - Detection of Copy-Move Forgery in Digital Image Using Multi-scale, Multi-stage Deep Learning Model
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC - Apple Disease Classification Built on Deep Learning
Harshit Singh, Kumud Saxena, and Ankit Kumar Jaiswal
IEEE
In horticulture and agriculture, classification and intelligent identification of disease is the need of the hour. Apple is one of the most cultivated and consumed fruit in the world. It is a nutritious fruit that contains vitamin A, B1, B12, and folic acid. It is a fruit that can even keep the doctors away. The same fruit is susceptible to various diseases such as blotch and nematode, leading to social and economic losses. This paper proposes the classification of diseased and healthy apples using the deep learning technique. A dataset of 570 images of 3 Apple diseases (Blotch, Rot, and Scab) are used in the model along with normal apple images. Further data is augmented and the state-of-the-art convolution neural network, ResNet 50 is utilized for the multiclass classification and prediction model. Then performance is measured via accuracy with the help of performance matrices and the result is analyzed with its future scope. - Forensic image analysis using inconsistent noise pattern
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC - Time-efficient spliced image analysis using higher-order statistics
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC - A technique for image splicing detection using hybrid feature set
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC - Detection of copy-move forgery using hybrid approach of DCT and BRISK
Ankit Kumar Jaiswal, Dhanin Gupta, and Rajeev Srivastava
IEEE
With the advancement in the image editing tools day by day and their increased usage, image forgery has become a serious problem. Copy-move forgery (CMF) is one of the most common image tampering techniques being used. There are many post-processing techniques applied on forged images such as scaling, blurring, JPEG compression and rotation to hide forgery traces. Single image might contain multiple forged regions. In this paper, we have proposed a hybrid method involving DCT (Discrete cosine Transform) and BRISK (Binary Robust Invariant Scalable Keypoints) features, for copy-move forgery detection. DCT is a feature set that would provide invariance to blurring, while BRISK would provide invariance to rotation and scaling. Features are extracted using DCT and BRISK keypoints and descriptors. For matching BRISK descriptors FLANN matcher is used, and for removing the false matches Euclidean distance-based clustering technique is used. The experimental result shows that our method is not only robust to blurring but also robust to transformations like rotation and scaling. It is also able to detect multiple forged regions. The method is tested on CoMoFoD dataset. Results of the proposed work are also compared with two standard approaches mentioned in experiment and result section. - Copy-Move Image Forgery Detection Using DCT and ORB Feature Set
Vikas Mehta, Ankit Kumar Jaiswal, and Rajeev Srivastava
Springer Singapore - Copy-move forgery detection using shift-invariant SWT and block division mean features
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Singapore - Comparative study of commit protocols in mobile environment: M2PC, UCM and TCOT
Ankit Kumar Jaiswal and Udai Shanker
IEEE
In the mobile environment the major issues for commit the transactions are disconnection due to mobile handoff or shut down of devices. Disconnection is frequent problem in mobile environment. This results transaction failure. A traditional two-phase commit protocol is best for the distributed environment. In case of mobile environment where devices are connected wirelessly we should deal with the issues of mobility. The paper presents comparison study of three major commit protocols in the mobile environment. The paper surveys different approaches proposed for mobile transaction and summarize how the conventional commitment are revisited to fit the needs of mobile environment.