@thapar.edu
Assistant Professor
Thapar Institute of Engineering and Technology
Scopus Publications
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC
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.
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.
Ankit Kumar Jaiswal, Shiksha Singh, Santosh Kr. Tripathy, Nirbhay Kr. Tagore, and Arya Shahi
Springer Nature Singapore
Nirbhay Kumar Tagore, Ramakant Kumar, Naina Yadav, and Ankit Kumar Jaiswal
Springer Nature Singapore
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer International Publishing
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC
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.
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Science and Business Media LLC
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.
Vikas Mehta, Ankit Kumar Jaiswal, and Rajeev Srivastava
Springer Singapore
Ankit Kumar Jaiswal and Rajeev Srivastava
Springer Singapore