efficient-multiscale-gradient-domain-filtering-for-image-video

Efficient Multiscale Gradient-Domain Filtering for Image and Video Dehazing with Enhanced Temporal Coherence

Dehazing is crucial in computer vision to restore image clarity affected by atmospheric scattering. Existing methods suffer from high computational costs, ...

Chitkara University

Many countries around the world have been influenced by Covid-19 which is a serious virus as it gets transmitted by human communication. Although, its syndrome is quite similar to the ordinary flu. The critical step involved in Covid-19 is the initial screening or testing of the infected patients. As there are no special detection tools, the demand for such diagnostic tools has been increasing continuously. So, it is eminently admissible to find out positive cases of this disease at the earliest so that the spreading of this dangerous virus can be controlled. Although, some methods for the detection of Covid-19 patients are available, which are performed upon respiratory based samples and among them, a critical approach for treatment is radiologic imaging or X-ray imaging. The latest conclusions obtained from X-ray digital imaging based algorithms and techniques recommend that such type of digital images may consist of significant facts regarding the SARS-CoV-2 virus. The utilization of Deep Neural Networks based methodologies clubbed with digital radiological imaging has been proved useful for accurately identifying this disease. This could also be adjuvant in conquering the problem of dearth of competent physicians in far-flung areas. In this paper, a CheXImageNet model has been introduced for detecting Covid-19 disease by using digital images of Chest X-ray with the help of an openly accessible dataset. Experiments for both binary class and multi-class have been performed in this work for benchmarking the effectiveness of the proposed work. An accuracy of 100  is reported for both binary classification (having cases of Covid-19 and Normal X-Ray) and classification for three classes (including cases of Covid-19, Normal X-Ray and, cases of Pneumonia disease) respectively.

CheXImageNet: a novel architecture for accurate classification of Covid-19 with chest x-ray digital images using deep convolutional neural networks.

Prognostic survival prediction in colorectal cancer (CRC) plays a crucial role in guiding treatment decisions and improving patient outcomes. In this research, we explore the application of deep learning techniques to predict survival outcomes based on histopathological images of human colorectal cancer. We present a retrospective multicenter study utilizing a dataset of 100,000 nonoverlapping image patches from hematoxylin & eosin-stained histological images of CRC and normal tissue. The dataset includes diverse tissue classes such as adipose, background, debris, lymphocytes, mucus, smooth muscle, normal colon mucosa, cancer-associated stroma, and colorectal adenocarcinoma epithelium. To perform survival prediction, we employ various deep learning architectures, including convolutional neural network, DenseNet201, InceptionResNetV2, VGG16, VGG19, and Xception. These architectures are trained on the dataset using a multicenter retrospective analysis approach. Extensive preprocessing steps are undertaken, including image normalization using Macenko's method and data augmentation techniques, to optimize model performance. The experimental findings reveal promising results, demonstrating the effectiveness of deep learning models in prognostic survival prediction. Our models achieve high accuracy, precision, recall, and validation metrics, showcasing their ability to capture relevant histological patterns associated with prognosis. Visualization techniques are employed to interpret the models' decision-making process, highlighting important features and regions contributing to survival predictions. The implications of this research are manifold. The accurate prediction of survival outcomes in CRC can aid in personalized medicine and clinical decision-making, facilitating tailored treatment plans for individual patients. The identification of important histological features and biomarkers provides valuable insights into disease mechanisms and may lead to the discovery of novel prognostic indicators. The transparency and explainability of the models enhance trust and acceptance, fostering their integration into clinical practice. Research demonstrates the potential of deep learning models for prognostic survival prediction in human colorectal cancer histology. The findings contribute to the understanding of disease progression and offer practical applications in personalized medicine. By harnessing the power of deep learning and histopathological analysis, we pave the way for improved patient care, clinical decision support, and advancements in prognostic prediction in CRC.

From slides to insights: Harnessing deep learning for prognostic survival prediction in human colorectal cancer histology.

The identification of gas leakages is a significant factor to be taken into consideration in various industries such as coal mines, chemical industries, etc., as well as in residential applications. In order to reduce damage to the environment as well as human lives, early detection and gas type identification are necessary. The main focus of this paper is multimodal gas data that were obtained simultaneously by using multiple sensors for gas detection and a thermal imaging camera. As the reliability and sensitivity of low-cost sensors are less, they are not suitable for gas detection over long distances. In order to overcome the drawbacks of relying just on sensors to identify gases, a thermal camera capable of detecting temperature changes is also used in the collection of the current multimodal dataset The multimodal dataset comprises 6400 samples, including smoke, perfume, a combination of both, and neutral environments. In this paper, convolutional neural networks (CNNs) are trained on thermal image data, utilizing variants such as bidirectional long-short-term memory (Bi-LSTM), dense LSTM, and a fusion of both datasets to effectively classify comma separated value (CSV) data from gas sensors. The dataset can be used as a valuable source for research scholars and system developers to improvise their artificial intelligence (AI) models used for gas leakage detection. Furthermore, in order to ensure the privacy of the client's data, this paper explores the implementation of federated learning for privacy-protected gas leakage classification, demonstrating comparable accuracy to traditional deep learning approaches.

Gas Detection and Classification Using Multimodal Data Based on Federated Learning.

Early detection of ocular diseases is vital to preventing severe complications, yet it remains challenging due to the need for skilled specialists, complex imaging processes, and limited resources. Automated solutions are essential to enhance diagnostic precision and support clinical workflows. This study presents a deep learning-based system for automated classification of ocular diseases using the Ocular Disease Intelligent Recognition (ODIR) dataset. The dataset includes 5,000 patient fundus images labeled into eight categories of ocular diseases. Initial experiments utilized transfer learning models such as DenseNet201, EfficientNetB3, and InceptionResNetV2. To optimize computational efficiency, a novel two-level feature selection framework combining Linear Discriminant Analysis (LDA) and advanced neural network classifiers-Deep Neural Networks (DNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM)-was introduced. Among the tested approaches, the "Combined Data" strategy utilizing features from all three models achieved the best results, with the BiLSTM classifier attaining 100% accuracy, precision, and recall on the training set, and over 98% performance on the validation set. The LDA-based framework significantly reduced computational complexity while enhancing classification accuracy. The proposed system demonstrates a scalable, efficient solution for ocular disease detection, offering robust support for clinical decision-making. By bridging the gap between clinical demands and technological capabilities, it has the potential to alleviate the workload of ophthalmologists, particularly in resource-constrained settings, and improve patient outcomes globally.

Multiple model visual feature embedding and selection method for an efficient oncular disease classification.

Correction: Multiple model visual feature embedding and selection method for an efficient ocular disease classification.

Agriculture 5.0 is a principal economic activity in the world with major workforce dependent crops cultivation. An automated system for crops field insect pest identification can help decrease labour, while also improving the speed and precision in compared to manual methods. Less computation and memory systems are getting utilized for remote deployments of classification systems. In this paper, efficient pretrained multiple deep learning models based visual feature extraction and Linear Discriminant Analysis (LDA) based feature selection to provide high efficacy with light resource requirements. This proposed approach also able to handle large number of classes. To achieve this, diverse pest datasets were combined including 9 and 12 classes respectively and the utilized combined dataset contains total 19 classes. Methodology of proposed system included the selection of multiple pretrained models including DenseNet201, EfficientNetB3 and InceptionResNetV2 based on less memory and less parametric requirements. The second last layer of mentioned models have been utilized for selection of features as DenseNet201, EfficientNetB3 and InceptionResNetV2 resulted 1920, 1536 and 4608 accordingly. The extracted features combined and selected using LDA according to the number of classes. At end a basic light dense neural network have been deployed for classification. This makes a low resource and high efficacy pest classification model for higher number of classes. The results obtained by proposed technique are 99.99% Accuracy, 100% validation, 99.99% Recall and negligible Loss. Further the proposed system has been analysed and compared with benchmark approaches including transfer learning and single model feature extraction and selection approach. The main advantage of our proposed hybrid feature selection is that it makes the classification process lighter because it involves selecting relevant features from the existing dataset without training additional models, whereas transfer learning typically involves retraining or fine-tuning pre-existing models, which can be more computationally intensive. Overall the proposed system and approach resulting higher results with lighter process resources that fitted better in the development of domain of precision agriculture.

Article	Year
CheXImageNet: a novel architecture for accurate classification of Covid-19 with chest x-ray digital images using deep convolutional neural networks. Health and technology\| PubMed ID: 35036283	2022
From slides to insights: Harnessing deep learning for prognostic survival prediction in human colorectal cancer histology. Open life sciences\| PubMed ID: 38152577	2023
Gas Detection and Classification Using Multimodal Data Based on Federated Learning. Sensors (Basel, Switzerland)\| PubMed ID: 39338648	2024
Multiple model visual feature embedding and selection method for an efficient oncular disease classification. Scientific reports\| PubMed ID: 39934192	2025
Correction: Multiple model visual feature embedding and selection method for an efficient ocular disease classification. Scientific reports\| PubMed ID: 40399482	2025
Multiple model visual feature embedding and selection method for an efficient pest classification supporting precision agriculture. Scientific reports\| PubMed ID: 40877365	2025

Isha Kansal

Biography

JoVE Journal Publications

Other Publications