A5078496897- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Domain Adaptation and Few-Shot Learning
- Neural Networks and Applications
- Machine Learning and Data Classification
- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Anomaly Detection Techniques and Applications
- Industrial Vision Systems and Defect Detection
- Spam and Phishing Detection
- Image Retrieval and Classification Techniques
- Radiomics and Machine Learning in Medical Imaging
- Music and Audio Processing
- Advanced Malware Detection Techniques
- COVID-19 diagnosis using AI
- Image Enhancement Techniques
- Smart Agriculture and AI
- Advanced Steganography and Watermarking Techniques
- Chaos-based Image/Signal Encryption
- Network Security and Intrusion Detection
- Video Analysis and Summarization
- Face recognition and analysis
- Artificial Intelligence in Healthcare
KLE Technological University
2015-2024
Vidyasagar University
2017-2022
Sanskriti Samvardhan Mandal
2011-2021
Pacific Dental College and Hospital
2019-2020
Institute of Engineering
2013-2019
University of Mumbai
2011-2019
Pacific University Oregon
2018
Shivaji University
2017
Bharati Vidyapeeth Deemed University
2011
Dr. Balasaheb Sawant Konkan Krishi Vidyapeeth
2010
Brain extraction, or skull-stripping, is an essential pre-processing step in neuro-imaging that has a direct impact on the quality of all subsequent processing and analyses steps. It also key requirement multi-institutional collaborations to comply with privacy-preserving regulations. Existing automated methods, including Deep Learning (DL) based methods have obtained state-of-the-art results recent years, primarily targeted brain extraction without considering pathologically-affected...
India is a country endowed with rich cultural heritage especially renowned architectural sites of which 37 are UNESCO listed sites. Cultural heritages connects generations over time and we need to preserve them. Architects, historians, travelers etc. They visit many historical where it often becomes difficult for them identify get details about the monument they interested in. The task archiving, documenting sharing knowledge these assets challenging due scale reliability information. An...
Steganography is the art of hiding existence data in another transmission medium to achieve secret communication. It does not replace cryptography but rather boosts security using its obscurity features. method used this paper based on biometrics. And biometric feature implement steganography skin tone region images. Here embedded within image that will provide an excellent secure location for hiding. For detection performed HSV (Hue, Saturation and Value) color space. Additionally embedding...
Steganography is the art of hiding existence data in another transmission medium to achieve secret communication.Steganography method used this paper based on biometrics.And biometric feature implement skin tone region images [1].Here embedded within image that will provide an excellent secure location for hiding.For detection performed using HSV (Hue, Saturation and Value) color space.Additionally embedding frequency domain approach -DWT (Discrete Wavelet Transform), DWT outperforms than...
The Deep Neural Network (DNN) model has been used in a number of commercial applications and we benefit from its accuracy numerous like virtual assistants chatbots. Due to the high computational demands significant memory requirements those models, quantization approaches have employed minimise loss while reducing size address problems. DNN's problems, including large model, which come at cost substantially increased computation storage resources, consume more power. study addresses these...
Since object oriented system is becoming more pervasive, it necessary that software engineers have quantitative measurements for accessing the quality of designs at both architectural and components level. These measures allow designer to access early in process, making changes will reduce complexity improve continuing capability product. Object design metrics an essential part engineering. This paper presents a case study applying assess quality. Six Java based open source systems are...
The ability to detect gender and age from voice is a valuable tool in variety of applications, like voice-based biometric identification, natural language processing, speech recognition. Recent advances Deep Learning have enabled the development highly accurate detection models. In this paper, discussion about Machine based model using voice. various approaches used extract features speech, data-set for evaluation classification are obtained different algorithms. opportunities challenges...
Recently, the convolutional neural network with residual learning models achieves high accuracy for single image super-resolution different scale factors. With adversarial model, effective of transformation function low-resolution input to a high-resolution target can be achieved. In this paper, we propose method and video using recurrent generative named SR <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> GAN. proposed model (SR GAN) use...
Every culture in the world reflects its magnificence and significance through heritage infrastructure it conceives course of civilization. India is composed diverse cultures which reflect grandeur architectural across territory. The necessity for digitizing storing information our country challenging due to sheer scale cultural data collection reliability sources. These challenges can be overcome by harnessing present state art technologies. Advancement technology has impacted every area...
As research in computer vision shifted from processing single, static images to the manipulation of video sequences concept movement recognition has become important. Movements are most atomic primitives, requiring no contextual or sequence knowledge be recognized. Movement is often addressed using either view-invariant view specific geometric techniques. Here an attempt made develop a view-based approach that designed support direct motion itself without reference underlying poses body. The...
With the popularity of social media like Instagram and Snapchat, facial filters or beautifying are used more often. These applications cannot store raw images faces when every time. Thus, they need unique characteristics a face to which can be applied. characteristic points called key points. increasing use such applications, point detection has become popular topic. The objective is extract coordinates in necessary sufficient detect image. Every person different coordinate for each very...
Denoising images is widely used in applications from critical medical systems to software based image enhancement our cell phones. The natural noise simulated by adding an random pixels. Currently the denoising problem can be solved either with greedy algorithm or deep learning techniques. In this paper we are discussing usage of Autoencoders a technique solve denoising. use down-sampling and up-sampling techniques remove unwanted image.By using Encoders compress gradually tiny details like...
Head Pose Estimation is one of the most sought after problems in Computer Vision, as it used many realtime applications such Advanced Driver Assistance System, Augmented Reality and other Artificial Intelligence applications. But existing systems are trained for controlled environment They not robust enough to apply them real-time critical systems. We present a System using convolution neural network augmented by transfer learning algorithm, which enables system adjust with wild environment....
Deep neural networks(DNN) are being extensively used in the field of image recognition, natural language processing(NLP), bioinformatics, computer vision domains and many other fields. DNN applications require huge models as they computationally expensive, over-parameterized have high memory footprints which becomes a bottleneck deployment on embedded devices. Optimization is crucial. In this paper, we summarized recent works done optimization DNNs using various pruning techniques their...