Sanskruti Patel

Dr. Sanskruti Patel

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 March 2016 in International Journal of Information Sciences and Techniques
Verified
Journal Article
Open access
SPSanskruti Patel
Sanskruti Patel
APAtul Patel
Atul Patel

30 August 2019 in International Journal of Engineering and Advanced Technology
Verified
Journal Article
Open access
IPIsha Patel
Isha Patel
SPSanskruti Patel
Sanskruti Patel
Computer vision techniques plays an important role in extracting meaningful information from images. A process of extraction, analysis, and understanding of information from images may accomplished by an automated process using computer vision and machine learning techniques. The paper proposed a hybrid methodology using MKL – SVM with multi-label classification that is experimented on a dataset contained 25000 flower images of 102 different spices. Basic and morphology features including color, size, texture, petal type, petal count, disk flower, corona, aestivation of flower and flower class are extracted to increase the classification accuracy. Various classifiers are applied on extracted feature set and their performance are discussed. The result of MKL – SVM with multi-label classification is very promising with 76.92% as an accuracy rate. In brief, this paper attempts to explore a novel morphology for feature extraction and the applicability of symbolic representation schemes along with different classification strategies for effective multi-label classification of flower spices.

6 July 2021
Verified
Book Chapter
Closed access
PDF file
RPRachana Patel
Rachana Patel
SPSanskruti Patel
Sanskruti Patel

2 February 2023
Verified
Conference Paper
Closed access
SPSanskruti Patel
Sanskruti Patel
Medical imaging technologies are widely utilized as a non-invasive diagnostic process that helps professionals identify diseases and injuries. Convolutional neural networks (CNNs) have become increasingly popular since they are considered to be the best approach for a variety of computer vision problems includes medical imaging and diagnostics. Image segmentation using CNN models makes image analysis easier that can effectively use with different image modalities like X-ray, MRI, CT, Ultrasound and PET. This review article provides a perspective on using CNN models for various medical image segmentation tasks. It contains the details of benchmark deep CNN models available for image segmentation, publicly available medical imaging datasets and various applications of deep CNN models for medical image segmentation tasks.

1 January 2022 in International Journal of Advanced Computer Science and Applications
Verified
Journal Article
Open access
PDF file
SPSanskruti Patel
Sanskruti Patel
RPRachana Patel
Rachana Patel
NGNilay Ganatra
Nilay Ganatra
APAtul Patel
Atul Patel
Biomedical imaging is a rapidly evolving field that covers different types of imaging techniques which are used for diagnostic and therapeutic purposes. It plays a vital role in diagnosis and treating health conditions of human body. Classification of different imaging modalities plays a vital role in terms of providing better care and treatment options to the patients. Advancements in technology open up the new doors for medical professionals and this involves deep learning methods for automatic image classification. Convolutional neural network (CNN) is a special class of deep learning that is applied to visual imagery. In this paper, a novel spatial feature fusion based deep CNN is proposed for classification of microscopic peripheral blood cell images. In this work, multiple transfer learning features are extracted through four pre-trained CNN architectures namely VGG19, ResNet50, MobileNetV2 and DenseNet169. These features are fused into a generalized feature space that increases the classification accuracy. The dataset considered for the experiment contains 17902 microscopic images that are categorized into 8 distinct classes. The result shows that the proposed CNN model with fusion of multiple transfer learning features outperforms the individual pre-trained CNN model. The proposed model achieved 96.10% accuracy, 96.55% F1-score, 96.40% Precision and 96.70% Recall values.

23 October 2020
Verified
Book Chapter
Closed access
PDF file
SPSanskruti Patel
Sanskruti Patel
APAtul Patel
Atul Patel