Diptee Chikmurge - Academia.edu (original) (raw)

Uploads

Papers by Diptee Chikmurge

2023 1st International Conference on Circuits, Power and Intelligent Systems (CCPIS)

2023 International Conference on Network, Multimedia and Information Technology (NMITCON)

Proceedings in adaptation, learning and optimization, 2023

International journal of scientific research in science, engineering and technology, Feb 25, 2016

A huge amount of image data is generated everyday due to rapid evolution of image capturing devic... more A huge amount of image data is generated everyday due to rapid evolution of image capturing devices. Information associated to images has got diversified applications. The medical imaging systems produce more and more digitized images in all medical fields. Most of these images are stored in image databases. There is a great interest to use them for diagnostic and clinical decision such as case-based reasoning. The purpose is to retrieve desired images from a large image databases using only the numerical content of images. CBIR system (Content-Based Image Retrieval) is one of the possible solutions to effectively manage image databases. Furthermore, fast access to such a huge database requires an efficient computing model. The Hadoop framework is one of the findings based on MapReduce distributed computing model. Lately, the MapReduce framework has emerged as one of the most widely used parallel computing platforms for processing data on terabyte and petabyte scales. It can able to provide more accurate results to the users. Therefore we are introducing a new method for retrieving images called as “CBIR over Hadoop using Map Reduce.”

In today's computing world 1 in 50 people have been diagnosed by some form of paralysis, temp... more In today's computing world 1 in 50 people have been diagnosed by some form of paralysis, temporary or permanent ,so the need for the physical reformatio n treatment for paralyzed patients is getting incr eased day by day. It is highly impossible to therapist and docto rs to assist each patient for the purpose of treatm ent, thus the problem is getting more and more serious in coming future and also physician experiences may not be sufficient to achieve high quality medical results. So that's wh y CPM machine is being developed and used in foreign country. This continuous passive motion device is very expen sive and barely available in our country. The purpo se of the project is to define standard and 100 percent accur ate therapy treatment methodology that specifies be tter settings of the continuous passive motion device could decrease the overall treatment time and may improve patient 's outcome, and also to make continuous passive motion affordable to common people.

The aim of this paper is to compare various methods for face recognition. In this paper we are go... more The aim of this paper is to compare various methods for face recognition. In this paper we are going to discuss various techniques for face recognition. This paper includes a brief description of PCA (Principle Component Analysis), LDA (Linear Discriminant Analysis), LBP (Local Binary Pattern), Gabor filter, LGBP (Local Gabor Binary Pattern). Comparative study of various methods is discussed in this paper and from this study a suitable and more efficient technique is found out which will give more effective result.

Within the last ten years we have been witnessing interest in research in the processing of Satel... more Within the last ten years we have been witnessing interest in research in the processing of Satellite Images. In today’s digital era, integration of any form of data from heterogeneous datasets is considered as inevitable. This becomes complex when database is of large size. Considering the increased importance surface recognition, segmentation, as well as event detection in satellite images with a highly scalable system is becoming more and more desirable. In this project, we will construct a semantic taxonomy for the land-cover classification of satellite images. According to statistics it is estimated that 90% of the modern digital multimedia data has been created in the last 10 years. As an open source distributed computational framework, Hadoop helps in processing large amounts of images on an infinite set of computing nodes by providing necessary infrastructures, which gives advantages over the existing MATLAB system which is closed under the licence and is complex. The system...

Advances in Intelligent Systems and Computing, 2017

Generally, in the medical field early diagnosis of the disease was performed using MRI, CT scans,... more Generally, in the medical field early diagnosis of the disease was performed using MRI, CT scans, X-ray, and ultrasound images. These medical images were captured in Digital Imaging and Communication in Medicine (DICOM) format (Bhagat and Atique in Medical Images: Formats, Compression Techniques and Dicom Image Retrieval Survey, 2012) [1]. As per the structure of DICOM image, physicians were unable to detect strangeness or disease in the patient without any image processing. Image processing and machine learning process can be useful to identify strangeness in these images by evaluating feature extraction and boundary detection of DICOM images which aims to help experts to analyze medical images. These medical images actively engaged in the medical field to diagnose disease and give proper treatment. Nowadays due to increase in the large database of DICOM images, the classification and retrieval of images have been a critical task for diagnosis of disease. The content-based image retrieval is effectively applicable for effective treatment of disease. Canny edge detection algorithm is useful for extracting features of medical images.

Hybrid Intelligent Systems, 2020

Marathi handwritten character recognition is the most challenging task in Optical Character Recog... more Marathi handwritten character recognition is the most challenging task in Optical Character Recognition (OCR) research domain. The need for OCR to convert Marathi handwritten documents or scripts to editable text, which can be attained by the proposed work, which will reduce the burden of storage space, the task of data entry in forms in Marathi language and converts degraded historical documents in editable text. Moreover, Handwritten Marathi characters tend to more complicated due to their structure, shape, several strokes, and different writing styles. The character recognition involved four necessary procedures like Pre-Processing on input character images, Segmentation of characters in words, Extraction of features of segmented characters, and Classification, to recognize the Marathi characters with a different style. In this paper, handwritten Marathi single character accepted as input, and the features are extracted using the Histogram Oriented Gradient method (HOG), whereas characters classified using Support Vector Machine (SVM) and K-Nearest Neighbor algorithm (KNN).