Papers by Dr. Kruti Dangarwala
International Journal of Computer Applications, 2016
Noise is an unwanted information present in an image. Such unwanted information in an image can b... more Noise is an unwanted information present in an image. Such unwanted information in an image can be removed with filters. In digital image processing, filters can be applied on an image in two ways, which include spatial and frequency domain. This paper mainly deals with the application of spatial domain filters on noisy images for the purpose of identifying the efficiency of the filters in terms of enhancing the quality of the image by removing the noise present on it.
Just about all the newest living room audio-video electronics and PC multimedia products being de... more Just about all the newest living room audio-video electronics and PC multimedia products being designed today will incorporate some form of compressed digitized-audio processing capability. Audio compression reduces the bit rate required to represent an analog audio signal while maintaining the perceived audio quality. Discarding inaudible data reduces the storage, transmission and compute requirements of handling high-quality audio files. This paper covers wave audio file format & algorithm of silence compression method and companding method to compress and decompress wave audio file. Then it compares the result of these two methods.
77 www.erpublication.org Abstract— Image segmentation is a considered to be an integral part of... more 77 www.erpublication.org Abstract— Image segmentation is a considered to be an integral part of the OCR process. The positives of the recent advancements in the OCR are imputed to the better manipulation of images in terms of segmentation. The proposed paper is a review of the progress made. Segmentation methods are listed under three main techniques. The first technique, Hough Transform, takes into consideration various mathematical equations to expedite the segmentation process. The second technique uses the connected components to segment the images. Lastly it uses clustering algorithm to define several of the data points of the image.
Survey on sportsperson positional marking system
2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), 2017
In the modern era game of professional and amateur basketball, automated statistical positional m... more In the modern era game of professional and amateur basketball, automated statistical positional marking, referral in actual time and video footage analysis for the same have become a part and parcel for the game. Every pre-match discussion is dominated by extensive study of the opponent's defensive and offensive formation, plays and metrics. A computerized video analysis is required for this reason as it will provide a concise guide for analysis. In addition there is a serious impact on the game due to dubious call by referees on real time judgemental calls. A video analysis will make real time video referrals a possibility. Thus in a nutshell a player positional marking system can generate statistical data for strategic planning and achieve proper rule enforcement. This research presents survey on available sports system which tries to place the point of sportsperson.
A Research Gap on Automatic Indian Sign Language Recognition Based on Hand Gesture Datasets and Methodologies
Sign language plays vital role in the life of any auditory impaired individual but it does not ge... more Sign language plays vital role in the life of any auditory impaired individual but it does not get same status as any other language. Hand gestures are most widely used as medium of sign language based communication framework among various forms of gestures. Recognizing gestures under dynamic parameters such as lighting conditions, multiple hands as background, left handed person, right handed person, size of finger etc. are thoughtprovoking field in automate Indian sign language recognition . A review is based on datasets of hand gestures alphabets, digits, words and sentences with various real time conditions used by different researchers at national and international level. The detailed summarization of various methodologies to automate Indian sign language is tabularized. A review is utilized to find out research gaps in existing system and give inspiration to develop interpreter for Indian sign language.
Diagnosis of plant disease is a task of identifying the disease in the leaf or fruit or vegetable... more Diagnosis of plant disease is a task of identifying the disease in the leaf or fruit or vegetable. About 42% of the world’s agriculture harvest is destroyed yearly by disease and pest. However, losses of harvest can be minimized and specific treatments can be applied if plant diseases are correctly identified early. Manual identification of disease in the plant is not only time consuming but also does not give accurate result. So, providing fast, automatic and accurate solution using image processing techniques can be a good realistic significance. Automatic identification of diseases using image processing techniques can be done by using five methods like Image Acquisition, Image Preprocessing, image segmentation, Feature extraction and classification. Over last few years, many research works are carrying out in this area. This paper provides a brief overview on methodology. Further, paper reviews recent research trends to identifying disease in the plant which is based on image pr...
Motion detection is a main task for video Surveillance system. In video surveillance, motion dete... more Motion detection is a main task for video Surveillance system. In video surveillance, motion detection refers to the capability of the surveillance system to detect motion. Video surveillance is the procedure of finding a moving object or various objects over a period utilizing camera. Video Surveillance is a term given to monitor the behavior of any kind through videos. It requires person to monitor the CCTV and huge volume of memory to record it. One of the major challenges involved is the huge volume of video storage and retrieval of the same on demand. In order to avoid the depletion of human resources and to detect the suspicious behaviors that threaten safety and security, Intelligent Video Surveillance system (IVS) is required Because of key feature of video surveillance, it has a various uses like human-computer associations, security and surveillance, video communication, traffic control, open territories, for example, airports, underground stations, mass events, and so on....
The shredded document reconstruction is a standout amongst the most widely utilized techniques fo... more The shredded document reconstruction is a standout amongst the most widely utilized techniques for semi computerized or mechanized recovery of detailed records from tore up documents. Reconstructing the shredded files manually is similar to resolve a jigsaw puzzle however because of uneven edges, shapes and measurement this assignment turns into very boring and intricate. It’s a helpful job for forensic investigation science, historical artefact reconstructions. A generalized architecture for the shredded document reconstruction is proposed on this paper. On this paper we have now talked concerning the routines to reconstruct the ripped documents using various algorithms with their advantages and disadvantages.
Alphabet Classification of Indian Sign Language with Deep Learning
Blind Source Separation (BSS) refers to the process of recovering source signals from a given mix... more Blind Source Separation (BSS) refers to the process of recovering source signals from a given mixture of unknown source signals were in no prior information about source and mixing methodology is known. Independent Component Analysis (ICA) is widely used BSS technique which allows separation of source components from complex mixture of signals based on certain statistical assumptions. This paper covers up the fundamental concepts of ICA and reviews different algorithms of Independent Component Analysis. In addition, the merits and demerits of each algorithm are outlined. Finally brief description of recent application in ICA is presented. Keywords—Blind Source Separation; Independent Component Analysis ; Mixing
Deep Convolution Neural Network Model for Indian Sign Language Classification
Lecture Notes in Electrical Engineering, 2020
Communication gap between non-hearing and hearing people results in many interaction difficulties... more Communication gap between non-hearing and hearing people results in many interaction difficulties across the globe. Indian sign language is the traditional communication alternative in our country. Recently, the integration of deep learning with convolution neural network plays a major role in solving various image classification problems. The proposed deep convolution neural network model is prepared with six convolution layers and three fully connected layers by altering different parameters. This model is evaluated based on 1000 number sign images. These datasets are created in college laboratory with 100 different students. Here, 1–10 number sign images are collected, and the proposed CNN model by six convolutional layers with 1000 epochs is applied. This study highlights the training and validation accuracy analysis as well as training and validation losses. Different performance metrics are calculated to find out the accuracy of the proposed model. The aim of developing the proposed model is to find out classification accuracy for each class. This is multiclass problems as each number signs contain 100 images. This model can predict 10 different signs classes. We have taken 200 signs from 1000 number signs for testing purpose. The results indicate that the accuracy of the proposed method is rapidly increased by increasing the epochs. We have achieved 73% average classification model accuracy.
International Journal of Recent Technology and Engineering (IJRTE), 2019
Indian sign language is communicating language among deaf and dumb people of India. Hand gestures... more Indian sign language is communicating language among deaf and dumb people of India. Hand gestures are broadly used as communication gestures among various forms of gesture. The real time classification of different signs is a challenging task due to the variation in shape and position of hands as well as due to the variation in the background which varies from person to person. There seems to be no availability of datasets resembling to Indian signs which poses a problem to the researcher. To address this problem, we design our own dataset which is formed by incorporating 1000 signs for the sign digits from 1 to 10 from 100 different people with varying backgrounds conditions by changing colour, and light illumination situations. The dataset comprises of the signs from left handed as well as right handed people. Feature extraction methodologies are studied and applied to recognition of Sign language. This paper focuses on deep learning CNN (convolution neural network) approach with ...
Image compression is the art of reducing the size of data that represents a digital image; withou... more Image compression is the art of reducing the size of data that represents a digital image; without degrading the quality of the image. Large quantity of digital data is required to store an image. Though there is technological advancement in storage space required to store data but the demand for storage capacities is not satisfied by the availability. In such scenario image compression can be considered as the only solution. This paper addresses different image compression techniques and comparative analysis of Huffman encoding, Arithmetic coding, Run length coding, Transform coding and Wavelet coding is provided. Review will allow new researchers to study different techniques of image compression and provide them direction to choose best technique for their application.
Ijca Proceedings on National Conference on Communication Technologies Its Impact on Next Generation Computing 2012, Jul 11, 2012
Digital Steganography is a process of hiding confidential digital information into a file of any ... more Digital Steganography is a process of hiding confidential digital information into a file of any kind. Digital Information is a resource which holds a lot of value in the modern world. In this paper we propose Steganography with SMS alert which is an approach to send secure digital information over a network in a secure way. The proposed algorithm secures files and messages and targets enterprise level security to hide and deploy digital information without the risk of network attacks or data theft.
Survey of Multimedia Efficient Compression Features
ABSTRACT
Security and Service Discovery Issues in Mobile Ad-hoc Networks
ABSTRACT
International Journal of Engineering Research and, 2015
The main goal of data compression is to decrease redundancy in warehouse or communicated data, so... more The main goal of data compression is to decrease redundancy in warehouse or communicated data, so growing effective data density. It is a common necessary for most of the applications. Data compression is very important relevancy in the area of file storage and distributed system just because of in distributed system data have to send from and to all system. Two configuration of data compression are there "lossy" and "lossless". But in this paper we only focus on Lossless data compression techniques. In lossless data compression, the wholeness of data is preserved. Data compression is a technique that decreases the data size, removing the extreme information. Data compression has many types of techniques that decrease redundancy. The methods which mentioned are Run Length Encoding, Shannon Fanon, Huffman, Arithmetic, adaptive Huffman, LZ77, LZ78 and LZW with its performance.
Moving object detection: Review of recent research trends
2015 International Conference on Pervasive Computing (ICPC), 2015
Moving object detection is the task of identifying the physical movement of an object in a given ... more Moving object detection is the task of identifying the physical movement of an object in a given region or area. Over last few years, moving object detection has received much of attraction due to its wide range of applications like video surveillance, human motion analysis, robot navigation, event detection, anomaly detection, video conferencing, traffic analysis and security. In addition, moving object detection is very consequential and efficacious research topic in field of computer vision and video processing since it forms a critical step for many complex processes like video object classification and video tracking activity. Consequently, identification of actual shape of moving object from a given sequence of video frames becomes pertinent. However, task of detecting actual shape of object in motion becomes tricky due to various challenges like dynamic scene changes, illumination variations, presence of shadow, camouflage and bootstrapping problem. To reduce the effect of these problems, researchers have proposed number of new approaches. This paper provides a brief classification of the classical approaches for moving object detection. Further, paper reviews recent research trends to detect moving object for single stationary camera along with discussion of key points and limitations of each approach.
International Journal of Engineering Research and, 2015
Image Compression is useful technique through which we can reduce the storage space of images whi... more Image Compression is useful technique through which we can reduce the storage space of images which will helpful to increase storage and transmission process with saving the channel bandwidth. There are number of algorithms available for lossy and lossless image compression. As lossy technique is not reversible so it is beneficial to use lossless technique to recover the original image. In this paper we analyze different types of existing method of lossless image compression. The methods which are discussed are Run Length Encoding, Huffman coding, Arithmetic, and LZW with its performance.
International Journal of Engineering Research and, 2015
Data compression is now almost a common requirement for every applications as it is a means for s... more Data compression is now almost a common requirement for every applications as it is a means for saving the channel bandwidth and storage space. Data Compression is an art of allowing a technique to reduce the volume of data i.e. excess information, by maintaining the quality of data. There a number of algorithms available for compression of files of different formats. But, algorithm is to be such a chosen which reduces redundancy of data by consuming less time and providing more compression ratio as compared to other techniques. So, even for a single data type, numbers of approaches are available and to select among them the best one depending upon the need is very important and a difficult task. Compression methods are categorized as Lossy and Lossless but in this paper focus is only on Lossless text compression techniques. The methods which are discussed are Run Length Encoding, Shannon Fanon, Huffman, Arithmetic, LZ77, LZ78 and LZW with its performance.
Uploads
Papers by Dr. Kruti Dangarwala