WorldServe Education

Bangalore, India

WorldServe Education

Bangalore, India
Time filter
Source Type

Rupanagudi S.R.,WorldServe Education | Vikas N.S.,WorldServe Education | Bharadwaj V.C.,WorldServe Education | Manju M.,WorldServe Education | And 2 more authors.
2014 International Conference on Advances in Electrical Engineering, ICAEE 2014 | Year: 2014

Communicating by those suffering from motor neuron disease has always been an arduous task. A lot of research has been carried out in finding new methods to assist this section of the society in order for them to freely communicate with the outside world. Though several methodologies exist using electrooculography or video oculography, most methods involve complex algorithms which are slow, power hungry and also area inefficient. In this paper we introduce a new proposition, that simple eye blinks could be used by these individuals in order to communicate. These blinks further on could be converted to Morse code to transmit messages, where in each blink represents a dot or a dash. In order to achieve the same, a novel algorithm to first identify the ocular region of the face and also to further identify the blinks using image processing has also been presented. All algorithms were designed and developed for a Spartan 3e series of FPGA and were tested using MATLAB 2011b software. Experiments were conducted under various lighting conditions for a wide set of people and an accuracy of 92% to identify different blinks was achieved. © 2014 IEEE.

Rupanagudi S.R.,WorldServe Education | Huddar S.,WorldServe Education | Bhat V.G.,WorldServe Education | Patil S.S.,WorldServe Education | Bhaskar M.K.,Atria Institute of Technology
2014 International Conference on Advances in Electrical Engineering, ICAEE 2014 | Year: 2014

With the introduction and popularization of text to speech convertors, a huge drop in literacy rates is being seen amongst the visually impaired. Also, since Braille is not well known to the masses, communication by the visually impaired with the outside world becomes an arduous task. A lot of research is being carried out in conversion of English text to Braille but not many concentrate on the alternative i.e. conversion of Braille to regional languages. In order to address this issue, in this paper we introduce a novel methodology to convert Braille characters representing the Kannada Language (a popular language of southern part of India), captured by a camera, into Kannada text or speech. An automated thresholding algorithm for segmentation of the Braille dots along with a novel algorithm for identification of the characters has been explained. All algorithms were designed and developed for a Xilinx Spartan 3E FPGA and were executed in real time. An accuracy of over 94% was achieved in Braille segmentation and detection. The algorithm for identification of the Kannada Braille character was found to be four times faster than many existing methodologies, on the FPGA. © 2014 IEEE.

Huddar S.R.,WorldServe Education | Rupanagudi S.R.,WorldServe Education | Kalpana M.,RYMEC | Mohan S.,Atria Institute of Technology
Proceedings - 2013 IEEE International Multi Conference on Automation, Computing, Control, Communication and Compressed Sensing, iMac4s 2013 | Year: 2013

With the advent of new technology in the fields of VLSI and communication, there is also an ever growing demand for high speed processing and low area design. It is also a well known fact that the multiplier unit forms an integral part of processor design. Due to this regard, high speed multiplier architectures become the need of the day. In this paper, we introduce a novel architecture to perform high speed multiplication using ancient Vedic maths techniques. A new high speed approach utilizing 4:2 compressors and novel 7:2 compressors for addition has also been incorporated in the same and has been explored. Upon comparison, the compressor based multiplier introduced in this paper, is almost two times faster than the popular methods of multiplication. With regards to area, a 1% reduction is seen. The design and experiments were carried out on a Xilinx Spartan 3e series of FPGA and the timing and area of the design, on the same have been calculated. © 2013 IEEE.

Rupanagudi S.R.,WorldServe Education | Ranjani B.S.,WorldServe Education | Nagaraj P.,WorldServe Education | Bhat V.G.,WorldServe Education | Thippeswamy G.,BMS College of Engineering
Proceedings - 2015 International Conference on Communication, Information and Computing Technology, ICCICT 2015 | Year: 2015

Every year farmers experience huge losses due to pest infestation in crops & this inturn impacts his livelihood. In this paper we discuss a novel approach to solve this problem by constantly monitoring crops using video processing, cloud computing and robotics. The paper concentrates in methodologies to detect pests in one of the most popular fruits in the world - the tomato. An insight into how the idea of the Internet of Things can also be conceptualized in this project has been elaborated. © 2015 IEEE.

Prashanth C.R.,BMS College of Engineering | Sagar T.,BMS College of Engineering | Bhat N.,BMS College of Engineering | Naveen D.,BMS College of Engineering | And 2 more authors.
Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013 | Year: 2013

In today's world, Artificial Intelligence (AI) has begun to take center stage. The recent trend has been moving towards the creation of robotic devices which are capable of making spontaneous and effective decisions in demanding situations. One of the challenges faced in such a scenario is dealing with the permutations and combinations of countless real-life circumstances, most of which require to comprehensively train the machine so that it is capable of taking appropriate actions, all the while taking care of any exceptions. Human errors may cause disastrous effects in certain circumstances; such errors can be reduced using AI. One of the most important uses of AI in recent times has been its application in automated vehicles. If the movement of vehicles were to be automated, much time can be saved, and moreover, some amount of travel related stress for humans is lifted. In order to implement the automation of locomotives, detection of any obstructions in the vehicle's path is a must. Also, the algorithm should be robust enough to detect any type of obstacle irrespective of it being a vehicle, barrier or people crossing the road. A successful attempt to perform the same has been discussed in this paper, through a novel yet simple algorithm utilizing image processing techniques. The simulation of the algorithm was performed using the Simulink tool in MATLAB, version 2012a. A success rate of 93% was achieved with respect to the detection of obstacles. © 2013 IEEE.

Dhruva N.,WorldServe Education | Rupanagudi S.R.,WorldServe Education | Sachin S.K.,RNS Institute of Technology | Sthuthi B.,RNS Institute of Technology | And 2 more authors.
Proceedings - 2013 IEEE International Multi Conference on Automation, Computing, Control, Communication and Compressed Sensing, iMac4s 2013 | Year: 2013

Sign language is the most important methodology using which hearing and speech impaired people can interact with the rest of the world. Conversation with hearing impaired individuals gets complicated if the listener is ignorant of sign language. Hence it becomes important to construct a bridge between these two banks. Many sign language and hand gesture recognition algorithms have been developed in the recent years, to assist people who do not have knowledge of sign language to converse with the speech impaired but very few with good results exist. One of the major concerns with respect to hand gesture recognition is segregation or segmentation of the hand and identifying the gesture. This paper explores the various possible ways of segmentation using different color spaces and models and presents the best algorithm with highest accuracy to perform the same. Various experiments were conducted for over 500 different gestures and an accuracy of around 97.4% was achieved with the segmentation algorithm selected. The algorithms were implemented in MATLAB programming language on MATLAB build R2012a. © 2013 IEEE.

Shastry S.,WorldServe Education | Gunasheela G.,WorldServe Education | Dutt T.,WorldServe Education | Vinay D.S.,WorldServe Education | Rupanagudi S.R.,WorldServe Education
Proceedings - 2013 IEEE International Multi Conference on Automation, Computing, Control, Communication and Compressed Sensing, iMac4s 2013 | Year: 2013

Computer vision, artificial intelligence and pattern recognition have been important areas of research for a while in the history of electronics and image processing. Optical character recognition (OCR) is one of the main aspects of computer vision and has evolved greatly since its inception. OCR is a method in which readable characters are recognized from optical data obtained digitally. Many methodologies and algorithms have been developed for this purpose using different approaches. Here we present one such approach for OCR named " i ". Amongst all other OCR systems available, " i " aims at a high speed, simple, font independent and size independent OCR system based on a unique segment extraction technique. This algorithm can be used as a kernel for single alphabet detection within a complete OCR solution system without the need for any complex mathematical operations. The highlight of this methodology is that, it does not use any libraries or databases of image matrices to recognize alphabets, but it has a unique algorithm to recognize alphabets instead. This algorithm has been implemented in MATLAB build R2012a on a test set of 500 images of text and an accuracy of 100% for three font families namely Arial, Times New Roman and Courier New has been obtained. © 2013 IEEE.

Rupanagudi S.R.,WorldServe Education | Ranjani B.S.,WorldServe Education | Nagaraj P.,WorldServe Education | Bhat V.G.,WorldServe Education
Proceedings of 2014 International Conference on Contemporary Computing and Informatics, IC3I 2014 | Year: 2014

Maturity grading or in other words classifying the ripeness of a fruit, based on its color or texture, forms a very important process to be carried out by agriculturists and the food processing industry worldwide. Current techniques mainly involve manual inspection, which leads to erroneous classification, which in turn would cause economical losses due to inferior produce entering the market chain. A loss of yield during storage may also occur with this type of classification, since it would lead to wrong expiry date predictions as well. Several methodologies to automate this process exist but involve highly expensive setups and complicated procedures which are not a viable solution, especially for the agriculturists of a developing nation. In this paper we discuss a cost effective maturity grading system for one of the most popular fruit in the world - the tomato. A novel setup utilizing inexpensive material and image processing algorithms to identify the six important stages of tomato ripening have been presented. All algorithms were designed and developed using Simulink, a part of MATLAB 2011b on a 2.5 GHz CPU. An overall 98% accuracy was achieved with respect to maturity grade detection and an execution speed of greater than 7.6 times was obtained in comparison with two other popular methodologies. © 2014 IEEE.

Dhruva N.,WorldServe Education | Rupanagudi S.R.,WorldServe Education | Neelkant Kashyap H.N.,National Institute of Technology Karnataka
Communications in Computer and Information Science | Year: 2013

The concept of hand gesture recognition has been widely used in communication, artificial intelligence and robotics. It is a staple method of interaction especially for the deaf and the blind. Techniques for recognizing hand gestures are in great demand. Many algorithms have been discovered for this purpose, each of them having their own advantages and disadvantages. In this paper we present a novel algorithm for hand recognition using image processing and explore its application in security based systems. The algorithm was tested for different gestures on over 50 samples and an accuracy of 95.2% was achieved. In terms of speed, the algorithm is 1.5 times faster than its contemporaries. An alternative to finding the centroid based on a less computationally complex algorithm has also been explored. The algorithm was implemented in MATLAB programming language on MATLAB 7.13 build R2011b and SIMULINK. © 2013 Springer-Verlag Berlin Heidelberg.

Ravoor P.C.,BMSCE | Ranjani B.S.,WorldServe Education | Rao Rupanagudi S.,WorldServe Education
Proceedings of the 2012 International Conference on Recent Advances in Computing and Software Systems, RACSS 2012 | Year: 2012

Almost undoubtedly, the greatest invention of the 20th century has been the computer. The computer uses several auxiliary devices to establish a seamless interaction with the user. One challenge faced during the development of these devices, was the lack of direct interfacing between the machine and the user. Today we see Natural User Interfaces (NUI), which include touch activated and speech activated inputs. One problem faced with the touch NUI's is ambiguity. This is mainly due to variations in finger size, proximity of icons, and the fact that the imprint of the finger, called a fingertip blob, may have to be mapped to a single pixel. In this paper we attempt to address the above problems, by focusing on achieving a high level of accuracy at low costs, utilizing image processing techniques, all the while keeping the process simple and fast. A novel algorithm for the same has also been discussed. The algorithm was implemented using the Java programming language on the Java Software Development Kit (JDK) version 1.5.0 (update 22). An accuracy of 100% in fingertip blob detection was achieved and an improvement of 15% was achieved in terms of execution time in comparison with existing algorithms, for various experiments conducted utilizing the new algorithm. © 2012 IEEE.

Loading WorldServe Education collaborators
Loading WorldServe Education collaborators