Suresh Salankar - Academia.edu (original) (raw)

Papers by Suresh Salankar

2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), 2017

2021 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON), 2021

2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), 2016

2021 IEEE International Conference on Mobile Networks and Wireless Communications (ICMNWC), 2021

Recent survey’s revealed that " IRIS" biometric recognition method becomes a very popul... more Recent survey’s revealed that " IRIS" biometric recognition method becomes a very popular technique and gained a lots of attraction by various researchers in different types of fields like security systems, industrial field, medical fields, educations fields etc. for detecting any personnel . As it has very high rate of accuracy and distinct features it has been widely applied and used in widen areas where the control on access and security factor plays a very important role. The need of iris recognition is going on increasing day-by-day as it has much accuracy, reliability, and distinct features. This technique gives a very effective and powerful identification features extraction technique from all the available biometric system as we all know that human iris is a static feature and will not be changed or get affected by any environmental situation during the complete life span of a human being. For the effective performance of an iris recognition system researchers have to do more work on different challenges arises during the operation of the iris system such as various images collected in unsteady environmental condition, noisy and blurred images and many other conditions. The main aim of our research work is to discuss the various methods and techniques has been used till now by different research scholars for iris recognition and various steps required in iris recognition process.

Image enhancement is used to reduce the noise and improve resolution contrast of the image. The i... more Image enhancement is used to reduce the noise and improve resolution contrast of the image. The images can be improved by improving the quality regarding the pixel values. The pixel values are manipulated with the number of inputs and the gray level values. On the other hand Fuzzy image enhancement is based on gray level mapping into a fuzzy plane, using a membership function. This paper compares the enhancement performance of commonly used Median Filter and Fuzzy Inference System. Both the methods are tested on 15 MRI brain images. The comparison is based on the parameter Peak Signal to Noise Ration. Fuzzy Inference System shows 17.74 percent improvement in PSNR than Median Filter with improvement in image appearance.

Smart Innovations in Communication and Computational Sciences, 2018

2015 International Conference on Computational Intelligence and Communication Networks (CICN), 2015

The quality of texture image classification depends on quality of texture features and classifica... more The quality of texture image classification depends on quality of texture features and classification algorithms. Most important is to select texture features with highly discriminative to inter-class textures. In this paper, features are extracted from texture images using Gray Level Co-occurrence method and Wavelet method. Haralick features with a feed forward neural network show classification accuracy of 98.21%, while Wavelet features show classification accuracy of 96.05% for the same data. These results show that Haralick features are suitable for texture classification.

2015 International Conference on Computational Intelligence and Communication Networks (CICN), 2015

2021 6th International Conference on Inventive Computation Technologies (ICICT), 2021

This paper describes the face tracking using Camshift with BLBP Algorithm in head gesture recogni... more This paper describes the face tracking using Camshift with BLBP Algorithm in head gesture recognition system. The major constraints of the head gesture recognition system such as face detection, feature extraction, tracking, and recognition are explained. Adaboost algorithm is used for detection and Camshift algorithm for tracking with different feature extraction methods. Performed extensive experimentations and presented a face tracking analysis in a head gesture recognition system under cluttered backgrounds, shadow, and sunshine conditions. Experimental results show the robustness in face detection, tracking, and direct recognition of the proposed method.

2019 9th International Conference on Emerging Trends in Engineering and Technology - Signal and Information Processing (ICETET-SIP-19), 2019

Security of data is a primary need for all the system. The AES-RC4 hybrid cryptosystem gives the ... more Security of data is a primary need for all the system. The AES-RC4 hybrid cryptosystem gives the combine advantages of Advanced Encryption Standard (AES) To data encryption and decryption, to secure the key used for data encryption-decryption Rivest Cipher 4 RC4 is used. This system is designed using the Co-designed approached where AES and RC4 run on the NIOS II integrated development environment (IDE) soft-core. The implementation is on Cyclone IV FPGA, Rijndael algorithm program supported " NIOS II + FPGA" are able to do better performance in the area of latency where it comparatively uses low resources. The results are analysed in the IDE console window of a personal computer system.

2015 International Conference on Computational Intelligence and Communication Networks (CICN), 2015

In this paper, a hybrid intelligent machine learning technique for automatic classification of br... more In this paper, a hybrid intelligent machine learning technique for automatic classification of brain magnetic resonance images is presented. The proposed multistage technique involves the following computational methods, Otsu's method for skull removal, Fuzzy Inference System for image enhancement, Modified Fuzzy C Means with the Optimized Ant Colony System for image segmentation, Second Order Statistical Analysis and Wavelet Transform Method for feature extraction and the Feed Forward back-propagation neural network to classify inputs into normal or abnormal. The experiments were carried out on 200 images consisting of 100 normal and 100 abnormal (malignant and benign tumors) from a real human brain MRI data set. Experimental results indicate that the proposed algorithm achieves high classification rate and outperforms recently introduced methods while it needs a least number of features for classification.

Face detection is a computer technology that determines the location & size of human faces in dig... more Face detection is a computer technology that determines the location & size of human faces in digital images. Thus by determining the head gesture of person sitting on robo chair the controlling of the chair can be done by the improved Adaboost algorithm. The recognized gestures are used to generate motion control commands to the low-level DSP motion controller so that it can control the motion of the Robo Chair according to the user’s need. Looking for something, when the commands for the movement are generating must be considered unnecessary movement, thus to avoid this, Head gesture interface focused on the central position of a person sitting on robo chair & identify only the useful head gesture. This paper determines, the improved Adaboost algorithm used for face detection is to increase the output results for the system, effectiveness of the system & efficiency on which the system implements. The concept of Obstacle detection is also used for the enhancement of the system, it ...

This paper proposes a novel approach for an optimal multi-objective optimization for VLSI impleme... more This paper proposes a novel approach for an optimal multi-objective optimization for VLSI implementation of Artificial Neural Network (ANN) which is area-power-speed efficient and has high degree of accuracy and dynamic range. A VLSI implementation of feed forward neural network in floating point arithmetic IEEE-754 single precision 32 bit format is presented that makes the use of digital weights and digital multiplier based on bit serial architecture. Simulation results with 45 nm & 90 nm tech file on Synopsis Design Vision Tool, Aldec’s Active HDL tool, Altera’s Quartus tool & MATLAB showed that the bit serial architecture (TYPE III) based multiplier implementation and use of floating point arithmetic (IEEE -754 Single Precision format) in ANN realization may provide a good multi-objective solution for VLSI implementation of ANN. Keyword — Artificial Neural Network (ANN), bit serial architecture (type III) based multiplier, array multiplier, floating point arithmetic, multi-layere...

This paper présents a new approach for multi-objective optimization of area-delay-power simultane... more This paper présents a new approach for multi-objective optimization of area-delay-power simultaneously for VLSI implementation of digital finite impulse response filter. It is based on use of concept of multiple constant multiplication approach with partial product sharing and coefficient reuse in multiplier module and /or digit serial architecture in adder module design along with fixed point arithmetic. Designs are synthesized using Synopsys Design Compiler in 90 nm & 45 nm process technology. The synthesis results shows that proposed approach provide a good multi-objective optimization technique for digital FIR filter compared to other previous findings published in last decade.

Automatic image analysis of breast histopathology images helps in efficient detection of breast c... more Automatic image analysis of breast histopathology images helps in efficient detection of breast cancer. Breast cancer is one of the most frequently diagnosed cancers in women. Breast cancer is one of the most common cancers among woman of the developing countries in the world, and it has also become a major cause of death.For cancer diagnosis and grading ,it is essential to examine the tissue specimens of histopathological images. This examination depends on visual interpretation of pathologists .To overcome this problem, it is important to develop computational quantative tool in which segmentation plays a vital role. This paper proposes an efficient segmentation of cell nuclei in breast histopathology images and its classification using neural network. The segmentation of cell nuclei is an important step in automatic analysis of digitized microscopic images, hence Graph cut algorithm is used for segmentation .After segmentation of cell nuclei features are extracted and are given a...

The image segmentation is the process of partitioning digital image into its multiple segments. I... more The image segmentation is the process of partitioning digital image into its multiple segments. Image segmentation is typically used to locate objects and boundaries in image. A robust segmentation technique based on an extension to the tradition improved fuzzy c-means (IFCM) clustering algorithm is proposed in this project. A neighborhood attraction, which is dependent on the relative location and features of neighboring pixels, is shown to improve the segmentation performance dramatically. Through this project we aim to segment MRI images of brain tissue with improved Fuzzy C-Means with the help of neural network optimization. In MR images, the presence of noise or artifacts can change the intensities of some pixels these may be segmented more appropriately with the help of their neighboring pixels in IFCM. The measurement of similarity was extended by considering neighborhood attraction. MRI images posses good contrast resolution for different tissues and has advantages over tomo...

In the present days, Iris recognition as a physiological attribute of biometric is an important b... more In the present days, Iris recognition as a physiological attribute of biometric is an important biometric process. Human eye iris acts as a significant task in vast identification of a human being. In this research work, the block sum and Haar transform algorithms i.e. hybrid algorithms are presented as a feature extraction method. After extracted features, hybrid based PSO classifier is used for classification. Hybrid based PSO classifier contains the combination of weighted DAG multi-class SVM and SNN i.e. spiking neural network. Internally weighted DAG multi class SVM is used for classification and SNN is used for optimization of PSO. For performing an experiment, we have taken 280 images of eye from 28 individuals and every person has 10 images of eye from CASIA version VI iris database. Experimental result shows that the hybrid PSO based classifier gives superior result in evaluation with other methods i.e. SVM and ANN. By using this method the average classification accuracy i...

The Digital era marked by the unrivalled growth of Internet and its services with day-to-day tech... more The Digital era marked by the unrivalled growth of Internet and its services with day-to-day technological advancements has paved way for a data driven society. This digital explosion offers opportunities for extracting valuable information from collected data, which are used by organizations and research establishments for synergistic advantage. However, privacy of online divulged data is an issue that gets overlooked as a consequence of such large-scale analytics. Although, privacy and security practices conjointly determine the ethics of data collection and its use, personal data of individuals is largely at risk of disclosure. Considerable research has gone into privacy preserving analytics, in the light of Big Data and IoT boom, but scalable and efficient techniques, that do not compromise the usefulness of privacy constrained data, continues to be a challenging arena for research. The proposed work makes use of a distance-based perturbation method to group data and further ran...

2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), 2021

In this article, hardware and software tools is proposed to process image in satellite image proc... more In this article, hardware and software tools is proposed to process image in satellite image processing systems so that the parameters can be calculated and make image viewable according to user requirements. This is a basic approach to solve real-time problems for water bodies like oceans. The extraction of Water bodies is difficult because of mountain and building shadow. There are three water indices for water bodies extraction namely, Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI) and Automated Water Extraction Index (AWEI) that extract water in real-time with onboard image processing system using FPGA. By selecting any input image there are given three options of NDWI, MNDWI and AWEI. When any one option is selected then the output is obtained according to selected indices. The proposed system of onboard real-time image processing using hardware software combination reduces total time to procure satellite image and extraction of wat...