Kishor Kinage | Pimpri Chinchwad College of Engineering (original) (raw)

Papers by Kishor Kinage

2010 2nd International Conference on Future Computer and Communication, 2010

This paper presents an effective and efficient feature detection method based on eyes location. H... more This paper presents an effective and efficient feature detection method based on eyes location. Here it is assumed that face is already detected. Then algorithm detects the position of pupils in the face image using geometric relation between the face and the eyes. Finally the algorithm normalizes the orientation and grayscale of the face image. The experimental results demonstrated that this algorithm can detect feature and normalize the face image efficiently and accurately. The algorithm can be used in face recognition because the normalized faces can improve the recognition rate.

2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA), 2017

In the digital revolution identifying the attributes of human population has become necessity for... more In the digital revolution identifying the attributes of human population has become necessity for social economic benefit distribution, security and surveillance. Age estimation is one of the interesting and challenging research problem from last several years. Estimation of Age is defined as determine particular person age or age group from given face image. Feature extraction is most important focusing area, were pixel level feature, global feature, local feature are extracted from face image. Person's age is determine based on biometric features. In this paper focus is given on feature extraction. We first perform Pre-processing using HSV Color space model and Gaussian filter from given face image then Hierarchical MAX(HMAX) model are used to extract Biologically Inspired features(BIF). This paper compares our feature extraction approach with standard HMAX algorithm for better age estimation. The experimental result shows that our proposed feature extraction method extract mo...

In this work, we focus on the efficient and effective way of authenticating the person on the bas... more In this work, we focus on the efficient and effective way of authenticating the person on the basis of users typing style. For keystroke biometrics authentication, we propose keystroke latency and total time to capture keystroke latency as parameters to security. Support vector Machine (SVM) algorithm uses the two class classifier to separate the imposter and genuine by using keystroke data of a user. We carried out two phase authentication and implementation of keystroke latency shows 2.38% FAR and 5% FRR.

Eye tracking provides results on when, where and for how long a person looks at a particular stim... more Eye tracking provides results on when, where and for how long a person looks at a particular stimulus. Detecting the face and tracking the eyes, allows getting valuable information to be captured and used in a wide range of applications. Eye location can be tracked using commercial trackers, but additional constraints and expensive hardware make these existing solutions unattractive and impossible to use on standard (visible wavelength), images of eyes with low-resolution. Our aim of the project is to detect the Iris Center with registered database and propose a system that makes the computer screen scroll as per eye gaze. Accuracy of the IC (iris center) localization is measured using Gaze tracking systems.

Visual cryptography (VC) is a encryption scheme used to share secret image. It encodes image into... more Visual cryptography (VC) is a encryption scheme used to share secret image. It encodes image into n shares. These shares are either printed on transparencies or are encoded and stored in a digital form. The shares can look as noise-like pixels or as meaningful images. Decoding does not require all n shares .These shares are printed on transparencies and stacking them top to each other reveal the secret image. In this survey paper, we present the readers a overview of visual cryptography scheme and different approaches of visual cryptography.

— Data management is much tedious task in growing data environment. Partitioning is the best poss... more — Data management is much tedious task in growing data environment. Partitioning is the best possible solution which is partially accepted. Partitioning provides availability, maintenance and improvised query performance to the database users. This paper focuses the three key methods of partitioning and helps to reduce the delay in response time. Paper also investigates the composite partition strategies which includes the date, range and hash partitions. The paper shows the encouraging result with partitioning methods and basic composite partition strategies.

There has been significant progress in improving the performance of computer-based face recogniti... more There has been significant progress in improving the performance of computer-based face recognition algorithms over the last decade. Race and gender also play an important role in face-related applications. Humans are better at recognizing faces of their own ethnicity/race than faces of other races. This phenomenon is sometimes referred to as cross-group deficit or own–group bias effect. In this paper, we investigated whether face recognition, using Eigenface show different racial effects in terms of verification error on the subjects. We performed experiments on a face database containing 143 subjects (1,849 face images, Indian and Non-Indian classes),

In recent years, many different image features have been used for face recognition. Wavelet Trans... more In recent years, many different image features have been used for face recognition. Wavelet Transform is a popular multiresolution analysis tool in image processing and computer vision. Recent researches on multi-scale analysis, especially the curvelet research, provide good opportunity to extract face image features. The transform was designed to represent edges and other singularities along curves much more efficiently than traditional transforms. In this paper we extract image features of facial images from curvelet transform. We then transformed this feature vector into the basis space of PCA and ICA and compared the performance using Euclidean distance measure as classifier. The results show maximum accuracy of 87.50% and 85.00% for curvelet-ICA and curvelet-PCA respectively. Whereas accuracy using PCA and ICA alone was 82.50 and 73% respectively.

— In this paper a multi-resolution analysis based on Independent Component Analysis (ICA) for fac... more — In this paper a multi-resolution analysis based on Independent Component Analysis (ICA) for face recognition is examined. We extract image features of facial images from various wavelet transforms (Haar, Daubechies, Coiflet, Symlet, Biothogonal and Reverse Biorthogonal) by decomposing face image in subbands 1 to 8. These features are analyzed by ICA and Euclidean distance measure. A series of experiments based on ORL database were then performed to evaluate the performance. The results show that for the entire wavelets, subbands 2 and 3 give the best accuracy and are computationally most efficient. Reverse Biorthogonal and 8 th order Symlet are found to be the best among all. Our experiments also prove that face recognition accuracy using ICA on wavelet subbands is higher than ICA used alone.

—In this paper a new face recognition technique based on Two-Dimensional Principal Component Anal... more —In this paper a new face recognition technique based on Two-Dimensional Principal Component Analysis (2DPCA) on Wavelet Subband is proposed. We extract image features of facial images from various wavelet transforms (Haar, Daubechies, Coiflet, Symlet, Biothogonal and Reverse Biorthogonal) by decomposing face image in subbands 1 to 8. These features are analyzed by 2DPCA and Euclidean distance measure. A series of experiments based on ORL database were then performed to evaluate the performance. The results show that for the entire wavelets, subband 3 give the best accuracy and is computationally most efficient. 7th order Symlet is found to be the best among all.

—In this paper a new face recognition technique based on Independent Component Analysis of GaborJ... more —In this paper a new face recognition technique based on Independent Component Analysis of GaborJet (GaborJet-ICA) is proposed. Existing face recognition systems using Gabor wavelets convolve a whole face image with a set of 40 Gabor wavelets. We have derived Gabor feature vector from facial landmarks (fiducial points) known as GaborJets. We then transformed this GaborJet feature vector into the basis space of PCA and ICA. A series of experiments based on ORL database were then performed to evaluate the performance. During our experiments we varied number of subspace dimensions from 2 to 40 and numbers of independent components derived were in the range 1 to 200. As literature on PCA and ICA subject is contradictory, we compared the performance for GaborJet-PCA and GaborJet-ICA. The results show maximum accuracy of 82.25% and 84.5% for GaborJet-PCA and GaborJet-ICA respectively. This proves that the difference in performance between ICA and PCA is of 2.25%, which is insignificant.

2010 2nd International Conference on Future Computer and Communication, 2010

2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA), 2017