Search

Hyperspectral face recognition is a very challenging task as well as time-consuming process. Hyperspectral face images (HFI) are a very big size images as compare to normal RGB images. HFI is always more than 10 bands with spatial resolution and its size varies from camera to camera. To execute these large numbers of files, a big memory is required due to high dimensions. Principle Component Analysis is used with double layer feature extraction to reduce the dimensional size without losing the prominent features. Double layer PCA is applied on the Hong Kong Polytechnic University’s Hyperspectral Face Database (PolyU-HSFD) and classify on the basis of k-nearest neighbor.

In this paper presents biometrics based fingerprint and palmprint recognition and authentication system. Fingerprint and palmprint images are enhanced using preprocessing techniques such as morphological operations. The feature extraction techniques such as neighborhood operation and FAST feature algorithm is used to independently extract fingerprint and palmprint features. These techniques are more reliable and faster than traditional techniques used. Experimental results shown recognition rate 89.29% for fingerprint and 100% for palmprint this implies that the proposed methodology has better performance and is more reliable over the techniques proposed and used earlier. Abbrevations SF Single Flat SFF Single Flat Flexi LT Left Thumb finger LI Left Index finger LM Left Middle finger LR Left Ring finger LL Left Little finger

Dorsum of the hand can be very useful in Personal identification but yet it has not that much extensive attention. Single scan of dorsum hand can give two biometric traits finger-knuckle and finger nail. This paper presents an approach to combine Finger-knuckle and finger-nail features. Finger nail biometric is considered as quite unique biometric trait hence we combine this trait with finger knuckle. We also developed an algorithm to extract ROI from Finger-knuckle and finger-nail. Finger- knuckle features are extracted using Mel Frequency Cepstral Coefficient (MFCC) technique and the features of finger-nail are extracted from second level wavelet decomposition. We combined these features using feature level fusion and feed forward back-propagation Neural Network for classification. The performance of the system has been tested on our own KVKR- knuckle database that includes 100 subject's dorsal hands. Evaluation results shows that increase in training set gives increased performance rate. The best performance of the proposed system reaches up to 97% with respective training of 90% of total dataset. 

Biometric is emerging area in the computer science for the secure various systems. Day to day life peoples are preferred to use, robust and highly acceptable security system which can surpass the human errors. Many scientists are engaged to develop a strong biometric system, but there are a lot of challenges in the real time application. It is observed and found that researchers are only working on too old laboratory databases such as Olivetti Research Laboratory (ORL). But now a day's various cost effective data acquisition sensors are coming on the market with high resolution of the data. When we are using a different type of data capturing devices gives the difference in performance of recognition rate. In this work we have proved that recognition rate is affected by the various sensors as well as database environment. For robust face recognition system suitable algorithms are suggested to different type of sensors.

Day to day life is more unsecure as per the hacking is concerned. Our data is not secure because it can be stolen, hacked, destroy, manipulate, password may forget, guess, Card, token, etc. To overcome this problem biometrics is used as a strong authentication system. The person should be present at the time of the instance. Biometric security is challenging task in day to day life because it is difficult to avoid the fraud. In this research paper emerging biometric trait, i.e. Hyper Spectral Face is considered for human authentication system. There are various visible spectrum of electromagnetic spectral bands are considered for face recognition instead of only three RGB bands. Hyper Spectral gives band wise more finite detail information on face. It is very novel and more accurate than ordinary face recognition system. Hong Kong PolyU Hyper Spectral Face Database used for Face recognition. Kernel Principle Component Analysis (KPCA) algorithm gives prominent features of the Hyperspectral Face Dataset. Extracted features are classified by Mahalinobis Cosine (Mahcos) similarity measurement technique. The Recognition rate calculated on the basis of One Rank Level it furnishes 69.20%.

Compound character recognition of Devanagari script is one of the challenging tasks since the characters are complex in structure and can be modified by writing combination of two or more characters. These compound characters occurs 12 to 15% in the Devanagari Script. The moment based techniques are being successfully applied to several image processing problems and represents a fundamental tool to generate feature descriptors where the Zernike moment technique has a rotation invariance property which found to be desirable for handwritten character recognition. This paper discusses extraction of features from handwritten compound characters using Zernike moment feature descriptor and proposes SVM and k-NN based classification system. The proposed classification system preprocess and normalize the 27000 handwritten character images into 30x30 pixels images and divides them into zones. The pre-classification produces three classes depending on presence or absence of vertical bar. Further Zernike moment feature extraction is performed on each zone. The overall recognition rate of proposed system using SVM and k-NN classifier is upto 98.37%, and 95.82% respectively.

Handwritten Devanagari Compound character recognition is one of the new challenging task for the researcher, because Compound character are complex in structure, they are written by combination two or more character. Their occurrence in the script is up to 12 to 15%. In this research paper, a recognition system for handwritten Devanagari Compound Character is proposed bases on Legendre moment feature descriptor are used to recognize. Moment function have been successfully applied to many pattern recognition problem, due to this they tends to capture global features which makes them well suited as feature descriptor. The process image is normalized to 30X30 pixel size divided into zone, from this structural as well as statistical feature are extracted from each zone. The proposed system is trained and tested on 27000 handwritten collected from different people. For classification we have used Artificial Neural Network. The overall recognition rate for basic is up to 98.25% and for all compound character is 98.36%.

Over many decades lines on hands used for astrological and numerology analysis because there is a trust that Lines never lie. Dorsum of the hand can be very useful in personal identification but yet it has not that much extensive attention. Single scan of dorsum hand can give two biometric traits finger-knuckle and finger nail. This paper presents an approach to combine Finger-knuckle and finger-nail features. Finger nail biometric is considered as quite unique biometric trait hence we combine this trait with finger knuckle. Finger knuckle features are extracted using Mel Frequency Cepstral Coefficient (MFCC) technique and the features of finger-nail are extracted from second level wavelet decomposition. We combined these features using feature level fusion and feed forward back propagation neural network for classification. The performance of the system has been tested on our own KVKR-knuckle database that includes 100 subjects dorsal hands. Evaluation results shows that increase in training set gives increased performance rate. The best performance of the proposed system reaches up to 97% with respective training of 90% of total dataset.