Research Cell: An International Journal of Engineering Sciences

Manpreet Kaur ¹

Affiliations
1 Computer Engineering Department, Yadavindra College of Engineering, Punjabi University, Guru Kashi Campus, Talwandi Sabo (Punjab), IN

Abstract

Machine printed and handwritten words are sometimes mixed in a single document like in data entry forms. Since the algorithms for recognition of machine-printed and handwritten text are based on different techniques, so it is necessary to separate between these two types of texts before feeding it to respective optical character recognition systems. This separation will definitely increase the performance and overall system quality. Handwritten/machine-printed classification is the process to discriminate handwritten from machine-printed text and is a challenging task. It includes two issues first is detecting the letters and then classifier will classify the machine written text and hand written text. The proposed techniques is based on structural features of text i.e. aspect ratio of the text is calculated to discriminate between handwritten and machine printed text and results show the effectiveness of proposed approach.

Keywords

OCR, Machine-Printed Text, Handwritten Text.

Full Text

   

Manpreet Kaur ¹, Manpreet Kaur ¹, Lalit Kumar ¹

Affiliations
1 Department of Computer Science and Engineering, GZS PTU CAMPUS, Bathinda, Punjab, IN

Abstract

While people have had the inborn ability to identify and compare different faces for millions of years, computers are just now captivating this. In this paper, the techniques of how computers are shaping your face into computer code are compared to millions of other faces are illustrated. How facial recognition software is being used in criminal investigations, elections and to protect your personal computer.

A facial recognition system is a computer application for automatically recognizing or verifying a human from a digital image or a video frame from videos. This can be done by distinguishing selected facial features from the image and a facial database. It is widely used in security systems and can be compared to other biometrics such as fingerprint or eye iris recognition systems.

3-D facial recognition system and biometric facial recognition system is focussed. This paper also illustrates future scope of enhancement of facial recognition system in India.

Keywords

3D Facial Recognition, Biometrics Facial Recognition, Alignment, Identification.

Full Text

   

Manpreet Kaur ¹, Jagroop Kaur ²

Affiliations
1 Computer Science Department, UCOE, Punjabi University, Patiala, IN
2 Department of Computer Science, UCOE, Punjabi University, Patiala, IN

Abstract

In the recent years, an exponential increase of using new linguistic feature Acronyms in the available electronic information documents to produce shorter text causes a big necessity to quickly understand large volumes of data. In the recent years, Automatic Recognition of Acronym-Definition Pairs has gained a One challenge derives from the common and uncontrolled use of acronyms in the medical and political field. In this paper we have developed an Algorithm for Extracting Acronym Definitions from Gurmukhi Text by using First-Letter matching technique. For improving the recall we have provided Common Acronym-Definition Pairs database. We tested our system over two types of data- Medical and Political data. We have applied three standard measures 1) Recall 2) precision 3) F-Score. The proposed system achieved 86% recall, 86.04% precision, yielding F-score of 86.01% for Medical document and 86.53% recall, 95.55% precision, yielding F-score of 90.81% for Political document by using Database of common Acronym-Definition pairs.

Keywords

Acronyms, Acronym identification, Abbreviation, Tokenization, Normalization, Recall, Precision, Medline.

Full Text

   

Manpreet Kaur ¹, Rajneesh Randhawa ¹

Affiliations
1 Department of Computer Science, Punjabi University, Patiala, IN

Abstract

LEACH is based on the assumption that each sensor node contain square with measure of energy which is not substantial in genuine situations. The DC-LEACH protocol cluster head race considers remaining energy of nodes, distance of node to the BS and neighbor nodes, which make cluster head decision sensible and node energy utilization adjust. It picks level-one cluster head from all individuals from the node, which is in charge for the information send from part nodes and arranging information combination to level-two CHs. At that point level-two CHs are chosen in all non-head nodes, which forward the packet to the sink node. Cluster head duties assigned to the two levels of CHs can significantly decrease the CHs energy utilization and enhance the system survival time. In this work, network lifetime is prolonging by the method of dispersed clustering. Dispersed Clustering Low Energy Adaptive Clustering Hierarchy (DC-LEACH) technique is proposed with the end goal to improve the system lifetime.

Keywords

LEACH, MTE, DC-LEACH, Cluster Heads Threshold, Energy Efficient.

Full Text