Chandigarh University

About: Chandigarh University is a education organization based out in Mohali, India. It is known for research contribution in the topics: Computer science & Chemistry. The organization has 1358 authors who have published 2104 publications receiving 10050 citations.

A Proposed Approach for Character Recognition Using Document Analysis with OCR

Abstract: Data entry has been a hectic job since the era of data accumulation started. Apparently, that is why there is a full-fledged career in data entry. Data entry method varies with requirements. Early days of computers relied on punch cards and gradually keyboards and mouse came into picture which we still use. Touchscreens didn't take much time to replace the physical keyboard inputs and now as the result of human intelligence and innovation, the era of the optical input is here. Where the user does not even have to take the pain of thinking about entering data but can simply use an optical reader or scanner to input data. Using the computational power the individual elements like text, images, and special characters can be distinguished. OCR-Optical Character Recognizer does the work. OCR works similar to humans when it comes to character recognition as it maintains a database of characters and compares all the scanned elements with the database which makes it really simple to understand. This paper explains the working of an OCR in its different stages. That study helps in finding the various drawbacks of the conventional system. The paper also tells about how those shortcomings can be eliminated and how a better OCR that is future ready can be achieved.

FOCALB: Fog Computing Architecture of Load Balancing for Scientific Workflow Applications

Abstract: Fog computing has a broad scope in real-time applications. It appears in the middle of Internet of Things (IoT) users and the cloud layer. The main applications of fog computing are to decrease latency and improve resource utilization for the end-users. Along with many advantages, fog computing also faces many challenges such as overloaded resources, security, deployment of nodes, and energy consumption. Load balancing is a challenging problem in a fog computing environment wherein, in more IoTs, the load distribution is required among all resources. Utilization of resources can be increased by the distribution of load in equal proportion among all fog resources. In scientific workflow systems, fog computing aids in proper resource utilization by uniformly dividing the workload. In this paper, we have proposed a Fog Computing Architecture of Load Balancing (FOCALB) for scientific workflow applications. The paper also proposed hybridized load balancing algorithm for scientific workflows (Tabu-GWO-ACO), which is an amalgamation of tabu search, Grey Wolf Optimization (GWO), and Ant Colony Optimization (ACO). The proposed model has been designed to enhance resource utilization by implementing load balancing at the fog layer. In the fog nodes, load scheduling is done when tasks are initialized, and local controller in fog clusters does load balancing. The simulation results are obtained with the help of iFogSim and Eclipse for 20 to 200 fog nodes. Simulated studies based on execution time, cost, and energy compared with various existing models show that FOCALB reduces energy consumption at fog nodes and reduces the execution time and implementation cost as well. The article is summarized by providing open challenges and future research directions.

Real-time crowd behavior detection using SIFT feature extraction technique in video sequences

Abstract: These days Crowd behavior detection in video surveillance is a latest research area in the field of computer vision. It focuses on the demanding assignment of monitoring crowded events for outbreaks of violent behavior. Such scenes have a need of human assessor to monitor multiple video screens, presenting crowds of people in a frequently changing sea of activity. In this paper, we propose an innovative approach for real-time crowd behavior detection using SIFT feature extraction technique in Video Sequences. For any detection and classification the feature extraction and feature optimization is very important metrics. So in proposed work SIFT feature extraction technique are used in appropriate segmented for background subtraction in video sense. After that feature extraction is applied in all regions, but a suitable feature extraction is not possible. To overcome this problem we have used Genetic Algorithm to optimize the extracted feature set. A genetic algorithm is best optimization technique and also operates in large data set. At last performance metrics of proposed work is calculates. In which we can compared propose work with previous existing work. And we calculate the performance metrics like precision rate, recall rate, and accuracy. The real-time crowd behavior using SIFT feature extraction technique in Video Sequences is implemented using Image Processing Toolbox within Matlab Software.

On 3D-printed ZnO-reinforced PLA matrix composite: Tensile, thermal, morphological and shape memory characteristics:

Abstract: The zinc oxide (ZnO)-reinforced polylactic acid (PLA) matrix has established shape memory characteristics. But hitherto little has been reported on two-way programmed 3D-printed ZnO-reinforced PLA ...