Performance is an action or process of performing a task or function. And evaluation is judgment about the quality / quantity of the assessment conducted. Thereby, “Performance evaluation is a systematic process of observing, assessing, and interpreting one’s actual performance”....

Application for identifying or authenticating a person from a digital image or a video frame from a source can be done by comparing the selected facial features from the image and database. The existing systems include poor face credits with illumination ailment and the methods for finding the varying face expressions is still an issue. YALE-B database provides new insights into the role of robust pre-processing methods played in dealing with difficult illumination conditions and thus being useful in the description of new methods for robust face recognition. The system derives important information regarding the image quality achieved during the acquisition of the image. This paper implements pre-processing tasks such as Gamma correction, Differences of Gaussian (DOG) filter Masking and Normalization by considering the overall composition of the images. A special form of dimensionality reduction called Feature Extraction is carried out. The features set will extract the relevant information from the input data in order to perform the desired task. A k-Nearest Neighbor (k-NN) classification procedure is adopted to recognize the unique and permanent facial characteristics of a single person and store these features in the database as face templates. Later on, whenever the individual revisits the ground, their faces are known by the system application automatically. The aim is to develop a system which helps in easy retrieval and classification of accurate face characteristics.

Keywords: illuminations, digital image, recognitions, robust, acquisition, extraction, templates, reliability .

This paper focuses on building a platform for Big Data analytics in the cloud by introducing a storage layer optimized for structured data and by providing a framework for executing SQL queries efficiently. This work considers processing data warehousing queries over very large datasets. Our goal is to maximize performance while, at the same time, not giving up fault tolerance and scalability. We analyze the complexity of this problem in the split execution environment of HadoopDB. Here, incoming queries are examined; parts of the query are pushed down and executed inside the higher performing database layer; and the rest of the query is processed in a more generic MapReduce framework. In this paper, we discuss in detail performance-oriented query execution strategies for data warehouse queries in split execution environments, with particular focus on join and aggregation operations. The efficiency of our techniques is demonstrated by running experiments using the TPC- H benchmark with 3TB of data. In these experiments we compare our results with a standard commercial parallel database and an open-source MapReduce implementation featuring a SQL interface (Hive). We show that query execution and map reduce successfully competes with other systems.

Keywords: Split Query Execution, TPC-H Benchmark, MapReduce, Experimentation .