Hadoop Small Image Processing Technology Based on Big Data Processing and Its Application Effect in Face Feature Extraction and Face Recognition System Design

Abstract

From standard software to crucial applications, face recognition (FR) is always at the core of many unique advances over the past 20 years. Big data is a rapidly growing collection of data. It is important in many applications such as medical, academic, and industries, and it refers to vast data sources that are hard to analyze, store, and interpret for subsequent procedures. Hadoop is an open-source large data processing platform that stores and analyses data in scalable computer clusters. FR technology is built on Hadoop processing to boost the effectiveness of recognition using MapReduce computing. This paper presents a novel adaptive fine-tuned AdaBoost (AFTA) algorithm to enhance the FR in the Hadoop processing. Collected face data sets are employed in preprocessing stage to normalize and enhance the superiority through the median filter (MF) and contour-based image enhancement (CIE), correspondingly. To handle vast quantities of the data, boosted k-means clustering (BKC) approach is used over the Hadoop servers for the MapReduce process. The binary partition tree (BPT) approach is employed in the segmentation stage to split the data into many subgroups. To lessen the dimension of the data, we use the Gabor filter. To select the consistent features, threshold-based binary particle swarm optimization (T-BPSO) is applied. Then, our proposed technique is utilized in the FR process. Finally, the performance metrics of the proposed technique are examined and compared with existing techniques to accomplish our research with the greatest effectiveness. For accuracy, precision, recall, and F-score, we attained the proposed (AFTA) values of 99.67, 97.13, 95.21, and 94.11, respectively. The outcomes are depicted in graphical representation by employing the MATLAB tool.