No abstract

The pupil detection system plays a vital role in ophthalmology diagnosis equipments because pupil has a center place of human eye to locate the exact position. To identify the exact human eye pupil region in near infrared (NIR) images, this work proposes the Center of gravity method and its real time FPGA hardware implementation. The proposed work involves global threshold method to segment the pupil region from human eye and the bright spot suppression process removes the light reflections on the pupil due to the IR (Infra red) rays then the morphology dilation process removes unnecessary black pixels other than pupil region on the image. Finally, center of gravity (COG) method provides the exact pupil center coordinate and radius of the human eye. CASIA IRIS V4 and UBIRIS iris database images used in this work and achieved 90-95% of recognition rate.

No abstract

Background: The purpose of the present investigation is to unravel the complexity involved in Lung Cancer diagnosis by inculcating a new automated deep learning based MobileNet (DLMN) with deep belief network (DBN), called DLMN-DBN model in Internet of Things and cloud enabled environment. Methods: This paper presents an optimal DLMN-DBN model for lung cancer diagnosis where the parameters of DLMN-DBN model are optimized, and feature extraction and classification takes place by DLMN and DBN model respectively. The experimentation part takes place on four dimensions: 1) IoT devices enabled data acquisition for lung cancer diagnosis and the data are transmitted to the cloud server for diagnostic process, 2) the Guassian Filtering (GF) based preprocessing technique for noise removal, 3) feature extraction using DLMN model and 4) Optimal classification using DBN model. For experimental validation, an extensive experimentation analysis is performed to highlight the superior diagnostic outcome of the DLMN-DBN model. Findings:The experimental values stated that the DLMN-DBN model has resulted in superior results when compared with existing models with higher accuracy, sensitivity, and specificity of 95.55%, 93.94%, and 96.49% respectively. Novelty and applications: The new state of the art DLMN-DBN model and its robustness help general practitioners efficiently and effectively diagnose lung cancer conditions at the initial stage thereby reducing further complications and morbidity.