<p>Images captured under turbulent atmospheric conditions get twisted, distorted, and are difficult to identify. Imaging with the plenoptic camera efficiently collects four-dimensional information that includes the spherical and Cartesian coordinates of an observed target. It improves the image formation process under turbulent atmospheric conditions, which is not possible using a conventional camera. In this paper, we compare the results of conventional and plenoptic imaging systems and propose a plenoptic imaging system that efficiently captures images under turbulent conditions within the range of a few kilometers. This work demonstrates the laboratory test results of the developed plenoptic imaging system. The turbulent condition is created by blowing hot air in the path during imaging. Thereafter, image reconstruction algorithms are developed and implemented on the captured data. The best image was computed, followed by image registration, super-resolution, and de-blurring algorithms to reconstruct images free from distortions and blurring effects. We compare four different methods of feature detection and three different image de-blurring methods. We illustrate that the Maximally Stable Extremal Regions (MSER) technique extracts maximum features while sparse de-blurring produces sharper edges. Our image reconstruction algorithms can obtain a 6.33% better Signal-to-Noise Ratio (SNR) and 16% more similar images as compared to the recently developed state-of- the-art algorithm on deep neural networks for turbulence removal. Our image reconstruction approach is able to produce super-resolved and de-blurred images with high SNR. We tested the developed image reconstruction approaches, which proved useful for real-time applications.</p>