Transparent Object Reconstruction Based on Compressive Sensing and Super-Resolution Convolutional Neural Network

The detection and reconstruction of transparent objects have remained challenging due to the absence of their features and variations in the local features with variations in illumination.In this paper,both compressive sensing(CS)and super-resolution convolutional neural network(SRCNN)techniques are combined to capture transparent objects.With the proposed method,the transparent object’s details are extracted accurately using a single pixel detector during the surface reconstruction.The resultant images obtained from the experimental setup are low in quality due to speckles and deformations on the object.However,the implemented SRCNN algorithm has obviated the mentioned drawbacks and reconstructed images visually plausibly.The developed algorithm locates the deformities in the resultant images and improves the image quality.Additionally,the inclusion of compressive sensing minimizes the measurements required for reconstruction,thereby reducing image post-processing and hardware requirements during network training.The result obtained indicates that the visual quality of the reconstructed images has increased from a structural similarity index(SSIM)value of 0.2 to 0.53.In this work,we demonstrate the efficiency of the proposed method in imaging and reconstructing transparent objects with the application of a compressive single pixel imaging technique and improving the image quality to a satisfactory level using the SRCNN algorithm.

Compressive Sensing Reconstruction Based on Weighted Directional Total Variation

Directionality of image plays a very important role in human visual system and it is important prior information of image. In this paper we propose a weighted directional total variation model to reconstruct image from its finite number of noisy compressive samples. A novel self-adaption, texture preservation method is designed to select the weight. Inspired by majorization-minimization scheme, we develop an efficient algorithm to seek the optimal solution of the proposed model by minimizing a sequence of quadratic surrogate penalties. The numerical examples are performed to compare its performance with four state-of-the-art algorithms. Experimental results clearly show that our method has better reconstruction accuracy on texture images than the existing scheme.