Inpainting helps to fill in the lost data in visual images. Inpainting techniques also refer to unusual image editing in distorted regions. These include areas that are noisy, blurred and watery areas. The most appropriate pixel values must be replaced in these regions to achieve good performance. Artists used to play it, and still now, pieces that are not in the picture can be inpainted in the same manner, though it takes more time. In the present age of automation, inpainting can be automated to obtain quicker and better outcomes by deep learning technologies. In this area, many of the latest techniques have been created, however, many methods produce blurred findings and data loss. Two adversarial networks are used to achieve this task, where first network aims at inpainting and the second network aims at super-resolution. The input generated as a part of first stage network is passed on to the second stage super-resolution network to overcome blurriness that is caused in the initial inpainting network. The network efficiency is determined in terms of increased PSNR obtained which is 28.19 dB with less training period of approximately 14 hours in comparison with other network models which performs similar task.
A conventional Secret key Steganography scheme focuses mainly to reduce the distortion when secret information is embedded into the cover image. On the other hand, the transmitted images may be compressed or faces transmitting errors. If such errors occur, the receiver cannot extract the correct information from the stegoimage. Furthermore the three main attributes of steganography are capacity, invisibility and Robustness. In the previous models [3, 4] we mainly concentrated on capacity and invisibility but in this method equal importance will be given to robustness. To increase the stochasticity of information hiding we use pixel indicator techniques which are implemented using three methods. Among these the first method enjoins that red channel steers the other two channels and the second method gives us the liberty to select the steering channel which successively increases the robustness of the shrouded message but its limits when MSE is considered. In third method, the steering channel is selected in a cyclic mode which enhances further the capacity along with security of the shrouded message as the MSE gets equally distributed. To increase the robustness here we introduce a factor E which gives us an option to select the position to plant the message to be concealed. The factor E addresses the bit where the embedding can be started. Once an image is compressed the LSBs of the covered media will get affected which defiles the concealed message. The essence of this method rests in the withstanding capability of the carrier media as the factor E is altered. As the value of E increases the MSE gets stepped up and hence the imperceptibility of the carrier image gets diluted. This can be heightened by using Optimal Pixel Adjustment Process (OPAP).
General Terms
Information Security
KeywordsModified LSB, Optimal Pixel Adjustment Process (OPAP), Pixel Indicator(PI).
Method 3: Embedding Algorithm: Inputs :Secret Data(S), Cover Image (I), Key D for DES No of secret bits embedded per pixel k∈{1,2,3,4} Key W for Modified LSB embedding W∈{1,2,3,4} Output: Stego image (O) with secret data embedded in it.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.