A Survey on Adaptive Techniques of Image Super resolution

Computer Engineering

Superresolution is a concept to increase the resolution. The main objective is super-resolving low resolution of a leaf diseased images. Plant diseases can cause significant reduction in both quality and quantity of agricultural products. This restrict the growth of plant and reduces quality and quantity of plant and eventually cause major reduction in economic production. The naked eye observation of experts is the traditional approach which is too much time consuming. Thus automatic disease detection systems are developed but here need arise for high definition input images. Superresolution is the cheap solution of this problem. In many practical applications super resolution algorithms are applied but the results obtained are not really satisfactory, being affected by relevant artifacts like blurring, over smoothed or sharped and jaggies. Here ICBI: Iterative Curvature Based Interpolation combined with NEDI: New Edge Detection Interpolation is described for super resolving. Further to remove over smoothing or over sharping, PSO: Particle Swarm Optimization technique is applied. Using a cost function, the image pixels are classified using the Particle Swarm Optimization technique. The cost function measured similarity/dissimilarity among pixels using not only the intensity values, but also the positions of the pixels. The detection technique enforced PSO based clustering, which is very simple and robust. The filtering operator Gabor filter and Log filter are used to restore only the noisy pixels keeping noise free pixels intact. Finally, corrected image is generated which can be used for agricultural applications like leaf disease detection system, leaf identification system and such others.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.