An efficient deconvolution technique by identification and estimation of blur

Distortion in images is a biggest challenge now-a-days. This affects in many areas ranging from photography to medical imaging, astronomy, remote sensing and microscopy. Images get obscured due to many reasons like vibration due to hand movement as well as launch of vehicle (Satellite), Noise in image, Adverse Image/Environment condition, and Quick movement of objects. A technique is required which can solve the above mentioned problems and make possible steps to keep image obscureness as minimum as possible. Out of several steps of restoration, blur detection is a primary step required for any blind image restoration. In this paper comparison of various techniques are proposed which finds out type of blur from the corrupted/degraded image using features like Moment Invariants, Histogram of Oriented Gradients, ZernikeMoment. This paper also describes comparison of different linear and nonlinear restoration techniques. The analysis and comparison was yielded out based on types of blur, estimation of blur, Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR).