Safe Red-Eye Correction Plug-in Using Adaptive Methods

Abstract

An important issue with red-eye correction is that it might result in image degradation. This can be due to the detection of false positives or, even in the case of correct detection, to an inadequate correction technique. Three correction methods are proposed and compared according to their image degradation risk and their expected perceptual quality improvement. Based on those analyses an adaptive system is designed which selects the correction strategy dependent on those measures and the detection confidence. Finally, both qualitative (visual preferences) and quantitative (pixel counts on manual segmented images) evaluation results are shown.

Automatic Redeye Correction Algorithm with Multilevel Eye Confirmation

“…Marchesotti et al 6 designed an adaptive system which selects the correction strategy based on three correction methods and compared according to their image degradation risk and their expected perceptual quality improvement. The latest development to our knowledge was from Yoo and Park 23 who proposed a redeye removal algorithm using inpainting and eye-metric information.…”

“…Even though several automatic correction techniques have been proposed previously, 1-5 only few perform eye verification tests to confirm the located candidate as redeye. 6 It is worth mentioning here that using methods such as machine learning frameworks will increase the complexity and are computationally expensive. Our algorithm ( Figure 2) starts with skin and red pixel extraction and proceeds by hybrid confirmation stages including confirmation by glint and redness variation, statistical properties of eye region and eye-lips geometry and finally the detected region is corrected to preserve natural appearance.…”

A Review of Redeye Detection and Removal in Digital Images Through Patents

“…Marchesotti et al, in particular, have closely considered the problem of red eye correction, [36]. They have proposed three correction methods, evaluating what they have called their image degradation risk and their expected perceptual quality improvement.…”

“…• presence of glint, which is the specular reflection of the flash in the eye [19,39,36] • presence of sclera [31] o sclera/eye ratio…”

Automatic Redeye Correction in Digital Photos

“…The correction part implemented a soft red eye correction establish on the resulting probability map. In 2007, Marchesotti et al [19] have closely considered the problem of red eye correction, mostly less analyzed than red eye detection. They proposed three correction methods and compared regarding to their image degradation risk and their expected perceptual quality development.…”