An Enhanced Technique for Red-Eye Detection and Correction using Neural Network
Rashmi Chandra1, Rohit Raja2

1Rashmi Chandra, Department of Computer Science and Engineering, Shri Shankaracharya College of Engineering & Technology, Bhilai (C.G.), India.
2Rohit Raja, Department of Computer Science and Engineering, M..M.. College of Technology, Raipur (C.G.), India.
Manuscript received on February 05, 2013. | Revised Manuscript Received on February 11, 2013. | Manuscript published on February 20, 2013. | PP: 39-44 | Volume-1 Issue-3, February 2013. | Retrieval Number: D0138021413/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering & Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Redeye is a common problem in consumer photography. When a flash is needed to illuminate the scene, the ambient illumination is usually low and a person’s pupils will be dilated. Light from the flash can thus reflect off the blood vessels in the person’s retina. In this case, it appears red in color and this reddish light is recorded by the camera. Though commercial solutions exist for red-eye correction, all of them require some measure of user intervention. A method is presented to automatically detect and correct red-eye in digital images. The algorithm contains a redeye detection part and a correction part. The detection part is modeled as a feature based object detection problem. Adaboost is used to simultaneously select features and train the classifier. A new feature set is designed to address the orientation-dependency problem associated with the Haar-like features commonly used for object detection design. For each detected redeye, a correction algorithm is applied to do adaptive desaturation and darkening over the redeye region. . The experimental results indicate that, the system can remove the red-eye automatically and effectively in the digital photo and has good robustness and rapidity.
Keywords: Redeye detection, redeye correction, face detection, image processing, neural network.