Probabilistic Exposure Fusion

NANO SCIENTIFIC RESEARCH CENTRE PVT.LTD.,  AMEERPET, HYD

WWW.NSRCNANO.COM, 09640648777, 09652926926

JAVA PROJECTS LIST--2013

JAVA 2013 IEEE PAPERS

Probabilistic Exposure Fusion

Abstract

            The luminance of a natural scene is often of high dynamic range (HDR). In this paper, we propose a new scheme to handle HDR scenes by integrating locally adaptive scene detail capture and suppressing gradient reversals introduced by the local adaptation. The proposed scheme is novel for capturing an HDR scene by using a standard dynamic range (SDR) device and synthesizing an image suitable for SDR displays. In particular, we use an SDR capture device to record scene details (i.e., the visible contrasts and the scene gradients) in a series of SDR images with different exposure levels. Each SDR image responds to a fraction of the HDR and partially records scene details. With the captured SDR image series, we first calculate the image luminance levels, which maximize the visible contrasts, and then the scene gradients embedded in these images.

            Next, we synthesize an SDR image by using a probabilistic model that preserves the calculated image luminance levels and suppresses reversals in the image luminance gradients. The synthesized SDR image contains much more scene details than any of the captured SDR image. Moreover, the proposed scheme also functions as the tone mapping of an HDR image to the SDR image, and it is superior to both global and local tone mapping operators. This is because global operators fail to preserve visual details when the contrast ratio of a scene is large, whereas local operators often produce halos in the synthesized SDR image. The proposed scheme does not require any human interaction or parameter tuning for different scenes. Subjective evaluations have shown that it is preferred over a number of existing approaches.

Existing System

            When HDR capture devices are not available, existing systems typically first apply algorithms to synthesize an HDR image via a set of SDR images, which record scene details, and then reproduce an SDR image via the synthesized HDR image, so that we can display the scene on an SDR device. This two-stage approach usually requires complex manual interactions and damages some scene details in both stages. A comprehensive review of algorithms for HDR image synthesis and display is given in the succeeding section.

Proposed System

            In this paper, we will present a new scheme for scene capture and display. Let us introduce some useful terms. The scene luminance is the luminance of the scene and is of HDR. The scene gradient is the difference between the scene luminance of a point and that of its neighbor points. If the difference between the luminance of a point and the average luminance of its surrounding points is visible for humans, we term the difference as the visible contrast. In the proposed approach, we use visible contrast and gradient of the whole scene to describe scene details. Given an SDR capture device, the scene luminance is recorded under a specific exposure level as the image luminance, which is determined by the response function of the film or the charge-coupled device. The image luminance is of SDR and only records a small scope of the dynamic range of the scene luminance. The key is how to preserve scene details in an SDR image.

Hardware Requirements

·         Hard disk                    :           80 GB

·         RAM                           :           1 GB

·         Processor                     :           Pentium IV

Software Requirements

·         Coding Language       :           Java

·         Operating System       :           Windows XP

Modules:

• Access Image
• Change Exposure Level
• Change to Halftone