Image enhancement using the averaging histogram equalization (AVHEQ) approach for contrast improvement and brightness preservation. (August 2015)

• Record Type: Journal Article
• Authors: Lin, S.C.F.; Wong, C.Y.; Rahman, M.A.; Jiang, G.; Liu, S.; Kwok, Ngaiming; Shi, Haiyan; Yu, Ying-Hao; Wu, Tonghai
• Is Part Of: Computers & electrical engineering. Volume 46(2015)
• Page Start: 356
• Page End: 370
• Publication Date: 2015-08
• Subjects: Image contrast enhancement -- Histogram smoothing -- Brightness preservation -- Dynamic stretching -- Sub-image separation optimization; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2015.06.001
• Languages: English
• ISSNs: 0045-7906

Abstract

Graphical abstract: Highlights: A histogram equalization method is proposed to preserve original image brightness. A histogram averaging technique is developed to recover image information lost. A histogram remapping technique is used to reduce artifacts introduced to images. An optimization minimizes the brightness change between input and output images. Results show that image brightness is preserved while image contrast is enhanced. Abstract: Image contrast enhancement and brightness preservation are fundamental requirements for many vision based applications. However, these are two conflicting objectives when the image is processed by histogram equalization approaches. Current available methods may not provide results simultaneously satisfying both requirements. In this work, a pipelined approach including color channel stretching, histogram averaging and re-mapping is developed. By using stretching, color information from a scene is restored. Averaging against a uniform distribution enables the output image to recover the information lost. Furthermore, histogram re-mapping reduces artifacts that often arise from the equalization procedure. The technique also employs a search process to find optimal algorithmic parameters, such that the mean brightness difference between the input and output images is minimized. The effectiveness of the proposed method was tested with a set of images captured in adverse environments and compared against available methods. High performing qualitative and quantitative results were obtained.