Automatic system for improving underwater image contrast and color through recursive adaptive histogram modification

• Published in: Computers and electronics in agriculture Vol. 141; pp. 181 - 195
• Main Authors: Abdul Ghani, Ahmad Shahrizan, Mat Isa, Nor Ashidi
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.09.2017; Elsevier BV
• Subjects: Adaptive systems; Color; Color improvement; Contrast enhancement; Darkness; Dual-intensity image; Entropy; Habitats; Histograms; Image acquisition; Image contrast; Image enhancement; Rayleigh distribution; Recursive methods; Recursive overlapped area; Saturation (color); Underwater; Underwater image; Underwater photography; Underwater resources; Color improvement; Dual-intensity image; Recursive overlapped area; Underwater image; Contrast enhancement
• DOI: 10.1016/j.compag.2017.07.021
• ISSN: 0168-1699

Flow chart of the implemented proposed method – recursive adaptive histogram modification (RAHIM). [Display omitted] •Automatic method to improve underwater image quality for marine habitat monitoring.•Implementation of histogram modification and gray-level mapping through recursive overlapped processing.•Adaptive method to enhance underwater image and increase the extraction rate of information.•Significant improvement in terms of contrast, color, and information through testing of 300 underwater images. Contrast and color are important attributes to extract and acquire much information from underwater images. However, normal underwater images contain bright foreground and dark background areas. Previous enhancement methods enhance the foreground areas but retain darkness and blue-green illumination of background areas. This study proposes a new method of enhancing underwater image, which is called recursive adaptive histogram modification (RAHIM), to modify image histograms column wisely in accordance with Rayleigh distribution. Modifying image saturation and brightness in the hue–saturation–value color model increases the natural impression of image color through the human visual system. Qualitative and quantitative evaluations prove the effectiveness of the proposed method. Comparison with state-of-the-art methods shows that the proposed method produces the highest average entropy, measure of enhancement (EME), and EME by entropy with the values of 7.618, 28.193, and 6.829, respectively.