No abstract

No abstract

Diatom is a dominant phytoplankton and commonly found in oceans or waterways. The captured phytoplankton microscopic images suffer from low contrast and surrounding debris. These images are not appropriated for identification. Integrated dual image contrast adaptive histogram specification with enhanced background removal (DIHS-BR) is proposed to address these issues by automatically removes the background of the phytoplankton image and improves the image quality while cropping phytoplankton cell. DIHS-BR will automatically remove the background and noises. DIHS-BR consists of two major steps, namely, contrast adaptive histogram specification and background removal by means of edge mask cropping. Results demonstrated that DIHS-BR filtered out the image background and left only the required phytoplankton cell image. Noises are minimized, while the contrast and colour of phytoplankton cells are improved. The average edge-based contrast measure (EBCM) of 83.065 demonstrates the best contrast improvement of the proposed methods compared with the other state-of-the-art methods.

When light travels through a water medium, selective attenuation and scattering have a profound impact on the underwater image. These limitations reduce image quality and impede the ability to perform visual tasks. The suggested integrated color correction with intelligence fusion of particle swarm technique (CCPF) is designed with four phases. The first phase presents a novel way to make improvement on underwater color cast. Limit the improvement to only red color channel. In the second phase, an image is then neutralized from the original image by brightness reconstruction technique resulting in enhancing the image contrast. Next, the mean adjustment based on particle swarm intelligence is implemented to improve the image detail. With the swarm intelligence method, the mean values of inferior color channels are shifted to be close to the mean value of a good color channel. Lastly, a fusion between the brightness reconstructed histogram and modified mean particle swarm intelligence histogram is applied to balance the image color. Analysis of underwater images taken in different depths shows that the proposed CCPF method improves the quality of the output image in terms of neutralizing effectiveness and details accuracy, consequently, significantly outperforming the other state-of-the-art methods. The proposed CCPF approach produces highest average entropy value of 7.823 and average UIQM value of 6.287.