A novel method to detect foreground region using morphological operations with block based enhancement for underwater images

Abstract

Automation of detecting the Foreground Region (FR) or Shape of the object is essential in several computer vision, object recognition applications and poses several challenges in case of underwater images. Although Synthetic Sonar Images produce better quality images scattering of light, color distortion and poor lighting conditions are the few characteristics that effects the natural scene of the captured image. A novel technique for extracting the foreground region from a low quality underwater image is presented in this paper. We have decomposed the image in to multiple levels based on discrete wavelet transforms (DWT) for improving the sharpness or to reduce the fogginess in the image in order to get the clear image. Subsequently, to determine the sharpness of the local patches in the image a block based SSI algorithm is presented. Finally, the segmentation is performed by computing the binary gradient mask with the Sobel edge detection algorithm along with morphological operations. The proposed method is fast, extracting the accurate foreground regions and also detect the smallest particles present in the image. The results are qualitatively compared with the improved fuzzy c-means clustering (FCM), Otsu's Threshold and FCM thresholding by considering the static background images.

An edge detection mechanism using L*A*B color-based contrast enhancement for underwater images

“…are having several issues in the detection of edges for underwater image [23]. We can utilize the edge detection results in several automatic foreground extraction applications [24,25], but still, it is a challenging issue to detect the efficient edges for applications such as ocean and oceanography. Low Error Rate, Good Localization, minimal response are the three important criteria of the optimal canny edge detection algorithm.…”

Multi-scale fusion for underwater image enhancement using multi-layer perceptron

“…It is hard to enhance an underwater image because of the typical underwater conditions and lighting effects [2], [3]. The color distortion influences underwater situations, and contrast degrades because of absorption [4]. These artifacts produce underwater images with less quality.…”