Automatic Side-Scan Sonar Image Enhancement in Curvelet Transform Domain

Abstract

We propose a novel automatic side-scan sonar image enhancement algorithm based on curvelet transform. The proposed algorithm uses the curvelet transform to construct a multichannel enhancement structure based on human visual system (HVS) and adopts a new adaptive nonlinear mapping scheme to modify the curvelet transform coefficients in each channel independently and automatically. Firstly, the noisy and low-contrast sonar image is decomposed into a low frequency channel and a series of high frequency channels by using curvelet transform. Secondly, a new nonlinear mapping scheme, which coincides with the logarithmic nonlinear enhancement characteristic of the HVS perception, is designed without any parameter tuning to adjust the curvelet transform coefficients in each channel. Finally, the enhanced image can be reconstructed with the modified coefficients via inverse curvelet transform. The enhancement is achieved by amplifying subtle features, improving contrast, and eliminating noise simultaneously. Experiment results show that the proposed algorithm produces better enhanced results than state-of-the-art algorithms.

Efficient edge‐preserved sonar image enhancement method based on CVT for object recognition

“…CVT and NSCT are not optimised to sonar image. However, since they have been widely used methods for image processing [8–14, 25, 26], we introduce them into the comparison method.…”

“…The CVT [8–11] is a multi‐scale geometric WT, can represent edge features and curve singularities much more efficiently than classical WT. Fig.…”

“…However, WT‐based methods perform well only at representing point singularities, because they ignore the geometric properties of structures and do not exploit the regularity of edges. To overcome the limitation, curvelet transform (CVT) is proposed as a generalisation of high level [8–11]. For contrast enhancement, various enhancement methods had been studied with using the CVT in terms of high sensitivity and anisotropy [12–14].…”

Super resolution enhancement of underwater sonar images

“…PSNR is utilised as the performance measure. Zhou et al [19] presented a novel image enhancement algorithm based on curvelet transform for sonar images. The curvelet transform constructs multi-channel enhancement structure based on (HVS) human visual system.…”

A robust version of the Lee filter for speckle reduction and contrast enhancement applied to side scan sonar images

“…En la literatura de lasúltimas décadas, se han introducido numerosas alternativas de pre-procesamiento para eliminar el ruido speckle y mejorar el contraste de imágenes de SSS que abarcan diferentes niveles de complejidad que influyen notablemente en su etapa posterior de post-procesamiento, como por ejemplo en la detección y reconocimiento de objetos [6], [7]. Entre los métodos de pre-procesamiento de imágenes acústicas se encuentran el método variacional (variational approach) [8], representación escasa (sparse representation) [9], corrección de histograma (histogram Correction) [10] y estiramiento no lineal (nonlinear stretching) [11], transformada Curvelente (curvelent transform) [12], transformada Wavelet (wavelet transform), entre otros [13]. Los métodos detallados implican numerosos pasos secuenciales, utilizan técnicas combinadas, procedimientos complejos iterativos, establecen umbrales o parámetros subjetivos y además, requieren frecuentemente una cierta cantidad de información previa para obtener una imagen resultante de calidad.…”