When side-scan sonars collect data, sonar energy attenuation, the residual of time varying gain, beam patterns, angular responses, and sonar altitude variations occur, which lead to an uneven gray level in side-scan sonar images. Therefore, gray scale correction is needed before further processing of side-scan sonar images. In this paper, we introduce the causes of gray distortion in side-scan sonar images and the commonly used optical and side-scan sonar gray scale correction methods. As existing methods cannot effectively correct distortion, we propose a simple, yet effective gray scale correction method for side-scan sonar images based on Retinex given the characteristics of side-scan sonar images. Firstly, we smooth the original image and add a constant as an illumination map. Then, we divide the original image by the illumination map to produce the reflection map. Finally, we perform element-wise multiplication between the reflection map and a constant coefficient to produce the final enhanced image. Two different schemes are used to implement our algorithm. For gray scale correction of side-scan sonar images, the proposed method is more effective than the latest similar methods based on the Retinex theory, and the proposed method is faster. Experiments prove the validity of the proposed method.

Deep neural network (DNN) was applied in sonar image target recognition tasks, but it is very difficult to obtain enough sonar images that contain a target; as a result, the direct use of a small amount of data to train a DNN will cause overfitting and other problems. Transfer learning is the most effective way to address such scenarios. However, there is a large domain gap between optical images and sonar images, and common transfer learning methods may not be able to effectively handle it. In this paper, we propose a transfer learning method for sonar image classification and object detection called the texture feature removal network. We regard the texture features of an image as domain-specific features, and we narrow the domain gap by discarding the domain-specific features, and hence, make it easier to complete knowledge transfer. Our method can be easily embedded into other transfer learning methods, which makes it easier to apply to different application scenarios. Experimental results show that our method is effective in side-scan sonar image classification tasks and forward-looking sonar image detection tasks. For side-scan sonar image classification tasks, the classification accuracy of our method is enhanced by 4.5% in a supervised learning experiment, and for forward-looking sonar detection tasks, the average precision (AP) is also significantly improved.